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:dcbade616042489d898627eb84adda32f52669f370441475a86032a24489a145
+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 sha256:3db0510a8f69a31c2dfa9e12ac195733bdd15699c9cae618c7f4523b03ece56e
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc45128258c2b1fb86b3677da7852a878aaecdd1c7430a93d7d37a0ddbbf44a5
+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 sha256:131fd6c7407733cfe828e6cee13e38e2322e59c74363bb47e422804d000106e3
+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": 0.18316441737121253,
+  "eval_steps": 500,
+  "global_step": 12208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000465112789851539,
+      "grad_norm": 2.768016815185547,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.3097,
+      "step": 31
+    },
+    {
+      "epoch": 0.000930225579703078,
+      "grad_norm": 1.7586184740066528,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 1.2415,
+      "step": 62
+    },
+    {
+      "epoch": 0.001395338369554617,
+      "grad_norm": 1.6319445371627808,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.1785,
+      "step": 93
+    },
+    {
+      "epoch": 0.001860451159406156,
+      "grad_norm": 1.667987585067749,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.165,
+      "step": 124
+    },
+    {
+      "epoch": 0.002325563949257695,
+      "grad_norm": 1.6823372840881348,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.1241,
+      "step": 155
+    },
+    {
+      "epoch": 0.002790676739109234,
+      "grad_norm": 1.7869504690170288,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.1232,
+      "step": 186
+    },
+    {
+      "epoch": 0.003255789528960773,
+      "grad_norm": 1.9446443319320679,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.108,
+      "step": 217
+    },
+    {
+      "epoch": 0.003720902318812312,
+      "grad_norm": 1.9483426809310913,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.118,
+      "step": 248
+    },
+    {
+      "epoch": 0.004186015108663851,
+      "grad_norm": 1.837703824043274,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.091,
+      "step": 279
+    },
+    {
+      "epoch": 0.00465112789851539,
+      "grad_norm": 1.9819648265838623,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 1.075,
+      "step": 310
+    },
+    {
+      "epoch": 0.005116240688366929,
+      "grad_norm": 1.9136595726013184,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 1.0668,
+      "step": 341
+    },
+    {
+      "epoch": 0.005581353478218468,
+      "grad_norm": 1.720566987991333,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.0769,
+      "step": 372
+    },
+    {
+      "epoch": 0.006046466268070007,
+      "grad_norm": 1.9698255062103271,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 1.0543,
+      "step": 403
+    },
+    {
+      "epoch": 0.006511579057921546,
+      "grad_norm": 1.665868878364563,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 1.0524,
+      "step": 434
+    },
+    {
+      "epoch": 0.006976691847773085,
+      "grad_norm": 1.9344353675842285,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 1.0518,
+      "step": 465
+    },
+    {
+      "epoch": 0.007441804637624624,
+      "grad_norm": 2.173403024673462,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 1.0476,
+      "step": 496
+    },
+    {
+      "epoch": 0.007906917427476163,
+      "grad_norm": 2.1878745555877686,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 1.0385,
+      "step": 527
+    },
+    {
+      "epoch": 0.008372030217327702,
+      "grad_norm": 1.8220405578613281,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 1.0374,
+      "step": 558
+    },
+    {
+      "epoch": 0.00883714300717924,
+      "grad_norm": 2.0194647312164307,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 1.0408,
+      "step": 589
+    },
+    {
+      "epoch": 0.00930225579703078,
+      "grad_norm": 1.9656147956848145,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 1.0252,
+      "step": 620
+    },
+    {
+      "epoch": 0.009767368586882319,
+      "grad_norm": 1.6676087379455566,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 1.0209,
+      "step": 651
+    },
+    {
+      "epoch": 0.010232481376733858,
+      "grad_norm": 1.8552638292312622,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 1.0077,
+      "step": 682
+    },
+    {
+      "epoch": 0.010697594166585398,
+      "grad_norm": 1.7905389070510864,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 1.0099,
+      "step": 713
+    },
+    {
+      "epoch": 0.011162706956436936,
+      "grad_norm": 1.8298577070236206,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 1.01,
+      "step": 744
+    },
+    {
+      "epoch": 0.011627819746288475,
+      "grad_norm": 1.6317881345748901,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 1.003,
+      "step": 775
+    },
+    {
+      "epoch": 0.012092932536140013,
+      "grad_norm": 1.9337595701217651,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 1.005,
+      "step": 806
+    },
+    {
+      "epoch": 0.012558045325991554,
+      "grad_norm": 1.655259132385254,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.992,
+      "step": 837
+    },
+    {
+      "epoch": 0.013023158115843092,
+      "grad_norm": 1.6854184865951538,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.9922,
+      "step": 868
+    },
+    {
+      "epoch": 0.01348827090569463,
+      "grad_norm": 1.7627979516983032,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.9828,
+      "step": 899
+    },
+    {
+      "epoch": 0.01395338369554617,
+      "grad_norm": 1.7015711069107056,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.9896,
+      "step": 930
+    },
