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 sha256:4085307ac9eb4fe782d2f29dfa8363beac3faa5464b6237f0521a8b96fb9433f
+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 sha256:4a6368f1115a48941a0dd35c7ad0045b67827d3550f13f19997cc3fc0443ffa3
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae667589e56921b2b4fc5881e54267daeaca2d5411678b240fe3a336d0dba5be
+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:f5c8e51ba07e28cf52c8f9356fc05f89dfa7c6758a7b332e9dbd72f80e98b82f
+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": 0.1882686776623717,
+  "eval_steps": 500,
+  "global_step": 12208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004780741323340042,
+      "grad_norm": 3.1866345405578613,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.194,
+      "step": 31
+    },
+    {
+      "epoch": 0.0009561482646680084,
+      "grad_norm": 1.7708723545074463,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 1.1124,
+      "step": 62
+    },
+    {
+      "epoch": 0.0014342223970020126,
+      "grad_norm": 1.6835601329803467,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.0585,
+      "step": 93
+    },
+    {
+      "epoch": 0.0019122965293360168,
+      "grad_norm": 1.642537236213684,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.0213,
+      "step": 124
+    },
+    {
+      "epoch": 0.002390370661670021,
+      "grad_norm": 1.8476150035858154,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.0024,
+      "step": 155
+    },
+    {
+      "epoch": 0.0028684447940040252,
+      "grad_norm": 1.96336829662323,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 0.9938,
+      "step": 186
+    },
+    {
+      "epoch": 0.0033465189263380294,
+      "grad_norm": 1.8158528804779053,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 0.969,
+      "step": 217
+    },
+    {
+      "epoch": 0.0038245930586720336,
+      "grad_norm": 1.9796783924102783,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 0.9573,
+      "step": 248
+    },
+    {
+      "epoch": 0.004302667191006038,
+      "grad_norm": 1.8192514181137085,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 0.9498,
+      "step": 279
+    },
+    {
+      "epoch": 0.004780741323340042,
+      "grad_norm": 2.1396358013153076,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 0.9294,
+      "step": 310
+    },
+    {
+      "epoch": 0.005258815455674046,
+      "grad_norm": 2.0807156562805176,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 0.9186,
+      "step": 341
+    },
+    {
+      "epoch": 0.0057368895880080505,
+      "grad_norm": 2.002887010574341,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 0.9149,
+      "step": 372
+    },
+    {
+      "epoch": 0.006214963720342055,
+      "grad_norm": 2.240675687789917,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 0.9139,
+      "step": 403
+    },
+    {
+      "epoch": 0.006693037852676059,
+      "grad_norm": 1.9016591310501099,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 0.8946,
+      "step": 434
+    },
+    {
+      "epoch": 0.007171111985010063,
+      "grad_norm": 1.6729310750961304,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 0.8959,
+      "step": 465
+    },
+    {
+      "epoch": 0.007649186117344067,
+      "grad_norm": 2.2607779502868652,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 0.8847,
+      "step": 496
+    },
+    {
+      "epoch": 0.00812726024967807,
+      "grad_norm": 1.699507236480713,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 0.8773,
+      "step": 527
+    },
+    {
+      "epoch": 0.008605334382012076,
+      "grad_norm": 1.93502938747406,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 0.8773,
+      "step": 558
+    },
+    {
+      "epoch": 0.009083408514346079,
+      "grad_norm": 2.1234281063079834,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 0.8669,
+      "step": 589
+    },
+    {
+      "epoch": 0.009561482646680084,
+      "grad_norm": 1.7465944290161133,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 0.8536,
+      "step": 620
+    },
+    {
+      "epoch": 0.010039556779014087,
+      "grad_norm": 1.7039932012557983,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 0.8624,
+      "step": 651
+    },
+    {
+      "epoch": 0.010517630911348093,
+      "grad_norm": 1.551837682723999,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 0.8555,
+      "step": 682
+    },
+    {
+      "epoch": 0.010995705043682096,
+      "grad_norm": 1.7622497081756592,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 0.8475,
+      "step": 713
+    },
+    {
+      "epoch": 0.011473779176016101,
+      "grad_norm": 2.000936269760132,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 0.852,
+      "step": 744
+    },
+    {
+      "epoch": 0.011951853308350104,
+      "grad_norm": 1.6770379543304443,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.8455,
+      "step": 775
+    },
+    {
+      "epoch": 0.01242992744068411,
+      "grad_norm": 1.746506929397583,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.8406,
+      "step": 806
+    },
+    {
+      "epoch": 0.012908001573018113,
+      "grad_norm": 1.507759690284729,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.8556,
+      "step": 837
+    },
+    {
+      "epoch": 0.013386075705352118,
+      "grad_norm": 1.6984492540359497,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.8281,
+      "step": 868
+    },
+    {
+      "epoch": 0.013864149837686121,
+      "grad_norm": 1.5145736932754517,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.8359,
+      "step": 899
+    },
+    {
+      "epoch": 0.014342223970020126,
+      "grad_norm": 1.5700000524520874,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.8305,
+      "step": 930
+    },
+    {
+      "epoch": 0.01482029810235413,
+      "grad_norm": 1.6657596826553345,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.8263,
+      "step": 961
+    },
+    {
+      "epoch": 0.015298372234688135,
+      "grad_norm": 1.527628779411316,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.8318,
+      "step": 992
+    },
+    {
+      "epoch": 0.015776446367022138,
+      "grad_norm": 1.8353967666625977,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.8192,
+      "step": 1023
+    },
+    {
+      "epoch": 0.01625452049935614,
+      "grad_norm": 1.2118042707443237,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.819,
+      "step": 1054
+    },
+    {
+      "epoch": 0.016732594631690145,
+      "grad_norm": 1.3235970735549927,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.8176,
+      "step": 1085
+    },
+    {
+      "epoch": 0.01721066876402415,
+      "grad_norm": 1.6729888916015625,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.8202,
+      "step": 1116
+    },
+    {
+      "epoch": 0.017688742896358155,
+      "grad_norm": 1.3251298666000366,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.8104,
+      "step": 1147
+    },
+    {
+      "epoch": 0.018166817028692158,
+      "grad_norm": 1.5231342315673828,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.8113,
+      "step": 1178
+    },
+    {
+      "epoch": 0.01864489116102616,
+      "grad_norm": 1.3263883590698242,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.7981,
+      "step": 1209
+    },
+    {
+      "epoch": 0.019122965293360168,
+      "grad_norm": 1.317791223526001,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.7962,
+      "step": 1240
+    },
+    {
+      "epoch": 0.01960103942569417,
+      "grad_norm": 1.566698670387268,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.8072,
+      "step": 1271
+    },
+    {
+      "epoch": 0.020079113558028175,
+      "grad_norm": 1.2935110330581665,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.7818,
+      "step": 1302
+    },
+    {
+      "epoch": 0.020557187690362178,
+      "grad_norm": 1.336227536201477,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.7917,
+      "step": 1333
+    },
+    {
+      "epoch": 0.021035261822696185,
+      "grad_norm": 1.5656548738479614,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.7785,
+      "step": 1364
+    },
+    {
+      "epoch": 0.02151333595503019,
+      "grad_norm": 1.5208159685134888,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.7839,
+      "step": 1395
+    },
+    {
+      "epoch": 0.02199141008736419,
+      "grad_norm": 1.4816375970840454,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.7789,
+      "step": 1426
+    },
+    {
+      "epoch": 0.022469484219698195,
+      "grad_norm": 1.402166485786438,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.7803,
+      "step": 1457
+    },
+    {
+      "epoch": 0.022947558352032202,
+      "grad_norm": 1.2986265420913696,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.7739,
+      "step": 1488
+    },
+    {
+      "epoch": 0.023425632484366205,
+      "grad_norm": 1.3171271085739136,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.7694,
+      "step": 1519
+    },
+    {
+      "epoch": 0.02390370661670021,
+      "grad_norm": 1.4870030879974365,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.7663,
+      "step": 1550
+    },
+    {
+      "epoch": 0.024381780749034212,
+      "grad_norm": 1.7419476509094238,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.7731,
+      "step": 1581
+    },
+    {
+      "epoch": 0.02485985488136822,
+      "grad_norm": 1.109238624572754,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.7704,
+      "step": 1612
+    },
+    {
+      "epoch": 0.025337929013702222,
+      "grad_norm": 1.3478920459747314,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.7723,
+      "step": 1643
+    },
+    {
+      "epoch": 0.025816003146036225,
+      "grad_norm": 1.2739650011062622,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.7699,
+      "step": 1674
+    },
+    {
+      "epoch": 0.02629407727837023,
+      "grad_norm": 1.3892935514450073,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.7709,
+      "step": 1705
+    },
+    {
+      "epoch": 0.026772151410704235,
+      "grad_norm": 1.2031512260437012,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.7557,
+      "step": 1736
+    },
+    {
+      "epoch": 0.02725022554303824,
+      "grad_norm": 1.185471773147583,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.7645,
+      "step": 1767
+    },
+    {
+      "epoch": 0.027728299675372242,
+      "grad_norm": 1.2331740856170654,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.7655,
+      "step": 1798
+    },
+    {
+      "epoch": 0.028206373807706245,
+      "grad_norm": 1.1817049980163574,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.7617,
+      "step": 1829
+    },
+    {
+      "epoch": 0.028684447940040252,
+      "grad_norm": 1.2225860357284546,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.7558,
+      "step": 1860
+    },
+    {
+      "epoch": 0.029162522072374256,
+      "grad_norm": 1.6452528238296509,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.7566,
+      "step": 1891
+    },
+    {
+      "epoch": 0.02964059620470826,
+      "grad_norm": 1.3764828443527222,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.7545,
+      "step": 1922
+    },
+    {
+      "epoch": 0.030118670337042262,
+      "grad_norm": 1.6581465005874634,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.7519,
+      "step": 1953
+    },
+    {
+      "epoch": 0.03059674446937627,
+      "grad_norm": 1.1065036058425903,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.7579,
+      "step": 1984
+    },
+    {
+      "epoch": 0.031074818601710272,
+      "grad_norm": 2.6465444564819336,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.7538,
+      "step": 2015
+    },
+    {
+      "epoch": 0.031552892734044276,
+      "grad_norm": 1.3028968572616577,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.7522,
+      "step": 2046
+    },
+    {
+      "epoch": 0.03203096686637828,
+      "grad_norm": 1.0450382232666016,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.742,
+      "step": 2077
+    },
+    {
+      "epoch": 0.03250904099871228,
+      "grad_norm": 0.9411994814872742,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.7401,
+      "step": 2108
+    },
+    {
+      "epoch": 0.03298711513104629,
+      "grad_norm": 1.0501608848571777,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.7455,
+      "step": 2139
+    },
+    {
+      "epoch": 0.03346518926338029,
+      "grad_norm": 1.266400694847107,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.7391,
+      "step": 2170
+    },
+    {
+      "epoch": 0.033943263395714296,
+      "grad_norm": 1.2862213850021362,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.7397,
+      "step": 2201
+    },
+    {
+      "epoch": 0.0344213375280483,
+      "grad_norm": 1.2715409994125366,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.7467,
+      "step": 2232
+    },
+    {
+      "epoch": 0.0348994116603823,
+      "grad_norm": 1.3290003538131714,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.7432,
+      "step": 2263
+    },
+    {
+      "epoch": 0.03537748579271631,
+      "grad_norm": 1.0561761856079102,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.7336,
+      "step": 2294
+    },
+    {
+      "epoch": 0.035855559925050316,
+      "grad_norm": 1.3272422552108765,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.7251,
+      "step": 2325
+    },
+    {
+      "epoch": 0.036333634057384316,
+      "grad_norm": 1.0749491453170776,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.7205,
+      "step": 2356
+    },
+    {
+      "epoch": 0.03681170818971832,
+      "grad_norm": 1.1581461429595947,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.7311,
+      "step": 2387
+    },
+    {
+      "epoch": 0.03728978232205232,
+      "grad_norm": 1.0796961784362793,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.7259,
+      "step": 2418
+    },
+    {
+      "epoch": 0.03776785645438633,
+      "grad_norm": 1.1916818618774414,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.7258,
+      "step": 2449
+    },
+    {
+      "epoch": 0.038245930586720336,
+      "grad_norm": 0.9515872001647949,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.7273,
+      "step": 2480
+    },
+    {
+      "epoch": 0.038724004719054336,
+      "grad_norm": 1.1217246055603027,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.7269,
+      "step": 2511
+    },
+    {
+      "epoch": 0.03920207885138834,
+      "grad_norm": 0.9570199847221375,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.7289,
+      "step": 2542
+    },
+    {
+      "epoch": 0.03968015298372235,
+      "grad_norm": 1.2980682849884033,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.7382,
+      "step": 2573
+    },
+    {
+      "epoch": 0.04015822711605635,
+      "grad_norm": 2.1257143020629883,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.8112,
+      "step": 2604
+    },
+    {
+      "epoch": 0.04063630124839036,
+      "grad_norm": 1.5091110467910767,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.7451,
+      "step": 2635
+    },
+    {
+      "epoch": 0.041114375380724356,
+      "grad_norm": 2.4548749923706055,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.7358,
+      "step": 2666
+    },
+    {
+      "epoch": 0.04159244951305836,
+      "grad_norm": 1.176115870475769,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.7368,
+      "step": 2697
+    },
+    {
+      "epoch": 0.04207052364539237,
+      "grad_norm": 1.063672661781311,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.7465,
+      "step": 2728
+    },
+    {
+      "epoch": 0.04254859777772637,
+      "grad_norm": 1.3062779903411865,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.7413,
+      "step": 2759
+    },
+    {
+      "epoch": 0.04302667191006038,
+      "grad_norm": 1.5550280809402466,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.724,
+      "step": 2790
+    },
+    {
+      "epoch": 0.043504746042394384,
+      "grad_norm": 1.2525728940963745,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.7216,
+      "step": 2821
+    },
+    {
+      "epoch": 0.04398282017472838,
+      "grad_norm": 1.158134937286377,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.728,
+      "step": 2852
+    },
+    {
+      "epoch": 0.04446089430706239,
+      "grad_norm": 1.262291669845581,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.7191,
+      "step": 2883
+    },
+    {
+      "epoch": 0.04493896843939639,
+      "grad_norm": 2.826028347015381,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.7211,
+      "step": 2914
+    },
+    {
+      "epoch": 0.0454170425717304,
+      "grad_norm": 1.0346958637237549,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.7268,
+      "step": 2945
+    },
+    {
+      "epoch": 0.045895116704064404,
+      "grad_norm": 1.4338330030441284,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.7154,
+      "step": 2976
+    },
+    {
+      "epoch": 0.046373190836398404,
+      "grad_norm": 0.9223676919937134,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.7195,
+      "step": 3007
+    },
+    {
+      "epoch": 0.04685126496873241,
+      "grad_norm": 0.9936623573303223,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.7194,
+      "step": 3038
+    },
+    {
+      "epoch": 0.04732933910106642,
+      "grad_norm": 1.017962098121643,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.713,
+      "step": 3069
+    },
+    {
+      "epoch": 0.04780741323340042,
+      "grad_norm": 0.9654473662376404,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.7096,
+      "step": 3100
+    },
+    {
+      "epoch": 0.048285487365734424,
+      "grad_norm": 0.9372695684432983,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.7116,
+      "step": 3131
+    },
+    {
+      "epoch": 0.048763561498068424,
+      "grad_norm": 0.9450846910476685,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.7129,
+      "step": 3162
+    },
+    {
+      "epoch": 0.04924163563040243,
+      "grad_norm": 1.0803054571151733,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.706,
+      "step": 3193
+    },
+    {
+      "epoch": 0.04971970976273644,
+      "grad_norm": 1.2218348979949951,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.7076,
+      "step": 3224
+    },
+    {
+      "epoch": 0.05019778389507044,
+      "grad_norm": 1.0429767370224,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.7089,
+      "step": 3255
+    },
+    {
+      "epoch": 0.050675858027404444,
+      "grad_norm": 0.9912049770355225,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.7016,
+      "step": 3286
+    },
+    {
+      "epoch": 0.051153932159738444,
+      "grad_norm": 0.9687103033065796,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.7071,
+      "step": 3317
+    },
+    {
+      "epoch": 0.05163200629207245,
+      "grad_norm": 0.8178670406341553,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.6991,
+      "step": 3348
+    },
+    {
+      "epoch": 0.05211008042440646,
