Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-12208/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-12208/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-12208/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23530b4c6142a98454c822e8df719c0d09c4ffa9f2cdd26e35a0fa46b094bc5b
+size 4976687216

checkpoint-12208/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edb205482e80b5d03e63693e387d459b0cb9c97948cde971ff025ba98f1396d
+size 4778622352

checkpoint-12208/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2222b40c6fea7def1d5911b059ab36bf97b9328e0251689f78a0a9ebd98cd18d
+size 4932743960

checkpoint-12208/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-12208/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-12208/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827b08d59b6211ba8c4aa70e4e95d2b19e1f626b56ba6e955457a0b2493d6b2e
+size 3662865184

checkpoint-12208/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a83a903453e7fbeb3d034a300ae8a1e4ac6a6a57185612fec493e338938824f
+size 2179989632

checkpoint-12208/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-12208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa1da95157de2f053e8ad467dbdc3ab8a95671eb92ad99f69d65fe41dcf1bc1
+size 16177880918

checkpoint-12208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-12208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe644ed33a3c4139223f0857a985127f3e6fbaa8c89fa14b57671b49ca52c21
+size 1064

checkpoint-12208/trainer_state.json

@@ -0,0 +1,2784 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1052450084485672,
+  "eval_steps": 500,
+  "global_step": 12208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0002672505948480982,
+      "grad_norm": 3.2076423168182373,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.4511,
+      "step": 31
+    },
+    {
+      "epoch": 0.0005345011896961964,
+      "grad_norm": 2.221529006958008,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 1.3342,
+      "step": 62
+    },
+    {
+      "epoch": 0.0008017517845442946,
+      "grad_norm": 2.961315393447876,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.2649,
+      "step": 93
+    },
+    {
+      "epoch": 0.0010690023793923928,
+      "grad_norm": 2.311617612838745,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.2278,
+      "step": 124
+    },
+    {
+      "epoch": 0.001336252974240491,
+      "grad_norm": 3.4343724250793457,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.2061,
+      "step": 155
+    },
+    {
+      "epoch": 0.0016035035690885892,
+      "grad_norm": 2.421396017074585,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.1848,
+      "step": 186
+    },
+    {
+      "epoch": 0.0018707541639366874,
+      "grad_norm": 2.8230600357055664,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.1586,
+      "step": 217
+    },
+    {
+      "epoch": 0.0021380047587847856,
+      "grad_norm": 2.021296501159668,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.1552,
+      "step": 248
+    },
+    {
+      "epoch": 0.002405255353632884,
+      "grad_norm": 2.2329111099243164,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.1342,
+      "step": 279
+    },
+    {
+      "epoch": 0.002672505948480982,
+      "grad_norm": 2.8933441638946533,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 1.1092,
+      "step": 310
+    },
+    {
+      "epoch": 0.0029397565433290805,
+      "grad_norm": 2.510772705078125,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 1.108,
+      "step": 341
+    },
+    {
+      "epoch": 0.0032070071381771785,
+      "grad_norm": 2.170926094055176,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.0982,
+      "step": 372
+    },
+    {
+      "epoch": 0.003474257733025277,
+      "grad_norm": 2.1116831302642822,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 1.0977,
+      "step": 403
+    },
+    {
+      "epoch": 0.003741508327873375,
+      "grad_norm": 2.5462026596069336,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 1.0797,
+      "step": 434
+    },
+    {
+      "epoch": 0.004008758922721473,
+      "grad_norm": 2.5239830017089844,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 1.0691,
+      "step": 465
+    },
+    {
+      "epoch": 0.004276009517569571,
+      "grad_norm": 2.640591859817505,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 1.0547,
+      "step": 496
+    },
+    {
+      "epoch": 0.004543260112417669,
+      "grad_norm": 1.9566192626953125,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 1.0526,
+      "step": 527
+    },
+    {
+      "epoch": 0.004810510707265768,
+      "grad_norm": 2.515118360519409,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 1.0614,
+      "step": 558
+    },
+    {
+      "epoch": 0.005077761302113866,
+      "grad_norm": 2.1588094234466553,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 1.0461,
+      "step": 589
+    },
+    {
+      "epoch": 0.005345011896961964,
+      "grad_norm": 2.448280096054077,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 1.0333,
+      "step": 620
+    },
+    {
+      "epoch": 0.005612262491810062,
+      "grad_norm": 2.9539694786071777,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 1.0224,
+      "step": 651
+    },
+    {
+      "epoch": 0.005879513086658161,
+      "grad_norm": 2.6804676055908203,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 1.0145,
+      "step": 682
+    },
+    {
+      "epoch": 0.006146763681506259,
+      "grad_norm": 2.176100730895996,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 1.0164,
+      "step": 713
+    },
+    {
+      "epoch": 0.006414014276354357,
+      "grad_norm": 1.9107022285461426,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 1.004,
+      "step": 744
+    },
+    {
+      "epoch": 0.006681264871202455,
+      "grad_norm": 3.175410270690918,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.9986,
+      "step": 775
+    },
+    {
+      "epoch": 0.006948515466050554,
+      "grad_norm": 1.7941040992736816,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.9979,
+      "step": 806
+    },
+    {
+      "epoch": 0.007215766060898652,
+      "grad_norm": 2.428041458129883,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 1.0056,
+      "step": 837
+    },
+    {
+      "epoch": 0.00748301665574675,
+      "grad_norm": 2.1440467834472656,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.9908,
+      "step": 868
+    },
+    {
+      "epoch": 0.007750267250594848,
+      "grad_norm": 2.138157844543457,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.986,
+      "step": 899
+    },
+    {
+      "epoch": 0.008017517845442947,
+      "grad_norm": 2.144076108932495,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.9768,
+      "step": 930
+    },
+    {
+      "epoch": 0.008284768440291045,
+      "grad_norm": 2.116927146911621,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.975,
+      "step": 961
+    },
+    {
+      "epoch": 0.008552019035139143,
+      "grad_norm": 2.0087051391601562,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.9746,
+      "step": 992
+    },
+    {
+      "epoch": 0.00881926962998724,
+      "grad_norm": 2.008014440536499,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.9612,
+      "step": 1023
+    },
+    {
+      "epoch": 0.009086520224835339,
+      "grad_norm": 2.5932323932647705,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.9611,
+      "step": 1054
+    },
+    {
+      "epoch": 0.009353770819683437,
+      "grad_norm": 1.7766073942184448,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.9529,
+      "step": 1085
+    },
+    {
+      "epoch": 0.009621021414531536,
+      "grad_norm": 1.699992299079895,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.9638,
+      "step": 1116
+    },
+    {
+      "epoch": 0.009888272009379634,
+      "grad_norm": 2.139831304550171,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.9518,
+      "step": 1147
+    },
+    {
+      "epoch": 0.010155522604227732,
+      "grad_norm": 2.510404109954834,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.9557,
+      "step": 1178
+    },
+    {
+      "epoch": 0.01042277319907583,
+      "grad_norm": 1.7539429664611816,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.949,
+      "step": 1209
+    },
+    {
+      "epoch": 0.010690023793923928,
+      "grad_norm": 1.7679015398025513,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.9285,
+      "step": 1240
+    },
+    {
+      "epoch": 0.010957274388772026,
+      "grad_norm": 1.6701771020889282,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.9391,
+      "step": 1271
+    },
+    {
+      "epoch": 0.011224524983620124,
+      "grad_norm": 1.7283812761306763,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.9328,
+      "step": 1302
+    },
+    {
+      "epoch": 0.011491775578468222,
+      "grad_norm": 1.363319754600525,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.9353,
+      "step": 1333
+    },
+    {
+      "epoch": 0.011759026173316322,
+      "grad_norm": 1.847582459449768,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.9272,
+      "step": 1364
+    },
+    {
+      "epoch": 0.01202627676816442,
+      "grad_norm": 1.6437714099884033,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.9219,
+      "step": 1395
+    },
+    {
+      "epoch": 0.012293527363012518,
+      "grad_norm": 1.979443073272705,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.91,
+      "step": 1426
+    },
+    {
+      "epoch": 0.012560777957860616,
+      "grad_norm": 1.601218342781067,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.9229,
+      "step": 1457
+    },
+    {
+      "epoch": 0.012828028552708714,
+      "grad_norm": 2.36148738861084,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.9199,
+      "step": 1488
+    },
+    {
+      "epoch": 0.013095279147556812,
+      "grad_norm": 4.211123466491699,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 1.0419,
+      "step": 1519
+    },
+    {
+      "epoch": 0.01336252974240491,
+      "grad_norm": 1.620786428451538,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.954,
+      "step": 1550
+    },
+    {
+      "epoch": 0.01362978033725301,
+      "grad_norm": 3.2490246295928955,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.9464,
+      "step": 1581
+    },
+    {
+      "epoch": 0.013897030932101108,
+      "grad_norm": 1.9302624464035034,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.9294,
+      "step": 1612
+    },
+    {
+      "epoch": 0.014164281526949206,
+      "grad_norm": 1.5750601291656494,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.922,
+      "step": 1643
+    },
+    {
+      "epoch": 0.014431532121797304,
+      "grad_norm": 53.0409049987793,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 1.0611,
+      "step": 1674
+    },
+    {
+      "epoch": 0.014698782716645402,
+      "grad_norm": 1.841700553894043,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 1.0363,
+      "step": 1705
+    },
+    {
+      "epoch": 0.0149660333114935,
+      "grad_norm": 1.2549737691879272,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.938,
+      "step": 1736
+    },
+    {
+      "epoch": 0.015233283906341597,
+      "grad_norm": 1.3289740085601807,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.9113,
+      "step": 1767
+    },
+    {
+      "epoch": 0.015500534501189695,
+      "grad_norm": 1.5228811502456665,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.921,
+      "step": 1798
+    },
+    {
+      "epoch": 0.015767785096037795,
+      "grad_norm": 1.5058027505874634,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.9214,
+      "step": 1829
+    },
+    {
+      "epoch": 0.016035035690885893,
+      "grad_norm": 9.535687446594238,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 1.3068,
+      "step": 1860
+    },
+    {
+      "epoch": 0.01630228628573399,
+      "grad_norm": 2.5820651054382324,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 1.7033,
+      "step": 1891
+    },
+    {
+      "epoch": 0.01656953688058209,
+      "grad_norm": 148.47412109375,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 1.6935,
+      "step": 1922
+    },
+    {
+      "epoch": 0.016836787475430187,
+      "grad_norm": 8.416805267333984,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 1.6607,
+      "step": 1953
+    },
+    {
+      "epoch": 0.017104038070278285,
+      "grad_norm": 5.2713470458984375,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 1.1301,
+      "step": 1984
+    },
+    {
+      "epoch": 0.017371288665126383,
+      "grad_norm": 2.096306800842285,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.9931,
+      "step": 2015
+    },
+    {
+      "epoch": 0.01763853925997448,
+      "grad_norm": 1.5476640462875366,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.9514,
+      "step": 2046
+    },
+    {
+      "epoch": 0.01790578985482258,
+      "grad_norm": 1.727232813835144,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.9409,
+      "step": 2077
+    },
+    {
+      "epoch": 0.018173040449670677,
+      "grad_norm": 26.08816909790039,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.9368,
+      "step": 2108
+    },
+    {
+      "epoch": 0.018440291044518775,
+      "grad_norm": 1.7082202434539795,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.9155,
+      "step": 2139
+    },
+    {
+      "epoch": 0.018707541639366873,
+      "grad_norm": 1.5962992906570435,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.9233,
+      "step": 2170
+    },
+    {
+      "epoch": 0.018974792234214975,
+      "grad_norm": 2.024268627166748,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.9128,
+      "step": 2201
+    },
+    {
+      "epoch": 0.019242042829063073,
+      "grad_norm": 1.4828873872756958,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.8957,
+      "step": 2232
+    },
+    {
+      "epoch": 0.01950929342391117,
+      "grad_norm": 1.745612382888794,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.9005,
+      "step": 2263
+    },
+    {
+      "epoch": 0.01977654401875927,
+      "grad_norm": 1.354095458984375,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.9002,
+      "step": 2294
+    },
+    {
+      "epoch": 0.020043794613607367,
+      "grad_norm": 2.6227681636810303,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.9004,
+      "step": 2325
+    },
+    {
+      "epoch": 0.020311045208455464,
+      "grad_norm": 1.3870893716812134,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.9018,
+      "step": 2356
+    },
+    {
+      "epoch": 0.020578295803303562,
+      "grad_norm": 1.2884349822998047,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.8993,
+      "step": 2387
+    },
+    {
+      "epoch": 0.02084554639815166,
+      "grad_norm": 1.215851068496704,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.8925,
+      "step": 2418
+    },
+    {
+      "epoch": 0.02111279699299976,
+      "grad_norm": 1.4246628284454346,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.8893,
+      "step": 2449
+    },
+    {
+      "epoch": 0.021380047587847856,
+      "grad_norm": 1.5495259761810303,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.8749,
+      "step": 2480
+    },
+    {
+      "epoch": 0.021647298182695954,
+      "grad_norm": 1.0121793746948242,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.8803,
+      "step": 2511
+    },
+    {
+      "epoch": 0.021914548777544052,
+      "grad_norm": 1.1507561206817627,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.8843,
+      "step": 2542
+    },
+    {
+      "epoch": 0.02218179937239215,
+      "grad_norm": 1.612584114074707,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.8733,
+      "step": 2573
+    },
+    {
+      "epoch": 0.02244904996724025,
+      "grad_norm": 1.4475393295288086,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.8669,
+      "step": 2604
+    },
+    {
+      "epoch": 0.022716300562088346,
+      "grad_norm": 1.9612644910812378,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.8791,
+      "step": 2635
+    },
+    {
+      "epoch": 0.022983551156936444,
+      "grad_norm": 1.6032893657684326,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.8646,
+      "step": 2666
+    },
+    {
+      "epoch": 0.023250801751784546,
+      "grad_norm": 1.6368708610534668,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.871,
+      "step": 2697
+    },
+    {
+      "epoch": 0.023518052346632644,
+      "grad_norm": 1.0245656967163086,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.8534,
+      "step": 2728
+    },
+    {
+      "epoch": 0.023785302941480742,
+      "grad_norm": 0.9378401041030884,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.8478,
+      "step": 2759
+    },
+    {
+      "epoch": 0.02405255353632884,
+      "grad_norm": 1.4262951612472534,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.8634,
+      "step": 2790
+    },
+    {
+      "epoch": 0.024319804131176938,
+      "grad_norm": 1.3320890665054321,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.8505,
+      "step": 2821
+    },
+    {
+      "epoch": 0.024587054726025036,
+      "grad_norm": 1.043971061706543,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.863,
+      "step": 2852
+    },
+    {
+      "epoch": 0.024854305320873134,
+      "grad_norm": 1.387088418006897,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.8505,
+      "step": 2883
+    },
+    {
+      "epoch": 0.025121555915721232,
+      "grad_norm": 1.1267746686935425,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.8528,
+      "step": 2914
+    },
+    {
+      "epoch": 0.02538880651056933,
+      "grad_norm": 0.9636305570602417,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.8453,
+      "step": 2945
+    },
+    {
+      "epoch": 0.025656057105417428,
+      "grad_norm": 1.1140860319137573,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.8664,
+      "step": 2976
+    },
+    {
+      "epoch": 0.025923307700265526,
+      "grad_norm": 1.1886147260665894,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.8569,
+      "step": 3007
+    },
+    {
+      "epoch": 0.026190558295113624,
+      "grad_norm": 1.0308467149734497,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.85,
+      "step": 3038
+    },
+    {
+      "epoch": 0.02645780888996172,
+      "grad_norm": 1.6353480815887451,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.8414,
+      "step": 3069
+    },
+    {
+      "epoch": 0.02672505948480982,
+      "grad_norm": 1.2031575441360474,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.8435,
+      "step": 3100
+    },
+    {
+      "epoch": 0.026992310079657918,
+      "grad_norm": 1.2575979232788086,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.8415,
+      "step": 3131
+    },
+    {
+      "epoch": 0.02725956067450602,
+      "grad_norm": 1.338584303855896,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.8414,
+      "step": 3162
+    },
+    {
+      "epoch": 0.027526811269354117,
+      "grad_norm": 1.3699461221694946,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.8397,
+      "step": 3193
+    },
+    {
+      "epoch": 0.027794061864202215,
+      "grad_norm": 1.1471112966537476,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.8304,
+      "step": 3224
+    },
+    {
+      "epoch": 0.028061312459050313,
+      "grad_norm": 1.1752680540084839,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.8408,
+      "step": 3255
+    },
+    {
+      "epoch": 0.02832856305389841,
+      "grad_norm": 1.089552879333496,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.8286,
+      "step": 3286
+    },
+    {
+      "epoch": 0.02859581364874651,
+      "grad_norm": 1.0688341856002808,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.8341,
+      "step": 3317
+    },
+    {
+      "epoch": 0.028863064243594607,
+      "grad_norm": 0.9290914535522461,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.8307,
+      "step": 3348
+    },
+    {
+      "epoch": 0.029130314838442705,
+      "grad_norm": 1.3211214542388916,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.8349,
+      "step": 3379
+    },
+    {
+      "epoch": 0.029397565433290803,
+      "grad_norm": 1.8893773555755615,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.8289,
+      "step": 3410
+    },
+    {
+      "epoch": 0.0296648160281389,
+      "grad_norm": 1.3086936473846436,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.8231,
+      "step": 3441
+    },
+    {
+      "epoch": 0.029932066622987,
+      "grad_norm": 1.356311559677124,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.8343,
+      "step": 3472
+    },
+    {
+      "epoch": 0.030199317217835097,
+      "grad_norm": 1.13872492313385,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.828,
+      "step": 3503
+    },
+    {
+      "epoch": 0.030466567812683195,
+      "grad_norm": 1.1912773847579956,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.8236,
+      "step": 3534
+    },
+    {
+      "epoch": 0.030733818407531293,
+      "grad_norm": 0.9231215715408325,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.8226,
+      "step": 3565
+    },
+    {
+      "epoch": 0.03100106900237939,
+      "grad_norm": 1.0268129110336304,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.8218,
+      "step": 3596
+    },
+    {
+      "epoch": 0.03126831959722749,
+      "grad_norm": 0.974876344203949,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.8149,
+      "step": 3627
+    },
+    {
+      "epoch": 0.03153557019207559,
+      "grad_norm": 1.2175925970077515,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.8152,
+      "step": 3658
+    },
+    {
+      "epoch": 0.03180282078692369,
+      "grad_norm": 1.2338181734085083,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.8089,
+      "step": 3689
+    },
+    {
+      "epoch": 0.032070071381771786,
+      "grad_norm": 1.1462433338165283,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.8216,
+      "step": 3720
+    },
+    {
+      "epoch": 0.032337321976619884,
+      "grad_norm": 1.1631278991699219,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.8272,
+      "step": 3751
+    },
+    {
+      "epoch": 0.03260457257146798,
+      "grad_norm": 0.903836727142334,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.816,
+      "step": 3782
+    },
+    {
+      "epoch": 0.03287182316631608,
+      "grad_norm": 0.944284975528717,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.8031,
+      "step": 3813
+    },
+    {
+      "epoch": 0.03313907376116418,
+      "grad_norm": 1.1210039854049683,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.8096,
+      "step": 3844
+    },
+    {
+      "epoch": 0.033406324356012276,
+      "grad_norm": 1.0448529720306396,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.8059,