+    {
+      "epoch": 0.01441849648539771,
+      "grad_norm": 1.6730037927627563,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.9847,
+      "step": 961
+    },
+    {
+      "epoch": 0.014883609275249248,
+      "grad_norm": 1.7218660116195679,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.9912,
+      "step": 992
+    },
+    {
+      "epoch": 0.015348722065100786,
+      "grad_norm": 1.5981271266937256,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.9791,
+      "step": 1023
+    },
+    {
+      "epoch": 0.015813834854952327,
+      "grad_norm": 2.0253615379333496,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.9693,
+      "step": 1054
+    },
+    {
+      "epoch": 0.016278947644803865,
+      "grad_norm": 1.62104070186615,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.9708,
+      "step": 1085
+    },
+    {
+      "epoch": 0.016744060434655404,
+      "grad_norm": 1.465540885925293,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.9603,
+      "step": 1116
+    },
+    {
+      "epoch": 0.017209173224506942,
+      "grad_norm": 1.3695433139801025,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.9643,
+      "step": 1147
+    },
+    {
+      "epoch": 0.01767428601435848,
+      "grad_norm": 1.5520803928375244,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.9652,
+      "step": 1178
+    },
+    {
+      "epoch": 0.018139398804210023,
+      "grad_norm": 1.5043976306915283,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.9609,
+      "step": 1209
+    },
+    {
+      "epoch": 0.01860451159406156,
+      "grad_norm": 1.5582523345947266,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.9549,
+      "step": 1240
+    },
+    {
+      "epoch": 0.0190696243839131,
+      "grad_norm": 1.5340025424957275,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.9596,
+      "step": 1271
+    },
+    {
+      "epoch": 0.019534737173764638,
+      "grad_norm": 1.2499620914459229,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.9499,
+      "step": 1302
+    },
+    {
+      "epoch": 0.019999849963616177,
+      "grad_norm": 1.3684868812561035,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.9499,
+      "step": 1333
+    },
+    {
+      "epoch": 0.020464962753467715,
+      "grad_norm": 1.3685338497161865,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.942,
+      "step": 1364
+    },
+    {
+      "epoch": 0.020930075543319254,
+      "grad_norm": 1.4686026573181152,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.9416,
+      "step": 1395
+    },
+    {
+      "epoch": 0.021395188333170796,
+      "grad_norm": 1.495653510093689,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.9439,
+      "step": 1426
+    },
+    {
+      "epoch": 0.021860301123022334,
+      "grad_norm": 1.2068424224853516,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.9509,
+      "step": 1457
+    },
+    {
+      "epoch": 0.022325413912873873,
+      "grad_norm": 1.6636161804199219,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.9343,
+      "step": 1488
+    },
+    {
+      "epoch": 0.02279052670272541,
+      "grad_norm": 1.2870069742202759,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.9407,
+      "step": 1519
+    },
+    {
+      "epoch": 0.02325563949257695,
+      "grad_norm": 1.5109976530075073,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.9395,
+      "step": 1550
+    },
+    {
+      "epoch": 0.023720752282428488,
+      "grad_norm": 1.5145201683044434,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.9293,
+      "step": 1581
+    },
+    {
+      "epoch": 0.024185865072280027,
+      "grad_norm": 1.4048824310302734,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.929,
+      "step": 1612
+    },
+    {
+      "epoch": 0.02465097786213157,
+      "grad_norm": 1.3233039379119873,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.9169,
+      "step": 1643
+    },
+    {
+      "epoch": 0.025116090651983107,
+      "grad_norm": 1.3225436210632324,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.9301,
+      "step": 1674
+    },
+    {
+      "epoch": 0.025581203441834646,
+      "grad_norm": 1.5295816659927368,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.9245,
+      "step": 1705
+    },
+    {
+      "epoch": 0.026046316231686184,
+      "grad_norm": 1.202820062637329,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.916,
+      "step": 1736
+    },
+    {
+      "epoch": 0.026511429021537723,
+      "grad_norm": 1.0473875999450684,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.9144,
+      "step": 1767
+    },
+    {
+      "epoch": 0.02697654181138926,
+      "grad_norm": 1.1044714450836182,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.9098,
+      "step": 1798
+    },
+    {
+      "epoch": 0.0274416546012408,
+      "grad_norm": 1.2836365699768066,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.9127,
+      "step": 1829
+    },
+    {
+      "epoch": 0.02790676739109234,
+      "grad_norm": 1.2214583158493042,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.9075,
+      "step": 1860
+    },
+    {
+      "epoch": 0.02837188018094388,
+      "grad_norm": 1.2603243589401245,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.8953,
+      "step": 1891
+    },
+    {
+      "epoch": 0.02883699297079542,
+      "grad_norm": 1.2945584058761597,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.903,
+      "step": 1922
+    },
+    {
+      "epoch": 0.029302105760646957,
+      "grad_norm": 1.0437217950820923,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.9013,
+      "step": 1953
+    },
+    {
+      "epoch": 0.029767218550498496,
+      "grad_norm": 1.5020360946655273,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.9078,