+      "grad_norm": 0.8601382374763489,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.6978,
+      "step": 3379
+    },
+    {
+      "epoch": 0.05258815455674046,
+      "grad_norm": 1.076370120048523,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.7044,
+      "step": 3410
+    },
+    {
+      "epoch": 0.053066228689074464,
+      "grad_norm": 3.9457356929779053,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.6978,
+      "step": 3441
+    },
+    {
+      "epoch": 0.05354430282140847,
+      "grad_norm": 0.8186474442481995,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.6974,
+      "step": 3472
+    },
+    {
+      "epoch": 0.05402237695374247,
+      "grad_norm": 0.9643816947937012,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.7025,
+      "step": 3503
+    },
+    {
+      "epoch": 0.05450045108607648,
+      "grad_norm": 1.024248480796814,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.7006,
+      "step": 3534
+    },
+    {
+      "epoch": 0.05497852521841048,
+      "grad_norm": 0.7718949317932129,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.7024,
+      "step": 3565
+    },
+    {
+      "epoch": 0.055456599350744484,
+      "grad_norm": 1.1313899755477905,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.701,
+      "step": 3596
+    },
+    {
+      "epoch": 0.05593467348307849,
+      "grad_norm": 1.0118827819824219,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.7036,
+      "step": 3627
+    },
+    {
+      "epoch": 0.05641274761541249,
+      "grad_norm": 0.9465724229812622,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.6869,
+      "step": 3658
+    },
+    {
+      "epoch": 0.0568908217477465,
+      "grad_norm": 1.0233882665634155,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.6944,
+      "step": 3689
+    },
+    {
+      "epoch": 0.057368895880080505,
+      "grad_norm": 1.008609652519226,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.6916,
+      "step": 3720
+    },
+    {
+      "epoch": 0.057846970012414504,
+      "grad_norm": 1.0083181858062744,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.6886,
+      "step": 3751
+    },
+    {
+      "epoch": 0.05832504414474851,
+      "grad_norm": 0.9374220967292786,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.6976,
+      "step": 3782
+    },
+    {
+      "epoch": 0.05880311827708251,
+      "grad_norm": 0.9066904783248901,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.6911,
+      "step": 3813
+    },
+    {
+      "epoch": 0.05928119240941652,
+      "grad_norm": 0.9702699780464172,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.6959,
+      "step": 3844
+    },
+    {
+      "epoch": 0.059759266541750525,
+      "grad_norm": 0.8405037522315979,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.6896,
+      "step": 3875
+    },
+    {
+      "epoch": 0.060237340674084525,
+      "grad_norm": 0.9460383653640747,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.6871,
+      "step": 3906
+    },
+    {
+      "epoch": 0.06071541480641853,
+      "grad_norm": 0.9355078339576721,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.6843,
+      "step": 3937
+    },
+    {
+      "epoch": 0.06119348893875254,
+      "grad_norm": 0.7211058735847473,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.6861,
+      "step": 3968
+    },
+    {
+      "epoch": 0.06167156307108654,
+      "grad_norm": 0.8674766421318054,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.6939,
+      "step": 3999
+    },
+    {
+      "epoch": 0.062149637203420545,
+      "grad_norm": 0.8166181445121765,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.692,
+      "step": 4030
+    },
+    {
+      "epoch": 0.06262771133575455,
+      "grad_norm": 0.841305136680603,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.6855,
+      "step": 4061
+    },
+    {
+      "epoch": 0.06310578546808855,
+      "grad_norm": 0.8942857384681702,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.6946,
+      "step": 4092
+    },
+    {
+      "epoch": 0.06358385960042255,
+      "grad_norm": 0.8595120310783386,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.6825,
+      "step": 4123
+    },
+    {
+      "epoch": 0.06406193373275657,
+      "grad_norm": 0.8155812621116638,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.6821,
+      "step": 4154
+    },
+    {
+      "epoch": 0.06454000786509057,
+      "grad_norm": 0.8901113271713257,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.6898,
+      "step": 4185
+    },
+    {
+      "epoch": 0.06501808199742456,
+      "grad_norm": 0.9637976288795471,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.6829,
+      "step": 4216
+    },
+    {
+      "epoch": 0.06549615612975858,
+      "grad_norm": 0.7048139572143555,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.6834,
+      "step": 4247
+    },
+    {
+      "epoch": 0.06597423026209258,
+      "grad_norm": 0.8655612468719482,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.6778,
+      "step": 4278
+    },
+    {
+      "epoch": 0.06645230439442658,
+      "grad_norm": 0.8204261064529419,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.6672,
+      "step": 4309
+    },
+    {
+      "epoch": 0.06693037852676058,
+      "grad_norm": 0.9259466528892517,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.6778,
+      "step": 4340
+    },
+    {
+      "epoch": 0.06740845265909459,
+      "grad_norm": 0.9826278686523438,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.6882,
+      "step": 4371
+    },
+    {
+      "epoch": 0.06788652679142859,
+      "grad_norm": 0.7376586198806763,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.6802,
+      "step": 4402
+    },
+    {
+      "epoch": 0.06836460092376259,
+      "grad_norm": 0.6778755784034729,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.6814,
+      "step": 4433
+    },
+    {
+      "epoch": 0.0688426750560966,
+      "grad_norm": 0.8117042183876038,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.6759,
+      "step": 4464
+    },
+    {
+      "epoch": 0.0693207491884306,
+      "grad_norm": 0.9493227005004883,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.6744,
+      "step": 4495
+    },
+    {
+      "epoch": 0.0697988233207646,
+      "grad_norm": 1.3356900215148926,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.6763,
+      "step": 4526
+    },
+    {
+      "epoch": 0.07027689745309862,
+      "grad_norm": 1.1542543172836304,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.6788,
+      "step": 4557
+    },
+    {
+      "epoch": 0.07075497158543262,
+      "grad_norm": 0.785176157951355,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.6853,
+      "step": 4588
+    },
+    {
+      "epoch": 0.07123304571776662,
+      "grad_norm": 0.8102776408195496,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.6794,
+      "step": 4619
+    },
+    {
+      "epoch": 0.07171111985010063,
+      "grad_norm": 0.9685975313186646,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.6823,
+      "step": 4650
+    },
+    {
+      "epoch": 0.07218919398243463,
+      "grad_norm": 0.7929072976112366,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.6781,
+      "step": 4681
+    },
+    {
+      "epoch": 0.07266726811476863,
+      "grad_norm": 0.8171564340591431,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.6685,
+      "step": 4712
+    },
+    {
+      "epoch": 0.07314534224710265,
+      "grad_norm": 0.9218119382858276,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.6796,
+      "step": 4743
+    },
+    {
+      "epoch": 0.07362341637943665,
+      "grad_norm": 3.1681158542633057,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.676,
+      "step": 4774
+    },
+    {
+      "epoch": 0.07410149051177065,
+      "grad_norm": 0.9336240887641907,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.6734,
+      "step": 4805
+    },
+    {
+      "epoch": 0.07457956464410465,
+      "grad_norm": 0.8264138102531433,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.6905,
+      "step": 4836
+    },
+    {
+      "epoch": 0.07505763877643866,
+      "grad_norm": 0.819663405418396,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.6814,
+      "step": 4867
+    },
+    {
+      "epoch": 0.07553571290877266,
+      "grad_norm": 3.124502420425415,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.6704,
+      "step": 4898
+    },
+    {
+      "epoch": 0.07601378704110666,
+      "grad_norm": 0.7769860625267029,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.6728,
+      "step": 4929
+    },
+    {
+      "epoch": 0.07649186117344067,
+      "grad_norm": 0.8232171535491943,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.6798,
+      "step": 4960
+    },
+    {
+      "epoch": 0.07696993530577467,
+      "grad_norm": 0.8771420121192932,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.6722,
+      "step": 4991
+    },
+    {
+      "epoch": 0.07744800943810867,
+      "grad_norm": 0.8321033716201782,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.6724,
+      "step": 5022
+    },
+    {
+      "epoch": 0.07792608357044269,
+      "grad_norm": 0.9346029162406921,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.6764,
+      "step": 5053
+    },
+    {
+      "epoch": 0.07840415770277669,
+      "grad_norm": 0.9193580150604248,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.6789,
+      "step": 5084
+    },
+    {
+      "epoch": 0.07888223183511069,
+      "grad_norm": 1.0850661993026733,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.6685,
+      "step": 5115
+    },
+    {
+      "epoch": 0.0793603059674447,
+      "grad_norm": 0.6851856708526611,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.6621,
+      "step": 5146
+    },
+    {
+      "epoch": 0.0798383800997787,
+      "grad_norm": 0.7950114607810974,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.6642,
+      "step": 5177
+    },
+    {
+      "epoch": 0.0803164542321127,
+      "grad_norm": 0.9632556438446045,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.6628,
+      "step": 5208
+    },
+    {
+      "epoch": 0.0807945283644467,
+      "grad_norm": 0.7066652178764343,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.6642,
+      "step": 5239
+    },
+    {
+      "epoch": 0.08127260249678071,
+      "grad_norm": 0.7749651670455933,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.6633,
+      "step": 5270
+    },
+    {
+      "epoch": 0.08175067662911471,
+      "grad_norm": 1.702022671699524,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.6745,
+      "step": 5301
+    },
+    {
+      "epoch": 0.08222875076144871,
+      "grad_norm": 0.8134759068489075,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.659,
+      "step": 5332
+    },
+    {
+      "epoch": 0.08270682489378273,
+      "grad_norm": 0.8805097341537476,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.6779,
+      "step": 5363
+    },
+    {
+      "epoch": 0.08318489902611673,
+      "grad_norm": 0.9312698841094971,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.6634,
+      "step": 5394
+    },
+    {
+      "epoch": 0.08366297315845073,
+      "grad_norm": 0.7013948559761047,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.6589,
+      "step": 5425
+    },
+    {
+      "epoch": 0.08414104729078474,
+      "grad_norm": 0.8027428388595581,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.6603,
+      "step": 5456
+    },
+    {
+      "epoch": 0.08461912142311874,
+      "grad_norm": 1.0179306268692017,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.6595,
+      "step": 5487
+    },
+    {
+      "epoch": 0.08509719555545274,
+      "grad_norm": 0.8512592911720276,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.6659,
+      "step": 5518
+    },
+    {
+      "epoch": 0.08557526968778675,
+      "grad_norm": 0.8476304411888123,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.6658,
+      "step": 5549
+    },
+    {
+      "epoch": 0.08605334382012075,
+      "grad_norm": 0.771584153175354,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.6622,
+      "step": 5580
+    },
+    {
+      "epoch": 0.08653141795245475,
+      "grad_norm": 0.8719794154167175,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.661,
+      "step": 5611
+    },
+    {
+      "epoch": 0.08700949208478877,
+      "grad_norm": 0.9247443675994873,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.6475,
+      "step": 5642
+    },
+    {
+      "epoch": 0.08748756621712277,
+      "grad_norm": 0.9540857672691345,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.662,
+      "step": 5673
+    },
+    {
+      "epoch": 0.08796564034945677,
+      "grad_norm": 0.7939008474349976,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.6514,
+      "step": 5704
+    },
+    {
+      "epoch": 0.08844371448179077,
+      "grad_norm": 0.613531768321991,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.6513,
+      "step": 5735
+    },
+    {
+      "epoch": 0.08892178861412478,
+      "grad_norm": 0.8084924817085266,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.6465,
+      "step": 5766
+    },
+    {
+      "epoch": 0.08939986274645878,
+      "grad_norm": 0.7709007263183594,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.6618,
+      "step": 5797
+    },
+    {
+      "epoch": 0.08987793687879278,
+      "grad_norm": 0.6461811065673828,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.6516,
+      "step": 5828
+    },
+    {
+      "epoch": 0.0903560110111268,
+      "grad_norm": 0.6879326105117798,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.655,
+      "step": 5859
+    },
+    {
+      "epoch": 0.0908340851434608,
+      "grad_norm": 0.7594075798988342,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.655,
+      "step": 5890
+    },
+    {
+      "epoch": 0.0913121592757948,
+      "grad_norm": 0.774758517742157,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.6697,
+      "step": 5921
+    },
+    {
+      "epoch": 0.09179023340812881,
+      "grad_norm": 0.9164844155311584,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.6483,
+      "step": 5952
+    },
+    {
+      "epoch": 0.09226830754046281,
+      "grad_norm": 0.792631208896637,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.6644,
+      "step": 5983
+    },
+    {
+      "epoch": 0.09274638167279681,
+      "grad_norm": 0.7735174298286438,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.6545,
+      "step": 6014
+    },
+    {
+      "epoch": 0.09322445580513082,
+      "grad_norm": 0.725825309753418,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.6579,
+      "step": 6045
+    },
+    {
+      "epoch": 0.09370252993746482,
+      "grad_norm": 0.7191294431686401,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.6509,
+      "step": 6076
+    },
+    {
+      "epoch": 0.09418060406979882,
+      "grad_norm": 0.8470766544342041,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.6515,
+      "step": 6107
+    },
+    {
+      "epoch": 0.09465867820213283,
+      "grad_norm": 0.7250267863273621,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.6484,
+      "step": 6138
+    },
+    {
+      "epoch": 0.09513675233446683,
+      "grad_norm": 0.7370029091835022,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.6639,
+      "step": 6169
+    },
+    {
+      "epoch": 0.09561482646680083,
+      "grad_norm": 0.7768808007240295,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.657,
+      "step": 6200
+    },
+    {
+      "epoch": 0.09609290059913483,
+      "grad_norm": 0.770039439201355,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.6588,
+      "step": 6231
+    },
+    {
+      "epoch": 0.09657097473146885,
+      "grad_norm": 0.637853741645813,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.6438,
+      "step": 6262
+    },
+    {
+      "epoch": 0.09704904886380285,
+      "grad_norm": 0.6896365284919739,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.6493,
+      "step": 6293
+    },
+    {
+      "epoch": 0.09752712299613685,
+      "grad_norm": 0.721318781375885,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.6427,
+      "step": 6324
+    },
+    {
+      "epoch": 0.09800519712847086,
+      "grad_norm": 0.7492154836654663,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.6474,
+      "step": 6355
+    },
+    {
+      "epoch": 0.09848327126080486,
+      "grad_norm": 0.8512872457504272,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.6423,
+      "step": 6386
+    },
+    {
+      "epoch": 0.09896134539313886,
+      "grad_norm": 0.6349690556526184,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.6499,
+      "step": 6417
+    },
+    {
+      "epoch": 0.09943941952547287,
+      "grad_norm": 0.8040255904197693,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.6495,
+      "step": 6448
+    },
+    {
+      "epoch": 0.09991749365780687,
+      "grad_norm": 0.6428426504135132,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.6565,
+      "step": 6479
+    },
+    {
+      "epoch": 0.10039556779014087,
+      "grad_norm": 0.8141711950302124,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.6592,
+      "step": 6510
+    },
+    {
+      "epoch": 0.10087364192247489,
+      "grad_norm": 0.8665099740028381,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.6497,
+      "step": 6541
+    },
+    {
+      "epoch": 0.10135171605480889,
+      "grad_norm": 0.709786057472229,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.6546,
+      "step": 6572
+    },
+    {
+      "epoch": 0.10182979018714289,
+      "grad_norm": 0.8345597982406616,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.6547,
+      "step": 6603
+    },
+    {
+      "epoch": 0.10230786431947689,
+      "grad_norm": 0.746769905090332,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.6526,
+      "step": 6634
+    },
+    {
+      "epoch": 0.1027859384518109,
+      "grad_norm": 0.7869583368301392,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.6458,
+      "step": 6665
+    },
+    {
+      "epoch": 0.1032640125841449,
+      "grad_norm": 0.5438331365585327,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.6468,
+      "step": 6696
+    },
+    {
+      "epoch": 0.1037420867164789,
+      "grad_norm": 0.7230411171913147,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.6435,
+      "step": 6727
+    },
+    {
+      "epoch": 0.10422016084881291,
+      "grad_norm": 0.9861361384391785,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.6488,
+      "step": 6758
+    },
+    {
+      "epoch": 0.10469823498114691,
+      "grad_norm": 0.7873183488845825,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.6485,
+      "step": 6789
+    },
+    {
+      "epoch": 0.10517630911348091,
+      "grad_norm": 0.7746345400810242,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.6384,
+      "step": 6820
+    },
+    {
+      "epoch": 0.10565438324581493,
+      "grad_norm": 0.8218130469322205,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.6434,
+      "step": 6851
+    },
+    {