+      "step": 3875
+    },
+    {
+      "epoch": 0.033673574950860374,
+      "grad_norm": 1.0655525922775269,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.81,
+      "step": 3906
+    },
+    {
+      "epoch": 0.03394082554570847,
+      "grad_norm": 1.223928451538086,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.8175,
+      "step": 3937
+    },
+    {
+      "epoch": 0.03420807614055657,
+      "grad_norm": 1.0895342826843262,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.7992,
+      "step": 3968
+    },
+    {
+      "epoch": 0.03447532673540467,
+      "grad_norm": 1.1117792129516602,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.8122,
+      "step": 3999
+    },
+    {
+      "epoch": 0.034742577330252766,
+      "grad_norm": 1.0806598663330078,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.811,
+      "step": 4030
+    },
+    {
+      "epoch": 0.035009827925100864,
+      "grad_norm": 0.7528677582740784,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.8036,
+      "step": 4061
+    },
+    {
+      "epoch": 0.03527707851994896,
+      "grad_norm": 1.1509230136871338,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.8047,
+      "step": 4092
+    },
+    {
+      "epoch": 0.03554432911479706,
+      "grad_norm": 1.1190931797027588,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.8123,
+      "step": 4123
+    },
+    {
+      "epoch": 0.03581157970964516,
+      "grad_norm": 0.8739308714866638,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.8015,
+      "step": 4154
+    },
+    {
+      "epoch": 0.036078830304493256,
+      "grad_norm": 0.9889201521873474,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.8056,
+      "step": 4185
+    },
+    {
+      "epoch": 0.036346080899341354,
+      "grad_norm": 1.1964142322540283,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.8083,
+      "step": 4216
+    },
+    {
+      "epoch": 0.03661333149418945,
+      "grad_norm": 1.0793588161468506,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.7976,
+      "step": 4247
+    },
+    {
+      "epoch": 0.03688058208903755,
+      "grad_norm": 1.2313084602355957,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.7954,
+      "step": 4278
+    },
+    {
+      "epoch": 0.03714783268388565,
+      "grad_norm": 1.1145700216293335,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.7947,
+      "step": 4309
+    },
+    {
+      "epoch": 0.037415083278733746,
+      "grad_norm": 0.9714220762252808,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.7973,
+      "step": 4340
+    },
+    {
+      "epoch": 0.03768233387358185,
+      "grad_norm": 1.0865004062652588,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.7918,
+      "step": 4371
+    },
+    {
+      "epoch": 0.03794958446842995,
+      "grad_norm": 0.8420351147651672,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.805,
+      "step": 4402
+    },
+    {
+      "epoch": 0.03821683506327805,
+      "grad_norm": 1.0622302293777466,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.7977,
+      "step": 4433
+    },
+    {
+      "epoch": 0.038484085658126145,
+      "grad_norm": 0.8536683320999146,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.7946,
+      "step": 4464
+    },
+    {
+      "epoch": 0.03875133625297424,
+      "grad_norm": 0.9905999302864075,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.7932,
+      "step": 4495
+    },
+    {
+      "epoch": 0.03901858684782234,
+      "grad_norm": 1.005560278892517,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.7956,
+      "step": 4526
+    },
+    {
+      "epoch": 0.03928583744267044,
+      "grad_norm": 0.8386696577072144,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.7865,
+      "step": 4557
+    },
+    {
+      "epoch": 0.03955308803751854,
+      "grad_norm": 0.8390759229660034,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.7925,
+      "step": 4588
+    },
+    {
+      "epoch": 0.039820338632366635,
+      "grad_norm": 0.7457160949707031,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.7911,
+      "step": 4619
+    },
+    {
+      "epoch": 0.04008758922721473,
+      "grad_norm": 0.9717801213264465,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.7917,
+      "step": 4650
+    },
+    {
+      "epoch": 0.04035483982206283,
+      "grad_norm": 0.8517304062843323,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.7966,
+      "step": 4681
+    },
+    {
+      "epoch": 0.04062209041691093,
+      "grad_norm": 0.7597792744636536,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.7798,
+      "step": 4712
+    },
+    {
+      "epoch": 0.04088934101175903,
+      "grad_norm": 0.9633410573005676,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.784,
+      "step": 4743
+    },
+    {
+      "epoch": 0.041156591606607125,
+      "grad_norm": 0.8668884634971619,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.7925,
+      "step": 4774
+    },
+    {
+      "epoch": 0.04142384220145522,
+      "grad_norm": 1.348170280456543,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.7882,
+      "step": 4805
+    },
+    {
+      "epoch": 0.04169109279630332,
+      "grad_norm": 0.9085477590560913,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.7834,
+      "step": 4836
+    },
+    {
+      "epoch": 0.04195834339115142,
+      "grad_norm": 1.2533594369888306,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.7968,
+      "step": 4867
+    },
+    {
+      "epoch": 0.04222559398599952,
+      "grad_norm": 1.0250332355499268,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.7755,
+      "step": 4898
+    },
+    {
+      "epoch": 0.042492844580847615,
+      "grad_norm": 0.8610180616378784,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.7819,
+      "step": 4929
+    },
+    {
+      "epoch": 0.04276009517569571,
+      "grad_norm": 0.8235286474227905,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.7834,
+      "step": 4960
+    },
+    {
+      "epoch": 0.04302734577054381,
+      "grad_norm": 0.95796799659729,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.7822,
+      "step": 4991
+    },
+    {
+      "epoch": 0.04329459636539191,
+      "grad_norm": 1.022430419921875,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.781,
+      "step": 5022
+    },
+    {
+      "epoch": 0.04356184696024001,
+      "grad_norm": 0.9080584645271301,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.783,
+      "step": 5053
+    },
+    {
+      "epoch": 0.043829097555088105,
+      "grad_norm": 0.9808719158172607,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.7838,
+      "step": 5084
+    },
+    {
+      "epoch": 0.0440963481499362,
+      "grad_norm": 0.8997575640678406,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.7816,
+      "step": 5115
+    },
+    {
+      "epoch": 0.0443635987447843,
+      "grad_norm": 0.8737884163856506,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.7785,
+      "step": 5146
+    },
+    {
+      "epoch": 0.0446308493396324,
+      "grad_norm": 0.7924982309341431,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.7752,
+      "step": 5177
+    },
+    {
+      "epoch": 0.0448980999344805,
+      "grad_norm": 1.1685878038406372,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.7881,
+      "step": 5208
+    },
+    {
+      "epoch": 0.045165350529328595,
+      "grad_norm": 1.0199975967407227,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.7663,
+      "step": 5239
+    },
+    {
+      "epoch": 0.04543260112417669,
+      "grad_norm": 0.8155254125595093,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.7775,
+      "step": 5270
+    },
+    {
+      "epoch": 0.04569985171902479,
+      "grad_norm": 0.976006805896759,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.7797,
+      "step": 5301
+    },
+    {
+      "epoch": 0.04596710231387289,
+      "grad_norm": 1.1252824068069458,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.7824,
+      "step": 5332
+    },
+    {
+      "epoch": 0.046234352908720994,
+      "grad_norm": 0.7603053450584412,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.7759,
+      "step": 5363
+    },
+    {
+      "epoch": 0.04650160350356909,
+      "grad_norm": 1.007767915725708,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.7832,
+      "step": 5394
+    },
+    {
+      "epoch": 0.04676885409841719,
+      "grad_norm": 1.1207255125045776,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.7849,
+      "step": 5425
+    },
+    {
+      "epoch": 0.04703610469326529,
+      "grad_norm": 1.0699808597564697,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.7814,
+      "step": 5456
+    },
+    {
+      "epoch": 0.047303355288113386,
+      "grad_norm": 0.8154749274253845,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.7806,
+      "step": 5487
+    },
+    {
+      "epoch": 0.047570605882961484,
+      "grad_norm": 0.7383331060409546,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.7765,
+      "step": 5518
+    },
+    {
+      "epoch": 0.04783785647780958,
+      "grad_norm": 0.9729552865028381,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.7754,
+      "step": 5549
+    },
+    {
+      "epoch": 0.04810510707265768,
+      "grad_norm": 0.9568310379981995,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.7733,
+      "step": 5580
+    },
+    {
+      "epoch": 0.04837235766750578,
+      "grad_norm": 1.0747005939483643,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.7764,
+      "step": 5611
+    },
+    {
+      "epoch": 0.048639608262353876,
+      "grad_norm": 1.2053782939910889,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.7725,
+      "step": 5642
+    },
+    {
+      "epoch": 0.048906858857201974,
+      "grad_norm": 0.8168059587478638,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.7779,
+      "step": 5673
+    },
+    {
+      "epoch": 0.04917410945205007,
+      "grad_norm": 0.812278151512146,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.7884,
+      "step": 5704
+    },
+    {
+      "epoch": 0.04944136004689817,
+      "grad_norm": 0.9640679359436035,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.7794,
+      "step": 5735
+    },
+    {
+      "epoch": 0.04970861064174627,
+      "grad_norm": 0.8488368988037109,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.7705,
+      "step": 5766
+    },
+    {
+      "epoch": 0.049975861236594366,
+      "grad_norm": 0.7826496362686157,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.7665,
+      "step": 5797
+    },
+    {
+      "epoch": 0.050243111831442464,
+      "grad_norm": 0.7388876676559448,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.7715,
+      "step": 5828
+    },
+    {
+      "epoch": 0.05051036242629056,
+      "grad_norm": 0.7776780128479004,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.7777,
+      "step": 5859
+    },
+    {
+      "epoch": 0.05077761302113866,
+      "grad_norm": 1.1687864065170288,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.7698,
+      "step": 5890
+    },
+    {
+      "epoch": 0.05104486361598676,
+      "grad_norm": 1.069354772567749,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.7671,
+      "step": 5921
+    },
+    {
+      "epoch": 0.051312114210834855,
+      "grad_norm": 0.955895185470581,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.7641,
+      "step": 5952
+    },
+    {
+      "epoch": 0.05157936480568295,
+      "grad_norm": 0.8063961267471313,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.772,
+      "step": 5983
+    },
+    {
+      "epoch": 0.05184661540053105,
+      "grad_norm": 0.9584303498268127,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.762,
+      "step": 6014
+    },
+    {
+      "epoch": 0.05211386599537915,
+      "grad_norm": 0.9711636900901794,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.7742,
+      "step": 6045
+    },
+    {
+      "epoch": 0.05238111659022725,
+      "grad_norm": 0.8177659511566162,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.7532,
+      "step": 6076
+    },
+    {
+      "epoch": 0.052648367185075345,
+      "grad_norm": 0.7204889059066772,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.7674,
+      "step": 6107
+    },
+    {
+      "epoch": 0.05291561777992344,
+      "grad_norm": 0.7740707993507385,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.759,
+      "step": 6138
+    },
+    {
+      "epoch": 0.05318286837477154,
+      "grad_norm": 0.9027112126350403,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.7606,
+      "step": 6169
+    },
+    {
+      "epoch": 0.05345011896961964,
+      "grad_norm": 0.8888375759124756,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.7668,
+      "step": 6200
+    },
+    {
+      "epoch": 0.05371736956446774,
+      "grad_norm": 0.7049738764762878,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.7678,
+      "step": 6231
+    },
+    {
+      "epoch": 0.053984620159315835,
+      "grad_norm": 0.8254877924919128,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.766,
+      "step": 6262
+    },
+    {
+      "epoch": 0.05425187075416393,
+      "grad_norm": 0.8231219053268433,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.7577,
+      "step": 6293
+    },
+    {
+      "epoch": 0.05451912134901204,
+      "grad_norm": 0.859380841255188,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.7613,
+      "step": 6324
+    },
+    {
+      "epoch": 0.054786371943860136,
+      "grad_norm": 0.7607110142707825,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.7622,
+      "step": 6355
+    },
+    {
+      "epoch": 0.055053622538708234,
+      "grad_norm": 0.8904584646224976,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.7622,
+      "step": 6386
+    },
+    {
+      "epoch": 0.05532087313355633,
+      "grad_norm": 0.8488460183143616,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.7588,
+      "step": 6417
+    },
+    {
+      "epoch": 0.05558812372840443,
+      "grad_norm": 0.7917813062667847,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.7712,
+      "step": 6448
+    },
+    {
+      "epoch": 0.05585537432325253,
+      "grad_norm": 0.830741822719574,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.7615,
+      "step": 6479
+    },
+    {
+      "epoch": 0.056122624918100626,
+      "grad_norm": 0.9170836806297302,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.7572,
+      "step": 6510
+    },
+    {
+      "epoch": 0.056389875512948724,
+      "grad_norm": 0.8450523614883423,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.7497,
+      "step": 6541
+    },
+    {
+      "epoch": 0.05665712610779682,
+      "grad_norm": 0.8187207579612732,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.7684,
+      "step": 6572
+    },
+    {
+      "epoch": 0.05692437670264492,
+      "grad_norm": 0.8315821886062622,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.7685,
+      "step": 6603
+    },
+    {
+      "epoch": 0.05719162729749302,
+      "grad_norm": 1.0876758098602295,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.7617,
+      "step": 6634
+    },
+    {
+      "epoch": 0.057458877892341116,
+      "grad_norm": 0.9182093143463135,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.7621,
+      "step": 6665
+    },
+    {
+      "epoch": 0.057726128487189214,
+      "grad_norm": 0.6726477742195129,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.7637,
+      "step": 6696
+    },
+    {
+      "epoch": 0.05799337908203731,
+      "grad_norm": 0.8932876586914062,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.7643,
+      "step": 6727
+    },
+    {
+      "epoch": 0.05826062967688541,
+      "grad_norm": 0.7158175706863403,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.7585,
+      "step": 6758
+    },
+    {
+      "epoch": 0.05852788027173351,
+      "grad_norm": 0.7973946928977966,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.7594,
+      "step": 6789
+    },
+    {
+      "epoch": 0.058795130866581606,
+      "grad_norm": 0.8311556577682495,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.7646,
+      "step": 6820
+    },
+    {
+      "epoch": 0.059062381461429704,
+      "grad_norm": 1.623862385749817,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.7528,
+      "step": 6851
+    },
+    {
+      "epoch": 0.0593296320562778,
+      "grad_norm": 0.8134210109710693,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.752,
+      "step": 6882
+    },
+    {
+      "epoch": 0.0595968826511259,
+      "grad_norm": 0.8656156063079834,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.7504,
+      "step": 6913
+    },
+    {
+      "epoch": 0.059864133245974,
+      "grad_norm": 0.7220660448074341,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.7574,
+      "step": 6944
+    },
+    {
+      "epoch": 0.060131383840822096,
+      "grad_norm": 0.8750848174095154,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.7442,
+      "step": 6975
+    },
+    {
+      "epoch": 0.060398634435670194,
+      "grad_norm": 0.9824672937393188,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.7493,
+      "step": 7006
+    },
+    {
+      "epoch": 0.06066588503051829,
+      "grad_norm": 1.1746909618377686,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.7615,
+      "step": 7037
+    },
+    {
+      "epoch": 0.06093313562536639,
+      "grad_norm": 0.7957736849784851,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.7567,
+      "step": 7068
+    },
+    {
+      "epoch": 0.06120038622021449,
+      "grad_norm": 0.7611691355705261,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.7539,
+      "step": 7099
+    },
+    {
+      "epoch": 0.061467636815062586,
+      "grad_norm": 0.7961061596870422,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.7549,
+      "step": 7130
+    },
+    {
+      "epoch": 0.061734887409910684,
+      "grad_norm": 0.7554512023925781,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.7541,
+      "step": 7161
+    },
+    {
+      "epoch": 0.06200213800475878,
+      "grad_norm": 1.0506978034973145,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.7477,
+      "step": 7192
+    },
+    {
+      "epoch": 0.06226938859960688,
+      "grad_norm": 0.8036066889762878,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.7455,
+      "step": 7223
+    },
+    {
+      "epoch": 0.06253663919445498,
+      "grad_norm": 0.8787280917167664,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.747,
+      "step": 7254
+    },
+    {
+      "epoch": 0.06280388978930308,
+      "grad_norm": 0.7274677753448486,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.7568,
+      "step": 7285
+    },
+    {
+      "epoch": 0.06307114038415118,
+      "grad_norm": 0.7349788546562195,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.7472,
+      "step": 7316
+    },
+    {
+      "epoch": 0.06333839097899928,
+      "grad_norm": 0.7945473790168762,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.7581,
+      "step": 7347
+    },
+    {
+      "epoch": 0.06360564157384738,
+      "grad_norm": 0.7640956044197083,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.7451,
+      "step": 7378
+    },
+    {
+      "epoch": 0.06387289216869547,
+      "grad_norm": 0.7245631217956543,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.7437,
+      "step": 7409
+    },
+    {
+      "epoch": 0.06414014276354357,
+      "grad_norm": 0.7420781254768372,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.7626,
+      "step": 7440
+    },
+    {
+      "epoch": 0.06440739335839167,
+      "grad_norm": 0.774943470954895,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.7608,
+      "step": 7471
+    },
+    {
+      "epoch": 0.06467464395323977,
+      "grad_norm": 0.7587719559669495,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.7631,
+      "step": 7502
+    },
+    {
+      "epoch": 0.06494189454808787,
+      "grad_norm": 0.7052931785583496,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.7437,
+      "step": 7533
+    },
+    {
+      "epoch": 0.06520914514293596,
+      "grad_norm": 0.8177131414413452,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.75,
+      "step": 7564
+    },
+    {
+      "epoch": 0.06547639573778406,
+      "grad_norm": 0.8247653245925903,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.7446,
+      "step": 7595
+    },
+    {
+      "epoch": 0.06574364633263216,
+      "grad_norm": 0.6302705407142639,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.7459,
+      "step": 7626
+    },
+    {
+      "epoch": 0.06601089692748026,
+      "grad_norm": 0.645069420337677,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.7545,
+      "step": 7657
+    },
+    {
+      "epoch": 0.06627814752232836,
+      "grad_norm": 0.6515899300575256,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.7439,
+      "step": 7688
+    },
+    {
+      "epoch": 0.06654539811717645,
+      "grad_norm": 0.8527146577835083,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.7491,
+      "step": 7719
+    },
+    {
+      "epoch": 0.06681264871202455,
+      "grad_norm": 0.6546400785446167,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.7459,
+      "step": 7750
+    },
+    {
+      "epoch": 0.06707989930687265,
+      "grad_norm": 1.2422056198120117,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.747,
+      "step": 7781
+    },
+    {
+      "epoch": 0.06734714990172075,
+      "grad_norm": 0.7785826325416565,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.7454,
+      "step": 7812
+    },
+    {
+      "epoch": 0.06761440049656885,
+      "grad_norm": 0.7051584720611572,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.748,
+      "step": 7843
+    },
+    {
+      "epoch": 0.06788165109141694,
+      "grad_norm": 0.6893256306648254,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.7466,
+      "step": 7874
+    },
+    {
+      "epoch": 0.06814890168626504,
+      "grad_norm": 0.6570892930030823,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.7404,
+      "step": 7905
+    },
+    {
+      "epoch": 0.06841615228111314,
+      "grad_norm": 1.0755282640457153,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.7462,
+      "step": 7936
+    },
+    {
+      "epoch": 0.06868340287596124,
+      "grad_norm": 0.9138249158859253,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.7425,
+      "step": 7967
+    },
+    {
+      "epoch": 0.06895065347080934,
+      "grad_norm": 0.8147562146186829,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.7473,
+      "step": 7998
+    },
+    {
+      "epoch": 0.06921790406565743,
+      "grad_norm": 0.9558604955673218,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.7372,
+      "step": 8029
+    },
+    {
+      "epoch": 0.06948515466050553,