+      "step": 1984
+    },
+    {
+      "epoch": 0.030232331340350034,
+      "grad_norm": 1.097151517868042,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.9061,
+      "step": 2015
+    },
+    {
+      "epoch": 0.030697444130201573,
+      "grad_norm": 1.043756365776062,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.9005,
+      "step": 2046
+    },
+    {
+      "epoch": 0.031162556920053115,
+      "grad_norm": 1.3543506860733032,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.9024,
+      "step": 2077
+    },
+    {
+      "epoch": 0.03162766970990465,
+      "grad_norm": 2.175954818725586,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.89,
+      "step": 2108
+    },
+    {
+      "epoch": 0.03209278249975619,
+      "grad_norm": 3.4427719116210938,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.9204,
+      "step": 2139
+    },
+    {
+      "epoch": 0.03255789528960773,
+      "grad_norm": 4.699759006500244,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.9871,
+      "step": 2170
+    },
+    {
+      "epoch": 0.03302300807945927,
+      "grad_norm": 16.819217681884766,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.9176,
+      "step": 2201
+    },
+    {
+      "epoch": 0.03348812086931081,
+      "grad_norm": 3.4251508712768555,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.9154,
+      "step": 2232
+    },
+    {
+      "epoch": 0.03395323365916235,
+      "grad_norm": 1.1965570449829102,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.9446,
+      "step": 2263
+    },
+    {
+      "epoch": 0.034418346449013884,
+      "grad_norm": 5.077923774719238,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.9097,
+      "step": 2294
+    },
+    {
+      "epoch": 0.034883459238865426,
+      "grad_norm": 1.3503797054290771,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.9086,
+      "step": 2325
+    },
+    {
+      "epoch": 0.03534857202871696,
+      "grad_norm": 19.319576263427734,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.9072,
+      "step": 2356
+    },
+    {
+      "epoch": 0.0358136848185685,
+      "grad_norm": 1.2770804166793823,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.9093,
+      "step": 2387
+    },
+    {
+      "epoch": 0.036278797608420045,
+      "grad_norm": 1.0560117959976196,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.9032,
+      "step": 2418
+    },
+    {
+      "epoch": 0.03674391039827158,
+      "grad_norm": 1.1471630334854126,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.9002,
+      "step": 2449
+    },
+    {
+      "epoch": 0.03720902318812312,
+      "grad_norm": 1.1387799978256226,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.8875,
+      "step": 2480
+    },
+    {
+      "epoch": 0.03767413597797466,
+      "grad_norm": 2.4223828315734863,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.891,
+      "step": 2511
+    },
+    {
+      "epoch": 0.0381392487678262,
+      "grad_norm": 1.2967392206192017,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.8886,
+      "step": 2542
+    },
+    {
+      "epoch": 0.038604361557677734,
+      "grad_norm": 1.3206738233566284,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.8888,
+      "step": 2573
+    },
+    {
+      "epoch": 0.039069474347529276,
+      "grad_norm": 1.1495088338851929,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.8853,
+      "step": 2604
+    },
+    {
+      "epoch": 0.03953458713738082,
+      "grad_norm": 1.116990089416504,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.8776,
+      "step": 2635
+    },
+    {
+      "epoch": 0.03999969992723235,
+      "grad_norm": 1.0922496318817139,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.8921,
+      "step": 2666
+    },
+    {
+      "epoch": 0.040464812717083895,
+      "grad_norm": 1.0340460538864136,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.8782,
+      "step": 2697
+    },
+    {
+      "epoch": 0.04092992550693543,
+      "grad_norm": 1.066490888595581,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.8945,
+      "step": 2728
+    },
+    {
+      "epoch": 0.04139503829678697,
+      "grad_norm": 0.9310857057571411,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.8791,
+      "step": 2759
+    },
+    {
+      "epoch": 0.04186015108663851,
+      "grad_norm": 1.0934898853302002,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.8802,
+      "step": 2790
+    },
+    {
+      "epoch": 0.04232526387649005,
+      "grad_norm": 1.0999833345413208,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.8742,
+      "step": 2821
+    },
+    {
+      "epoch": 0.04279037666634159,
+      "grad_norm": 1.1188342571258545,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.8793,
+      "step": 2852
+    },
+    {
+      "epoch": 0.043255489456193126,
+      "grad_norm": 3.3688652515411377,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.8777,
+      "step": 2883
+    },
+    {
+      "epoch": 0.04372060224604467,
+      "grad_norm": 1.2814080715179443,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.8654,
+      "step": 2914
+    },
+    {
+      "epoch": 0.0441857150358962,
+      "grad_norm": 0.9839452505111694,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.8662,
+      "step": 2945
+    },
+    {
+      "epoch": 0.044650827825747745,
+      "grad_norm": 1.0929216146469116,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.8709,
+      "step": 2976
+    },
+    {
+      "epoch": 0.04511594061559928,
+      "grad_norm": 1.228953242301941,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.8618,
+      "step": 3007
+    },
+    {
+      "epoch": 0.04558105340545082,
+      "grad_norm": 0.9897522926330566,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.8671,