+      "epoch": 0.10613245737814893,
+      "grad_norm": 0.7047727108001709,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.6562,
+      "step": 6882
+    },
+    {
+      "epoch": 0.10661053151048293,
+      "grad_norm": 0.9560827612876892,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.6422,
+      "step": 6913
+    },
+    {
+      "epoch": 0.10708860564281694,
+      "grad_norm": 1.1834834814071655,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.6525,
+      "step": 6944
+    },
+    {
+      "epoch": 0.10756667977515094,
+      "grad_norm": 0.8007238507270813,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.6575,
+      "step": 6975
+    },
+    {
+      "epoch": 0.10804475390748494,
+      "grad_norm": 0.6816396713256836,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.6453,
+      "step": 7006
+    },
+    {
+      "epoch": 0.10852282803981896,
+      "grad_norm": 0.7240257859230042,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.6542,
+      "step": 7037
+    },
+    {
+      "epoch": 0.10900090217215296,
+      "grad_norm": 0.6335741877555847,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.6449,
+      "step": 7068
+    },
+    {
+      "epoch": 0.10947897630448696,
+      "grad_norm": 0.6071763038635254,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.6572,
+      "step": 7099
+    },
+    {
+      "epoch": 0.10995705043682096,
+      "grad_norm": 0.8242653608322144,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.6483,
+      "step": 7130
+    },
+    {
+      "epoch": 0.11043512456915497,
+      "grad_norm": 0.7106221318244934,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.6376,
+      "step": 7161
+    },
+    {
+      "epoch": 0.11091319870148897,
+      "grad_norm": 0.6587203145027161,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.6426,
+      "step": 7192
+    },
+    {
+      "epoch": 0.11139127283382297,
+      "grad_norm": 0.8035815954208374,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.6428,
+      "step": 7223
+    },
+    {
+      "epoch": 0.11186934696615698,
+      "grad_norm": 0.6661431193351746,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.6431,
+      "step": 7254
+    },
+    {
+      "epoch": 0.11234742109849098,
+      "grad_norm": 0.5891786813735962,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.6356,
+      "step": 7285
+    },
+    {
+      "epoch": 0.11282549523082498,
+      "grad_norm": 0.7475966811180115,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.6348,
+      "step": 7316
+    },
+    {
+      "epoch": 0.113303569363159,
+      "grad_norm": 0.7461502552032471,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.639,
+      "step": 7347
+    },
+    {
+      "epoch": 0.113781643495493,
+      "grad_norm": 0.7351141571998596,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.6473,
+      "step": 7378
+    },
+    {
+      "epoch": 0.114259717627827,
+      "grad_norm": 0.7713771462440491,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.6433,
+      "step": 7409
+    },
+    {
+      "epoch": 0.11473779176016101,
+      "grad_norm": 0.639986515045166,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.6411,
+      "step": 7440
+    },
+    {
+      "epoch": 0.11521586589249501,
+      "grad_norm": 0.8399244546890259,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.6421,
+      "step": 7471
+    },
+    {
+      "epoch": 0.11569394002482901,
+      "grad_norm": 0.7681542634963989,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.6371,
+      "step": 7502
+    },
+    {
+      "epoch": 0.11617201415716301,
+      "grad_norm": 0.6907945275306702,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.6446,
+      "step": 7533
+    },
+    {
+      "epoch": 0.11665008828949702,
+      "grad_norm": 0.7653492093086243,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.6407,
+      "step": 7564
+    },
+    {
+      "epoch": 0.11712816242183102,
+      "grad_norm": 0.6535690426826477,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.6388,
+      "step": 7595
+    },
+    {
+      "epoch": 0.11760623655416502,
+      "grad_norm": 2.6184701919555664,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.6382,
+      "step": 7626
+    },
+    {
+      "epoch": 0.11808431068649904,
+      "grad_norm": 0.7846981287002563,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.6364,
+      "step": 7657
+    },
+    {
+      "epoch": 0.11856238481883304,
+      "grad_norm": 0.8151688575744629,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.6427,
+      "step": 7688
+    },
+    {
+      "epoch": 0.11904045895116704,
+      "grad_norm": 0.7663447856903076,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.643,
+      "step": 7719
+    },
+    {
+      "epoch": 0.11951853308350105,
+      "grad_norm": 0.7225657105445862,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.6395,
+      "step": 7750
+    },
+    {
+      "epoch": 0.11999660721583505,
+      "grad_norm": 0.7033439874649048,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.6354,
+      "step": 7781
+    },
+    {
+      "epoch": 0.12047468134816905,
+      "grad_norm": 0.7693649530410767,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.6436,
+      "step": 7812
+    },
+    {
+      "epoch": 0.12095275548050306,
+      "grad_norm": 0.7597894668579102,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.6411,
+      "step": 7843
+    },
+    {
+      "epoch": 0.12143082961283706,
+      "grad_norm": 0.7899183630943298,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.6381,
+      "step": 7874
+    },
+    {
+      "epoch": 0.12190890374517106,
+      "grad_norm": 0.7656906247138977,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.6386,
+      "step": 7905
+    },
+    {
+      "epoch": 0.12238697787750508,
+      "grad_norm": 0.8353867530822754,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.6386,
+      "step": 7936
+    },
+    {
+      "epoch": 0.12286505200983908,
+      "grad_norm": 0.6712770462036133,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.6438,
+      "step": 7967
+    },
+    {
+      "epoch": 0.12334312614217308,
+      "grad_norm": 0.8008986115455627,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.6384,
+      "step": 7998
+    },
+    {
+      "epoch": 0.12382120027450708,
+      "grad_norm": 0.6632928252220154,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.629,
+      "step": 8029
+    },
+    {
+      "epoch": 0.12429927440684109,
+      "grad_norm": 0.6943359971046448,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.6456,
+      "step": 8060
+    },
+    {
+      "epoch": 0.12477734853917509,
+      "grad_norm": 0.6177495718002319,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.6426,
+      "step": 8091
+    },
+    {
+      "epoch": 0.1252554226715091,
+      "grad_norm": 0.6089790463447571,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.6396,
+      "step": 8122
+    },
+    {
+      "epoch": 0.1257334968038431,
+      "grad_norm": 0.6960969567298889,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.6293,
+      "step": 8153
+    },
+    {
+      "epoch": 0.1262115709361771,
+      "grad_norm": 0.6519069075584412,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.6284,
+      "step": 8184
+    },
+    {
+      "epoch": 0.1266896450685111,
+      "grad_norm": 0.6861445903778076,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.6386,
+      "step": 8215
+    },
+    {
+      "epoch": 0.1271677192008451,
+      "grad_norm": 0.7522263526916504,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.6424,
+      "step": 8246
+    },
+    {
+      "epoch": 0.1276457933331791,
+      "grad_norm": 0.6868363618850708,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.6367,
+      "step": 8277
+    },
+    {
+      "epoch": 0.12812386746551313,
+      "grad_norm": 0.5939040780067444,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.6406,
+      "step": 8308
+    },
+    {
+      "epoch": 0.12860194159784713,
+      "grad_norm": 0.7341668605804443,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.6346,
+      "step": 8339
+    },
+    {
+      "epoch": 0.12908001573018113,
+      "grad_norm": 0.7468376755714417,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.6398,
+      "step": 8370
+    },
+    {
+      "epoch": 0.12955808986251513,
+      "grad_norm": 0.6253494024276733,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.6375,
+      "step": 8401
+    },
+    {
+      "epoch": 0.13003616399484913,
+      "grad_norm": 0.6635178923606873,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.6299,
+      "step": 8432
+    },
+    {
+      "epoch": 0.13051423812718313,
+      "grad_norm": 0.584648609161377,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.6277,
+      "step": 8463
+    },
+    {
+      "epoch": 0.13099231225951716,
+      "grad_norm": 0.5907359719276428,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.6328,
+      "step": 8494
+    },
+    {
+      "epoch": 0.13147038639185116,
+      "grad_norm": 0.7864153385162354,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.6365,
+      "step": 8525
+    },
+    {
+      "epoch": 0.13194846052418516,
+      "grad_norm": 0.6572133302688599,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.6312,
+      "step": 8556
+    },
+    {
+      "epoch": 0.13242653465651916,
+      "grad_norm": 0.7108786702156067,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.6355,
+      "step": 8587
+    },
+    {
+      "epoch": 0.13290460878885316,
+      "grad_norm": 0.6737267374992371,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.6256,
+      "step": 8618
+    },
+    {
+      "epoch": 0.13338268292118716,
+      "grad_norm": 0.6710911989212036,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.632,
+      "step": 8649
+    },
+    {
+      "epoch": 0.13386075705352116,
+      "grad_norm": 0.6295626759529114,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.6372,
+      "step": 8680
+    },
+    {
+      "epoch": 0.13433883118585518,
+      "grad_norm": 0.6405526399612427,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.6364,
+      "step": 8711
+    },
+    {
+      "epoch": 0.13481690531818918,
+      "grad_norm": 0.6847979426383972,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.6246,
+      "step": 8742
+    },
+    {
+      "epoch": 0.13529497945052318,
+      "grad_norm": 0.7338352799415588,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.6373,
+      "step": 8773
+    },
+    {
+      "epoch": 0.13577305358285718,
+      "grad_norm": 0.6530189514160156,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.6217,
+      "step": 8804
+    },
+    {
+      "epoch": 0.13625112771519118,
+      "grad_norm": 0.6450487375259399,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.6365,
+      "step": 8835
+    },
+    {
+      "epoch": 0.13672920184752518,
+      "grad_norm": 0.706732988357544,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.6294,
+      "step": 8866
+    },
+    {
+      "epoch": 0.1372072759798592,
+      "grad_norm": 0.687240481376648,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.6332,
+      "step": 8897
+    },
+    {
+      "epoch": 0.1376853501121932,
+      "grad_norm": 0.6686804890632629,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.6334,
+      "step": 8928
+    },
+    {
+      "epoch": 0.1381634242445272,
+      "grad_norm": 0.8371458649635315,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.6249,
+      "step": 8959
+    },
+    {
+      "epoch": 0.1386414983768612,
+      "grad_norm": 0.7204101085662842,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.6309,
+      "step": 8990
+    },
+    {
+      "epoch": 0.1391195725091952,
+      "grad_norm": 0.8539360165596008,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.6326,
+      "step": 9021
+    },
+    {
+      "epoch": 0.1395976466415292,
+      "grad_norm": 0.7264754176139832,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.6342,
+      "step": 9052
+    },
+    {
+      "epoch": 0.14007572077386324,
+      "grad_norm": 0.6681591868400574,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.6295,
+      "step": 9083
+    },
+    {
+      "epoch": 0.14055379490619724,
+      "grad_norm": 0.6293045282363892,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.6304,
+      "step": 9114
+    },
+    {
+      "epoch": 0.14103186903853124,
+      "grad_norm": 0.6432914137840271,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.6215,
+      "step": 9145
+    },
+    {
+      "epoch": 0.14150994317086524,
+      "grad_norm": 0.7524629235267639,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.625,
+      "step": 9176
+    },
+    {
+      "epoch": 0.14198801730319924,
+      "grad_norm": 0.7128170728683472,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.6342,
+      "step": 9207
+    },
+    {
+      "epoch": 0.14246609143553324,
+      "grad_norm": 0.651841938495636,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.6303,
+      "step": 9238
+    },
+    {
+      "epoch": 0.14294416556786724,
+      "grad_norm": 0.6290706396102905,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.6297,
+      "step": 9269
+    },
+    {
+      "epoch": 0.14342223970020127,
+      "grad_norm": 0.6372231841087341,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.6244,
+      "step": 9300
+    },
+    {
+      "epoch": 0.14390031383253526,
+      "grad_norm": 0.8424429297447205,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.6363,
+      "step": 9331
+    },
+    {
+      "epoch": 0.14437838796486926,
+      "grad_norm": 0.7121688723564148,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.63,
+      "step": 9362
+    },
+    {
+      "epoch": 0.14485646209720326,
+      "grad_norm": 0.7196950316429138,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.6254,
+      "step": 9393
+    },
+    {
+      "epoch": 0.14533453622953726,
+      "grad_norm": 0.6595038175582886,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.6207,
+      "step": 9424
+    },
+    {
+      "epoch": 0.14581261036187126,
+      "grad_norm": 0.6118171811103821,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.6233,
+      "step": 9455
+    },
+    {
+      "epoch": 0.1462906844942053,
+      "grad_norm": 0.7232321500778198,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.6328,
+      "step": 9486
+    },
+    {
+      "epoch": 0.1467687586265393,
+      "grad_norm": 0.691681981086731,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.634,
+      "step": 9517
+    },
+    {
+      "epoch": 0.1472468327588733,
+      "grad_norm": 0.6887443661689758,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.6275,
+      "step": 9548
+    },
+    {
+      "epoch": 0.1477249068912073,
+      "grad_norm": 0.6932326555252075,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.6233,
+      "step": 9579
+    },
+    {
+      "epoch": 0.1482029810235413,
+      "grad_norm": 0.7189227342605591,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.6229,
+      "step": 9610
+    },
+    {
+      "epoch": 0.1486810551558753,
+      "grad_norm": 0.6898639798164368,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.6251,
+      "step": 9641
+    },
+    {
+      "epoch": 0.1491591292882093,
+      "grad_norm": 0.6311922669410706,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.6249,
+      "step": 9672
+    },
+    {
+      "epoch": 0.14963720342054332,
+      "grad_norm": 0.5781577825546265,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.6337,
+      "step": 9703
+    },
+    {
+      "epoch": 0.15011527755287732,
+      "grad_norm": 0.6525286436080933,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.6347,
+      "step": 9734
+    },
+    {
+      "epoch": 0.15059335168521132,
+      "grad_norm": 0.6761188507080078,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.6267,
+      "step": 9765
+    },
+    {
+      "epoch": 0.15107142581754532,
+      "grad_norm": 0.674532413482666,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.6303,
+      "step": 9796
+    },
+    {
+      "epoch": 0.15154949994987932,
+      "grad_norm": 0.5923493504524231,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.6241,
+      "step": 9827
+    },
+    {
+      "epoch": 0.15202757408221332,
+      "grad_norm": 0.6309007406234741,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.6231,
+      "step": 9858
+    },
+    {
+      "epoch": 0.15250564821454735,
+      "grad_norm": 0.7521491050720215,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.6214,
+      "step": 9889
+    },
+    {
+      "epoch": 0.15298372234688135,
+      "grad_norm": 0.8196119666099548,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.6254,
+      "step": 9920
+    },
+    {
+      "epoch": 0.15346179647921535,
+      "grad_norm": 0.6895152926445007,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.6227,
+      "step": 9951
+    },
+    {
+      "epoch": 0.15393987061154935,
+      "grad_norm": 0.6823534369468689,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.6281,
+      "step": 9982
+    },
+    {
+      "epoch": 0.15441794474388335,
+      "grad_norm": 0.6531606912612915,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.6259,
+      "step": 10013
+    },
+    {
+      "epoch": 0.15489601887621735,
+      "grad_norm": 0.5898056626319885,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.6184,
+      "step": 10044
+    },
+    {
+      "epoch": 0.15537409300855134,
+      "grad_norm": 0.6368978023529053,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.6196,
+      "step": 10075
+    },
+    {
+      "epoch": 0.15585216714088537,
+      "grad_norm": 0.8086898922920227,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.6226,
+      "step": 10106
+    },
+    {
+      "epoch": 0.15633024127321937,
+      "grad_norm": 0.6620404124259949,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.6146,
+      "step": 10137
+    },
+    {
+      "epoch": 0.15680831540555337,
+      "grad_norm": 0.6264041662216187,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.6254,
+      "step": 10168
+    },
+    {
+      "epoch": 0.15728638953788737,
+      "grad_norm": 0.6619133353233337,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.6233,
+      "step": 10199
+    },
+    {
+      "epoch": 0.15776446367022137,
+      "grad_norm": 0.6223868131637573,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.6232,
+      "step": 10230
+    },
+    {
+      "epoch": 0.15824253780255537,
+      "grad_norm": 0.7436427474021912,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.6194,
+      "step": 10261
+    },
+    {
+      "epoch": 0.1587206119348894,
+      "grad_norm": 0.7166286110877991,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.6267,
+      "step": 10292
+    },
+    {
+      "epoch": 0.1591986860672234,
+      "grad_norm": 0.6377813220024109,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.6145,
+      "step": 10323
+    },
+    {
+      "epoch": 0.1596767601995574,
+      "grad_norm": 1.5197011232376099,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.6261,