+      "grad_norm": 0.6429873704910278,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.7397,
+      "step": 8060
+    },
+    {
+      "epoch": 0.06975240525535363,
+      "grad_norm": 0.840124249458313,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.7462,
+      "step": 8091
+    },
+    {
+      "epoch": 0.07001965585020173,
+      "grad_norm": 0.8520084023475647,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.746,
+      "step": 8122
+    },
+    {
+      "epoch": 0.07028690644504983,
+      "grad_norm": 0.9427956938743591,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.7628,
+      "step": 8153
+    },
+    {
+      "epoch": 0.07055415703989792,
+      "grad_norm": 0.6754634380340576,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.7387,
+      "step": 8184
+    },
+    {
+      "epoch": 0.07082140763474602,
+      "grad_norm": 0.7089795470237732,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.7462,
+      "step": 8215
+    },
+    {
+      "epoch": 0.07108865822959412,
+      "grad_norm": 0.6123281717300415,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.7363,
+      "step": 8246
+    },
+    {
+      "epoch": 0.07135590882444222,
+      "grad_norm": 0.7722983360290527,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.7489,
+      "step": 8277
+    },
+    {
+      "epoch": 0.07162315941929032,
+      "grad_norm": 0.7888938784599304,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.7407,
+      "step": 8308
+    },
+    {
+      "epoch": 0.07189041001413841,
+      "grad_norm": 0.778743326663971,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.7412,
+      "step": 8339
+    },
+    {
+      "epoch": 0.07215766060898651,
+      "grad_norm": 0.7543514966964722,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.7408,
+      "step": 8370
+    },
+    {
+      "epoch": 0.07242491120383461,
+      "grad_norm": 0.8665831089019775,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.7332,
+      "step": 8401
+    },
+    {
+      "epoch": 0.07269216179868271,
+      "grad_norm": 0.8533165454864502,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.742,
+      "step": 8432
+    },
+    {
+      "epoch": 0.0729594123935308,
+      "grad_norm": 0.7969794869422913,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.7412,
+      "step": 8463
+    },
+    {
+      "epoch": 0.0732266629883789,
+      "grad_norm": 0.6950485706329346,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.748,
+      "step": 8494
+    },
+    {
+      "epoch": 0.073493913583227,
+      "grad_norm": 0.7154302000999451,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.7377,
+      "step": 8525
+    },
+    {
+      "epoch": 0.0737611641780751,
+      "grad_norm": 0.8694846630096436,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.7391,
+      "step": 8556
+    },
+    {
+      "epoch": 0.0740284147729232,
+      "grad_norm": 0.6354366540908813,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.7397,
+      "step": 8587
+    },
+    {
+      "epoch": 0.0742956653677713,
+      "grad_norm": 0.8266158699989319,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.7294,
+      "step": 8618
+    },
+    {
+      "epoch": 0.0745629159626194,
+      "grad_norm": 0.8990344405174255,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.7364,
+      "step": 8649
+    },
+    {
+      "epoch": 0.07483016655746749,
+      "grad_norm": 0.6664773225784302,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.7453,
+      "step": 8680
+    },
+    {
+      "epoch": 0.07509741715231559,
+      "grad_norm": 0.7253682017326355,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.7383,
+      "step": 8711
+    },
+    {
+      "epoch": 0.0753646677471637,
+      "grad_norm": 0.7291272878646851,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.7469,
+      "step": 8742
+    },
+    {
+      "epoch": 0.0756319183420118,
+      "grad_norm": 0.7150599956512451,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.7365,
+      "step": 8773
+    },
+    {
+      "epoch": 0.0758991689368599,
+      "grad_norm": 0.6730013489723206,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.7244,
+      "step": 8804
+    },
+    {
+      "epoch": 0.076166419531708,
+      "grad_norm": 0.8112632632255554,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.733,
+      "step": 8835
+    },
+    {
+      "epoch": 0.0764336701265561,
+      "grad_norm": 0.8358544707298279,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.7423,
+      "step": 8866
+    },
+    {
+      "epoch": 0.07670092072140419,
+      "grad_norm": 1.0025874376296997,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.7393,
+      "step": 8897
+    },
+    {
+      "epoch": 0.07696817131625229,
+      "grad_norm": 0.7373897433280945,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.7343,
+      "step": 8928
+    },
+    {
+      "epoch": 0.07723542191110039,
+      "grad_norm": 0.7370135188102722,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.7394,
+      "step": 8959
+    },
+    {
+      "epoch": 0.07750267250594849,
+      "grad_norm": 0.7160916924476624,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.7426,
+      "step": 8990
+    },
+    {
+      "epoch": 0.07776992310079658,
+      "grad_norm": 0.688937783241272,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.7345,
+      "step": 9021
+    },
+    {
+      "epoch": 0.07803717369564468,
+      "grad_norm": 0.6157529950141907,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.7437,
+      "step": 9052
+    },
+    {
+      "epoch": 0.07830442429049278,
+      "grad_norm": 0.7043218612670898,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.7346,
+      "step": 9083
+    },
+    {
+      "epoch": 0.07857167488534088,
+      "grad_norm": 0.7695103883743286,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.7243,
+      "step": 9114
+    },
+    {
+      "epoch": 0.07883892548018898,
+      "grad_norm": 0.7572926878929138,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.7307,
+      "step": 9145
+    },
+    {
+      "epoch": 0.07910617607503707,
+      "grad_norm": 0.7854665517807007,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.7317,
+      "step": 9176
+    },
+    {
+      "epoch": 0.07937342666988517,
+      "grad_norm": 0.8939421772956848,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.731,
+      "step": 9207
+    },
+    {
+      "epoch": 0.07964067726473327,
+      "grad_norm": 0.799430251121521,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.7322,
+      "step": 9238
+    },
+    {
+      "epoch": 0.07990792785958137,
+      "grad_norm": 0.7589206099510193,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.7273,
+      "step": 9269
+    },
+    {
+      "epoch": 0.08017517845442947,
+      "grad_norm": 0.5817182064056396,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.7357,
+      "step": 9300
+    },
+    {
+      "epoch": 0.08044242904927756,
+      "grad_norm": 1.0037076473236084,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.7296,
+      "step": 9331
+    },
+    {
+      "epoch": 0.08070967964412566,
+      "grad_norm": 0.8309381604194641,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.7324,
+      "step": 9362
+    },
+    {
+      "epoch": 0.08097693023897376,
+      "grad_norm": 0.7340037226676941,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.7343,
+      "step": 9393
+    },
+    {
+      "epoch": 0.08124418083382186,
+      "grad_norm": 0.6870521903038025,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.7314,
+      "step": 9424
+    },
+    {
+      "epoch": 0.08151143142866996,
+      "grad_norm": 0.6890373826026917,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.7316,
+      "step": 9455
+    },
+    {
+      "epoch": 0.08177868202351805,
+      "grad_norm": 0.7693931460380554,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.7332,
+      "step": 9486
+    },
+    {
+      "epoch": 0.08204593261836615,
+      "grad_norm": 0.8764196634292603,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.7267,
+      "step": 9517
+    },
+    {
+      "epoch": 0.08231318321321425,
+      "grad_norm": 0.7419659495353699,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.7344,
+      "step": 9548
+    },
+    {
+      "epoch": 0.08258043380806235,
+      "grad_norm": 0.754749596118927,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.7312,
+      "step": 9579
+    },
+    {
+      "epoch": 0.08284768440291045,
+      "grad_norm": 0.9303844571113586,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.7359,
+      "step": 9610
+    },
+    {
+      "epoch": 0.08311493499775854,
+      "grad_norm": 0.8202078342437744,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.7362,
+      "step": 9641
+    },
+    {
+      "epoch": 0.08338218559260664,
+      "grad_norm": 0.8347437977790833,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.7188,
+      "step": 9672
+    },
+    {
+      "epoch": 0.08364943618745474,
+      "grad_norm": 0.8407759070396423,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.7326,
+      "step": 9703
+    },
+    {
+      "epoch": 0.08391668678230284,
+      "grad_norm": 0.745712399482727,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.7286,
+      "step": 9734
+    },
+    {
+      "epoch": 0.08418393737715094,
+      "grad_norm": 0.630031168460846,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.7262,
+      "step": 9765
+    },
+    {
+      "epoch": 0.08445118797199903,
+      "grad_norm": 0.8924230933189392,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.7315,
+      "step": 9796
+    },
+    {
+      "epoch": 0.08471843856684713,
+      "grad_norm": 0.7842046022415161,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.7309,
+      "step": 9827
+    },
+    {
+      "epoch": 0.08498568916169523,
+      "grad_norm": 0.783723771572113,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.7307,
+      "step": 9858
+    },
+    {
+      "epoch": 0.08525293975654333,
+      "grad_norm": 0.6454151272773743,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.7277,
+      "step": 9889
+    },
+    {
+      "epoch": 0.08552019035139143,
+      "grad_norm": 0.781913697719574,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.7267,
+      "step": 9920
+    },
+    {
+      "epoch": 0.08578744094623952,
+      "grad_norm": 0.7176892161369324,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.7309,
+      "step": 9951
+    },
+    {
+      "epoch": 0.08605469154108762,
+      "grad_norm": 0.9282059669494629,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.7483,
+      "step": 9982
+    },
+    {
+      "epoch": 0.08632194213593572,
+      "grad_norm": 1.0737770795822144,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.7262,
+      "step": 10013
+    },
+    {
+      "epoch": 0.08658919273078382,
+      "grad_norm": 0.7671861052513123,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.7257,
+      "step": 10044
+    },
+    {
+      "epoch": 0.08685644332563192,
+      "grad_norm": 0.8341594934463501,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.72,
+      "step": 10075
+    },
+    {
+      "epoch": 0.08712369392048001,
+      "grad_norm": 0.9360256195068359,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.7277,
+      "step": 10106
+    },
+    {
+      "epoch": 0.08739094451532811,
+      "grad_norm": 0.6352283358573914,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.7258,
+      "step": 10137
+    },
+    {
+      "epoch": 0.08765819511017621,
+      "grad_norm": 0.6871002912521362,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.7184,
+      "step": 10168
+    },
+    {
+      "epoch": 0.08792544570502431,
+      "grad_norm": 0.6639994382858276,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.727,
+      "step": 10199
+    },
+    {
+      "epoch": 0.0881926962998724,
+      "grad_norm": 0.7937990427017212,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.7286,
+      "step": 10230
+    },
+    {
+      "epoch": 0.0884599468947205,
+      "grad_norm": 0.6229277849197388,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.7223,
+      "step": 10261
+    },
+    {
+      "epoch": 0.0887271974895686,
+      "grad_norm": 0.6489992737770081,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.7247,
+      "step": 10292
+    },
+    {
+      "epoch": 0.0889944480844167,
+      "grad_norm": 0.7326925992965698,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.7334,
+      "step": 10323
+    },
+    {
+      "epoch": 0.0892616986792648,
+      "grad_norm": 0.7646430730819702,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.7278,
+      "step": 10354
+    },
+    {
+      "epoch": 0.0895289492741129,
+      "grad_norm": 0.7933580279350281,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.7205,
+      "step": 10385
+    },
+    {
+      "epoch": 0.089796199868961,
+      "grad_norm": 1.0031253099441528,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.7224,
+      "step": 10416
+    },
+    {
+      "epoch": 0.09006345046380909,
+      "grad_norm": 0.9162613153457642,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.7382,
+      "step": 10447
+    },
+    {
+      "epoch": 0.09033070105865719,
+      "grad_norm": 0.8875689506530762,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.7224,
+      "step": 10478
+    },
+    {
+      "epoch": 0.09059795165350529,
+      "grad_norm": 0.8086528778076172,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.7278,
+      "step": 10509
+    },
+    {
+      "epoch": 0.09086520224835339,
+      "grad_norm": 0.6289557218551636,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.722,
+      "step": 10540
+    },
+    {
+      "epoch": 0.09113245284320148,
+      "grad_norm": 0.7295290231704712,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.7188,
+      "step": 10571
+    },
+    {
+      "epoch": 0.09139970343804958,
+      "grad_norm": 0.7659655809402466,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.7259,
+      "step": 10602
+    },
+    {
+      "epoch": 0.09166695403289768,
+      "grad_norm": 0.7740941047668457,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.7271,
+      "step": 10633
+    },
+    {
+      "epoch": 0.09193420462774578,
+      "grad_norm": 0.6929652094841003,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.7222,
+      "step": 10664
+    },
+    {
+      "epoch": 0.09220145522259389,
+      "grad_norm": 0.7807513475418091,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.7106,
+      "step": 10695
+    },
+    {
+      "epoch": 0.09246870581744199,
+      "grad_norm": 0.6159222722053528,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.7198,
+      "step": 10726
+    },
+    {
+      "epoch": 0.09273595641229009,
+      "grad_norm": 0.6694709658622742,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.7087,
+      "step": 10757
+    },
+    {
+      "epoch": 0.09300320700713818,
+      "grad_norm": 0.7234062552452087,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.7267,
+      "step": 10788
+    },
+    {
+      "epoch": 0.09327045760198628,
+      "grad_norm": 0.7624971270561218,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.725,
+      "step": 10819
+    },
+    {
+      "epoch": 0.09353770819683438,
+      "grad_norm": 0.7923869490623474,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.7226,
+      "step": 10850
+    },
+    {
+      "epoch": 0.09380495879168248,
+      "grad_norm": 0.7016533613204956,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.7295,
+      "step": 10881
+    },
+    {
+      "epoch": 0.09407220938653058,
+      "grad_norm": 0.6347571015357971,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.7129,
+      "step": 10912
+    },
+    {
+      "epoch": 0.09433945998137867,
+      "grad_norm": 0.7254231572151184,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.7181,
+      "step": 10943
+    },
+    {
+      "epoch": 0.09460671057622677,
+      "grad_norm": 0.7181808948516846,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.7179,
+      "step": 10974
+    },
+    {
+      "epoch": 0.09487396117107487,
+      "grad_norm": 0.7308523058891296,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.7243,
+      "step": 11005
+    },
+    {
+      "epoch": 0.09514121176592297,
+      "grad_norm": 0.8678077459335327,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.7254,
+      "step": 11036
+    },
+    {
+      "epoch": 0.09540846236077107,
+      "grad_norm": 0.6927953958511353,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.7242,
+      "step": 11067
+    },
+    {
+      "epoch": 0.09567571295561916,
+      "grad_norm": 0.5659973621368408,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.7157,
+      "step": 11098
+    },
+    {
+      "epoch": 0.09594296355046726,
+      "grad_norm": 0.8592713475227356,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.7117,
+      "step": 11129
+    },
+    {
+      "epoch": 0.09621021414531536,
+      "grad_norm": 0.6449655294418335,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.7197,
+      "step": 11160
+    },
+    {
+      "epoch": 0.09647746474016346,
+      "grad_norm": 0.7201160192489624,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.7189,
+      "step": 11191
+    },
+    {
+      "epoch": 0.09674471533501156,
+      "grad_norm": 0.6577209830284119,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.7235,
+      "step": 11222
+    },
+    {
+      "epoch": 0.09701196592985965,
+      "grad_norm": 0.7682704329490662,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.7183,
+      "step": 11253
+    },
+    {
+      "epoch": 0.09727921652470775,
+      "grad_norm": 0.6187945604324341,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.7046,
+      "step": 11284
+    },
+    {
+      "epoch": 0.09754646711955585,
+      "grad_norm": 0.6507108807563782,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.7253,
+      "step": 11315
+    },
+    {
+      "epoch": 0.09781371771440395,
+      "grad_norm": 0.6345822215080261,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.719,
+      "step": 11346
+    },
+    {
+      "epoch": 0.09808096830925205,
+      "grad_norm": 0.6644492149353027,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.7241,
+      "step": 11377
+    },
+    {
+      "epoch": 0.09834821890410014,
+      "grad_norm": 0.6215960383415222,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.7196,
+      "step": 11408
+    },
+    {
+      "epoch": 0.09861546949894824,
+      "grad_norm": 0.8039011359214783,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.7212,
+      "step": 11439
+    },
+    {
+      "epoch": 0.09888272009379634,
+      "grad_norm": 0.9103333353996277,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.7245,
+      "step": 11470
+    },
+    {
+      "epoch": 0.09914997068864444,
+      "grad_norm": 0.7850680947303772,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.7249,
+      "step": 11501
+    },
+    {
+      "epoch": 0.09941722128349254,
+      "grad_norm": 0.6277598738670349,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.7234,
+      "step": 11532
+    },
+    {
+      "epoch": 0.09968447187834063,
+      "grad_norm": 0.6920484900474548,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.7126,
+      "step": 11563
+    },
+    {
+      "epoch": 0.09995172247318873,
+      "grad_norm": 0.6442444324493408,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.7148,
+      "step": 11594
+    },
+    {
+      "epoch": 0.10021897306803683,
+      "grad_norm": 0.741570770740509,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.7216,
+      "step": 11625
+    },
+    {
+      "epoch": 0.10048622366288493,
+      "grad_norm": 0.7592952251434326,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.7143,
+      "step": 11656
+    },
+    {
+      "epoch": 0.10075347425773303,
+      "grad_norm": 0.6915357708930969,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.7166,
+      "step": 11687
+    },
+    {
+      "epoch": 0.10102072485258112,
+      "grad_norm": 0.8318819403648376,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.7092,
+      "step": 11718
+    },
+    {
+      "epoch": 0.10128797544742922,
+      "grad_norm": 0.8602069616317749,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.7196,
+      "step": 11749
+    },
+    {
+      "epoch": 0.10155522604227732,
+      "grad_norm": 0.7524039149284363,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.7115,
+      "step": 11780
+    },
+    {
+      "epoch": 0.10182247663712542,
+      "grad_norm": 0.6467952728271484,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.722,
+      "step": 11811
+    },
+    {
+      "epoch": 0.10208972723197351,
+      "grad_norm": 0.6989237070083618,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.7221,
+      "step": 11842
+    },
+    {
+      "epoch": 0.10235697782682161,
+      "grad_norm": 0.5162470936775208,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.7134,
+      "step": 11873
+    },
+    {
+      "epoch": 0.10262422842166971,
+      "grad_norm": 0.7181512713432312,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.7187,
+      "step": 11904
+    },
+    {
+      "epoch": 0.10289147901651781,
+      "grad_norm": 0.6398524641990662,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.7089,
+      "step": 11935
+    },
+    {
+      "epoch": 0.1031587296113659,
+      "grad_norm": 0.7089547514915466,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.7192,
+      "step": 11966
+    },
+    {
+      "epoch": 0.103425980206214,
+      "grad_norm": 0.8613171577453613,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.7192,
+      "step": 11997
+    },
+    {
+      "epoch": 0.1036932308010621,
+      "grad_norm": 0.6494088768959045,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.7162,
+      "step": 12028
+    },
+    {
+      "epoch": 0.1039604813959102,
+      "grad_norm": 0.6777063012123108,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.7252,
+      "step": 12059
+    },
+    {
+      "epoch": 0.1042277319907583,
+      "grad_norm": 0.7733666300773621,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.7196,
+      "step": 12090
+    },
+    {
+      "epoch": 0.1044949825856064,
+      "grad_norm": 0.6725175976753235,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.7191,
+      "step": 12121
+    },
+    {
+      "epoch": 0.1047622331804545,
+      "grad_norm": 0.6679649353027344,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.7207,
+      "step": 12152
+    },
+    {
+      "epoch": 0.10502948377530259,
+      "grad_norm": 0.7206579446792603,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.7166,
+      "step": 12183
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.48541631240156e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d58e858f50ca10fb06d8ff9f1c4584a3e2f380b3fe5f85a62b31928bcca534
+size 5304