+      "step": 3038
+    },
+    {
+      "epoch": 0.046046166195302364,
+      "grad_norm": 1.0972915887832642,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.8629,
+      "step": 3069
+    },
+    {
+      "epoch": 0.0465112789851539,
+      "grad_norm": 1.1006323099136353,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.8613,
+      "step": 3100
+    },
+    {
+      "epoch": 0.04697639177500544,
+      "grad_norm": 1.2656612396240234,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.8852,
+      "step": 3131
+    },
+    {
+      "epoch": 0.047441504564856976,
+      "grad_norm": 0.9964312314987183,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.8767,
+      "step": 3162
+    },
+    {
+      "epoch": 0.04790661735470852,
+      "grad_norm": 0.9271666407585144,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.8542,
+      "step": 3193
+    },
+    {
+      "epoch": 0.04837173014456005,
+      "grad_norm": 1.241882562637329,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.8578,
+      "step": 3224
+    },
+    {
+      "epoch": 0.048836842934411595,
+      "grad_norm": 0.9396510720252991,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.8645,
+      "step": 3255
+    },
+    {
+      "epoch": 0.04930195572426314,
+      "grad_norm": 0.987626850605011,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.8613,
+      "step": 3286
+    },
+    {
+      "epoch": 0.04976706851411467,
+      "grad_norm": 0.9133639931678772,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.8601,
+      "step": 3317
+    },
+    {
+      "epoch": 0.050232181303966214,
+      "grad_norm": 0.784701943397522,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.849,
+      "step": 3348
+    },
+    {
+      "epoch": 0.05069729409381775,
+      "grad_norm": 0.9144874811172485,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.8591,
+      "step": 3379
+    },
+    {
+      "epoch": 0.05116240688366929,
+      "grad_norm": 0.8831948041915894,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.8579,
+      "step": 3410
+    },
+    {
+      "epoch": 0.051627519673520826,
+      "grad_norm": 0.9127451181411743,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.8632,
+      "step": 3441
+    },
+    {
+      "epoch": 0.05209263246337237,
+      "grad_norm": 0.939115047454834,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.8526,
+      "step": 3472
+    },
+    {
+      "epoch": 0.05255774525322391,
+      "grad_norm": 0.9380930066108704,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.8684,
+      "step": 3503
+    },
+    {
+      "epoch": 0.053022858043075445,
+      "grad_norm": 0.9686013460159302,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.8443,
+      "step": 3534
+    },
+    {
+      "epoch": 0.05348797083292699,
+      "grad_norm": 1.1282305717468262,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.8612,
+      "step": 3565
+    },
+    {
+      "epoch": 0.05395308362277852,
+      "grad_norm": 0.9129716753959656,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.8535,
+      "step": 3596
+    },
+    {
+      "epoch": 0.054418196412630064,
+      "grad_norm": 1.0998603105545044,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.8578,
+      "step": 3627
+    },
+    {
+      "epoch": 0.0548833092024816,
+      "grad_norm": 0.9199731945991516,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.8487,
+      "step": 3658
+    },
+    {
+      "epoch": 0.05534842199233314,
+      "grad_norm": 0.8940901160240173,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.8438,
+      "step": 3689
+    },
+    {
+      "epoch": 0.05581353478218468,
+      "grad_norm": 0.7387672066688538,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.848,
+      "step": 3720
+    },
+    {
+      "epoch": 0.05627864757203622,
+      "grad_norm": 1.0379717350006104,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.8433,
+      "step": 3751
+    },
+    {
+      "epoch": 0.05674376036188776,
+      "grad_norm": 1.020926594734192,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.8505,
+      "step": 3782
+    },
+    {
+      "epoch": 0.057208873151739295,
+      "grad_norm": 0.9726930856704712,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.8533,
+      "step": 3813
+    },
+    {
+      "epoch": 0.05767398594159084,
+      "grad_norm": 2.112886905670166,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.8416,
+      "step": 3844
+    },
+    {
+      "epoch": 0.05813909873144237,
+      "grad_norm": 0.9767888188362122,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.8453,
+      "step": 3875
+    },
+    {
+      "epoch": 0.058604211521293914,
+      "grad_norm": 1.101620078086853,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.8509,
+      "step": 3906
+    },
+    {
+      "epoch": 0.059069324311145456,
+      "grad_norm": 0.8144866824150085,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.847,
+      "step": 3937
+    },
+    {
+      "epoch": 0.05953443710099699,
+      "grad_norm": 0.9438722729682922,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.8319,
+      "step": 3968
+    },
+    {
+      "epoch": 0.05999954989084853,
+      "grad_norm": 1.0541943311691284,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.838,
+      "step": 3999
+    },
+    {
+      "epoch": 0.06046466268070007,
+      "grad_norm": 0.9656486511230469,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.8334,
+      "step": 4030
+    },
+    {
+      "epoch": 0.06092977547055161,
+      "grad_norm": 0.8693748116493225,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.8332,
+      "step": 4061
+    },
+    {
+      "epoch": 0.061394888260403145,