+      "step": 10354
+    },
+    {
+      "epoch": 0.1601548343318914,
+      "grad_norm": 0.6208730340003967,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.6201,
+      "step": 10385
+    },
+    {
+      "epoch": 0.1606329084642254,
+      "grad_norm": 0.6887170076370239,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.6235,
+      "step": 10416
+    },
+    {
+      "epoch": 0.1611109825965594,
+      "grad_norm": 0.6381047368049622,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.6189,
+      "step": 10447
+    },
+    {
+      "epoch": 0.1615890567288934,
+      "grad_norm": 0.6249068379402161,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.6222,
+      "step": 10478
+    },
+    {
+      "epoch": 0.16206713086122743,
+      "grad_norm": 0.659757137298584,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.6345,
+      "step": 10509
+    },
+    {
+      "epoch": 0.16254520499356143,
+      "grad_norm": 0.6268470883369446,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.6197,
+      "step": 10540
+    },
+    {
+      "epoch": 0.16302327912589543,
+      "grad_norm": 0.6520307660102844,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.6122,
+      "step": 10571
+    },
+    {
+      "epoch": 0.16350135325822943,
+      "grad_norm": 0.5919711589813232,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.6237,
+      "step": 10602
+    },
+    {
+      "epoch": 0.16397942739056343,
+      "grad_norm": 0.6761168837547302,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.615,
+      "step": 10633
+    },
+    {
+      "epoch": 0.16445750152289743,
+      "grad_norm": 0.7123913168907166,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.6178,
+      "step": 10664
+    },
+    {
+      "epoch": 0.16493557565523145,
+      "grad_norm": 0.5414535403251648,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.6319,
+      "step": 10695
+    },
+    {
+      "epoch": 0.16541364978756545,
+      "grad_norm": 0.741256594657898,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.6102,
+      "step": 10726
+    },
+    {
+      "epoch": 0.16589172391989945,
+      "grad_norm": 0.6938264966011047,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.6127,
+      "step": 10757
+    },
+    {
+      "epoch": 0.16636979805223345,
+      "grad_norm": 0.7152143716812134,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.6119,
+      "step": 10788
+    },
+    {
+      "epoch": 0.16684787218456745,
+      "grad_norm": 0.6516321897506714,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.6224,
+      "step": 10819
+    },
+    {
+      "epoch": 0.16732594631690145,
+      "grad_norm": 0.6300469040870667,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.6229,
+      "step": 10850
+    },
+    {
+      "epoch": 0.16780402044923548,
+      "grad_norm": 0.645636260509491,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.6284,
+      "step": 10881
+    },
+    {
+      "epoch": 0.16828209458156948,
+      "grad_norm": 0.5895135402679443,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.6142,
+      "step": 10912
+    },
+    {
+      "epoch": 0.16876016871390348,
+      "grad_norm": 0.6440445184707642,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.6158,
+      "step": 10943
+    },
+    {
+      "epoch": 0.16923824284623748,
+      "grad_norm": 0.6739510893821716,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.6149,
+      "step": 10974
+    },
+    {
+      "epoch": 0.16971631697857148,
+      "grad_norm": 0.627185046672821,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.614,
+      "step": 11005
+    },
+    {
+      "epoch": 0.17019439111090548,
+      "grad_norm": 0.710350513458252,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.6214,
+      "step": 11036
+    },
+    {
+      "epoch": 0.17067246524323948,
+      "grad_norm": 0.6784375309944153,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.6123,
+      "step": 11067
+    },
+    {
+      "epoch": 0.1711505393755735,
+      "grad_norm": 0.6646184325218201,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.6178,
+      "step": 11098
+    },
+    {
+      "epoch": 0.1716286135079075,
+      "grad_norm": 0.7227056622505188,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.6158,
+      "step": 11129
+    },
+    {
+      "epoch": 0.1721066876402415,
+      "grad_norm": 0.5937723517417908,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.6194,
+      "step": 11160
+    },
+    {
+      "epoch": 0.1725847617725755,
+      "grad_norm": 0.6352291703224182,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.6286,
+      "step": 11191
+    },
+    {
+      "epoch": 0.1730628359049095,
+      "grad_norm": 0.5864464044570923,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.6186,
+      "step": 11222
+    },
+    {
+      "epoch": 0.1735409100372435,
+      "grad_norm": 0.5402609705924988,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.6072,
+      "step": 11253
+    },
+    {
+      "epoch": 0.17401898416957753,
+      "grad_norm": 0.6429933905601501,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.608,
+      "step": 11284
+    },
+    {
+      "epoch": 0.17449705830191153,
+      "grad_norm": 0.5420451164245605,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.6174,
+      "step": 11315
+    },
+    {
+      "epoch": 0.17497513243424553,
+      "grad_norm": 0.5691730380058289,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.6138,
+      "step": 11346
+    },
+    {
+      "epoch": 0.17545320656657953,
+      "grad_norm": 0.6198572516441345,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.6166,
+      "step": 11377
+    },
+    {
+      "epoch": 0.17593128069891353,
+      "grad_norm": 0.6781229972839355,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.6083,
+      "step": 11408
+    },
+    {
+      "epoch": 0.17640935483124753,
+      "grad_norm": 0.6572268605232239,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.6179,
+      "step": 11439
+    },
+    {
+      "epoch": 0.17688742896358153,
+      "grad_norm": 0.6720935702323914,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.6039,
+      "step": 11470
+    },
+    {
+      "epoch": 0.17736550309591556,
+      "grad_norm": 0.6098059415817261,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.608,
+      "step": 11501
+    },
+    {
+      "epoch": 0.17784357722824956,
+      "grad_norm": 0.6108371615409851,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.6147,
+      "step": 11532
+    },
+    {
+      "epoch": 0.17832165136058356,
+      "grad_norm": 0.8087718486785889,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.6091,
+      "step": 11563
+    },
+    {
+      "epoch": 0.17879972549291756,
+      "grad_norm": 0.719902753829956,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.6107,
+      "step": 11594
+    },
+    {
+      "epoch": 0.17927779962525156,
+      "grad_norm": 0.5758282542228699,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.6236,
+      "step": 11625
+    },
+    {
+      "epoch": 0.17975587375758556,
+      "grad_norm": 0.5602071285247803,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.611,
+      "step": 11656
+    },
+    {
+      "epoch": 0.1802339478899196,
+      "grad_norm": 0.6070683002471924,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.609,
+      "step": 11687
+    },
+    {
+      "epoch": 0.1807120220222536,
+      "grad_norm": 0.64506596326828,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.605,
+      "step": 11718
+    },
+    {
+      "epoch": 0.1811900961545876,
+      "grad_norm": 0.6906920075416565,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.6168,
+      "step": 11749
+    },
+    {
+      "epoch": 0.1816681702869216,
+      "grad_norm": 0.6724758148193359,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.6143,
+      "step": 11780
+    },
+    {
+      "epoch": 0.1821462444192556,
+      "grad_norm": 0.6033251881599426,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.6161,
+      "step": 11811
+    },
+    {
+      "epoch": 0.1826243185515896,
+      "grad_norm": 0.6713966727256775,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.619,
+      "step": 11842
+    },
+    {
+      "epoch": 0.1831023926839236,
+      "grad_norm": 0.6794861555099487,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.6116,
+      "step": 11873
+    },
+    {
+      "epoch": 0.18358046681625761,
+      "grad_norm": 0.5780847668647766,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.6159,
+      "step": 11904
+    },
+    {
+      "epoch": 0.18405854094859161,
+      "grad_norm": 0.6031593680381775,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.6135,
+      "step": 11935
+    },
+    {
+      "epoch": 0.18453661508092561,
+      "grad_norm": 0.6339271664619446,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.6113,
+      "step": 11966
+    },
+    {
+      "epoch": 0.18501468921325961,
+      "grad_norm": 0.6663223505020142,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.6184,
+      "step": 11997
+    },
+    {
+      "epoch": 0.18549276334559361,
+      "grad_norm": 0.9799377918243408,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.6103,
+      "step": 12028
+    },
+    {
+      "epoch": 0.18597083747792761,
+      "grad_norm": 0.7260358929634094,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.6245,
+      "step": 12059
+    },
+    {
+      "epoch": 0.18644891161026164,
+      "grad_norm": 0.7097154259681702,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.6194,
+      "step": 12090
+    },
+    {
+      "epoch": 0.18692698574259564,
+      "grad_norm": 0.5897482633590698,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.6171,
+      "step": 12121
+    },
+    {
+      "epoch": 0.18740505987492964,
+      "grad_norm": 0.6374841332435608,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.6141,
+      "step": 12152
+    },
+    {
+      "epoch": 0.18788313400726364,
+      "grad_norm": 0.6854335069656372,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.6077,
+      "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 sha256:8d2fa98715a72411d7d405e41015b5b23c93a1244803c7a5a69a929926c53d35
+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 sha256:628ae930c2d0e45bfb31fffd4e3c4f745876549d702d6c969bdfb2de61f428ef
+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 sha256:959587ffdc21357d366ea146ab22b4c08d05e36e0d4ca63a6d52141c108e3dba
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d731c0482c31d0627127a5db346acf32959b4379c2eea2adcff808ab6ac198a
+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 sha256:99b73557d18aac2bf4b2351ff09ef002e9f3223b0ea5fdd466b720ae7b9c9cf5
+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": 0.23533584707796465,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004780741323340042,
+      "grad_norm": 3.1866345405578613,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.194,
+      "step": 31
+    },
+    {
+      "epoch": 0.0009561482646680084,
+      "grad_norm": 1.7708723545074463,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 1.1124,
+      "step": 62
+    },
+    {
+      "epoch": 0.0014342223970020126,
+      "grad_norm": 1.6835601329803467,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.0585,
+      "step": 93
+    },
+    {
+      "epoch": 0.0019122965293360168,
+      "grad_norm": 1.642537236213684,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.0213,
+      "step": 124
+    },
+    {
+      "epoch": 0.002390370661670021,
+      "grad_norm": 1.8476150035858154,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.0024,
+      "step": 155
+    },
+    {
+      "epoch": 0.0028684447940040252,
+      "grad_norm": 1.96336829662323,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 0.9938,
+      "step": 186
+    },
+    {
+      "epoch": 0.0033465189263380294,
+      "grad_norm": 1.8158528804779053,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 0.969,
+      "step": 217
+    },
+    {
+      "epoch": 0.0038245930586720336,
+      "grad_norm": 1.9796783924102783,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 0.9573,
+      "step": 248
+    },
+    {
+      "epoch": 0.004302667191006038,
+      "grad_norm": 1.8192514181137085,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 0.9498,
+      "step": 279
+    },
+    {
+      "epoch": 0.004780741323340042,
+      "grad_norm": 2.1396358013153076,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 0.9294,
+      "step": 310
+    },
+    {
+      "epoch": 0.005258815455674046,
+      "grad_norm": 2.0807156562805176,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 0.9186,
+      "step": 341
+    },
+    {
+      "epoch": 0.0057368895880080505,
+      "grad_norm": 2.002887010574341,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 0.9149,
+      "step": 372
+    },
+    {
+      "epoch": 0.006214963720342055,
+      "grad_norm": 2.240675687789917,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 0.9139,
+      "step": 403
+    },
+    {
+      "epoch": 0.006693037852676059,
+      "grad_norm": 1.9016591310501099,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 0.8946,
+      "step": 434
+    },
+    {
+      "epoch": 0.007171111985010063,
+      "grad_norm": 1.6729310750961304,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 0.8959,
+      "step": 465
+    },
+    {
+      "epoch": 0.007649186117344067,
+      "grad_norm": 2.2607779502868652,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 0.8847,
+      "step": 496
+    },
+    {
+      "epoch": 0.00812726024967807,
+      "grad_norm": 1.699507236480713,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 0.8773,
+      "step": 527
+    },
+    {
+      "epoch": 0.008605334382012076,
+      "grad_norm": 1.93502938747406,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 0.8773,
+      "step": 558
+    },
+    {
+      "epoch": 0.009083408514346079,
+      "grad_norm": 2.1234281063079834,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 0.8669,
+      "step": 589
+    },
+    {
+      "epoch": 0.009561482646680084,
+      "grad_norm": 1.7465944290161133,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 0.8536,
+      "step": 620
+    },
+    {
+      "epoch": 0.010039556779014087,
+      "grad_norm": 1.7039932012557983,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 0.8624,
+      "step": 651
+    },
+    {
+      "epoch": 0.010517630911348093,
+      "grad_norm": 1.551837682723999,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 0.8555,
+      "step": 682
+    },
+    {
+      "epoch": 0.010995705043682096,
+      "grad_norm": 1.7622497081756592,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 0.8475,
+      "step": 713
+    },
+    {
+      "epoch": 0.011473779176016101,
+      "grad_norm": 2.000936269760132,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 0.852,
+      "step": 744
+    },
+    {
+      "epoch": 0.011951853308350104,
+      "grad_norm": 1.6770379543304443,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.8455,
+      "step": 775
+    },
+    {
+      "epoch": 0.01242992744068411,
+      "grad_norm": 1.746506929397583,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.8406,
+      "step": 806
+    },
+    {
+      "epoch": 0.012908001573018113,
+      "grad_norm": 1.507759690284729,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.8556,
+      "step": 837
+    },
+    {
+      "epoch": 0.013386075705352118,
+      "grad_norm": 1.6984492540359497,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.8281,
+      "step": 868
+    },
+    {
+      "epoch": 0.013864149837686121,
+      "grad_norm": 1.5145736932754517,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.8359,
+      "step": 899
+    },
+    {
+      "epoch": 0.014342223970020126,
+      "grad_norm": 1.5700000524520874,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.8305,
+      "step": 930
+    },
+    {
+      "epoch": 0.01482029810235413,
+      "grad_norm": 1.6657596826553345,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.8263,
+      "step": 961
+    },
+    {
+      "epoch": 0.015298372234688135,
+      "grad_norm": 1.527628779411316,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.8318,
+      "step": 992
+    },
+    {
+      "epoch": 0.015776446367022138,
+      "grad_norm": 1.8353967666625977,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.8192,
+      "step": 1023
+    },
+    {
+      "epoch": 0.01625452049935614,
+      "grad_norm": 1.2118042707443237,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.819,
+      "step": 1054
+    },
+    {
+      "epoch": 0.016732594631690145,
+      "grad_norm": 1.3235970735549927,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.8176,
+      "step": 1085
+    },
+    {
+      "epoch": 0.01721066876402415,
+      "grad_norm": 1.6729888916015625,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.8202,
+      "step": 1116
+    },
+    {
+      "epoch": 0.017688742896358155,
+      "grad_norm": 1.3251298666000366,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.8104,
+      "step": 1147
+    },
+    {
+      "epoch": 0.018166817028692158,
+      "grad_norm": 1.5231342315673828,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.8113,
+      "step": 1178
+    },
+    {
+      "epoch": 0.01864489116102616,
+      "grad_norm": 1.3263883590698242,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.7981,
+      "step": 1209
+    },
+    {
+      "epoch": 0.019122965293360168,
+      "grad_norm": 1.317791223526001,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.7962,
+      "step": 1240
+    },
+    {
+      "epoch": 0.01960103942569417,
+      "grad_norm": 1.566698670387268,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.8072,
+      "step": 1271
+    },
+    {
+      "epoch": 0.020079113558028175,
+      "grad_norm": 1.2935110330581665,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.7818,
+      "step": 1302
+    },
+    {
+      "epoch": 0.020557187690362178,
+      "grad_norm": 1.336227536201477,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.7917,
+      "step": 1333
+    },
+    {
+      "epoch": 0.021035261822696185,
+      "grad_norm": 1.5656548738479614,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.7785,
+      "step": 1364
+    },
+    {
+      "epoch": 0.02151333595503019,
+      "grad_norm": 1.5208159685134888,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.7839,
+      "step": 1395
+    },
+    {
+      "epoch": 0.02199141008736419,
+      "grad_norm": 1.4816375970840454,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.7789,
+      "step": 1426
+    },
+    {
+      "epoch": 0.022469484219698195,
+      "grad_norm": 1.402166485786438,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.7803,
+      "step": 1457
+    },
+    {
+      "epoch": 0.022947558352032202,
+      "grad_norm": 1.2986265420913696,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.7739,
+      "step": 1488
+    },
+    {
+      "epoch": 0.023425632484366205,
+      "grad_norm": 1.3171271085739136,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.7694,