checkpoint-15260/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-15260/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-15260/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90400601fcaede83330f55166d2ddc6d21f182cf945b9d36480ba04d51b4c2ba
+size 4976687216

checkpoint-15260/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edb205482e80b5d03e63693e387d459b0cb9c97948cde971ff025ba98f1396d
+size 4778622352

checkpoint-15260/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2222b40c6fea7def1d5911b059ab36bf97b9328e0251689f78a0a9ebd98cd18d
+size 4932743960

checkpoint-15260/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-15260/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-15260/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947c19e4e85f2e7835b2c23fe2d5a110672bd75a35821858a2475b8e42c3fb8b
+size 3662865184

checkpoint-15260/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f696f9d5564cd6cff7cb9c764503b9b12776c595db64a1056b830eff358878ff
+size 2179989632

checkpoint-15260/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-15260/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00c070a24cc23a95d836ba0e4b7188d0e4b4633256ea736dc831d7a89d520bf
+size 16177880918

checkpoint-15260/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-15260/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce335347efaebf038b8915bc0a8d2d587a4a1aa08ad0e015b4bc7cc4fba634e
+size 1064

checkpoint-15260/trainer_state.json

@@ -0,0 +1,3477 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.131556260560709,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0002672505948480982,
+      "grad_norm": 3.2076423168182373,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.4511,
+      "step": 31
+    },
+    {
+      "epoch": 0.0005345011896961964,
+      "grad_norm": 2.221529006958008,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 1.3342,
+      "step": 62
+    },
+    {
+      "epoch": 0.0008017517845442946,
+      "grad_norm": 2.961315393447876,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.2649,
+      "step": 93
+    },
+    {
+      "epoch": 0.0010690023793923928,
+      "grad_norm": 2.311617612838745,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.2278,
+      "step": 124
+    },
+    {
+      "epoch": 0.001336252974240491,
+      "grad_norm": 3.4343724250793457,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.2061,
+      "step": 155
+    },
+    {
+      "epoch": 0.0016035035690885892,
+      "grad_norm": 2.421396017074585,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.1848,
+      "step": 186
+    },
+    {
+      "epoch": 0.0018707541639366874,
+      "grad_norm": 2.8230600357055664,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.1586,
+      "step": 217
+    },
+    {
+      "epoch": 0.0021380047587847856,
+      "grad_norm": 2.021296501159668,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.1552,
+      "step": 248
+    },
+    {
+      "epoch": 0.002405255353632884,
+      "grad_norm": 2.2329111099243164,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.1342,
+      "step": 279
+    },
+    {
+      "epoch": 0.002672505948480982,
+      "grad_norm": 2.8933441638946533,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 1.1092,
+      "step": 310
+    },
+    {
+      "epoch": 0.0029397565433290805,
+      "grad_norm": 2.510772705078125,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 1.108,
+      "step": 341
+    },
+    {
+      "epoch": 0.0032070071381771785,
+      "grad_norm": 2.170926094055176,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.0982,
+      "step": 372
+    },
+    {
+      "epoch": 0.003474257733025277,
+      "grad_norm": 2.1116831302642822,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 1.0977,
+      "step": 403
+    },
+    {
+      "epoch": 0.003741508327873375,
+      "grad_norm": 2.5462026596069336,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 1.0797,
+      "step": 434
+    },
+    {
+      "epoch": 0.004008758922721473,
+      "grad_norm": 2.5239830017089844,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 1.0691,
+      "step": 465
+    },
+    {
+      "epoch": 0.004276009517569571,
+      "grad_norm": 2.640591859817505,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 1.0547,
+      "step": 496
+    },
+    {
+      "epoch": 0.004543260112417669,
+      "grad_norm": 1.9566192626953125,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 1.0526,
+      "step": 527
+    },
+    {
+      "epoch": 0.004810510707265768,
+      "grad_norm": 2.515118360519409,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 1.0614,
+      "step": 558
+    },
+    {
+      "epoch": 0.005077761302113866,
+      "grad_norm": 2.1588094234466553,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 1.0461,
+      "step": 589
+    },
+    {
+      "epoch": 0.005345011896961964,
+      "grad_norm": 2.448280096054077,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 1.0333,
+      "step": 620
+    },
+    {
+      "epoch": 0.005612262491810062,
+      "grad_norm": 2.9539694786071777,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 1.0224,
+      "step": 651
+    },
+    {
+      "epoch": 0.005879513086658161,
+      "grad_norm": 2.6804676055908203,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 1.0145,
+      "step": 682
+    },
+    {
+      "epoch": 0.006146763681506259,
+      "grad_norm": 2.176100730895996,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 1.0164,
+      "step": 713
+    },
+    {
+      "epoch": 0.006414014276354357,
+      "grad_norm": 1.9107022285461426,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 1.004,
+      "step": 744
+    },
+    {
+      "epoch": 0.006681264871202455,
+      "grad_norm": 3.175410270690918,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.9986,
+      "step": 775
+    },
+    {
+      "epoch": 0.006948515466050554,
+      "grad_norm": 1.7941040992736816,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.9979,
+      "step": 806
+    },
+    {
+      "epoch": 0.007215766060898652,
+      "grad_norm": 2.428041458129883,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 1.0056,
+      "step": 837
+    },
+    {
+      "epoch": 0.00748301665574675,
+      "grad_norm": 2.1440467834472656,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.9908,
+      "step": 868
+    },
+    {
+      "epoch": 0.007750267250594848,
+      "grad_norm": 2.138157844543457,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.986,
+      "step": 899
+    },
+    {
+      "epoch": 0.008017517845442947,
+      "grad_norm": 2.144076108932495,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.9768,
+      "step": 930
+    },
+    {
+      "epoch": 0.008284768440291045,
+      "grad_norm": 2.116927146911621,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.975,
+      "step": 961
+    },
+    {
+      "epoch": 0.008552019035139143,
+      "grad_norm": 2.0087051391601562,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.9746,
+      "step": 992
+    },
+    {
+      "epoch": 0.00881926962998724,
+      "grad_norm": 2.008014440536499,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.9612,
+      "step": 1023
+    },
+    {
+      "epoch": 0.009086520224835339,
+      "grad_norm": 2.5932323932647705,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.9611,
+      "step": 1054
+    },
+    {
+      "epoch": 0.009353770819683437,
+      "grad_norm": 1.7766073942184448,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.9529,
+      "step": 1085
+    },
+    {
+      "epoch": 0.009621021414531536,
+      "grad_norm": 1.699992299079895,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.9638,
+      "step": 1116
+    },
+    {
+      "epoch": 0.009888272009379634,
+      "grad_norm": 2.139831304550171,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.9518,
+      "step": 1147
+    },
+    {
+      "epoch": 0.010155522604227732,
+      "grad_norm": 2.510404109954834,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.9557,
+      "step": 1178
+    },
+    {
+      "epoch": 0.01042277319907583,
+      "grad_norm": 1.7539429664611816,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.949,
+      "step": 1209
+    },
+    {
+      "epoch": 0.010690023793923928,
+      "grad_norm": 1.7679015398025513,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.9285,
+      "step": 1240
+    },
+    {
+      "epoch": 0.010957274388772026,
+      "grad_norm": 1.6701771020889282,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.9391,
+      "step": 1271
+    },
+    {
+      "epoch": 0.011224524983620124,
+      "grad_norm": 1.7283812761306763,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.9328,
+      "step": 1302
+    },
+    {
+      "epoch": 0.011491775578468222,
+      "grad_norm": 1.363319754600525,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.9353,
+      "step": 1333
+    },
+    {
+      "epoch": 0.011759026173316322,
+      "grad_norm": 1.847582459449768,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.9272,
+      "step": 1364
+    },
+    {
+      "epoch": 0.01202627676816442,
+      "grad_norm": 1.6437714099884033,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.9219,
+      "step": 1395
+    },
+    {
+      "epoch": 0.012293527363012518,
+      "grad_norm": 1.979443073272705,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.91,
+      "step": 1426
+    },
+    {
+      "epoch": 0.012560777957860616,
+      "grad_norm": 1.601218342781067,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.9229,
+      "step": 1457
+    },
+    {
+      "epoch": 0.012828028552708714,
+      "grad_norm": 2.36148738861084,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.9199,
+      "step": 1488
+    },
+    {
+      "epoch": 0.013095279147556812,
+      "grad_norm": 4.211123466491699,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 1.0419,
+      "step": 1519
+    },
+    {
+      "epoch": 0.01336252974240491,
+      "grad_norm": 1.620786428451538,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.954,
+      "step": 1550
+    },
+    {
+      "epoch": 0.01362978033725301,
+      "grad_norm": 3.2490246295928955,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.9464,
+      "step": 1581
+    },
+    {
+      "epoch": 0.013897030932101108,
+      "grad_norm": 1.9302624464035034,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.9294,
+      "step": 1612
+    },
+    {
+      "epoch": 0.014164281526949206,
+      "grad_norm": 1.5750601291656494,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.922,
+      "step": 1643
+    },
+    {
+      "epoch": 0.014431532121797304,
+      "grad_norm": 53.0409049987793,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 1.0611,
+      "step": 1674
+    },
+    {
+      "epoch": 0.014698782716645402,
+      "grad_norm": 1.841700553894043,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 1.0363,
+      "step": 1705
+    },
+    {
+      "epoch": 0.0149660333114935,
+      "grad_norm": 1.2549737691879272,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.938,
+      "step": 1736
+    },
+    {
+      "epoch": 0.015233283906341597,
+      "grad_norm": 1.3289740085601807,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.9113,
+      "step": 1767
+    },
+    {
+      "epoch": 0.015500534501189695,
+      "grad_norm": 1.5228811502456665,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.921,
+      "step": 1798
+    },
+    {
+      "epoch": 0.015767785096037795,
+      "grad_norm": 1.5058027505874634,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.9214,
+      "step": 1829
+    },
+    {
+      "epoch": 0.016035035690885893,
+      "grad_norm": 9.535687446594238,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 1.3068,
+      "step": 1860
+    },
+    {
+      "epoch": 0.01630228628573399,
+      "grad_norm": 2.5820651054382324,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 1.7033,
+      "step": 1891
+    },
+    {
+      "epoch": 0.01656953688058209,
+      "grad_norm": 148.47412109375,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 1.6935,
+      "step": 1922
+    },
+    {
+      "epoch": 0.016836787475430187,
+      "grad_norm": 8.416805267333984,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 1.6607,
+      "step": 1953
+    },
+    {
+      "epoch": 0.017104038070278285,
+      "grad_norm": 5.2713470458984375,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 1.1301,
+      "step": 1984
+    },
+    {
+      "epoch": 0.017371288665126383,
+      "grad_norm": 2.096306800842285,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.9931,
+      "step": 2015
+    },
+    {
+      "epoch": 0.01763853925997448,
+      "grad_norm": 1.5476640462875366,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.9514,
+      "step": 2046
+    },
+    {
+      "epoch": 0.01790578985482258,
+      "grad_norm": 1.727232813835144,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.9409,
+      "step": 2077
+    },
+    {
+      "epoch": 0.018173040449670677,
+      "grad_norm": 26.08816909790039,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.9368,
+      "step": 2108
+    },
+    {
+      "epoch": 0.018440291044518775,
+      "grad_norm": 1.7082202434539795,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.9155,
+      "step": 2139
+    },
+    {
+      "epoch": 0.018707541639366873,
+      "grad_norm": 1.5962992906570435,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.9233,
+      "step": 2170
+    },
+    {
+      "epoch": 0.018974792234214975,
+      "grad_norm": 2.024268627166748,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.9128,
+      "step": 2201
+    },
+    {
+      "epoch": 0.019242042829063073,
+      "grad_norm": 1.4828873872756958,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.8957,
+      "step": 2232
+    },
+    {
+      "epoch": 0.01950929342391117,
+      "grad_norm": 1.745612382888794,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.9005,
+      "step": 2263
+    },
+    {
+      "epoch": 0.01977654401875927,
+      "grad_norm": 1.354095458984375,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.9002,
+      "step": 2294
+    },
+    {
+      "epoch": 0.020043794613607367,
+      "grad_norm": 2.6227681636810303,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.9004,
+      "step": 2325
+    },
+    {
+      "epoch": 0.020311045208455464,
+      "grad_norm": 1.3870893716812134,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.9018,
+      "step": 2356
+    },
+    {
+      "epoch": 0.020578295803303562,
+      "grad_norm": 1.2884349822998047,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.8993,
+      "step": 2387
+    },
+    {
+      "epoch": 0.02084554639815166,
+      "grad_norm": 1.215851068496704,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.8925,
+      "step": 2418
+    },
+    {
+      "epoch": 0.02111279699299976,
+      "grad_norm": 1.4246628284454346,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.8893,
+      "step": 2449
+    },
+    {
+      "epoch": 0.021380047587847856,
+      "grad_norm": 1.5495259761810303,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.8749,
+      "step": 2480
+    },
+    {
+      "epoch": 0.021647298182695954,
+      "grad_norm": 1.0121793746948242,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.8803,
+      "step": 2511
+    },
+    {
+      "epoch": 0.021914548777544052,
+      "grad_norm": 1.1507561206817627,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.8843,
+      "step": 2542
+    },
+    {
+      "epoch": 0.02218179937239215,
+      "grad_norm": 1.612584114074707,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.8733,
+      "step": 2573
+    },
+    {
+      "epoch": 0.02244904996724025,
+      "grad_norm": 1.4475393295288086,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.8669,
+      "step": 2604
+    },
+    {
+      "epoch": 0.022716300562088346,
+      "grad_norm": 1.9612644910812378,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.8791,
+      "step": 2635
+    },
+    {
+      "epoch": 0.022983551156936444,
+      "grad_norm": 1.6032893657684326,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.8646,
+      "step": 2666
+    },
+    {
+      "epoch": 0.023250801751784546,
+      "grad_norm": 1.6368708610534668,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.871,
+      "step": 2697
+    },
+    {
+      "epoch": 0.023518052346632644,
+      "grad_norm": 1.0245656967163086,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.8534,
+      "step": 2728
+    },
+    {
+      "epoch": 0.023785302941480742,
+      "grad_norm": 0.9378401041030884,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.8478,
+      "step": 2759
+    },
+    {
+      "epoch": 0.02405255353632884,
+      "grad_norm": 1.4262951612472534,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.8634,
+      "step": 2790
+    },
+    {
+      "epoch": 0.024319804131176938,
+      "grad_norm": 1.3320890665054321,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.8505,
+      "step": 2821
+    },
+    {
+      "epoch": 0.024587054726025036,
+      "grad_norm": 1.043971061706543,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.863,
+      "step": 2852
+    },
+    {
+      "epoch": 0.024854305320873134,
+      "grad_norm": 1.387088418006897,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.8505,
+      "step": 2883
+    },
+    {
+      "epoch": 0.025121555915721232,
+      "grad_norm": 1.1267746686935425,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.8528,
+      "step": 2914
+    },
+    {
+      "epoch": 0.02538880651056933,
+      "grad_norm": 0.9636305570602417,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.8453,
+      "step": 2945
+    },
+    {
+      "epoch": 0.025656057105417428,
+      "grad_norm": 1.1140860319137573,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.8664,
+      "step": 2976
+    },
+    {
+      "epoch": 0.025923307700265526,
+      "grad_norm": 1.1886147260665894,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.8569,
+      "step": 3007
+    },
+    {
+      "epoch": 0.026190558295113624,
+      "grad_norm": 1.0308467149734497,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.85,
+      "step": 3038
+    },
+    {
+      "epoch": 0.02645780888996172,
+      "grad_norm": 1.6353480815887451,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.8414,
+      "step": 3069
+    },
+    {
+      "epoch": 0.02672505948480982,
+      "grad_norm": 1.2031575441360474,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.8435,
+      "step": 3100
+    },
+    {
+      "epoch": 0.026992310079657918,
+      "grad_norm": 1.2575979232788086,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.8415,
+      "step": 3131
+    },
+    {
+      "epoch": 0.02725956067450602,
+      "grad_norm": 1.338584303855896,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.8414,
+      "step": 3162
+    },
+    {
+      "epoch": 0.027526811269354117,
+      "grad_norm": 1.3699461221694946,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.8397,
+      "step": 3193
+    },
+    {
+      "epoch": 0.027794061864202215,
+      "grad_norm": 1.1471112966537476,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.8304,
+      "step": 3224
+    },
+    {
+      "epoch": 0.028061312459050313,
+      "grad_norm": 1.1752680540084839,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.8408,
+      "step": 3255
+    },
+    {
+      "epoch": 0.02832856305389841,
+      "grad_norm": 1.089552879333496,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.8286,
+      "step": 3286
+    },
+    {
+      "epoch": 0.02859581364874651,
+      "grad_norm": 1.0688341856002808,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.8341,
+      "step": 3317
+    },
+    {
+      "epoch": 0.028863064243594607,
+      "grad_norm": 0.9290914535522461,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.8307,
+      "step": 3348
+    },
+    {
+      "epoch": 0.029130314838442705,
+      "grad_norm": 1.3211214542388916,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.8349,
+      "step": 3379
+    },
+    {
+      "epoch": 0.029397565433290803,
+      "grad_norm": 1.8893773555755615,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.8289,
+      "step": 3410
+    },
+    {
+      "epoch": 0.0296648160281389,
+      "grad_norm": 1.3086936473846436,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.8231,
+      "step": 3441
+    },
+    {
+      "epoch": 0.029932066622987,
+      "grad_norm": 1.356311559677124,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.8343,
+      "step": 3472
+    },
+    {
+      "epoch": 0.030199317217835097,
+      "grad_norm": 1.13872492313385,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.828,
+      "step": 3503
+    },
+    {
+      "epoch": 0.030466567812683195,
+      "grad_norm": 1.1912773847579956,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.8236,
+      "step": 3534
+    },
+    {
+      "epoch": 0.030733818407531293,
+      "grad_norm": 0.9231215715408325,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.8226,
+      "step": 3565
+    },
+    {
+      "epoch": 0.03100106900237939,
+      "grad_norm": 1.0268129110336304,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.8218,
+      "step": 3596
+    },
+    {
+      "epoch": 0.03126831959722749,
+      "grad_norm": 0.974876344203949,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.8149,