+      "grad_norm": 0.8312646746635437,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.8364,
+      "step": 4092
+    },
+    {
+      "epoch": 0.06186000105025469,
+      "grad_norm": 0.9871633648872375,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.8344,
+      "step": 4123
+    },
+    {
+      "epoch": 0.06232511384010623,
+      "grad_norm": 1.1861239671707153,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.8386,
+      "step": 4154
+    },
+    {
+      "epoch": 0.06279022662995777,
+      "grad_norm": 0.7850369215011597,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.8361,
+      "step": 4185
+    },
+    {
+      "epoch": 0.0632553394198093,
+      "grad_norm": 0.888320803642273,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.8309,
+      "step": 4216
+    },
+    {
+      "epoch": 0.06372045220966084,
+      "grad_norm": 1.0985304117202759,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.8289,
+      "step": 4247
+    },
+    {
+      "epoch": 0.06418556499951238,
+      "grad_norm": 0.980798065662384,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.8232,
+      "step": 4278
+    },
+    {
+      "epoch": 0.06465067778936393,
+      "grad_norm": 0.7904775142669678,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.8253,
+      "step": 4309
+    },
+    {
+      "epoch": 0.06511579057921546,
+      "grad_norm": 0.9444935321807861,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.8409,
+      "step": 4340
+    },
+    {
+      "epoch": 0.065580903369067,
+      "grad_norm": 0.9295307993888855,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.8429,
+      "step": 4371
+    },
+    {
+      "epoch": 0.06604601615891854,
+      "grad_norm": 0.9563235640525818,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.8203,
+      "step": 4402
+    },
+    {
+      "epoch": 0.06651112894877008,
+      "grad_norm": 0.7902786135673523,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.823,
+      "step": 4433
+    },
+    {
+      "epoch": 0.06697624173862161,
+      "grad_norm": 0.9005814790725708,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.8262,
+      "step": 4464
+    },
+    {
+      "epoch": 0.06744135452847315,
+      "grad_norm": 0.9644972085952759,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.8505,
+      "step": 4495
+    },
+    {
+      "epoch": 0.0679064673183247,
+      "grad_norm": 0.8087597489356995,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.8303,
+      "step": 4526
+    },
+    {
+      "epoch": 0.06837158010817623,
+      "grad_norm": 1.06015145778656,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.841,
+      "step": 4557
+    },
+    {
+      "epoch": 0.06883669289802777,
+      "grad_norm": 0.9413964152336121,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.8297,
+      "step": 4588
+    },
+    {
+      "epoch": 0.06930180568787932,
+      "grad_norm": 0.7894837260246277,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.8313,
+      "step": 4619
+    },
+    {
+      "epoch": 0.06976691847773085,
+      "grad_norm": 1.7959920167922974,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.8343,
+      "step": 4650
+    },
+    {
+      "epoch": 0.07023203126758239,
+      "grad_norm": 0.9917001128196716,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.8324,
+      "step": 4681
+    },
+    {
+      "epoch": 0.07069714405743392,
+      "grad_norm": 0.8763757944107056,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.8245,
+      "step": 4712
+    },
+    {
+      "epoch": 0.07116225684728547,
+      "grad_norm": 0.7827804684638977,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.8135,
+      "step": 4743
+    },
+    {
+      "epoch": 0.071627369637137,
+      "grad_norm": 0.7496729493141174,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.8218,
+      "step": 4774
+    },
+    {
+      "epoch": 0.07209248242698854,
+      "grad_norm": 0.9856346249580383,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.8206,
+      "step": 4805
+    },
+    {
+      "epoch": 0.07255759521684009,
+      "grad_norm": 0.8173674941062927,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.8174,
+      "step": 4836
+    },
+    {
+      "epoch": 0.07302270800669163,
+      "grad_norm": 0.943686842918396,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.8297,
+      "step": 4867
+    },
+    {
+      "epoch": 0.07348782079654316,
+      "grad_norm": 0.8119473457336426,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.8255,
+      "step": 4898
+    },
+    {
+      "epoch": 0.0739529335863947,
+      "grad_norm": 2.7093794345855713,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.8145,
+      "step": 4929
+    },
+    {
+      "epoch": 0.07441804637624624,
+      "grad_norm": 0.9842637777328491,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.8116,
+      "step": 4960
+    },
+    {
+      "epoch": 0.07488315916609778,
+      "grad_norm": 0.9502723813056946,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.8222,
+      "step": 4991
+    },
+    {
+      "epoch": 0.07534827195594931,
+      "grad_norm": 0.8006568551063538,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.8303,
+      "step": 5022
+    },
+    {
+      "epoch": 0.07581338474580086,
+      "grad_norm": 0.7108177542686462,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.8202,
+      "step": 5053
+    },
+    {
+      "epoch": 0.0762784975356524,
+      "grad_norm": 0.7464533448219299,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.8035,
+      "step": 5084
+    },
+    {
+      "epoch": 0.07674361032550393,
+      "grad_norm": 0.815014123916626,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.8161,
+      "step": 5115
+    },
+    {
+      "epoch": 0.07720872311535547,