+      "step": 1519
+    },
+    {
+      "epoch": 0.02390370661670021,
+      "grad_norm": 1.4870030879974365,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.7663,
+      "step": 1550
+    },
+    {
+      "epoch": 0.024381780749034212,
+      "grad_norm": 1.7419476509094238,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.7731,
+      "step": 1581
+    },
+    {
+      "epoch": 0.02485985488136822,
+      "grad_norm": 1.109238624572754,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.7704,
+      "step": 1612
+    },
+    {
+      "epoch": 0.025337929013702222,
+      "grad_norm": 1.3478920459747314,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.7723,
+      "step": 1643
+    },
+    {
+      "epoch": 0.025816003146036225,
+      "grad_norm": 1.2739650011062622,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.7699,
+      "step": 1674
+    },
+    {
+      "epoch": 0.02629407727837023,
+      "grad_norm": 1.3892935514450073,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.7709,
+      "step": 1705
+    },
+    {
+      "epoch": 0.026772151410704235,
+      "grad_norm": 1.2031512260437012,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.7557,
+      "step": 1736
+    },
+    {
+      "epoch": 0.02725022554303824,
+      "grad_norm": 1.185471773147583,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.7645,
+      "step": 1767
+    },
+    {
+      "epoch": 0.027728299675372242,
+      "grad_norm": 1.2331740856170654,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.7655,
+      "step": 1798
+    },
+    {
+      "epoch": 0.028206373807706245,
+      "grad_norm": 1.1817049980163574,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.7617,
+      "step": 1829
+    },
+    {
+      "epoch": 0.028684447940040252,
+      "grad_norm": 1.2225860357284546,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.7558,
+      "step": 1860
+    },
+    {
+      "epoch": 0.029162522072374256,
+      "grad_norm": 1.6452528238296509,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.7566,
+      "step": 1891
+    },
+    {
+      "epoch": 0.02964059620470826,
+      "grad_norm": 1.3764828443527222,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.7545,
+      "step": 1922
+    },
+    {
+      "epoch": 0.030118670337042262,
+      "grad_norm": 1.6581465005874634,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.7519,
+      "step": 1953
+    },
+    {
+      "epoch": 0.03059674446937627,
+      "grad_norm": 1.1065036058425903,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.7579,
+      "step": 1984
+    },
+    {
+      "epoch": 0.031074818601710272,
+      "grad_norm": 2.6465444564819336,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.7538,
+      "step": 2015
+    },
+    {
+      "epoch": 0.031552892734044276,
+      "grad_norm": 1.3028968572616577,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.7522,
+      "step": 2046
+    },
+    {
+      "epoch": 0.03203096686637828,
+      "grad_norm": 1.0450382232666016,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.742,
+      "step": 2077
+    },
+    {
+      "epoch": 0.03250904099871228,
+      "grad_norm": 0.9411994814872742,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.7401,
+      "step": 2108
+    },
+    {
+      "epoch": 0.03298711513104629,
+      "grad_norm": 1.0501608848571777,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.7455,
+      "step": 2139
+    },
+    {
+      "epoch": 0.03346518926338029,
+      "grad_norm": 1.266400694847107,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.7391,
+      "step": 2170
+    },
+    {
+      "epoch": 0.033943263395714296,
+      "grad_norm": 1.2862213850021362,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.7397,
+      "step": 2201
+    },
+    {
+      "epoch": 0.0344213375280483,
+      "grad_norm": 1.2715409994125366,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.7467,
+      "step": 2232
+    },
+    {
+      "epoch": 0.0348994116603823,
+      "grad_norm": 1.3290003538131714,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.7432,
+      "step": 2263
+    },
+    {
+      "epoch": 0.03537748579271631,
+      "grad_norm": 1.0561761856079102,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.7336,
+      "step": 2294
+    },
+    {
+      "epoch": 0.035855559925050316,
+      "grad_norm": 1.3272422552108765,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.7251,
+      "step": 2325
+    },
+    {
+      "epoch": 0.036333634057384316,
+      "grad_norm": 1.0749491453170776,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.7205,
+      "step": 2356
+    },
+    {
+      "epoch": 0.03681170818971832,
+      "grad_norm": 1.1581461429595947,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.7311,
+      "step": 2387
+    },
+    {
+      "epoch": 0.03728978232205232,
+      "grad_norm": 1.0796961784362793,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.7259,
+      "step": 2418
+    },
+    {
+      "epoch": 0.03776785645438633,
+      "grad_norm": 1.1916818618774414,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.7258,
+      "step": 2449
+    },
+    {
+      "epoch": 0.038245930586720336,
+      "grad_norm": 0.9515872001647949,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.7273,
+      "step": 2480
+    },
+    {
+      "epoch": 0.038724004719054336,
+      "grad_norm": 1.1217246055603027,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.7269,
+      "step": 2511
+    },
+    {
+      "epoch": 0.03920207885138834,
+      "grad_norm": 0.9570199847221375,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.7289,
+      "step": 2542
+    },
+    {
+      "epoch": 0.03968015298372235,
+      "grad_norm": 1.2980682849884033,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.7382,
+      "step": 2573
+    },
+    {
+      "epoch": 0.04015822711605635,
+      "grad_norm": 2.1257143020629883,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.8112,
+      "step": 2604
+    },
+    {
+      "epoch": 0.04063630124839036,
+      "grad_norm": 1.5091110467910767,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.7451,
+      "step": 2635
+    },
+    {
+      "epoch": 0.041114375380724356,
+      "grad_norm": 2.4548749923706055,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.7358,
+      "step": 2666
+    },
+    {
+      "epoch": 0.04159244951305836,
+      "grad_norm": 1.176115870475769,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.7368,
+      "step": 2697
+    },
+    {
+      "epoch": 0.04207052364539237,
+      "grad_norm": 1.063672661781311,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.7465,
+      "step": 2728
+    },
+    {
+      "epoch": 0.04254859777772637,
+      "grad_norm": 1.3062779903411865,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.7413,
+      "step": 2759
+    },
+    {
+      "epoch": 0.04302667191006038,
+      "grad_norm": 1.5550280809402466,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.724,
+      "step": 2790
+    },
+    {
+      "epoch": 0.043504746042394384,
+      "grad_norm": 1.2525728940963745,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.7216,
+      "step": 2821
+    },
+    {
+      "epoch": 0.04398282017472838,
+      "grad_norm": 1.158134937286377,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.728,
+      "step": 2852
+    },
+    {
+      "epoch": 0.04446089430706239,
+      "grad_norm": 1.262291669845581,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.7191,
+      "step": 2883
+    },
+    {
+      "epoch": 0.04493896843939639,
+      "grad_norm": 2.826028347015381,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.7211,
+      "step": 2914
+    },
+    {
+      "epoch": 0.0454170425717304,
+      "grad_norm": 1.0346958637237549,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.7268,
+      "step": 2945
+    },
+    {
+      "epoch": 0.045895116704064404,
+      "grad_norm": 1.4338330030441284,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.7154,
+      "step": 2976
+    },
+    {
+      "epoch": 0.046373190836398404,
+      "grad_norm": 0.9223676919937134,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.7195,
+      "step": 3007
+    },
+    {
+      "epoch": 0.04685126496873241,
+      "grad_norm": 0.9936623573303223,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.7194,
+      "step": 3038
+    },
+    {
+      "epoch": 0.04732933910106642,
+      "grad_norm": 1.017962098121643,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.713,
+      "step": 3069
+    },
+    {
+      "epoch": 0.04780741323340042,
+      "grad_norm": 0.9654473662376404,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.7096,
+      "step": 3100
+    },
+    {
+      "epoch": 0.048285487365734424,
+      "grad_norm": 0.9372695684432983,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.7116,
+      "step": 3131
+    },
+    {
+      "epoch": 0.048763561498068424,
+      "grad_norm": 0.9450846910476685,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.7129,
+      "step": 3162
+    },
+    {
+      "epoch": 0.04924163563040243,
+      "grad_norm": 1.0803054571151733,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.706,
+      "step": 3193
+    },
+    {
+      "epoch": 0.04971970976273644,
+      "grad_norm": 1.2218348979949951,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.7076,
+      "step": 3224
+    },
+    {
+      "epoch": 0.05019778389507044,
+      "grad_norm": 1.0429767370224,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.7089,
+      "step": 3255
+    },
+    {
+      "epoch": 0.050675858027404444,
+      "grad_norm": 0.9912049770355225,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.7016,
+      "step": 3286
+    },
+    {
+      "epoch": 0.051153932159738444,
+      "grad_norm": 0.9687103033065796,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.7071,
+      "step": 3317
+    },
+    {
+      "epoch": 0.05163200629207245,
+      "grad_norm": 0.8178670406341553,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.6991,
+      "step": 3348
+    },
+    {
+      "epoch": 0.05211008042440646,
+      "grad_norm": 0.8601382374763489,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.6978,
+      "step": 3379
+    },
+    {
+      "epoch": 0.05258815455674046,
+      "grad_norm": 1.076370120048523,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.7044,
+      "step": 3410
+    },
+    {
+      "epoch": 0.053066228689074464,
+      "grad_norm": 3.9457356929779053,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.6978,
+      "step": 3441
+    },
+    {
+      "epoch": 0.05354430282140847,
+      "grad_norm": 0.8186474442481995,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.6974,
+      "step": 3472
+    },
+    {
+      "epoch": 0.05402237695374247,
+      "grad_norm": 0.9643816947937012,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.7025,
+      "step": 3503
+    },
+    {
+      "epoch": 0.05450045108607648,
+      "grad_norm": 1.024248480796814,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.7006,
+      "step": 3534
+    },
+    {
+      "epoch": 0.05497852521841048,
+      "grad_norm": 0.7718949317932129,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.7024,
+      "step": 3565
+    },
+    {
+      "epoch": 0.055456599350744484,
+      "grad_norm": 1.1313899755477905,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.701,
+      "step": 3596
+    },
+    {
+      "epoch": 0.05593467348307849,
+      "grad_norm": 1.0118827819824219,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.7036,
+      "step": 3627
+    },
+    {
+      "epoch": 0.05641274761541249,
+      "grad_norm": 0.9465724229812622,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.6869,
+      "step": 3658
+    },
+    {
+      "epoch": 0.0568908217477465,
+      "grad_norm": 1.0233882665634155,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.6944,
+      "step": 3689
+    },
+    {
+      "epoch": 0.057368895880080505,
+      "grad_norm": 1.008609652519226,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.6916,
+      "step": 3720
+    },
+    {
+      "epoch": 0.057846970012414504,
+      "grad_norm": 1.0083181858062744,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.6886,
+      "step": 3751
+    },
+    {
+      "epoch": 0.05832504414474851,
+      "grad_norm": 0.9374220967292786,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.6976,
+      "step": 3782
+    },
+    {
+      "epoch": 0.05880311827708251,
+      "grad_norm": 0.9066904783248901,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.6911,
+      "step": 3813
+    },
+    {
+      "epoch": 0.05928119240941652,
+      "grad_norm": 0.9702699780464172,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.6959,
+      "step": 3844
+    },
+    {
+      "epoch": 0.059759266541750525,
+      "grad_norm": 0.8405037522315979,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.6896,
+      "step": 3875
+    },
+    {
+      "epoch": 0.060237340674084525,
+      "grad_norm": 0.9460383653640747,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.6871,
+      "step": 3906
+    },
+    {
+      "epoch": 0.06071541480641853,
+      "grad_norm": 0.9355078339576721,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.6843,
+      "step": 3937
+    },
+    {
+      "epoch": 0.06119348893875254,
+      "grad_norm": 0.7211058735847473,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.6861,
+      "step": 3968
+    },
+    {
+      "epoch": 0.06167156307108654,
+      "grad_norm": 0.8674766421318054,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.6939,
+      "step": 3999
+    },
+    {
+      "epoch": 0.062149637203420545,
+      "grad_norm": 0.8166181445121765,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.692,
+      "step": 4030
+    },
+    {
+      "epoch": 0.06262771133575455,
+      "grad_norm": 0.841305136680603,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.6855,
+      "step": 4061
+    },
+    {
+      "epoch": 0.06310578546808855,
+      "grad_norm": 0.8942857384681702,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.6946,
+      "step": 4092
+    },
+    {
+      "epoch": 0.06358385960042255,
+      "grad_norm": 0.8595120310783386,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.6825,
+      "step": 4123
+    },
+    {
+      "epoch": 0.06406193373275657,
+      "grad_norm": 0.8155812621116638,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.6821,
+      "step": 4154
+    },
+    {
+      "epoch": 0.06454000786509057,
+      "grad_norm": 0.8901113271713257,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.6898,
+      "step": 4185
+    },
+    {
+      "epoch": 0.06501808199742456,
+      "grad_norm": 0.9637976288795471,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.6829,
+      "step": 4216
+    },
+    {
+      "epoch": 0.06549615612975858,
+      "grad_norm": 0.7048139572143555,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.6834,
+      "step": 4247
+    },
+    {
+      "epoch": 0.06597423026209258,
+      "grad_norm": 0.8655612468719482,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.6778,
+      "step": 4278
+    },
+    {
+      "epoch": 0.06645230439442658,
+      "grad_norm": 0.8204261064529419,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.6672,
+      "step": 4309
+    },
+    {
+      "epoch": 0.06693037852676058,
+      "grad_norm": 0.9259466528892517,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.6778,
+      "step": 4340
+    },
+    {
+      "epoch": 0.06740845265909459,
+      "grad_norm": 0.9826278686523438,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.6882,
+      "step": 4371
+    },
+    {
+      "epoch": 0.06788652679142859,
+      "grad_norm": 0.7376586198806763,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.6802,
+      "step": 4402
+    },
+    {
+      "epoch": 0.06836460092376259,
+      "grad_norm": 0.6778755784034729,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.6814,
+      "step": 4433
+    },
+    {
+      "epoch": 0.0688426750560966,
+      "grad_norm": 0.8117042183876038,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.6759,
+      "step": 4464
+    },
+    {
+      "epoch": 0.0693207491884306,
+      "grad_norm": 0.9493227005004883,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.6744,
+      "step": 4495
+    },
+    {
+      "epoch": 0.0697988233207646,
+      "grad_norm": 1.3356900215148926,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.6763,
+      "step": 4526
+    },
+    {
+      "epoch": 0.07027689745309862,
+      "grad_norm": 1.1542543172836304,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.6788,
+      "step": 4557
+    },
+    {
+      "epoch": 0.07075497158543262,
+      "grad_norm": 0.785176157951355,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.6853,
+      "step": 4588
+    },
+    {
+      "epoch": 0.07123304571776662,
+      "grad_norm": 0.8102776408195496,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.6794,
+      "step": 4619
+    },
+    {
+      "epoch": 0.07171111985010063,
+      "grad_norm": 0.9685975313186646,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.6823,
+      "step": 4650
+    },
+    {
+      "epoch": 0.07218919398243463,
+      "grad_norm": 0.7929072976112366,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.6781,
+      "step": 4681
+    },
+    {
+      "epoch": 0.07266726811476863,
+      "grad_norm": 0.8171564340591431,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.6685,
+      "step": 4712
+    },
+    {
+      "epoch": 0.07314534224710265,
+      "grad_norm": 0.9218119382858276,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.6796,
+      "step": 4743
+    },
+    {
+      "epoch": 0.07362341637943665,
+      "grad_norm": 3.1681158542633057,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.676,
+      "step": 4774
+    },
+    {
+      "epoch": 0.07410149051177065,
+      "grad_norm": 0.9336240887641907,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.6734,
+      "step": 4805
+    },
+    {
+      "epoch": 0.07457956464410465,
+      "grad_norm": 0.8264138102531433,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.6905,
+      "step": 4836
+    },
+    {
+      "epoch": 0.07505763877643866,
+      "grad_norm": 0.819663405418396,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.6814,
+      "step": 4867
+    },
+    {
+      "epoch": 0.07553571290877266,
+      "grad_norm": 3.124502420425415,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.6704,
+      "step": 4898
+    },
+    {
+      "epoch": 0.07601378704110666,
+      "grad_norm": 0.7769860625267029,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.6728,
+      "step": 4929
+    },
+    {
+      "epoch": 0.07649186117344067,
+      "grad_norm": 0.8232171535491943,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.6798,
+      "step": 4960
+    },
+    {
+      "epoch": 0.07696993530577467,
+      "grad_norm": 0.8771420121192932,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.6722,
+      "step": 4991
+    },
+    {