+      "step": 3627
+    },
+    {
+      "epoch": 0.03153557019207559,
+      "grad_norm": 1.2175925970077515,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.8152,
+      "step": 3658
+    },
+    {
+      "epoch": 0.03180282078692369,
+      "grad_norm": 1.2338181734085083,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.8089,
+      "step": 3689
+    },
+    {
+      "epoch": 0.032070071381771786,
+      "grad_norm": 1.1462433338165283,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.8216,
+      "step": 3720
+    },
+    {
+      "epoch": 0.032337321976619884,
+      "grad_norm": 1.1631278991699219,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.8272,
+      "step": 3751
+    },
+    {
+      "epoch": 0.03260457257146798,
+      "grad_norm": 0.903836727142334,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.816,
+      "step": 3782
+    },
+    {
+      "epoch": 0.03287182316631608,
+      "grad_norm": 0.944284975528717,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.8031,
+      "step": 3813
+    },
+    {
+      "epoch": 0.03313907376116418,
+      "grad_norm": 1.1210039854049683,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.8096,
+      "step": 3844
+    },
+    {
+      "epoch": 0.033406324356012276,
+      "grad_norm": 1.0448529720306396,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.8059,
+      "step": 3875
+    },
+    {
+      "epoch": 0.033673574950860374,
+      "grad_norm": 1.0655525922775269,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.81,
+      "step": 3906
+    },
+    {
+      "epoch": 0.03394082554570847,
+      "grad_norm": 1.223928451538086,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.8175,
+      "step": 3937
+    },
+    {
+      "epoch": 0.03420807614055657,
+      "grad_norm": 1.0895342826843262,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.7992,
+      "step": 3968
+    },
+    {
+      "epoch": 0.03447532673540467,
+      "grad_norm": 1.1117792129516602,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.8122,
+      "step": 3999
+    },
+    {
+      "epoch": 0.034742577330252766,
+      "grad_norm": 1.0806598663330078,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.811,
+      "step": 4030
+    },
+    {
+      "epoch": 0.035009827925100864,
+      "grad_norm": 0.7528677582740784,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.8036,
+      "step": 4061
+    },
+    {
+      "epoch": 0.03527707851994896,
+      "grad_norm": 1.1509230136871338,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.8047,
+      "step": 4092
+    },
+    {
+      "epoch": 0.03554432911479706,
+      "grad_norm": 1.1190931797027588,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.8123,
+      "step": 4123
+    },
+    {
+      "epoch": 0.03581157970964516,
+      "grad_norm": 0.8739308714866638,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.8015,
+      "step": 4154
+    },
+    {
+      "epoch": 0.036078830304493256,
+      "grad_norm": 0.9889201521873474,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.8056,
+      "step": 4185
+    },
+    {
+      "epoch": 0.036346080899341354,
+      "grad_norm": 1.1964142322540283,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.8083,
+      "step": 4216
+    },
+    {
+      "epoch": 0.03661333149418945,
+      "grad_norm": 1.0793588161468506,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.7976,
+      "step": 4247
+    },
+    {
+      "epoch": 0.03688058208903755,
+      "grad_norm": 1.2313084602355957,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.7954,
+      "step": 4278
+    },
+    {
+      "epoch": 0.03714783268388565,
+      "grad_norm": 1.1145700216293335,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.7947,
+      "step": 4309
+    },
+    {
+      "epoch": 0.037415083278733746,
+      "grad_norm": 0.9714220762252808,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.7973,
+      "step": 4340
+    },
+    {
+      "epoch": 0.03768233387358185,
+      "grad_norm": 1.0865004062652588,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.7918,
+      "step": 4371
+    },
+    {
+      "epoch": 0.03794958446842995,
+      "grad_norm": 0.8420351147651672,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.805,
+      "step": 4402
+    },
+    {
+      "epoch": 0.03821683506327805,
+      "grad_norm": 1.0622302293777466,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.7977,
+      "step": 4433
+    },
+    {
+      "epoch": 0.038484085658126145,
+      "grad_norm": 0.8536683320999146,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.7946,
+      "step": 4464
+    },
+    {
+      "epoch": 0.03875133625297424,
+      "grad_norm": 0.9905999302864075,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.7932,
+      "step": 4495
+    },
+    {
+      "epoch": 0.03901858684782234,
+      "grad_norm": 1.005560278892517,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.7956,
+      "step": 4526
+    },
+    {
+      "epoch": 0.03928583744267044,
+      "grad_norm": 0.8386696577072144,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.7865,
+      "step": 4557
+    },
+    {
+      "epoch": 0.03955308803751854,
+      "grad_norm": 0.8390759229660034,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.7925,
+      "step": 4588
+    },
+    {
+      "epoch": 0.039820338632366635,
+      "grad_norm": 0.7457160949707031,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.7911,
+      "step": 4619
+    },
+    {
+      "epoch": 0.04008758922721473,
+      "grad_norm": 0.9717801213264465,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.7917,
+      "step": 4650
+    },
+    {
+      "epoch": 0.04035483982206283,
+      "grad_norm": 0.8517304062843323,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.7966,
+      "step": 4681
+    },
+    {
+      "epoch": 0.04062209041691093,
+      "grad_norm": 0.7597792744636536,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.7798,
+      "step": 4712
+    },
+    {
+      "epoch": 0.04088934101175903,
+      "grad_norm": 0.9633410573005676,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.784,
+      "step": 4743
+    },
+    {
+      "epoch": 0.041156591606607125,
+      "grad_norm": 0.8668884634971619,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.7925,
+      "step": 4774
+    },
+    {
+      "epoch": 0.04142384220145522,
+      "grad_norm": 1.348170280456543,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.7882,
+      "step": 4805
+    },
+    {
+      "epoch": 0.04169109279630332,
+      "grad_norm": 0.9085477590560913,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.7834,
+      "step": 4836
+    },
+    {
+      "epoch": 0.04195834339115142,
+      "grad_norm": 1.2533594369888306,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.7968,
+      "step": 4867
+    },
+    {
+      "epoch": 0.04222559398599952,
+      "grad_norm": 1.0250332355499268,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.7755,
+      "step": 4898
+    },
+    {
+      "epoch": 0.042492844580847615,
+      "grad_norm": 0.8610180616378784,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.7819,
+      "step": 4929
+    },
+    {
+      "epoch": 0.04276009517569571,
+      "grad_norm": 0.8235286474227905,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.7834,
+      "step": 4960
+    },
+    {
+      "epoch": 0.04302734577054381,
+      "grad_norm": 0.95796799659729,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.7822,
+      "step": 4991
+    },
+    {
+      "epoch": 0.04329459636539191,
+      "grad_norm": 1.022430419921875,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.781,
+      "step": 5022
+    },
+    {
+      "epoch": 0.04356184696024001,
+      "grad_norm": 0.9080584645271301,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.783,
+      "step": 5053
+    },
+    {
+      "epoch": 0.043829097555088105,
+      "grad_norm": 0.9808719158172607,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.7838,
+      "step": 5084
+    },
+    {
+      "epoch": 0.0440963481499362,
+      "grad_norm": 0.8997575640678406,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.7816,
+      "step": 5115
+    },
+    {
+      "epoch": 0.0443635987447843,
+      "grad_norm": 0.8737884163856506,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.7785,
+      "step": 5146
+    },
+    {
+      "epoch": 0.0446308493396324,
+      "grad_norm": 0.7924982309341431,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.7752,
+      "step": 5177
+    },
+    {
+      "epoch": 0.0448980999344805,
+      "grad_norm": 1.1685878038406372,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.7881,
+      "step": 5208
+    },
+    {
+      "epoch": 0.045165350529328595,
+      "grad_norm": 1.0199975967407227,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.7663,
+      "step": 5239
+    },
+    {
+      "epoch": 0.04543260112417669,
+      "grad_norm": 0.8155254125595093,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.7775,
+      "step": 5270
+    },
+    {
+      "epoch": 0.04569985171902479,
+      "grad_norm": 0.976006805896759,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.7797,
+      "step": 5301
+    },
+    {
+      "epoch": 0.04596710231387289,
+      "grad_norm": 1.1252824068069458,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.7824,
+      "step": 5332
+    },
+    {
+      "epoch": 0.046234352908720994,
+      "grad_norm": 0.7603053450584412,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.7759,
+      "step": 5363
+    },
+    {
+      "epoch": 0.04650160350356909,
+      "grad_norm": 1.007767915725708,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.7832,
+      "step": 5394
+    },
+    {
+      "epoch": 0.04676885409841719,
+      "grad_norm": 1.1207255125045776,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.7849,
+      "step": 5425
+    },
+    {
+      "epoch": 0.04703610469326529,
+      "grad_norm": 1.0699808597564697,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.7814,
+      "step": 5456
+    },
+    {
+      "epoch": 0.047303355288113386,
+      "grad_norm": 0.8154749274253845,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.7806,
+      "step": 5487
+    },
+    {
+      "epoch": 0.047570605882961484,
+      "grad_norm": 0.7383331060409546,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.7765,
+      "step": 5518
+    },
+    {
+      "epoch": 0.04783785647780958,
+      "grad_norm": 0.9729552865028381,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.7754,
+      "step": 5549
+    },
+    {
+      "epoch": 0.04810510707265768,
+      "grad_norm": 0.9568310379981995,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.7733,
+      "step": 5580
+    },
+    {
+      "epoch": 0.04837235766750578,
+      "grad_norm": 1.0747005939483643,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.7764,
+      "step": 5611
+    },
+    {
+      "epoch": 0.048639608262353876,
+      "grad_norm": 1.2053782939910889,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.7725,
+      "step": 5642
+    },
+    {
+      "epoch": 0.048906858857201974,
+      "grad_norm": 0.8168059587478638,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.7779,
+      "step": 5673
+    },
+    {
+      "epoch": 0.04917410945205007,
+      "grad_norm": 0.812278151512146,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.7884,
+      "step": 5704
+    },
+    {
+      "epoch": 0.04944136004689817,
+      "grad_norm": 0.9640679359436035,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.7794,
+      "step": 5735
+    },
+    {
+      "epoch": 0.04970861064174627,
+      "grad_norm": 0.8488368988037109,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.7705,
+      "step": 5766
+    },
+    {
+      "epoch": 0.049975861236594366,
+      "grad_norm": 0.7826496362686157,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.7665,
+      "step": 5797
+    },
+    {
+      "epoch": 0.050243111831442464,
+      "grad_norm": 0.7388876676559448,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.7715,
+      "step": 5828
+    },
+    {
+      "epoch": 0.05051036242629056,
+      "grad_norm": 0.7776780128479004,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.7777,
+      "step": 5859
+    },
+    {
+      "epoch": 0.05077761302113866,
+      "grad_norm": 1.1687864065170288,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.7698,
+      "step": 5890
+    },
+    {
+      "epoch": 0.05104486361598676,
+      "grad_norm": 1.069354772567749,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.7671,
+      "step": 5921
+    },
+    {
+      "epoch": 0.051312114210834855,
+      "grad_norm": 0.955895185470581,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.7641,
+      "step": 5952
+    },
+    {
+      "epoch": 0.05157936480568295,
+      "grad_norm": 0.8063961267471313,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.772,
+      "step": 5983
+    },
+    {
+      "epoch": 0.05184661540053105,
+      "grad_norm": 0.9584303498268127,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.762,
+      "step": 6014
+    },
+    {
+      "epoch": 0.05211386599537915,
+      "grad_norm": 0.9711636900901794,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.7742,
+      "step": 6045
+    },
+    {
+      "epoch": 0.05238111659022725,
+      "grad_norm": 0.8177659511566162,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.7532,
+      "step": 6076
+    },
+    {
+      "epoch": 0.052648367185075345,
+      "grad_norm": 0.7204889059066772,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.7674,
+      "step": 6107
+    },
+    {
+      "epoch": 0.05291561777992344,
+      "grad_norm": 0.7740707993507385,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.759,
+      "step": 6138
+    },
+    {
+      "epoch": 0.05318286837477154,
+      "grad_norm": 0.9027112126350403,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.7606,
+      "step": 6169
+    },
+    {
+      "epoch": 0.05345011896961964,
+      "grad_norm": 0.8888375759124756,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.7668,
+      "step": 6200
+    },
+    {
+      "epoch": 0.05371736956446774,
+      "grad_norm": 0.7049738764762878,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.7678,
+      "step": 6231
+    },
+    {
+      "epoch": 0.053984620159315835,
+      "grad_norm": 0.8254877924919128,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.766,
+      "step": 6262
+    },
+    {
+      "epoch": 0.05425187075416393,
+      "grad_norm": 0.8231219053268433,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.7577,
+      "step": 6293
+    },
+    {
+      "epoch": 0.05451912134901204,
+      "grad_norm": 0.859380841255188,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.7613,
+      "step": 6324
+    },
+    {
+      "epoch": 0.054786371943860136,
+      "grad_norm": 0.7607110142707825,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.7622,
+      "step": 6355
+    },
+    {
+      "epoch": 0.055053622538708234,
+      "grad_norm": 0.8904584646224976,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.7622,
+      "step": 6386
+    },
+    {
+      "epoch": 0.05532087313355633,
+      "grad_norm": 0.8488460183143616,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.7588,
+      "step": 6417
+    },
+    {
+      "epoch": 0.05558812372840443,
+      "grad_norm": 0.7917813062667847,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.7712,
+      "step": 6448
+    },
+    {
+      "epoch": 0.05585537432325253,
+      "grad_norm": 0.830741822719574,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.7615,
+      "step": 6479
+    },
+    {
+      "epoch": 0.056122624918100626,
+      "grad_norm": 0.9170836806297302,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.7572,
+      "step": 6510
+    },
+    {
+      "epoch": 0.056389875512948724,
+      "grad_norm": 0.8450523614883423,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.7497,
+      "step": 6541
+    },
+    {
+      "epoch": 0.05665712610779682,
+      "grad_norm": 0.8187207579612732,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.7684,
+      "step": 6572
+    },
+    {
+      "epoch": 0.05692437670264492,
+      "grad_norm": 0.8315821886062622,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.7685,
+      "step": 6603
+    },
+    {
+      "epoch": 0.05719162729749302,
+      "grad_norm": 1.0876758098602295,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.7617,
+      "step": 6634
+    },
+    {
+      "epoch": 0.057458877892341116,
+      "grad_norm": 0.9182093143463135,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.7621,
+      "step": 6665
+    },
+    {
+      "epoch": 0.057726128487189214,
+      "grad_norm": 0.6726477742195129,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.7637,
+      "step": 6696
+    },
+    {
+      "epoch": 0.05799337908203731,
+      "grad_norm": 0.8932876586914062,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.7643,
+      "step": 6727
+    },
+    {
+      "epoch": 0.05826062967688541,
+      "grad_norm": 0.7158175706863403,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.7585,
+      "step": 6758
+    },
+    {
+      "epoch": 0.05852788027173351,
+      "grad_norm": 0.7973946928977966,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.7594,
+      "step": 6789
+    },
+    {
+      "epoch": 0.058795130866581606,
+      "grad_norm": 0.8311556577682495,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.7646,
+      "step": 6820
+    },
+    {
+      "epoch": 0.059062381461429704,
+      "grad_norm": 1.623862385749817,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.7528,
+      "step": 6851
+    },
+    {
+      "epoch": 0.0593296320562778,
+      "grad_norm": 0.8134210109710693,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.752,
+      "step": 6882
+    },
+    {
+      "epoch": 0.0595968826511259,
+      "grad_norm": 0.8656156063079834,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.7504,
+      "step": 6913
+    },
+    {
+      "epoch": 0.059864133245974,
+      "grad_norm": 0.7220660448074341,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.7574,
+      "step": 6944
+    },
+    {
+      "epoch": 0.060131383840822096,
+      "grad_norm": 0.8750848174095154,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.7442,
+      "step": 6975
+    },
+    {
+      "epoch": 0.060398634435670194,
+      "grad_norm": 0.9824672937393188,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.7493,
+      "step": 7006
+    },
+    {
+      "epoch": 0.06066588503051829,
+      "grad_norm": 1.1746909618377686,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.7615,
+      "step": 7037
+    },
+    {
+      "epoch": 0.06093313562536639,
+      "grad_norm": 0.7957736849784851,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.7567,
+      "step": 7068
+    },
+    {
+      "epoch": 0.06120038622021449,
+      "grad_norm": 0.7611691355705261,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.7539,
+      "step": 7099
+    },
+    {
+      "epoch": 0.061467636815062586,
+      "grad_norm": 0.7961061596870422,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.7549,
+      "step": 7130
+    },
+    {
+      "epoch": 0.061734887409910684,
+      "grad_norm": 0.7554512023925781,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.7541,
+      "step": 7161
+    },
+    {
+      "epoch": 0.06200213800475878,
+      "grad_norm": 1.0506978034973145,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.7477,
+      "step": 7192
+    },
+    {
+      "epoch": 0.06226938859960688,
+      "grad_norm": 0.8036066889762878,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.7455,
+      "step": 7223
+    },
+    {
+      "epoch": 0.06253663919445498,
+      "grad_norm": 0.8787280917167664,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.747,
+      "step": 7254
+    },
+    {
+      "epoch": 0.06280388978930308,
+      "grad_norm": 0.7274677753448486,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.7568,
+      "step": 7285
+    },
+    {
+      "epoch": 0.06307114038415118,
+      "grad_norm": 0.7349788546562195,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.7472,
+      "step": 7316
+    },
+    {
+      "epoch": 0.06333839097899928,
+      "grad_norm": 0.7945473790168762,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.7581,
+      "step": 7347
+    },
+    {
+      "epoch": 0.06360564157384738,
+      "grad_norm": 0.7640956044197083,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.7451,
+      "step": 7378
+    },
+    {
+      "epoch": 0.06387289216869547,
+      "grad_norm": 0.7245631217956543,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.7437,
+      "step": 7409
+    },
+    {
+      "epoch": 0.06414014276354357,
+      "grad_norm": 0.7420781254768372,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.7626,
+      "step": 7440
+    },
+    {
+      "epoch": 0.06440739335839167,
+      "grad_norm": 0.774943470954895,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.7608,
+      "step": 7471
+    },
+    {
+      "epoch": 0.06467464395323977,
+      "grad_norm": 0.7587719559669495,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.7631,
+      "step": 7502
+    },
+    {
+      "epoch": 0.06494189454808787,
+      "grad_norm": 0.7052931785583496,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.7437,