+      "grad_norm": 0.8991546034812927,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.8013,
+      "step": 5146
+    },
+    {
+      "epoch": 0.07767383590520702,
+      "grad_norm": 1.0259745121002197,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.8069,
+      "step": 5177
+    },
+    {
+      "epoch": 0.07813894869505855,
+      "grad_norm": 0.8683953285217285,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.8053,
+      "step": 5208
+    },
+    {
+      "epoch": 0.07860406148491009,
+      "grad_norm": 0.6831669211387634,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.8183,
+      "step": 5239
+    },
+    {
+      "epoch": 0.07906917427476164,
+      "grad_norm": 1.005091667175293,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.8145,
+      "step": 5270
+    },
+    {
+      "epoch": 0.07953428706461317,
+      "grad_norm": 1.0526143312454224,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.8179,
+      "step": 5301
+    },
+    {
+      "epoch": 0.0799993998544647,
+      "grad_norm": 0.9000487327575684,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.8191,
+      "step": 5332
+    },
+    {
+      "epoch": 0.08046451264431624,
+      "grad_norm": 0.7542000412940979,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.8129,
+      "step": 5363
+    },
+    {
+      "epoch": 0.08092962543416779,
+      "grad_norm": 0.7871935963630676,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.8008,
+      "step": 5394
+    },
+    {
+      "epoch": 0.08139473822401933,
+      "grad_norm": 0.9389820098876953,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.8084,
+      "step": 5425
+    },
+    {
+      "epoch": 0.08185985101387086,
+      "grad_norm": 0.8348682522773743,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.8098,
+      "step": 5456
+    },
+    {
+      "epoch": 0.08232496380372241,
+      "grad_norm": 0.7959926724433899,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.8092,
+      "step": 5487
+    },
+    {
+      "epoch": 0.08279007659357394,
+      "grad_norm": 0.8719795346260071,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.812,
+      "step": 5518
+    },
+    {
+      "epoch": 0.08325518938342548,
+      "grad_norm": 0.7396957278251648,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.8052,
+      "step": 5549
+    },
+    {
+      "epoch": 0.08372030217327701,
+      "grad_norm": 0.7120716571807861,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.8198,
+      "step": 5580
+    },
+    {
+      "epoch": 0.08418541496312856,
+      "grad_norm": 0.6915568113327026,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.8167,
+      "step": 5611
+    },
+    {
+      "epoch": 0.0846505277529801,
+      "grad_norm": 0.7923029661178589,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.8102,
+      "step": 5642
+    },
+    {
+      "epoch": 0.08511564054283163,
+      "grad_norm": 0.9134017825126648,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.8044,
+      "step": 5673
+    },
+    {
+      "epoch": 0.08558075333268318,
+      "grad_norm": 0.6910101771354675,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.8033,
+      "step": 5704
+    },
+    {
+      "epoch": 0.08604586612253472,
+      "grad_norm": 1.0083701610565186,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.7984,
+      "step": 5735
+    },
+    {
+      "epoch": 0.08651097891238625,
+      "grad_norm": 0.7578200697898865,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.8028,
+      "step": 5766
+    },
+    {
+      "epoch": 0.08697609170223779,
+      "grad_norm": 0.6932199001312256,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.7913,
+      "step": 5797
+    },
+    {
+      "epoch": 0.08744120449208934,
+      "grad_norm": 0.8898211717605591,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.8087,
+      "step": 5828
+    },
+    {
+      "epoch": 0.08790631728194087,
+      "grad_norm": 0.8452892303466797,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.798,
+      "step": 5859
+    },
+    {
+      "epoch": 0.0883714300717924,
+      "grad_norm": 0.7200170159339905,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.8033,
+      "step": 5890
+    },
+    {
+      "epoch": 0.08883654286164396,
+      "grad_norm": 0.9801698923110962,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.801,
+      "step": 5921
+    },
+    {
+      "epoch": 0.08930165565149549,
+      "grad_norm": 0.6971285939216614,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.8004,
+      "step": 5952
+    },
+    {
+      "epoch": 0.08976676844134703,
+      "grad_norm": 0.6692901253700256,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.8079,
+      "step": 5983
+    },
+    {
+      "epoch": 0.09023188123119856,
+      "grad_norm": 0.7357479929924011,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.8047,
+      "step": 6014
+    },
+    {
+      "epoch": 0.09069699402105011,
+      "grad_norm": 0.9808568358421326,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.7943,
+      "step": 6045
+    },
+    {
+      "epoch": 0.09116210681090164,
+      "grad_norm": 0.8038450479507446,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.7962,
+      "step": 6076
+    },
+    {
+      "epoch": 0.09162721960075318,
+      "grad_norm": 1.1002798080444336,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.8133,
+      "step": 6107
+    },
+    {
+      "epoch": 0.09209233239060473,
+      "grad_norm": 0.8928295373916626,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.7968,
+      "step": 6138
+    },
+    {
+      "epoch": 0.09255744518045626,
+      "grad_norm": 0.8596677184104919,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.8087,
+      "step": 6169
+    },
+    {
+      "epoch": 0.0930225579703078,