+      "epoch": 0.07744800943810867,
+      "grad_norm": 0.8321033716201782,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.6724,
+      "step": 5022
+    },
+    {
+      "epoch": 0.07792608357044269,
+      "grad_norm": 0.9346029162406921,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.6764,
+      "step": 5053
+    },
+    {
+      "epoch": 0.07840415770277669,
+      "grad_norm": 0.9193580150604248,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.6789,
+      "step": 5084
+    },
+    {
+      "epoch": 0.07888223183511069,
+      "grad_norm": 1.0850661993026733,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.6685,
+      "step": 5115
+    },
+    {
+      "epoch": 0.0793603059674447,
+      "grad_norm": 0.6851856708526611,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.6621,
+      "step": 5146
+    },
+    {
+      "epoch": 0.0798383800997787,
+      "grad_norm": 0.7950114607810974,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.6642,
+      "step": 5177
+    },
+    {
+      "epoch": 0.0803164542321127,
+      "grad_norm": 0.9632556438446045,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.6628,
+      "step": 5208
+    },
+    {
+      "epoch": 0.0807945283644467,
+      "grad_norm": 0.7066652178764343,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.6642,
+      "step": 5239
+    },
+    {
+      "epoch": 0.08127260249678071,
+      "grad_norm": 0.7749651670455933,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.6633,
+      "step": 5270
+    },
+    {
+      "epoch": 0.08175067662911471,
+      "grad_norm": 1.702022671699524,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.6745,
+      "step": 5301
+    },
+    {
+      "epoch": 0.08222875076144871,
+      "grad_norm": 0.8134759068489075,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.659,
+      "step": 5332
+    },
+    {
+      "epoch": 0.08270682489378273,
+      "grad_norm": 0.8805097341537476,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.6779,
+      "step": 5363
+    },
+    {
+      "epoch": 0.08318489902611673,
+      "grad_norm": 0.9312698841094971,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.6634,
+      "step": 5394
+    },
+    {
+      "epoch": 0.08366297315845073,
+      "grad_norm": 0.7013948559761047,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.6589,
+      "step": 5425
+    },
+    {
+      "epoch": 0.08414104729078474,
+      "grad_norm": 0.8027428388595581,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.6603,
+      "step": 5456
+    },
+    {
+      "epoch": 0.08461912142311874,
+      "grad_norm": 1.0179306268692017,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.6595,
+      "step": 5487
+    },
+    {
+      "epoch": 0.08509719555545274,
+      "grad_norm": 0.8512592911720276,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.6659,
+      "step": 5518
+    },
+    {
+      "epoch": 0.08557526968778675,
+      "grad_norm": 0.8476304411888123,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.6658,
+      "step": 5549
+    },
+    {
+      "epoch": 0.08605334382012075,
+      "grad_norm": 0.771584153175354,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.6622,
+      "step": 5580
+    },
+    {
+      "epoch": 0.08653141795245475,
+      "grad_norm": 0.8719794154167175,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.661,
+      "step": 5611
+    },
+    {
+      "epoch": 0.08700949208478877,
+      "grad_norm": 0.9247443675994873,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.6475,
+      "step": 5642
+    },
+    {
+      "epoch": 0.08748756621712277,
+      "grad_norm": 0.9540857672691345,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.662,
+      "step": 5673
+    },
+    {
+      "epoch": 0.08796564034945677,
+      "grad_norm": 0.7939008474349976,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.6514,
+      "step": 5704
+    },
+    {
+      "epoch": 0.08844371448179077,
+      "grad_norm": 0.613531768321991,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.6513,
+      "step": 5735
+    },
+    {
+      "epoch": 0.08892178861412478,
+      "grad_norm": 0.8084924817085266,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.6465,
+      "step": 5766
+    },
+    {
+      "epoch": 0.08939986274645878,
+      "grad_norm": 0.7709007263183594,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.6618,
+      "step": 5797
+    },
+    {
+      "epoch": 0.08987793687879278,
+      "grad_norm": 0.6461811065673828,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.6516,
+      "step": 5828
+    },
+    {
+      "epoch": 0.0903560110111268,
+      "grad_norm": 0.6879326105117798,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.655,
+      "step": 5859
+    },
+    {
+      "epoch": 0.0908340851434608,
+      "grad_norm": 0.7594075798988342,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.655,
+      "step": 5890
+    },
+    {
+      "epoch": 0.0913121592757948,
+      "grad_norm": 0.774758517742157,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.6697,
+      "step": 5921
+    },
+    {
+      "epoch": 0.09179023340812881,
+      "grad_norm": 0.9164844155311584,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.6483,
+      "step": 5952
+    },
+    {
+      "epoch": 0.09226830754046281,
+      "grad_norm": 0.792631208896637,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.6644,
+      "step": 5983
+    },
+    {
+      "epoch": 0.09274638167279681,
+      "grad_norm": 0.7735174298286438,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.6545,
+      "step": 6014
+    },
+    {
+      "epoch": 0.09322445580513082,
+      "grad_norm": 0.725825309753418,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.6579,
+      "step": 6045
+    },
+    {
+      "epoch": 0.09370252993746482,
+      "grad_norm": 0.7191294431686401,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.6509,
+      "step": 6076
+    },
+    {
+      "epoch": 0.09418060406979882,
+      "grad_norm": 0.8470766544342041,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.6515,
+      "step": 6107
+    },
+    {
+      "epoch": 0.09465867820213283,
+      "grad_norm": 0.7250267863273621,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.6484,
+      "step": 6138
+    },
+    {
+      "epoch": 0.09513675233446683,
+      "grad_norm": 0.7370029091835022,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.6639,
+      "step": 6169
+    },
+    {
+      "epoch": 0.09561482646680083,
+      "grad_norm": 0.7768808007240295,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.657,
+      "step": 6200
+    },
+    {
+      "epoch": 0.09609290059913483,
+      "grad_norm": 0.770039439201355,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.6588,
+      "step": 6231
+    },
+    {
+      "epoch": 0.09657097473146885,
+      "grad_norm": 0.637853741645813,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.6438,
+      "step": 6262
+    },
+    {
+      "epoch": 0.09704904886380285,
+      "grad_norm": 0.6896365284919739,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.6493,
+      "step": 6293
+    },
+    {
+      "epoch": 0.09752712299613685,
+      "grad_norm": 0.721318781375885,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.6427,
+      "step": 6324
+    },
+    {
+      "epoch": 0.09800519712847086,
+      "grad_norm": 0.7492154836654663,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.6474,
+      "step": 6355
+    },
+    {
+      "epoch": 0.09848327126080486,
+      "grad_norm": 0.8512872457504272,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.6423,
+      "step": 6386
+    },
+    {
+      "epoch": 0.09896134539313886,
+      "grad_norm": 0.6349690556526184,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.6499,
+      "step": 6417
+    },
+    {
+      "epoch": 0.09943941952547287,
+      "grad_norm": 0.8040255904197693,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.6495,
+      "step": 6448
+    },
+    {
+      "epoch": 0.09991749365780687,
+      "grad_norm": 0.6428426504135132,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.6565,
+      "step": 6479
+    },
+    {
+      "epoch": 0.10039556779014087,
+      "grad_norm": 0.8141711950302124,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.6592,
+      "step": 6510
+    },
+    {
+      "epoch": 0.10087364192247489,
+      "grad_norm": 0.8665099740028381,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.6497,
+      "step": 6541
+    },
+    {
+      "epoch": 0.10135171605480889,
+      "grad_norm": 0.709786057472229,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.6546,
+      "step": 6572
+    },
+    {
+      "epoch": 0.10182979018714289,
+      "grad_norm": 0.8345597982406616,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.6547,
+      "step": 6603
+    },
+    {
+      "epoch": 0.10230786431947689,
+      "grad_norm": 0.746769905090332,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.6526,
+      "step": 6634
+    },
+    {
+      "epoch": 0.1027859384518109,
+      "grad_norm": 0.7869583368301392,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.6458,
+      "step": 6665
+    },
+    {
+      "epoch": 0.1032640125841449,
+      "grad_norm": 0.5438331365585327,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.6468,
+      "step": 6696
+    },
+    {
+      "epoch": 0.1037420867164789,
+      "grad_norm": 0.7230411171913147,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.6435,
+      "step": 6727
+    },
+    {
+      "epoch": 0.10422016084881291,
+      "grad_norm": 0.9861361384391785,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.6488,
+      "step": 6758
+    },
+    {
+      "epoch": 0.10469823498114691,
+      "grad_norm": 0.7873183488845825,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.6485,
+      "step": 6789
+    },
+    {
+      "epoch": 0.10517630911348091,
+      "grad_norm": 0.7746345400810242,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.6384,
+      "step": 6820
+    },
+    {
+      "epoch": 0.10565438324581493,
+      "grad_norm": 0.8218130469322205,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.6434,
+      "step": 6851
+    },
+    {
+      "epoch": 0.10613245737814893,
+      "grad_norm": 0.7047727108001709,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.6562,
+      "step": 6882
+    },
+    {
+      "epoch": 0.10661053151048293,
+      "grad_norm": 0.9560827612876892,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.6422,
+      "step": 6913
+    },
+    {
+      "epoch": 0.10708860564281694,
+      "grad_norm": 1.1834834814071655,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.6525,
+      "step": 6944
+    },
+    {
+      "epoch": 0.10756667977515094,
+      "grad_norm": 0.8007238507270813,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.6575,
+      "step": 6975
+    },
+    {
+      "epoch": 0.10804475390748494,
+      "grad_norm": 0.6816396713256836,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.6453,
+      "step": 7006
+    },
+    {
+      "epoch": 0.10852282803981896,
+      "grad_norm": 0.7240257859230042,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.6542,
+      "step": 7037
+    },
+    {
+      "epoch": 0.10900090217215296,
+      "grad_norm": 0.6335741877555847,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.6449,
+      "step": 7068
+    },
+    {
+      "epoch": 0.10947897630448696,
+      "grad_norm": 0.6071763038635254,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.6572,
+      "step": 7099
+    },
+    {
+      "epoch": 0.10995705043682096,
+      "grad_norm": 0.8242653608322144,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.6483,
+      "step": 7130
+    },
+    {
+      "epoch": 0.11043512456915497,
+      "grad_norm": 0.7106221318244934,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.6376,
+      "step": 7161
+    },
+    {
+      "epoch": 0.11091319870148897,
+      "grad_norm": 0.6587203145027161,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.6426,
+      "step": 7192
+    },
+    {
+      "epoch": 0.11139127283382297,
+      "grad_norm": 0.8035815954208374,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.6428,
+      "step": 7223
+    },
+    {
+      "epoch": 0.11186934696615698,
+      "grad_norm": 0.6661431193351746,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.6431,
+      "step": 7254
+    },
+    {
+      "epoch": 0.11234742109849098,
+      "grad_norm": 0.5891786813735962,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.6356,
+      "step": 7285
+    },
+    {
+      "epoch": 0.11282549523082498,
+      "grad_norm": 0.7475966811180115,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.6348,
+      "step": 7316
+    },
+    {
+      "epoch": 0.113303569363159,
+      "grad_norm": 0.7461502552032471,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.639,
+      "step": 7347
+    },
+    {
+      "epoch": 0.113781643495493,
+      "grad_norm": 0.7351141571998596,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.6473,
+      "step": 7378
+    },
+    {
+      "epoch": 0.114259717627827,
+      "grad_norm": 0.7713771462440491,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.6433,
+      "step": 7409
+    },
+    {
+      "epoch": 0.11473779176016101,
+      "grad_norm": 0.639986515045166,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.6411,
+      "step": 7440
+    },
+    {
+      "epoch": 0.11521586589249501,
+      "grad_norm": 0.8399244546890259,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.6421,
+      "step": 7471
+    },
+    {
+      "epoch": 0.11569394002482901,
+      "grad_norm": 0.7681542634963989,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.6371,
+      "step": 7502
+    },
+    {
+      "epoch": 0.11617201415716301,
+      "grad_norm": 0.6907945275306702,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.6446,
+      "step": 7533
+    },
+    {
+      "epoch": 0.11665008828949702,
+      "grad_norm": 0.7653492093086243,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.6407,
+      "step": 7564
+    },
+    {
+      "epoch": 0.11712816242183102,
+      "grad_norm": 0.6535690426826477,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.6388,
+      "step": 7595
+    },
+    {
+      "epoch": 0.11760623655416502,
+      "grad_norm": 2.6184701919555664,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.6382,
+      "step": 7626
+    },
+    {
+      "epoch": 0.11808431068649904,
+      "grad_norm": 0.7846981287002563,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.6364,
+      "step": 7657
+    },
+    {
+      "epoch": 0.11856238481883304,
+      "grad_norm": 0.8151688575744629,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.6427,
+      "step": 7688
+    },
+    {
+      "epoch": 0.11904045895116704,
+      "grad_norm": 0.7663447856903076,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.643,
+      "step": 7719
+    },
+    {
+      "epoch": 0.11951853308350105,
+      "grad_norm": 0.7225657105445862,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.6395,
+      "step": 7750
+    },
+    {
+      "epoch": 0.11999660721583505,
+      "grad_norm": 0.7033439874649048,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.6354,
+      "step": 7781
+    },
+    {
+      "epoch": 0.12047468134816905,
+      "grad_norm": 0.7693649530410767,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.6436,
+      "step": 7812
+    },
+    {
+      "epoch": 0.12095275548050306,
+      "grad_norm": 0.7597894668579102,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.6411,
+      "step": 7843
+    },
+    {
+      "epoch": 0.12143082961283706,
+      "grad_norm": 0.7899183630943298,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.6381,
+      "step": 7874
+    },
+    {
+      "epoch": 0.12190890374517106,
+      "grad_norm": 0.7656906247138977,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.6386,
+      "step": 7905
+    },
+    {
+      "epoch": 0.12238697787750508,
+      "grad_norm": 0.8353867530822754,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.6386,
+      "step": 7936
+    },
+    {
+      "epoch": 0.12286505200983908,
+      "grad_norm": 0.6712770462036133,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.6438,
+      "step": 7967
+    },
+    {
+      "epoch": 0.12334312614217308,
+      "grad_norm": 0.8008986115455627,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.6384,
+      "step": 7998
+    },
+    {
+      "epoch": 0.12382120027450708,
+      "grad_norm": 0.6632928252220154,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.629,
+      "step": 8029
+    },
+    {
+      "epoch": 0.12429927440684109,
+      "grad_norm": 0.6943359971046448,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.6456,
+      "step": 8060
+    },
+    {
+      "epoch": 0.12477734853917509,
+      "grad_norm": 0.6177495718002319,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.6426,
+      "step": 8091
+    },
+    {
+      "epoch": 0.1252554226715091,
+      "grad_norm": 0.6089790463447571,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.6396,
+      "step": 8122
+    },
+    {
+      "epoch": 0.1257334968038431,
+      "grad_norm": 0.6960969567298889,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.6293,
+      "step": 8153
+    },
+    {
+      "epoch": 0.1262115709361771,
+      "grad_norm": 0.6519069075584412,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.6284,
+      "step": 8184
+    },
+    {
+      "epoch": 0.1266896450685111,
+      "grad_norm": 0.6861445903778076,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.6386,
+      "step": 8215
+    },
+    {
+      "epoch": 0.1271677192008451,
+      "grad_norm": 0.7522263526916504,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.6424,
+      "step": 8246
+    },
+    {
+      "epoch": 0.1276457933331791,
+      "grad_norm": 0.6868363618850708,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.6367,
+      "step": 8277
+    },
+    {
+      "epoch": 0.12812386746551313,
+      "grad_norm": 0.5939040780067444,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.6406,
+      "step": 8308
+    },
+    {
+      "epoch": 0.12860194159784713,
+      "grad_norm": 0.7341668605804443,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.6346,
+      "step": 8339
+    },
+    {
+      "epoch": 0.12908001573018113,
+      "grad_norm": 0.7468376755714417,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.6398,
+      "step": 8370
+    },
+    {
+      "epoch": 0.12955808986251513,
+      "grad_norm": 0.6253494024276733,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.6375,
+      "step": 8401
+    },
+    {
+      "epoch": 0.13003616399484913,
+      "grad_norm": 0.6635178923606873,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.6299,
+      "step": 8432
+    },
+    {
+      "epoch": 0.13051423812718313,
+      "grad_norm": 0.584648609161377,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.6277,
+      "step": 8463
+    },
+    {
+      "epoch": 0.13099231225951716,
+      "grad_norm": 0.5907359719276428,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.6328,