+      "step": 7533
+    },
+    {
+      "epoch": 0.06520914514293596,
+      "grad_norm": 0.8177131414413452,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.75,
+      "step": 7564
+    },
+    {
+      "epoch": 0.06547639573778406,
+      "grad_norm": 0.8247653245925903,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.7446,
+      "step": 7595
+    },
+    {
+      "epoch": 0.06574364633263216,
+      "grad_norm": 0.6302705407142639,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.7459,
+      "step": 7626
+    },
+    {
+      "epoch": 0.06601089692748026,
+      "grad_norm": 0.645069420337677,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.7545,
+      "step": 7657
+    },
+    {
+      "epoch": 0.06627814752232836,
+      "grad_norm": 0.6515899300575256,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.7439,
+      "step": 7688
+    },
+    {
+      "epoch": 0.06654539811717645,
+      "grad_norm": 0.8527146577835083,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.7491,
+      "step": 7719
+    },
+    {
+      "epoch": 0.06681264871202455,
+      "grad_norm": 0.6546400785446167,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.7459,
+      "step": 7750
+    },
+    {
+      "epoch": 0.06707989930687265,
+      "grad_norm": 1.2422056198120117,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.747,
+      "step": 7781
+    },
+    {
+      "epoch": 0.06734714990172075,
+      "grad_norm": 0.7785826325416565,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.7454,
+      "step": 7812
+    },
+    {
+      "epoch": 0.06761440049656885,
+      "grad_norm": 0.7051584720611572,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.748,
+      "step": 7843
+    },
+    {
+      "epoch": 0.06788165109141694,
+      "grad_norm": 0.6893256306648254,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.7466,
+      "step": 7874
+    },
+    {
+      "epoch": 0.06814890168626504,
+      "grad_norm": 0.6570892930030823,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.7404,
+      "step": 7905
+    },
+    {
+      "epoch": 0.06841615228111314,
+      "grad_norm": 1.0755282640457153,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.7462,
+      "step": 7936
+    },
+    {
+      "epoch": 0.06868340287596124,
+      "grad_norm": 0.9138249158859253,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.7425,
+      "step": 7967
+    },
+    {
+      "epoch": 0.06895065347080934,
+      "grad_norm": 0.8147562146186829,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.7473,
+      "step": 7998
+    },
+    {
+      "epoch": 0.06921790406565743,
+      "grad_norm": 0.9558604955673218,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.7372,
+      "step": 8029
+    },
+    {
+      "epoch": 0.06948515466050553,
+      "grad_norm": 0.6429873704910278,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.7397,
+      "step": 8060
+    },
+    {
+      "epoch": 0.06975240525535363,
+      "grad_norm": 0.840124249458313,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.7462,
+      "step": 8091
+    },
+    {
+      "epoch": 0.07001965585020173,
+      "grad_norm": 0.8520084023475647,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.746,
+      "step": 8122
+    },
+    {
+      "epoch": 0.07028690644504983,
+      "grad_norm": 0.9427956938743591,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.7628,
+      "step": 8153
+    },
+    {
+      "epoch": 0.07055415703989792,
+      "grad_norm": 0.6754634380340576,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.7387,
+      "step": 8184
+    },
+    {
+      "epoch": 0.07082140763474602,
+      "grad_norm": 0.7089795470237732,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.7462,
+      "step": 8215
+    },
+    {
+      "epoch": 0.07108865822959412,
+      "grad_norm": 0.6123281717300415,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.7363,
+      "step": 8246
+    },
+    {
+      "epoch": 0.07135590882444222,
+      "grad_norm": 0.7722983360290527,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.7489,
+      "step": 8277
+    },
+    {
+      "epoch": 0.07162315941929032,
+      "grad_norm": 0.7888938784599304,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.7407,
+      "step": 8308
+    },
+    {
+      "epoch": 0.07189041001413841,
+      "grad_norm": 0.778743326663971,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.7412,
+      "step": 8339
+    },
+    {
+      "epoch": 0.07215766060898651,
+      "grad_norm": 0.7543514966964722,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.7408,
+      "step": 8370
+    },
+    {
+      "epoch": 0.07242491120383461,
+      "grad_norm": 0.8665831089019775,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.7332,
+      "step": 8401
+    },
+    {
+      "epoch": 0.07269216179868271,
+      "grad_norm": 0.8533165454864502,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.742,
+      "step": 8432
+    },
+    {
+      "epoch": 0.0729594123935308,
+      "grad_norm": 0.7969794869422913,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.7412,
+      "step": 8463
+    },
+    {
+      "epoch": 0.0732266629883789,
+      "grad_norm": 0.6950485706329346,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.748,
+      "step": 8494
+    },
+    {
+      "epoch": 0.073493913583227,
+      "grad_norm": 0.7154302000999451,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.7377,
+      "step": 8525
+    },
+    {
+      "epoch": 0.0737611641780751,
+      "grad_norm": 0.8694846630096436,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.7391,
+      "step": 8556
+    },
+    {
+      "epoch": 0.0740284147729232,
+      "grad_norm": 0.6354366540908813,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.7397,
+      "step": 8587
+    },
+    {
+      "epoch": 0.0742956653677713,
+      "grad_norm": 0.8266158699989319,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.7294,
+      "step": 8618
+    },
+    {
+      "epoch": 0.0745629159626194,
+      "grad_norm": 0.8990344405174255,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.7364,
+      "step": 8649
+    },
+    {
+      "epoch": 0.07483016655746749,
+      "grad_norm": 0.6664773225784302,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.7453,
+      "step": 8680
+    },
+    {
+      "epoch": 0.07509741715231559,
+      "grad_norm": 0.7253682017326355,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.7383,
+      "step": 8711
+    },
+    {
+      "epoch": 0.0753646677471637,
+      "grad_norm": 0.7291272878646851,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.7469,
+      "step": 8742
+    },
+    {
+      "epoch": 0.0756319183420118,
+      "grad_norm": 0.7150599956512451,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.7365,
+      "step": 8773
+    },
+    {
+      "epoch": 0.0758991689368599,
+      "grad_norm": 0.6730013489723206,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.7244,
+      "step": 8804
+    },
+    {
+      "epoch": 0.076166419531708,
+      "grad_norm": 0.8112632632255554,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.733,
+      "step": 8835
+    },
+    {
+      "epoch": 0.0764336701265561,
+      "grad_norm": 0.8358544707298279,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.7423,
+      "step": 8866
+    },
+    {
+      "epoch": 0.07670092072140419,
+      "grad_norm": 1.0025874376296997,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.7393,
+      "step": 8897
+    },
+    {
+      "epoch": 0.07696817131625229,
+      "grad_norm": 0.7373897433280945,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.7343,
+      "step": 8928
+    },
+    {
+      "epoch": 0.07723542191110039,
+      "grad_norm": 0.7370135188102722,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.7394,
+      "step": 8959
+    },
+    {
+      "epoch": 0.07750267250594849,
+      "grad_norm": 0.7160916924476624,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.7426,
+      "step": 8990
+    },
+    {
+      "epoch": 0.07776992310079658,
+      "grad_norm": 0.688937783241272,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.7345,
+      "step": 9021
+    },
+    {
+      "epoch": 0.07803717369564468,
+      "grad_norm": 0.6157529950141907,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.7437,
+      "step": 9052
+    },
+    {
+      "epoch": 0.07830442429049278,
+      "grad_norm": 0.7043218612670898,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.7346,
+      "step": 9083
+    },
+    {
+      "epoch": 0.07857167488534088,
+      "grad_norm": 0.7695103883743286,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.7243,
+      "step": 9114
+    },
+    {
+      "epoch": 0.07883892548018898,
+      "grad_norm": 0.7572926878929138,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.7307,
+      "step": 9145
+    },
+    {
+      "epoch": 0.07910617607503707,
+      "grad_norm": 0.7854665517807007,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.7317,
+      "step": 9176
+    },
+    {
+      "epoch": 0.07937342666988517,
+      "grad_norm": 0.8939421772956848,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.731,
+      "step": 9207
+    },
+    {
+      "epoch": 0.07964067726473327,
+      "grad_norm": 0.799430251121521,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.7322,
+      "step": 9238
+    },
+    {
+      "epoch": 0.07990792785958137,
+      "grad_norm": 0.7589206099510193,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.7273,
+      "step": 9269
+    },
+    {
+      "epoch": 0.08017517845442947,
+      "grad_norm": 0.5817182064056396,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.7357,
+      "step": 9300
+    },
+    {
+      "epoch": 0.08044242904927756,
+      "grad_norm": 1.0037076473236084,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.7296,
+      "step": 9331
+    },
+    {
+      "epoch": 0.08070967964412566,
+      "grad_norm": 0.8309381604194641,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.7324,
+      "step": 9362
+    },
+    {
+      "epoch": 0.08097693023897376,
+      "grad_norm": 0.7340037226676941,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.7343,
+      "step": 9393
+    },
+    {
+      "epoch": 0.08124418083382186,
+      "grad_norm": 0.6870521903038025,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.7314,
+      "step": 9424
+    },
+    {
+      "epoch": 0.08151143142866996,
+      "grad_norm": 0.6890373826026917,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.7316,
+      "step": 9455
+    },
+    {
+      "epoch": 0.08177868202351805,
+      "grad_norm": 0.7693931460380554,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.7332,
+      "step": 9486
+    },
+    {
+      "epoch": 0.08204593261836615,
+      "grad_norm": 0.8764196634292603,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.7267,
+      "step": 9517
+    },
+    {
+      "epoch": 0.08231318321321425,
+      "grad_norm": 0.7419659495353699,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.7344,
+      "step": 9548
+    },
+    {
+      "epoch": 0.08258043380806235,
+      "grad_norm": 0.754749596118927,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.7312,
+      "step": 9579
+    },
+    {
+      "epoch": 0.08284768440291045,
+      "grad_norm": 0.9303844571113586,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.7359,
+      "step": 9610
+    },
+    {
+      "epoch": 0.08311493499775854,
+      "grad_norm": 0.8202078342437744,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.7362,
+      "step": 9641
+    },
+    {
+      "epoch": 0.08338218559260664,
+      "grad_norm": 0.8347437977790833,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.7188,
+      "step": 9672
+    },
+    {
+      "epoch": 0.08364943618745474,
+      "grad_norm": 0.8407759070396423,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.7326,
+      "step": 9703
+    },
+    {
+      "epoch": 0.08391668678230284,
+      "grad_norm": 0.745712399482727,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.7286,
+      "step": 9734
+    },
+    {
+      "epoch": 0.08418393737715094,
+      "grad_norm": 0.630031168460846,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.7262,
+      "step": 9765
+    },
+    {
+      "epoch": 0.08445118797199903,
+      "grad_norm": 0.8924230933189392,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.7315,
+      "step": 9796
+    },
+    {
+      "epoch": 0.08471843856684713,
+      "grad_norm": 0.7842046022415161,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.7309,
+      "step": 9827
+    },
+    {
+      "epoch": 0.08498568916169523,
+      "grad_norm": 0.783723771572113,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.7307,
+      "step": 9858
+    },
+    {
+      "epoch": 0.08525293975654333,
+      "grad_norm": 0.6454151272773743,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.7277,
+      "step": 9889
+    },
+    {
+      "epoch": 0.08552019035139143,
+      "grad_norm": 0.781913697719574,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.7267,
+      "step": 9920
+    },
+    {
+      "epoch": 0.08578744094623952,
+      "grad_norm": 0.7176892161369324,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.7309,
+      "step": 9951
+    },
+    {
+      "epoch": 0.08605469154108762,
+      "grad_norm": 0.9282059669494629,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.7483,
+      "step": 9982
+    },
+    {
+      "epoch": 0.08632194213593572,
+      "grad_norm": 1.0737770795822144,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.7262,
+      "step": 10013
+    },
+    {
+      "epoch": 0.08658919273078382,
+      "grad_norm": 0.7671861052513123,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.7257,
+      "step": 10044
+    },
+    {
+      "epoch": 0.08685644332563192,
+      "grad_norm": 0.8341594934463501,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.72,
+      "step": 10075
+    },
+    {
+      "epoch": 0.08712369392048001,
+      "grad_norm": 0.9360256195068359,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.7277,
+      "step": 10106
+    },
+    {
+      "epoch": 0.08739094451532811,
+      "grad_norm": 0.6352283358573914,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.7258,
+      "step": 10137
+    },
+    {
+      "epoch": 0.08765819511017621,
+      "grad_norm": 0.6871002912521362,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.7184,
+      "step": 10168
+    },
+    {
+      "epoch": 0.08792544570502431,
+      "grad_norm": 0.6639994382858276,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.727,
+      "step": 10199
+    },
+    {
+      "epoch": 0.0881926962998724,
+      "grad_norm": 0.7937990427017212,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.7286,
+      "step": 10230
+    },
+    {
+      "epoch": 0.0884599468947205,
+      "grad_norm": 0.6229277849197388,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.7223,
+      "step": 10261
+    },
+    {
+      "epoch": 0.0887271974895686,
+      "grad_norm": 0.6489992737770081,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.7247,
+      "step": 10292
+    },
+    {
+      "epoch": 0.0889944480844167,
+      "grad_norm": 0.7326925992965698,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.7334,
+      "step": 10323
+    },
+    {
+      "epoch": 0.0892616986792648,
+      "grad_norm": 0.7646430730819702,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.7278,
+      "step": 10354
+    },
+    {
+      "epoch": 0.0895289492741129,
+      "grad_norm": 0.7933580279350281,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.7205,
+      "step": 10385
+    },
+    {
+      "epoch": 0.089796199868961,
+      "grad_norm": 1.0031253099441528,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.7224,
+      "step": 10416
+    },
+    {
+      "epoch": 0.09006345046380909,
+      "grad_norm": 0.9162613153457642,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.7382,
+      "step": 10447
+    },
+    {
+      "epoch": 0.09033070105865719,
+      "grad_norm": 0.8875689506530762,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.7224,
+      "step": 10478
+    },
+    {
+      "epoch": 0.09059795165350529,
+      "grad_norm": 0.8086528778076172,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.7278,
+      "step": 10509
+    },
+    {
+      "epoch": 0.09086520224835339,
+      "grad_norm": 0.6289557218551636,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.722,
+      "step": 10540
+    },
+    {
+      "epoch": 0.09113245284320148,
+      "grad_norm": 0.7295290231704712,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.7188,
+      "step": 10571
+    },
+    {
+      "epoch": 0.09139970343804958,
+      "grad_norm": 0.7659655809402466,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.7259,
+      "step": 10602
+    },
+    {
+      "epoch": 0.09166695403289768,
+      "grad_norm": 0.7740941047668457,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.7271,
+      "step": 10633
+    },
+    {
+      "epoch": 0.09193420462774578,
+      "grad_norm": 0.6929652094841003,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.7222,
+      "step": 10664
+    },
+    {
+      "epoch": 0.09220145522259389,
+      "grad_norm": 0.7807513475418091,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.7106,
+      "step": 10695
+    },
+    {
+      "epoch": 0.09246870581744199,
+      "grad_norm": 0.6159222722053528,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.7198,
+      "step": 10726
+    },
+    {
+      "epoch": 0.09273595641229009,
+      "grad_norm": 0.6694709658622742,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.7087,
+      "step": 10757
+    },
+    {
+      "epoch": 0.09300320700713818,
+      "grad_norm": 0.7234062552452087,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.7267,
+      "step": 10788
+    },
+    {
+      "epoch": 0.09327045760198628,
+      "grad_norm": 0.7624971270561218,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.725,
+      "step": 10819
+    },
+    {
+      "epoch": 0.09353770819683438,
+      "grad_norm": 0.7923869490623474,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.7226,
+      "step": 10850
+    },
+    {
+      "epoch": 0.09380495879168248,
+      "grad_norm": 0.7016533613204956,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.7295,
+      "step": 10881
+    },
+    {
+      "epoch": 0.09407220938653058,
+      "grad_norm": 0.6347571015357971,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.7129,
+      "step": 10912
+    },
+    {
+      "epoch": 0.09433945998137867,
+      "grad_norm": 0.7254231572151184,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.7181,
+      "step": 10943
+    },
+    {
+      "epoch": 0.09460671057622677,
+      "grad_norm": 0.7181808948516846,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.7179,
+      "step": 10974
+    },
+    {
+      "epoch": 0.09487396117107487,
+      "grad_norm": 0.7308523058891296,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.7243,
+      "step": 11005
+    },
+    {
+      "epoch": 0.09514121176592297,
+      "grad_norm": 0.8678077459335327,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.7254,
+      "step": 11036
+    },
+    {
+      "epoch": 0.09540846236077107,
+      "grad_norm": 0.6927953958511353,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.7242,
+      "step": 11067
+    },
+    {
+      "epoch": 0.09567571295561916,
+      "grad_norm": 0.5659973621368408,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.7157,
+      "step": 11098
+    },
+    {
+      "epoch": 0.09594296355046726,
+      "grad_norm": 0.8592713475227356,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.7117,
+      "step": 11129
+    },
+    {
+      "epoch": 0.09621021414531536,
+      "grad_norm": 0.6449655294418335,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.7197,
+      "step": 11160
+    },
+    {
+      "epoch": 0.09647746474016346,
+      "grad_norm": 0.7201160192489624,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.7189,
+      "step": 11191
+    },
+    {
+      "epoch": 0.09674471533501156,
+      "grad_norm": 0.6577209830284119,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.7235,
+      "step": 11222
+    },
+    {
+      "epoch": 0.09701196592985965,
+      "grad_norm": 0.7682704329490662,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.7183,
+      "step": 11253
+    },
+    {
+      "epoch": 0.09727921652470775,
+      "grad_norm": 0.6187945604324341,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.7046,
+      "step": 11284
+    },
+    {
+      "epoch": 0.09754646711955585,
+      "grad_norm": 0.6507108807563782,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.7253,
+      "step": 11315
+    },
+    {
+      "epoch": 0.09781371771440395,
+      "grad_norm": 0.6345822215080261,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.719,
+      "step": 11346
+    },
+    {
+      "epoch": 0.09808096830925205,
+      "grad_norm": 0.6644492149353027,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.7241,
+      "step": 11377
+    },
+    {
+      "epoch": 0.09834821890410014,
+      "grad_norm": 0.6215960383415222,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.7196,
+      "step": 11408
+    },
+    {
+      "epoch": 0.09861546949894824,
+      "grad_norm": 0.8039011359214783,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.7212,
+      "step": 11439