+      "grad_norm": 1.0481047630310059,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.7874,
+      "step": 6200
+    },
+    {
+      "epoch": 0.09348767076015933,
+      "grad_norm": 0.7633193731307983,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.7945,
+      "step": 6231
+    },
+    {
+      "epoch": 0.09395278355001088,
+      "grad_norm": 0.6666761040687561,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.7999,
+      "step": 6262
+    },
+    {
+      "epoch": 0.09441789633986242,
+      "grad_norm": 0.7834581732749939,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.8004,
+      "step": 6293
+    },
+    {
+      "epoch": 0.09488300912971395,
+      "grad_norm": 0.8548229932785034,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.7983,
+      "step": 6324
+    },
+    {
+      "epoch": 0.0953481219195655,
+      "grad_norm": 0.8321638703346252,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.8103,
+      "step": 6355
+    },
+    {
+      "epoch": 0.09581323470941704,
+      "grad_norm": 0.8134599924087524,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.8042,
+      "step": 6386
+    },
+    {
+      "epoch": 0.09627834749926857,
+      "grad_norm": 0.9421968460083008,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.8028,
+      "step": 6417
+    },
+    {
+      "epoch": 0.0967434602891201,
+      "grad_norm": 0.6998574137687683,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.809,
+      "step": 6448
+    },
+    {
+      "epoch": 0.09720857307897166,
+      "grad_norm": 0.7347880005836487,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.8115,
+      "step": 6479
+    },
+    {
+      "epoch": 0.09767368586882319,
+      "grad_norm": 0.8895875811576843,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.8023,
+      "step": 6510
+    },
+    {
+      "epoch": 0.09813879865867473,
+      "grad_norm": 0.588324785232544,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.7958,
+      "step": 6541
+    },
+    {
+      "epoch": 0.09860391144852627,
+      "grad_norm": 0.8145986199378967,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.8018,
+      "step": 6572
+    },
+    {
+      "epoch": 0.09906902423837781,
+      "grad_norm": 0.659679651260376,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.7904,
+      "step": 6603
+    },
+    {
+      "epoch": 0.09953413702822934,
+      "grad_norm": 0.7664335370063782,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.7953,
+      "step": 6634
+    },
+    {
+      "epoch": 0.09999924981808088,
+      "grad_norm": 0.630374550819397,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.7834,
+      "step": 6665
+    },
+    {
+      "epoch": 0.10046436260793243,
+      "grad_norm": 0.8089181780815125,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.7939,
+      "step": 6696
+    },
+    {
+      "epoch": 0.10092947539778396,
+      "grad_norm": 0.7410175204277039,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.7997,
+      "step": 6727
+    },
+    {
+      "epoch": 0.1013945881876355,
+      "grad_norm": 0.8867741823196411,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.7876,
+      "step": 6758
+    },
+    {
+      "epoch": 0.10185970097748705,
+      "grad_norm": 0.8592618107795715,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.7915,
+      "step": 6789
+    },
+    {
+      "epoch": 0.10232481376733858,
+      "grad_norm": 0.7498304843902588,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.7953,
+      "step": 6820
+    },
+    {
+      "epoch": 0.10278992655719012,
+      "grad_norm": 0.7439833879470825,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.7932,
+      "step": 6851
+    },
+    {
+      "epoch": 0.10325503934704165,
+      "grad_norm": 0.7184897065162659,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.7905,
+      "step": 6882
+    },
+    {
+      "epoch": 0.1037201521368932,
+      "grad_norm": 0.7455788254737854,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.7822,
+      "step": 6913
+    },
+    {
+      "epoch": 0.10418526492674474,
+      "grad_norm": 0.7429169416427612,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.7895,
+      "step": 6944
+    },
+    {
+      "epoch": 0.10465037771659627,
+      "grad_norm": 0.708569347858429,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.7922,
+      "step": 6975
+    },
+    {
+      "epoch": 0.10511549050644782,
+      "grad_norm": 0.6906721591949463,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.7932,
+      "step": 7006
+    },
+    {
+      "epoch": 0.10558060329629936,
+      "grad_norm": 0.7495471835136414,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.7849,
+      "step": 7037
+    },
+    {
+      "epoch": 0.10604571608615089,
+      "grad_norm": 0.7219502329826355,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.7842,
+      "step": 7068
+    },
+    {
+      "epoch": 0.10651082887600243,
+      "grad_norm": 0.7211415767669678,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.7822,
+      "step": 7099
+    },
+    {
+      "epoch": 0.10697594166585397,
+      "grad_norm": 0.7900408506393433,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.7956,
+      "step": 7130
+    },
+    {
+      "epoch": 0.10744105445570551,
+      "grad_norm": 0.8071913123130798,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.7884,
+      "step": 7161
+    },
+    {
+      "epoch": 0.10790616724555704,
+      "grad_norm": 0.6667525172233582,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.7815,
+      "step": 7192
+    },
+    {
+      "epoch": 0.1083712800354086,
+      "grad_norm": 0.8470203280448914,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.793,
+      "step": 7223
+    },
+    {