+      "step": 8494
+    },
+    {
+      "epoch": 0.13147038639185116,
+      "grad_norm": 0.7864153385162354,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.6365,
+      "step": 8525
+    },
+    {
+      "epoch": 0.13194846052418516,
+      "grad_norm": 0.6572133302688599,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.6312,
+      "step": 8556
+    },
+    {
+      "epoch": 0.13242653465651916,
+      "grad_norm": 0.7108786702156067,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.6355,
+      "step": 8587
+    },
+    {
+      "epoch": 0.13290460878885316,
+      "grad_norm": 0.6737267374992371,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.6256,
+      "step": 8618
+    },
+    {
+      "epoch": 0.13338268292118716,
+      "grad_norm": 0.6710911989212036,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.632,
+      "step": 8649
+    },
+    {
+      "epoch": 0.13386075705352116,
+      "grad_norm": 0.6295626759529114,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.6372,
+      "step": 8680
+    },
+    {
+      "epoch": 0.13433883118585518,
+      "grad_norm": 0.6405526399612427,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.6364,
+      "step": 8711
+    },
+    {
+      "epoch": 0.13481690531818918,
+      "grad_norm": 0.6847979426383972,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.6246,
+      "step": 8742
+    },
+    {
+      "epoch": 0.13529497945052318,
+      "grad_norm": 0.7338352799415588,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.6373,
+      "step": 8773
+    },
+    {
+      "epoch": 0.13577305358285718,
+      "grad_norm": 0.6530189514160156,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.6217,
+      "step": 8804
+    },
+    {
+      "epoch": 0.13625112771519118,
+      "grad_norm": 0.6450487375259399,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.6365,
+      "step": 8835
+    },
+    {
+      "epoch": 0.13672920184752518,
+      "grad_norm": 0.706732988357544,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.6294,
+      "step": 8866
+    },
+    {
+      "epoch": 0.1372072759798592,
+      "grad_norm": 0.687240481376648,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.6332,
+      "step": 8897
+    },
+    {
+      "epoch": 0.1376853501121932,
+      "grad_norm": 0.6686804890632629,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.6334,
+      "step": 8928
+    },
+    {
+      "epoch": 0.1381634242445272,
+      "grad_norm": 0.8371458649635315,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.6249,
+      "step": 8959
+    },
+    {
+      "epoch": 0.1386414983768612,
+      "grad_norm": 0.7204101085662842,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.6309,
+      "step": 8990
+    },
+    {
+      "epoch": 0.1391195725091952,
+      "grad_norm": 0.8539360165596008,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.6326,
+      "step": 9021
+    },
+    {
+      "epoch": 0.1395976466415292,
+      "grad_norm": 0.7264754176139832,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.6342,
+      "step": 9052
+    },
+    {
+      "epoch": 0.14007572077386324,
+      "grad_norm": 0.6681591868400574,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.6295,
+      "step": 9083
+    },
+    {
+      "epoch": 0.14055379490619724,
+      "grad_norm": 0.6293045282363892,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.6304,
+      "step": 9114
+    },
+    {
+      "epoch": 0.14103186903853124,
+      "grad_norm": 0.6432914137840271,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.6215,
+      "step": 9145
+    },
+    {
+      "epoch": 0.14150994317086524,
+      "grad_norm": 0.7524629235267639,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.625,
+      "step": 9176
+    },
+    {
+      "epoch": 0.14198801730319924,
+      "grad_norm": 0.7128170728683472,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.6342,
+      "step": 9207
+    },
+    {
+      "epoch": 0.14246609143553324,
+      "grad_norm": 0.651841938495636,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.6303,
+      "step": 9238
+    },
+    {
+      "epoch": 0.14294416556786724,
+      "grad_norm": 0.6290706396102905,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.6297,
+      "step": 9269
+    },
+    {
+      "epoch": 0.14342223970020127,
+      "grad_norm": 0.6372231841087341,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.6244,
+      "step": 9300
+    },
+    {
+      "epoch": 0.14390031383253526,
+      "grad_norm": 0.8424429297447205,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.6363,
+      "step": 9331
+    },
+    {
+      "epoch": 0.14437838796486926,
+      "grad_norm": 0.7121688723564148,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.63,
+      "step": 9362
+    },
+    {
+      "epoch": 0.14485646209720326,
+      "grad_norm": 0.7196950316429138,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.6254,
+      "step": 9393
+    },
+    {
+      "epoch": 0.14533453622953726,
+      "grad_norm": 0.6595038175582886,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.6207,
+      "step": 9424
+    },
+    {
+      "epoch": 0.14581261036187126,
+      "grad_norm": 0.6118171811103821,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.6233,
+      "step": 9455
+    },
+    {
+      "epoch": 0.1462906844942053,
+      "grad_norm": 0.7232321500778198,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.6328,
+      "step": 9486
+    },
+    {
+      "epoch": 0.1467687586265393,
+      "grad_norm": 0.691681981086731,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.634,
+      "step": 9517
+    },
+    {
+      "epoch": 0.1472468327588733,
+      "grad_norm": 0.6887443661689758,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.6275,
+      "step": 9548
+    },
+    {
+      "epoch": 0.1477249068912073,
+      "grad_norm": 0.6932326555252075,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.6233,
+      "step": 9579
+    },
+    {
+      "epoch": 0.1482029810235413,
+      "grad_norm": 0.7189227342605591,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.6229,
+      "step": 9610
+    },
+    {
+      "epoch": 0.1486810551558753,
+      "grad_norm": 0.6898639798164368,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.6251,
+      "step": 9641
+    },
+    {
+      "epoch": 0.1491591292882093,
+      "grad_norm": 0.6311922669410706,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.6249,
+      "step": 9672
+    },
+    {
+      "epoch": 0.14963720342054332,
+      "grad_norm": 0.5781577825546265,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.6337,
+      "step": 9703
+    },
+    {
+      "epoch": 0.15011527755287732,
+      "grad_norm": 0.6525286436080933,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.6347,
+      "step": 9734
+    },
+    {
+      "epoch": 0.15059335168521132,
+      "grad_norm": 0.6761188507080078,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.6267,
+      "step": 9765
+    },
+    {
+      "epoch": 0.15107142581754532,
+      "grad_norm": 0.674532413482666,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.6303,
+      "step": 9796
+    },
+    {
+      "epoch": 0.15154949994987932,
+      "grad_norm": 0.5923493504524231,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.6241,
+      "step": 9827
+    },
+    {
+      "epoch": 0.15202757408221332,
+      "grad_norm": 0.6309007406234741,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.6231,
+      "step": 9858
+    },
+    {
+      "epoch": 0.15250564821454735,
+      "grad_norm": 0.7521491050720215,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.6214,
+      "step": 9889
+    },
+    {
+      "epoch": 0.15298372234688135,
+      "grad_norm": 0.8196119666099548,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.6254,
+      "step": 9920
+    },
+    {
+      "epoch": 0.15346179647921535,
+      "grad_norm": 0.6895152926445007,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.6227,
+      "step": 9951
+    },
+    {
+      "epoch": 0.15393987061154935,
+      "grad_norm": 0.6823534369468689,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.6281,
+      "step": 9982
+    },
+    {
+      "epoch": 0.15441794474388335,
+      "grad_norm": 0.6531606912612915,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.6259,
+      "step": 10013
+    },
+    {
+      "epoch": 0.15489601887621735,
+      "grad_norm": 0.5898056626319885,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.6184,
+      "step": 10044
+    },
+    {
+      "epoch": 0.15537409300855134,
+      "grad_norm": 0.6368978023529053,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.6196,
+      "step": 10075
+    },
+    {
+      "epoch": 0.15585216714088537,
+      "grad_norm": 0.8086898922920227,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.6226,
+      "step": 10106
+    },
+    {
+      "epoch": 0.15633024127321937,
+      "grad_norm": 0.6620404124259949,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.6146,
+      "step": 10137
+    },
+    {
+      "epoch": 0.15680831540555337,
+      "grad_norm": 0.6264041662216187,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.6254,
+      "step": 10168
+    },
+    {
+      "epoch": 0.15728638953788737,
+      "grad_norm": 0.6619133353233337,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.6233,
+      "step": 10199
+    },
+    {
+      "epoch": 0.15776446367022137,
+      "grad_norm": 0.6223868131637573,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.6232,
+      "step": 10230
+    },
+    {
+      "epoch": 0.15824253780255537,
+      "grad_norm": 0.7436427474021912,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.6194,
+      "step": 10261
+    },
+    {
+      "epoch": 0.1587206119348894,
+      "grad_norm": 0.7166286110877991,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.6267,
+      "step": 10292
+    },
+    {
+      "epoch": 0.1591986860672234,
+      "grad_norm": 0.6377813220024109,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.6145,
+      "step": 10323
+    },
+    {
+      "epoch": 0.1596767601995574,
+      "grad_norm": 1.5197011232376099,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.6261,
+      "step": 10354
+    },
+    {
+      "epoch": 0.1601548343318914,
+      "grad_norm": 0.6208730340003967,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.6201,
+      "step": 10385
+    },
+    {
+      "epoch": 0.1606329084642254,
+      "grad_norm": 0.6887170076370239,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.6235,
+      "step": 10416
+    },
+    {
+      "epoch": 0.1611109825965594,
+      "grad_norm": 0.6381047368049622,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.6189,
+      "step": 10447
+    },
+    {
+      "epoch": 0.1615890567288934,
+      "grad_norm": 0.6249068379402161,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.6222,
+      "step": 10478
+    },
+    {
+      "epoch": 0.16206713086122743,
+      "grad_norm": 0.659757137298584,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.6345,
+      "step": 10509
+    },
+    {
+      "epoch": 0.16254520499356143,
+      "grad_norm": 0.6268470883369446,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.6197,
+      "step": 10540
+    },
+    {
+      "epoch": 0.16302327912589543,
+      "grad_norm": 0.6520307660102844,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.6122,
+      "step": 10571
+    },
+    {
+      "epoch": 0.16350135325822943,
+      "grad_norm": 0.5919711589813232,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.6237,
+      "step": 10602
+    },
+    {
+      "epoch": 0.16397942739056343,
+      "grad_norm": 0.6761168837547302,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.615,
+      "step": 10633
+    },
+    {
+      "epoch": 0.16445750152289743,
+      "grad_norm": 0.7123913168907166,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.6178,
+      "step": 10664
+    },
+    {
+      "epoch": 0.16493557565523145,
+      "grad_norm": 0.5414535403251648,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.6319,
+      "step": 10695
+    },
+    {
+      "epoch": 0.16541364978756545,
+      "grad_norm": 0.741256594657898,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.6102,
+      "step": 10726
+    },
+    {
+      "epoch": 0.16589172391989945,
+      "grad_norm": 0.6938264966011047,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.6127,
+      "step": 10757
+    },
+    {
+      "epoch": 0.16636979805223345,
+      "grad_norm": 0.7152143716812134,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.6119,
+      "step": 10788
+    },
+    {
+      "epoch": 0.16684787218456745,
+      "grad_norm": 0.6516321897506714,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.6224,
+      "step": 10819
+    },
+    {
+      "epoch": 0.16732594631690145,
+      "grad_norm": 0.6300469040870667,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.6229,
+      "step": 10850
+    },
+    {
+      "epoch": 0.16780402044923548,
+      "grad_norm": 0.645636260509491,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.6284,
+      "step": 10881
+    },
+    {
+      "epoch": 0.16828209458156948,
+      "grad_norm": 0.5895135402679443,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.6142,
+      "step": 10912
+    },
+    {
+      "epoch": 0.16876016871390348,
+      "grad_norm": 0.6440445184707642,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.6158,
+      "step": 10943
+    },
+    {
+      "epoch": 0.16923824284623748,
+      "grad_norm": 0.6739510893821716,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.6149,
+      "step": 10974
+    },
+    {
+      "epoch": 0.16971631697857148,
+      "grad_norm": 0.627185046672821,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.614,
+      "step": 11005
+    },
+    {
+      "epoch": 0.17019439111090548,
+      "grad_norm": 0.710350513458252,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.6214,
+      "step": 11036
+    },
+    {
+      "epoch": 0.17067246524323948,
+      "grad_norm": 0.6784375309944153,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.6123,
+      "step": 11067
+    },
+    {
+      "epoch": 0.1711505393755735,
+      "grad_norm": 0.6646184325218201,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.6178,
+      "step": 11098
+    },
+    {
+      "epoch": 0.1716286135079075,
+      "grad_norm": 0.7227056622505188,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.6158,
+      "step": 11129
+    },
+    {
+      "epoch": 0.1721066876402415,
+      "grad_norm": 0.5937723517417908,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.6194,
+      "step": 11160
+    },
+    {
+      "epoch": 0.1725847617725755,
+      "grad_norm": 0.6352291703224182,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.6286,
+      "step": 11191
+    },
+    {
+      "epoch": 0.1730628359049095,
+      "grad_norm": 0.5864464044570923,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.6186,
+      "step": 11222
+    },
+    {
+      "epoch": 0.1735409100372435,
+      "grad_norm": 0.5402609705924988,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.6072,
+      "step": 11253
+    },
+    {
+      "epoch": 0.17401898416957753,
+      "grad_norm": 0.6429933905601501,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.608,
+      "step": 11284
+    },
+    {
+      "epoch": 0.17449705830191153,
+      "grad_norm": 0.5420451164245605,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.6174,
+      "step": 11315
+    },
+    {
+      "epoch": 0.17497513243424553,
+      "grad_norm": 0.5691730380058289,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.6138,
+      "step": 11346
+    },
+    {
+      "epoch": 0.17545320656657953,
+      "grad_norm": 0.6198572516441345,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.6166,
+      "step": 11377
+    },
+    {
+      "epoch": 0.17593128069891353,
+      "grad_norm": 0.6781229972839355,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.6083,
+      "step": 11408
+    },
+    {
+      "epoch": 0.17640935483124753,
+      "grad_norm": 0.6572268605232239,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.6179,
+      "step": 11439
+    },
+    {
+      "epoch": 0.17688742896358153,
+      "grad_norm": 0.6720935702323914,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.6039,
+      "step": 11470
+    },
+    {
+      "epoch": 0.17736550309591556,
+      "grad_norm": 0.6098059415817261,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.608,
+      "step": 11501
+    },
+    {
+      "epoch": 0.17784357722824956,
+      "grad_norm": 0.6108371615409851,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.6147,
+      "step": 11532
+    },
+    {
+      "epoch": 0.17832165136058356,
+      "grad_norm": 0.8087718486785889,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.6091,
+      "step": 11563
+    },
+    {
+      "epoch": 0.17879972549291756,
+      "grad_norm": 0.719902753829956,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.6107,
+      "step": 11594
+    },
+    {
+      "epoch": 0.17927779962525156,
+      "grad_norm": 0.5758282542228699,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.6236,
+      "step": 11625
+    },
+    {
+      "epoch": 0.17975587375758556,
+      "grad_norm": 0.5602071285247803,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.611,
+      "step": 11656
+    },
+    {
+      "epoch": 0.1802339478899196,
+      "grad_norm": 0.6070683002471924,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.609,
+      "step": 11687
+    },
+    {
+      "epoch": 0.1807120220222536,
+      "grad_norm": 0.64506596326828,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.605,
+      "step": 11718
+    },
+    {
+      "epoch": 0.1811900961545876,
+      "grad_norm": 0.6906920075416565,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.6168,
+      "step": 11749
+    },
+    {
+      "epoch": 0.1816681702869216,
+      "grad_norm": 0.6724758148193359,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.6143,
+      "step": 11780
+    },
+    {
+      "epoch": 0.1821462444192556,
+      "grad_norm": 0.6033251881599426,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.6161,
+      "step": 11811
+    },
+    {
+      "epoch": 0.1826243185515896,
+      "grad_norm": 0.6713966727256775,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.619,
+      "step": 11842
+    },
+    {
+      "epoch": 0.1831023926839236,
+      "grad_norm": 0.6794861555099487,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.6116,
+      "step": 11873
+    },
+    {
+      "epoch": 0.18358046681625761,
+      "grad_norm": 0.5780847668647766,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.6159,
+      "step": 11904
+    },
+    {
+      "epoch": 0.18405854094859161,
+      "grad_norm": 0.6031593680381775,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.6135,
+      "step": 11935
+    },
+    {
+      "epoch": 0.18453661508092561,
+      "grad_norm": 0.6339271664619446,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.6113,
+      "step": 11966
+    },
+    {
+      "epoch": 0.18501468921325961,