+    },
+    {
+      "epoch": 0.09888272009379634,
+      "grad_norm": 0.9103333353996277,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.7245,
+      "step": 11470
+    },
+    {
+      "epoch": 0.09914997068864444,
+      "grad_norm": 0.7850680947303772,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.7249,
+      "step": 11501
+    },
+    {
+      "epoch": 0.09941722128349254,
+      "grad_norm": 0.6277598738670349,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.7234,
+      "step": 11532
+    },
+    {
+      "epoch": 0.09968447187834063,
+      "grad_norm": 0.6920484900474548,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.7126,
+      "step": 11563
+    },
+    {
+      "epoch": 0.09995172247318873,
+      "grad_norm": 0.6442444324493408,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.7148,
+      "step": 11594
+    },
+    {
+      "epoch": 0.10021897306803683,
+      "grad_norm": 0.741570770740509,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.7216,
+      "step": 11625
+    },
+    {
+      "epoch": 0.10048622366288493,
+      "grad_norm": 0.7592952251434326,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.7143,
+      "step": 11656
+    },
+    {
+      "epoch": 0.10075347425773303,
+      "grad_norm": 0.6915357708930969,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.7166,
+      "step": 11687
+    },
+    {
+      "epoch": 0.10102072485258112,
+      "grad_norm": 0.8318819403648376,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.7092,
+      "step": 11718
+    },
+    {
+      "epoch": 0.10128797544742922,
+      "grad_norm": 0.8602069616317749,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.7196,
+      "step": 11749
+    },
+    {
+      "epoch": 0.10155522604227732,
+      "grad_norm": 0.7524039149284363,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.7115,
+      "step": 11780
+    },
+    {
+      "epoch": 0.10182247663712542,
+      "grad_norm": 0.6467952728271484,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.722,
+      "step": 11811
+    },
+    {
+      "epoch": 0.10208972723197351,
+      "grad_norm": 0.6989237070083618,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.7221,
+      "step": 11842
+    },
+    {
+      "epoch": 0.10235697782682161,
+      "grad_norm": 0.5162470936775208,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.7134,
+      "step": 11873
+    },
+    {
+      "epoch": 0.10262422842166971,
+      "grad_norm": 0.7181512713432312,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.7187,
+      "step": 11904
+    },
+    {
+      "epoch": 0.10289147901651781,
+      "grad_norm": 0.6398524641990662,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.7089,
+      "step": 11935
+    },
+    {
+      "epoch": 0.1031587296113659,
+      "grad_norm": 0.7089547514915466,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.7192,
+      "step": 11966
+    },
+    {
+      "epoch": 0.103425980206214,
+      "grad_norm": 0.8613171577453613,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.7192,
+      "step": 11997
+    },
+    {
+      "epoch": 0.1036932308010621,
+      "grad_norm": 0.6494088768959045,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.7162,
+      "step": 12028
+    },
+    {
+      "epoch": 0.1039604813959102,
+      "grad_norm": 0.6777063012123108,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.7252,
+      "step": 12059
+    },
+    {
+      "epoch": 0.1042277319907583,
+      "grad_norm": 0.7733666300773621,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.7196,
+      "step": 12090
+    },
+    {
+      "epoch": 0.1044949825856064,
+      "grad_norm": 0.6725175976753235,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.7191,
+      "step": 12121
+    },
+    {
+      "epoch": 0.1047622331804545,
+      "grad_norm": 0.6679649353027344,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.7207,
+      "step": 12152
+    },
+    {
+      "epoch": 0.10502948377530259,
+      "grad_norm": 0.7206579446792603,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.7166,
+      "step": 12183
+    },
+    {
+      "epoch": 0.10529673437015069,
+      "grad_norm": 0.6833537817001343,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 0.7143,
+      "step": 12214
+    },
+    {
+      "epoch": 0.10556398496499879,
+      "grad_norm": 0.7469558119773865,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 0.7131,
+      "step": 12245
+    },
+    {
+      "epoch": 0.10583123555984689,
+      "grad_norm": 0.665662944316864,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 0.721,
+      "step": 12276
+    },
+    {
+      "epoch": 0.10609848615469498,
+      "grad_norm": 0.6722923517227173,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 0.717,
+      "step": 12307
+    },
+    {
+      "epoch": 0.10636573674954308,
+      "grad_norm": 0.7240269780158997,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 0.7188,
+      "step": 12338
+    },
+    {
+      "epoch": 0.10663298734439118,
+      "grad_norm": 0.6044260859489441,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 0.7114,
+      "step": 12369
+    },
+    {
+      "epoch": 0.10690023793923928,
+      "grad_norm": 0.5933346748352051,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 0.7224,
+      "step": 12400
+    },
+    {
+      "epoch": 0.10716748853408738,
+      "grad_norm": 0.6202985644340515,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 0.7114,
+      "step": 12431
+    },
+    {
+      "epoch": 0.10743473912893547,
+      "grad_norm": 0.7195279002189636,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 0.7074,
+      "step": 12462
+    },
+    {
+      "epoch": 0.10770198972378357,
+      "grad_norm": 0.6577067971229553,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 0.7103,
+      "step": 12493
+    },
+    {
+      "epoch": 0.10796924031863167,
+      "grad_norm": 0.5871012806892395,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 0.7143,
+      "step": 12524
+    },
+    {
+      "epoch": 0.10823649091347977,
+      "grad_norm": 0.7182403206825256,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 0.7131,
+      "step": 12555
+    },
+    {
+      "epoch": 0.10850374150832787,
+      "grad_norm": 0.7164127230644226,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 0.7078,
+      "step": 12586
+    },
+    {
+      "epoch": 0.10877099210317596,
+      "grad_norm": 0.6984509825706482,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 0.7052,
+      "step": 12617
+    },
+    {
+      "epoch": 0.10903824269802408,
+      "grad_norm": 0.7046581506729126,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 0.7087,
+      "step": 12648
+    },
+    {
+      "epoch": 0.10930549329287217,
+      "grad_norm": 0.7870312333106995,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 0.7073,
+      "step": 12679
+    },
+    {
+      "epoch": 0.10957274388772027,
+      "grad_norm": 0.6933169960975647,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 0.7123,
+      "step": 12710
+    },
+    {
+      "epoch": 0.10983999448256837,
+      "grad_norm": 0.8421098589897156,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 0.7074,
+      "step": 12741
+    },
+    {
+      "epoch": 0.11010724507741647,
+      "grad_norm": 0.6738384962081909,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 0.7102,
+      "step": 12772
+    },
+    {
+      "epoch": 0.11037449567226457,
+      "grad_norm": 1.22402024269104,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 0.7096,
+      "step": 12803
+    },
+    {
+      "epoch": 0.11064174626711266,
+      "grad_norm": 0.637190580368042,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 0.7094,
+      "step": 12834
+    },
+    {
+      "epoch": 0.11090899686196076,
+      "grad_norm": 0.6984738111495972,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 0.7039,
+      "step": 12865
+    },
+    {
+      "epoch": 0.11117624745680886,
+      "grad_norm": 0.6750801801681519,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 0.7109,
+      "step": 12896
+    },
+    {
+      "epoch": 0.11144349805165696,
+      "grad_norm": 0.605526864528656,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 0.7107,
+      "step": 12927
+    },
+    {
+      "epoch": 0.11171074864650506,
+      "grad_norm": 0.6708593964576721,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 0.7115,
+      "step": 12958
+    },
+    {
+      "epoch": 0.11197799924135315,
+      "grad_norm": 0.8030126690864563,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 0.6952,
+      "step": 12989
+    },
+    {
+      "epoch": 0.11224524983620125,
+      "grad_norm": 0.7429558038711548,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 0.7193,
+      "step": 13020
+    },
+    {
+      "epoch": 0.11251250043104935,
+      "grad_norm": 0.5634856224060059,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 0.7027,
+      "step": 13051
+    },
+    {
+      "epoch": 0.11277975102589745,
+      "grad_norm": 0.6698859930038452,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 0.706,
+      "step": 13082
+    },
+    {
+      "epoch": 0.11304700162074555,
+      "grad_norm": 0.6879245042800903,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 0.7145,
+      "step": 13113
+    },
+    {
+      "epoch": 0.11331425221559364,
+      "grad_norm": 0.6581853628158569,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 0.7052,
+      "step": 13144
+    },
+    {
+      "epoch": 0.11358150281044174,
+      "grad_norm": 0.7926408648490906,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 0.7055,
+      "step": 13175
+    },
+    {
+      "epoch": 0.11384875340528984,
+      "grad_norm": 0.7677760720252991,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 0.705,
+      "step": 13206
+    },
+    {
+      "epoch": 0.11411600400013794,
+      "grad_norm": 0.7506090998649597,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 0.7099,
+      "step": 13237
+    },
+    {
+      "epoch": 0.11438325459498604,
+      "grad_norm": 0.7195343375205994,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 0.7091,
+      "step": 13268
+    },
+    {
+      "epoch": 0.11465050518983413,
+      "grad_norm": 0.5797944068908691,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 0.7134,
+      "step": 13299
+    },
+    {
+      "epoch": 0.11491775578468223,
+      "grad_norm": 0.6853557229042053,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 0.7116,
+      "step": 13330
+    },
+    {
+      "epoch": 0.11518500637953033,
+      "grad_norm": 0.8225119113922119,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 0.7161,
+      "step": 13361
+    },
+    {
+      "epoch": 0.11545225697437843,
+      "grad_norm": 0.5669307708740234,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 0.7024,
+      "step": 13392
+    },
+    {
+      "epoch": 0.11571950756922653,
+      "grad_norm": 0.7186108827590942,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 0.7081,
+      "step": 13423
+    },
+    {
+      "epoch": 0.11598675816407462,
+      "grad_norm": 0.5777581334114075,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 0.7015,
+      "step": 13454
+    },
+    {
+      "epoch": 0.11625400875892272,
+      "grad_norm": 0.6641644239425659,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 0.7184,
+      "step": 13485
+    },
+    {
+      "epoch": 0.11652125935377082,
+      "grad_norm": 0.7468976974487305,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 0.7132,
+      "step": 13516
+    },
+    {
+      "epoch": 0.11678850994861892,
+      "grad_norm": 0.5197424292564392,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 0.7053,
+      "step": 13547
+    },
+    {
+      "epoch": 0.11705576054346702,
+      "grad_norm": 0.8400532603263855,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 0.7099,
+      "step": 13578
+    },
+    {
+      "epoch": 0.11732301113831511,
+      "grad_norm": 0.6441920399665833,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 0.7078,
+      "step": 13609
+    },
+    {
+      "epoch": 0.11759026173316321,
+      "grad_norm": 0.676284909248352,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 0.7073,
+      "step": 13640
+    },
+    {
+      "epoch": 0.11785751232801131,
+      "grad_norm": 0.7930014729499817,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 0.7057,
+      "step": 13671
+    },
+    {
+      "epoch": 0.11812476292285941,
+      "grad_norm": 0.5682835578918457,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 0.7029,
+      "step": 13702
+    },
+    {
+      "epoch": 0.1183920135177075,
+      "grad_norm": 0.699668824672699,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 0.7039,
+      "step": 13733
+    },
+    {
+      "epoch": 0.1186592641125556,
+      "grad_norm": 0.6139336824417114,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 0.7049,
+      "step": 13764
+    },
+    {
+      "epoch": 0.1189265147074037,
+      "grad_norm": 0.7547024488449097,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 0.7053,
+      "step": 13795
+    },
+    {
+      "epoch": 0.1191937653022518,
+      "grad_norm": 0.6330803036689758,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 0.7006,
+      "step": 13826
+    },
+    {
+      "epoch": 0.1194610158970999,
+      "grad_norm": 0.6040504574775696,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 0.7132,
+      "step": 13857
+    },
+    {
+      "epoch": 0.119728266491948,
+      "grad_norm": 0.6030833125114441,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 0.7164,
+      "step": 13888
+    },
+    {
+      "epoch": 0.1199955170867961,
+      "grad_norm": 0.6896437406539917,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 0.713,
+      "step": 13919
+    },
+    {
+      "epoch": 0.12026276768164419,
+      "grad_norm": 0.8433464169502258,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 0.6968,
+      "step": 13950
+    },
+    {
+      "epoch": 0.12053001827649229,
+      "grad_norm": 0.7637025713920593,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 0.7014,
+      "step": 13981
+    },
+    {
+      "epoch": 0.12079726887134039,
+      "grad_norm": 0.6914523243904114,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 0.6999,
+      "step": 14012
+    },
+    {
+      "epoch": 0.12106451946618849,
+      "grad_norm": 0.6796788573265076,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 0.7138,
+      "step": 14043
+    },
+    {
+      "epoch": 0.12133177006103658,
+      "grad_norm": 0.6779701113700867,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 0.6953,
+      "step": 14074
+    },
+    {
+      "epoch": 0.12159902065588468,
+      "grad_norm": 0.7082575559616089,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 0.7097,
+      "step": 14105
+    },
+    {
+      "epoch": 0.12186627125073278,
+      "grad_norm": 0.7408347129821777,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 0.6898,
+      "step": 14136
+    },
+    {
+      "epoch": 0.12213352184558088,
+      "grad_norm": 0.6222202181816101,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 0.6995,
+      "step": 14167
+    },
+    {
+      "epoch": 0.12240077244042898,
+      "grad_norm": 0.6858973503112793,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 0.7059,
+      "step": 14198
+    },
+    {
+      "epoch": 0.12266802303527707,
+      "grad_norm": 0.7068437337875366,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 0.7137,
+      "step": 14229
+    },
+    {
+      "epoch": 0.12293527363012517,
+      "grad_norm": 0.6153962016105652,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 0.6964,
+      "step": 14260
+    },
+    {
+      "epoch": 0.12320252422497327,
+      "grad_norm": 0.6866403818130493,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 0.7051,
+      "step": 14291
+    },
+    {
+      "epoch": 0.12346977481982137,
+      "grad_norm": 0.7551136612892151,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 0.7039,
+      "step": 14322
+    },
+    {
+      "epoch": 0.12373702541466947,
+      "grad_norm": 0.5940378904342651,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 0.6997,
+      "step": 14353
+    },
+    {
+      "epoch": 0.12400427600951756,
+      "grad_norm": 0.5693697929382324,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 0.6972,
+      "step": 14384
+    },
+    {
+      "epoch": 0.12427152660436566,
+      "grad_norm": 0.5443055033683777,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 0.6918,
+      "step": 14415
+    },
+    {
+      "epoch": 0.12453877719921376,
+      "grad_norm": 0.6901688575744629,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 0.7026,
+      "step": 14446
+    },
+    {
+      "epoch": 0.12480602779406186,
+      "grad_norm": 0.5541255474090576,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 0.7006,
+      "step": 14477
+    },
+    {
+      "epoch": 0.12507327838890997,
+      "grad_norm": 0.7744006514549255,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 0.7068,
+      "step": 14508
+    },
+    {
+      "epoch": 0.12534052898375805,
+      "grad_norm": 0.6032939553260803,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 0.7063,
+      "step": 14539
+    },
+    {
+      "epoch": 0.12560777957860617,
+      "grad_norm": 0.5508326888084412,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 0.7008,
+      "step": 14570
+    },
+    {
+      "epoch": 0.12587503017345425,
+      "grad_norm": 0.6029148697853088,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 0.6972,
+      "step": 14601
+    },
+    {
+      "epoch": 0.12614228076830236,
+      "grad_norm": 0.612224817276001,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 0.6998,
+      "step": 14632
+    },
+    {
+      "epoch": 0.12640953136315045,
+      "grad_norm": 0.5881705284118652,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 0.7026,
+      "step": 14663
+    },
+    {
+      "epoch": 0.12667678195799856,
+      "grad_norm": 0.6885594725608826,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 0.6987,
+      "step": 14694
+    },
+    {
+      "epoch": 0.12694403255284664,
+      "grad_norm": 0.5755457878112793,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 0.693,
+      "step": 14725
+    },
+    {
+      "epoch": 0.12721128314769475,
+      "grad_norm": 0.6199221611022949,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 0.7007,
+      "step": 14756
+    },
+    {
+      "epoch": 0.12747853374254284,
+      "grad_norm": 0.601020872592926,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 0.6949,
+      "step": 14787
+    },
+    {
+      "epoch": 0.12774578433739095,
+      "grad_norm": 0.5955238342285156,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 0.697,
+      "step": 14818
+    },
+    {
+      "epoch": 0.12801303493223903,
+      "grad_norm": 0.5562962293624878,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 0.7021,
+      "step": 14849
+    },
+    {
+      "epoch": 0.12828028552708715,
+      "grad_norm": 0.829988956451416,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 0.7028,
+      "step": 14880
+    },
+    {
+      "epoch": 0.12854753612193523,
+      "grad_norm": 0.6745316982269287,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 0.7081,
+      "step": 14911
+    },
+    {
+      "epoch": 0.12881478671678334,
+      "grad_norm": 0.5051907896995544,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 0.6984,
+      "step": 14942
+    },
+    {
+      "epoch": 0.12908203731163143,
+      "grad_norm": 0.7191225290298462,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 0.6976,
+      "step": 14973
+    },
+    {
+      "epoch": 0.12934928790647954,
+      "grad_norm": 0.6744056344032288,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 0.7,
+      "step": 15004
+    },
+    {
+      "epoch": 0.12961653850132762,
+      "grad_norm": 0.5787363648414612,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 0.704,
+      "step": 15035
+    },
+    {
+      "epoch": 0.12988378909617573,
+      "grad_norm": 0.7416272759437561,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 0.6961,
+      "step": 15066
+    },
+    {
+      "epoch": 0.13015103969102382,
+      "grad_norm": 0.7691118121147156,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 0.7045,
+      "step": 15097
+    },
+    {
+      "epoch": 0.13041829028587193,
+      "grad_norm": 0.6439851522445679,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 0.6935,
+      "step": 15128
+    },
+    {
+      "epoch": 0.13068554088072,
+      "grad_norm": 0.8656207919120789,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 0.7037,
+      "step": 15159
+    },
+    {
+      "epoch": 0.13095279147556813,
+      "grad_norm": 0.6430538296699524,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 0.702,
+      "step": 15190
+    },
+    {
+      "epoch": 0.1312200420704162,
+      "grad_norm": 0.840202271938324,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 0.6965,
+      "step": 15221
+    },
+    {
+      "epoch": 0.13148729266526432,
+      "grad_norm": 0.6381927728652954,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 0.6948,
+      "step": 15252
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.060677039050195e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15260/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d58e858f50ca10fb06d8ff9f1c4584a3e2f380b3fe5f85a62b31928bcca534
+size 5304