+      "grad_norm": 0.6663223505020142,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.6184,
+      "step": 11997
+    },
+    {
+      "epoch": 0.18549276334559361,
+      "grad_norm": 0.9799377918243408,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.6103,
+      "step": 12028
+    },
+    {
+      "epoch": 0.18597083747792761,
+      "grad_norm": 0.7260358929634094,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.6245,
+      "step": 12059
+    },
+    {
+      "epoch": 0.18644891161026164,
+      "grad_norm": 0.7097154259681702,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.6194,
+      "step": 12090
+    },
+    {
+      "epoch": 0.18692698574259564,
+      "grad_norm": 0.5897482633590698,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.6171,
+      "step": 12121
+    },
+    {
+      "epoch": 0.18740505987492964,
+      "grad_norm": 0.6374841332435608,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.6141,
+      "step": 12152
+    },
+    {
+      "epoch": 0.18788313400726364,
+      "grad_norm": 0.6854335069656372,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.6077,
+      "step": 12183
+    },
+    {
+      "epoch": 0.18836120813959764,
+      "grad_norm": 0.6838460564613342,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 0.6129,
+      "step": 12214
+    },
+    {
+      "epoch": 0.18883928227193164,
+      "grad_norm": 0.6604870557785034,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 0.6193,
+      "step": 12245
+    },
+    {
+      "epoch": 0.18931735640426567,
+      "grad_norm": 0.5817708373069763,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 0.6086,
+      "step": 12276
+    },
+    {
+      "epoch": 0.18979543053659967,
+      "grad_norm": 0.5379335284233093,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 0.6088,
+      "step": 12307
+    },
+    {
+      "epoch": 0.19027350466893367,
+      "grad_norm": 0.6126767992973328,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 0.6131,
+      "step": 12338
+    },
+    {
+      "epoch": 0.19075157880126767,
+      "grad_norm": 0.609724223613739,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 0.6106,
+      "step": 12369
+    },
+    {
+      "epoch": 0.19122965293360167,
+      "grad_norm": 0.6327598094940186,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 0.6134,
+      "step": 12400
+    },
+    {
+      "epoch": 0.19170772706593567,
+      "grad_norm": 0.5619271993637085,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 0.6161,
+      "step": 12431
+    },
+    {
+      "epoch": 0.19218580119826967,
+      "grad_norm": 0.6915563344955444,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 0.6046,
+      "step": 12462
+    },
+    {
+      "epoch": 0.1926638753306037,
+      "grad_norm": 0.7094136476516724,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 0.6087,
+      "step": 12493
+    },
+    {
+      "epoch": 0.1931419494629377,
+      "grad_norm": 0.627680778503418,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 0.604,
+      "step": 12524
+    },
+    {
+      "epoch": 0.1936200235952717,
+      "grad_norm": 0.6224892735481262,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 0.6047,
+      "step": 12555
+    },
+    {
+      "epoch": 0.1940980977276057,
+      "grad_norm": 0.5795034766197205,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 0.6111,
+      "step": 12586
+    },
+    {
+      "epoch": 0.1945761718599397,
+      "grad_norm": 0.7537661194801331,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 0.6079,
+      "step": 12617
+    },
+    {
+      "epoch": 0.1950542459922737,
+      "grad_norm": 0.838455319404602,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 0.6036,
+      "step": 12648
+    },
+    {
+      "epoch": 0.19553232012460772,
+      "grad_norm": 0.650592029094696,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 0.6088,
+      "step": 12679
+    },
+    {
+      "epoch": 0.19601039425694172,
+      "grad_norm": 0.7277738451957703,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 0.6073,
+      "step": 12710
+    },
+    {
+      "epoch": 0.19648846838927572,
+      "grad_norm": 0.6338685154914856,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 0.6085,
+      "step": 12741
+    },
+    {
+      "epoch": 0.19696654252160972,
+      "grad_norm": 0.5530194044113159,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 0.6063,
+      "step": 12772
+    },
+    {
+      "epoch": 0.19744461665394372,
+      "grad_norm": 0.634303867816925,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 0.6036,
+      "step": 12803
+    },
+    {
+      "epoch": 0.19792269078627772,
+      "grad_norm": 0.6769723892211914,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 0.6094,
+      "step": 12834
+    },
+    {
+      "epoch": 0.19840076491861172,
+      "grad_norm": 0.5914043188095093,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 0.6093,
+      "step": 12865
+    },
+    {
+      "epoch": 0.19887883905094575,
+      "grad_norm": 0.6945207118988037,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 0.609,
+      "step": 12896
+    },
+    {
+      "epoch": 0.19935691318327975,
+      "grad_norm": 0.7246667742729187,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 0.6245,
+      "step": 12927
+    },
+    {
+      "epoch": 0.19983498731561375,
+      "grad_norm": 0.5429117679595947,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 0.6112,
+      "step": 12958
+    },
+    {
+      "epoch": 0.20031306144794775,
+      "grad_norm": 0.5964083671569824,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 0.6037,
+      "step": 12989
+    },
+    {
+      "epoch": 0.20079113558028175,
+      "grad_norm": 0.6770813465118408,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 0.6046,
+      "step": 13020
+    },
+    {
+      "epoch": 0.20126920971261575,
+      "grad_norm": 0.5819186568260193,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 0.6102,
+      "step": 13051
+    },
+    {
+      "epoch": 0.20174728384494978,
+      "grad_norm": 0.6465575098991394,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 0.6082,
+      "step": 13082
+    },
+    {
+      "epoch": 0.20222535797728378,
+      "grad_norm": 0.607782244682312,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 0.6067,
+      "step": 13113
+    },
+    {
+      "epoch": 0.20270343210961778,
+      "grad_norm": 0.6200498938560486,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 0.6096,
+      "step": 13144
+    },
+    {
+      "epoch": 0.20318150624195178,
+      "grad_norm": 0.6002140045166016,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 0.6029,
+      "step": 13175
+    },
+    {
+      "epoch": 0.20365958037428578,
+      "grad_norm": 0.6123709082603455,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 0.6067,
+      "step": 13206
+    },
+    {
+      "epoch": 0.20413765450661978,
+      "grad_norm": 0.5950725078582764,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 0.6123,
+      "step": 13237
+    },
+    {
+      "epoch": 0.20461572863895378,
+      "grad_norm": 0.5370542407035828,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 0.6037,
+      "step": 13268
+    },
+    {
+      "epoch": 0.2050938027712878,
+      "grad_norm": 0.6526908874511719,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 0.6093,
+      "step": 13299
+    },
+    {
+      "epoch": 0.2055718769036218,
+      "grad_norm": 0.6925700306892395,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 0.6077,
+      "step": 13330
+    },
+    {
+      "epoch": 0.2060499510359558,
+      "grad_norm": 0.6531749367713928,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 0.6126,
+      "step": 13361
+    },
+    {
+      "epoch": 0.2065280251682898,
+      "grad_norm": 0.7173174023628235,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 0.5991,
+      "step": 13392
+    },
+    {
+      "epoch": 0.2070060993006238,
+      "grad_norm": 0.7028422355651855,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 0.6037,
+      "step": 13423
+    },
+    {
+      "epoch": 0.2074841734329578,
+      "grad_norm": 0.5837274193763733,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 0.6135,
+      "step": 13454
+    },
+    {
+      "epoch": 0.20796224756529183,
+      "grad_norm": 0.6421070098876953,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 0.6095,
+      "step": 13485
+    },
+    {
+      "epoch": 0.20844032169762583,
+      "grad_norm": 0.6141335964202881,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 0.6161,
+      "step": 13516
+    },
+    {
+      "epoch": 0.20891839582995983,
+      "grad_norm": 0.6881201267242432,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 0.6053,
+      "step": 13547
+    },
+    {
+      "epoch": 0.20939646996229383,
+      "grad_norm": 0.655423104763031,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 0.6037,
+      "step": 13578
+    },
+    {
+      "epoch": 0.20987454409462783,
+      "grad_norm": 0.5702130198478699,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 0.603,
+      "step": 13609
+    },
+    {
+      "epoch": 0.21035261822696183,
+      "grad_norm": 0.6374569535255432,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 0.6048,
+      "step": 13640
+    },
+    {
+      "epoch": 0.21083069235929583,
+      "grad_norm": 0.6103787422180176,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 0.608,
+      "step": 13671
+    },
+    {
+      "epoch": 0.21130876649162986,
+      "grad_norm": 0.6299352049827576,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 0.5993,
+      "step": 13702
+    },
+    {
+      "epoch": 0.21178684062396386,
+      "grad_norm": 0.6262964010238647,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 0.6085,
+      "step": 13733
+    },
+    {
+      "epoch": 0.21226491475629786,
+      "grad_norm": 0.5756493210792542,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 0.6051,
+      "step": 13764
+    },
+    {
+      "epoch": 0.21274298888863186,
+      "grad_norm": 0.5393940806388855,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 0.6072,
+      "step": 13795
+    },
+    {
+      "epoch": 0.21322106302096586,
+      "grad_norm": 0.5831958651542664,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 0.6015,
+      "step": 13826
+    },
+    {
+      "epoch": 0.21369913715329986,
+      "grad_norm": 0.6049664616584778,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 0.6136,
+      "step": 13857
+    },
+    {
+      "epoch": 0.21417721128563388,
+      "grad_norm": 0.6627909541130066,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 0.6027,
+      "step": 13888
+    },
+    {
+      "epoch": 0.21465528541796788,
+      "grad_norm": 0.568748950958252,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 0.601,
+      "step": 13919
+    },
+    {
+      "epoch": 0.21513335955030188,
+      "grad_norm": 0.6373331546783447,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 0.606,
+      "step": 13950
+    },
+    {
+      "epoch": 0.21561143368263588,
+      "grad_norm": 0.5549852252006531,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 0.5931,
+      "step": 13981
+    },
+    {
+      "epoch": 0.21608950781496988,
+      "grad_norm": 0.5983837246894836,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 0.6023,
+      "step": 14012
+    },
+    {
+      "epoch": 0.21656758194730388,
+      "grad_norm": 0.6063233017921448,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 0.5974,
+      "step": 14043
+    },
+    {
+      "epoch": 0.2170456560796379,
+      "grad_norm": 3.3559274673461914,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 0.6057,
+      "step": 14074
+    },
+    {
+      "epoch": 0.2175237302119719,
+      "grad_norm": 0.5984488725662231,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 0.5953,
+      "step": 14105
+    },
+    {
+      "epoch": 0.2180018043443059,
+      "grad_norm": 0.5625097751617432,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 0.6029,
+      "step": 14136
+    },
+    {
+      "epoch": 0.2184798784766399,
+      "grad_norm": 0.6621974110603333,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 0.6042,
+      "step": 14167
+    },
+    {
+      "epoch": 0.2189579526089739,
+      "grad_norm": 0.7209954857826233,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 0.6069,
+      "step": 14198
+    },
+    {
+      "epoch": 0.2194360267413079,
+      "grad_norm": 0.4810869097709656,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 0.6131,
+      "step": 14229
+    },
+    {
+      "epoch": 0.2199141008736419,
+      "grad_norm": 0.6061887145042419,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 0.6012,
+      "step": 14260
+    },
+    {
+      "epoch": 0.22039217500597594,
+      "grad_norm": 0.5912594795227051,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 0.6042,
+      "step": 14291
+    },
+    {
+      "epoch": 0.22087024913830994,
+      "grad_norm": 0.5847635269165039,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 0.5945,
+      "step": 14322
+    },
+    {
+      "epoch": 0.22134832327064394,
+      "grad_norm": 0.617660403251648,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 0.6008,
+      "step": 14353
+    },
+    {
+      "epoch": 0.22182639740297794,
+      "grad_norm": 0.6549617052078247,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 0.6055,
+      "step": 14384
+    },
+    {
+      "epoch": 0.22230447153531194,
+      "grad_norm": 0.6084825396537781,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 0.6059,
+      "step": 14415
+    },
+    {
+      "epoch": 0.22278254566764594,
+      "grad_norm": 0.619442880153656,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 0.6003,
+      "step": 14446
+    },
+    {
+      "epoch": 0.22326061979997996,
+      "grad_norm": 0.5925353169441223,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 0.6064,
+      "step": 14477
+    },
+    {
+      "epoch": 0.22373869393231396,
+      "grad_norm": 0.6110435724258423,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 0.5992,
+      "step": 14508
+    },
+    {
+      "epoch": 0.22421676806464796,
+      "grad_norm": 0.5053293108940125,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 0.5938,
+      "step": 14539
+    },
+    {
+      "epoch": 0.22469484219698196,
+      "grad_norm": 0.6076425909996033,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 0.6055,
+      "step": 14570
+    },
+    {
+      "epoch": 0.22517291632931596,
+      "grad_norm": 0.6807154417037964,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 0.602,
+      "step": 14601
+    },
+    {
+      "epoch": 0.22565099046164996,
+      "grad_norm": 0.6125125885009766,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 0.6044,
+      "step": 14632
+    },
+    {
+      "epoch": 0.22612906459398396,
+      "grad_norm": 0.6103615164756775,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 0.5956,
+      "step": 14663
+    },
+    {
+      "epoch": 0.226607138726318,
+      "grad_norm": 0.6321137547492981,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 0.6033,
+      "step": 14694
+    },
+    {
+      "epoch": 0.227085212858652,
+      "grad_norm": 0.5844994783401489,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 0.6015,
+      "step": 14725
+    },
+    {
+      "epoch": 0.227563286990986,
+      "grad_norm": 0.648857593536377,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 0.5939,
+      "step": 14756
+    },
+    {
+      "epoch": 0.22804136112332,
+      "grad_norm": 0.6076569557189941,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 0.5999,
+      "step": 14787
+    },
+    {
+      "epoch": 0.228519435255654,
+      "grad_norm": 0.5311121344566345,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 0.5961,
+      "step": 14818
+    },
+    {
+      "epoch": 0.228997509387988,
+      "grad_norm": 0.6423148512840271,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 0.5965,
+      "step": 14849
+    },
+    {
+      "epoch": 0.22947558352032202,
+      "grad_norm": 0.6332517266273499,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 0.5934,
+      "step": 14880
+    },
+    {
+      "epoch": 0.22995365765265602,
+      "grad_norm": 0.6193598508834839,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 0.6075,
+      "step": 14911
+    },
+    {
+      "epoch": 0.23043173178499002,
+      "grad_norm": 0.6870059967041016,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 0.6044,
+      "step": 14942
+    },
+    {
+      "epoch": 0.23090980591732402,
+      "grad_norm": 0.5324540138244629,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 0.5908,
+      "step": 14973
+    },
+    {
+      "epoch": 0.23138788004965802,
+      "grad_norm": 1.536717414855957,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 0.5953,
+      "step": 15004
+    },
+    {
+      "epoch": 0.23186595418199202,
+      "grad_norm": 0.550554096698761,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 0.5952,
+      "step": 15035
+    },
+    {
+      "epoch": 0.23234402831432602,
+      "grad_norm": 1.174824833869934,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 0.6065,
+      "step": 15066
+    },
+    {
+      "epoch": 0.23282210244666005,
+      "grad_norm": 0.6926533579826355,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 0.6031,
+      "step": 15097
+    },
+    {
+      "epoch": 0.23330017657899405,
+      "grad_norm": 0.6488378047943115,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 0.5977,
+      "step": 15128
+    },
+    {
+      "epoch": 0.23377825071132805,
+      "grad_norm": 0.5631073713302612,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 0.6024,
+      "step": 15159
+    },
+    {
+      "epoch": 0.23425632484366204,
+      "grad_norm": 0.5837413668632507,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 0.5961,
+      "step": 15190
+    },
+    {
+      "epoch": 0.23473439897599604,
+      "grad_norm": 0.5875633955001831,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 0.6027,
+      "step": 15221
+    },
+    {
+      "epoch": 0.23521247310833004,
+      "grad_norm": 0.5024504661560059,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 0.5951,
+      "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 sha256:8d2fa98715a72411d7d405e41015b5b23c93a1244803c7a5a69a929926c53d35
+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:e2231dbd172162387fd685893be549b58b690ff06d1c87ee5b1ace117d6ebaf8
+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:af2d7513b9d8125056c9bb61939bc5ce3cbfb12c2f695d078a0042bdf75dcd02
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab04cabf5f954d080ea8d5eb52385e0dcce325628a5b58a069f36d4410a8f02f
+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:d88901ff0c05c2e4670d32e3bb4a51e8cc0cc43f145904dfcf3673bc6b0f76bd
+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 sha256:8d2fa98715a72411d7d405e41015b5b23c93a1244803c7a5a69a929926c53d35
+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 sha256:0b615715d79d84c2ad4a877f6592e07e4d5fcb8dc48f43894dadee9274309a76
+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