checkpoint-18312/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-18312/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-18312/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f4de035c790dc0f3456f8034f2ff2aff31b385d5276fcf70222dfba8fa53aa
+size 4976687216

checkpoint-18312/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edb205482e80b5d03e63693e387d459b0cb9c97948cde971ff025ba98f1396d
+size 4778622352

checkpoint-18312/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2222b40c6fea7def1d5911b059ab36bf97b9328e0251689f78a0a9ebd98cd18d
+size 4932743960

checkpoint-18312/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-18312/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-18312/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a05350139ea3f852f2a843867bb27259fcbe5fdebc7940d4226a962ef1cbb7
+size 3662865184

checkpoint-18312/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9567d0b8fcc67b5d325673e38251d8e2c5a579d979acc6f7b6eccfb87bb139
+size 2179989632

checkpoint-18312/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-18312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fd134ef6f656f66d6ce613b1e01b1059702b3b1025fb84c17dd5db0274ce92
+size 16177880918

checkpoint-18312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-18312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e65c3d6f29e706fd941a38280ce5628189a6998eac6d29abbeab00ad838d00
+size 1064

checkpoint-18312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d58e858f50ca10fb06d8ff9f1c4584a3e2f380b3fe5f85a62b31928bcca534
+size 5304

checkpoint-21364/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-21364/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-21364/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd72eb848e0ebb16734d5817b05437d65e25cde36c20df37019472a8bc26a02
+size 4976687216

checkpoint-21364/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edb205482e80b5d03e63693e387d459b0cb9c97948cde971ff025ba98f1396d
+size 4778622352