+      "epoch": 0.10883639282526013,
+      "grad_norm": 0.7718335390090942,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.787,
+      "step": 7254
+    },
+    {
+      "epoch": 0.10930150561511166,
+      "grad_norm": 0.67174232006073,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.7859,
+      "step": 7285
+    },
+    {
+      "epoch": 0.1097666184049632,
+      "grad_norm": 0.9030664563179016,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.785,
+      "step": 7316
+    },
+    {
+      "epoch": 0.11023173119481475,
+      "grad_norm": 0.6775389313697815,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.7835,
+      "step": 7347
+    },
+    {
+      "epoch": 0.11069684398466628,
+      "grad_norm": 0.6373648643493652,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.7816,
+      "step": 7378
+    },
+    {
+      "epoch": 0.11116195677451782,
+      "grad_norm": 0.7260624170303345,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.7878,
+      "step": 7409
+    },
+    {
+      "epoch": 0.11162706956436937,
+      "grad_norm": 0.7170141935348511,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.7754,
+      "step": 7440
+    },
+    {
+      "epoch": 0.1120921823542209,
+      "grad_norm": 0.7276513576507568,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.7854,
+      "step": 7471
+    },
+    {
+      "epoch": 0.11255729514407244,
+      "grad_norm": 0.7349756956100464,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.791,
+      "step": 7502
+    },
+    {
+      "epoch": 0.11302240793392397,
+      "grad_norm": 0.8739349246025085,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.7926,
+      "step": 7533
+    },
+    {
+      "epoch": 0.11348752072377552,
+      "grad_norm": 0.7612133622169495,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.7954,
+      "step": 7564
+    },
+    {
+      "epoch": 0.11395263351362706,
+      "grad_norm": 0.7819641828536987,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.7813,
+      "step": 7595
+    },
+    {
+      "epoch": 0.11441774630347859,
+      "grad_norm": 0.789462685585022,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.7982,
+      "step": 7626
+    },
+    {
+      "epoch": 0.11488285909333014,
+      "grad_norm": 0.677481472492218,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.778,
+      "step": 7657
+    },
+    {
+      "epoch": 0.11534797188318167,
+      "grad_norm": 0.8899239301681519,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.7841,
+      "step": 7688
+    },
+    {
+      "epoch": 0.11581308467303321,
+      "grad_norm": 0.9114879369735718,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.7962,
+      "step": 7719
+    },
+    {
+      "epoch": 0.11627819746288474,
+      "grad_norm": 0.7342079877853394,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.784,
+      "step": 7750
+    },
+    {
+      "epoch": 0.1167433102527363,
+      "grad_norm": 0.7678495049476624,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.7831,
+      "step": 7781
+    },
+    {
+      "epoch": 0.11720842304258783,
+      "grad_norm": 0.8216970562934875,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.7782,
+      "step": 7812
+    },
+    {
+      "epoch": 0.11767353583243936,
+      "grad_norm": 0.8297589421272278,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.7851,
+      "step": 7843
+    },
+    {
+      "epoch": 0.11813864862229091,
+      "grad_norm": 0.6707519292831421,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.7801,
+      "step": 7874
+    },
+    {
+      "epoch": 0.11860376141214245,
+      "grad_norm": 0.6816626787185669,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.7872,
+      "step": 7905
+    },
+    {
+      "epoch": 0.11906887420199398,
+      "grad_norm": 0.9005252122879028,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.7936,
+      "step": 7936
+    },
+    {
+      "epoch": 0.11953398699184552,
+      "grad_norm": 0.8328778147697449,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.7786,
+      "step": 7967
+    },
+    {
+      "epoch": 0.11999909978169707,
+      "grad_norm": 0.8410969376564026,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.7848,
+      "step": 7998
+    },
+    {
+      "epoch": 0.1204642125715486,
+      "grad_norm": 0.7608590722084045,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.7834,
+      "step": 8029
+    },
+    {
+      "epoch": 0.12092932536140014,
+      "grad_norm": 0.8817543983459473,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.7852,
+      "step": 8060
+    },
+    {
+      "epoch": 0.12139443815125169,
+      "grad_norm": 0.7609240412712097,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.7766,
+      "step": 8091
+    },
+    {
+      "epoch": 0.12185955094110322,
+      "grad_norm": 1.1703492403030396,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.7844,
+      "step": 8122
+    },
+    {
+      "epoch": 0.12232466373095476,
+      "grad_norm": 0.7617055773735046,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.7806,
+      "step": 8153
+    },
+    {
+      "epoch": 0.12278977652080629,
+      "grad_norm": 0.7049508690834045,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.7807,
+      "step": 8184
+    },
+    {
+      "epoch": 0.12325488931065784,
+      "grad_norm": 0.7807313203811646,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.7825,
+      "step": 8215
+    },
+    {
+      "epoch": 0.12372000210050937,
+      "grad_norm": 0.9308986067771912,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.7803,
+      "step": 8246
+    },
+    {
+      "epoch": 0.12418511489036091,
+      "grad_norm": 0.7101467251777649,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.7762,
+      "step": 8277
+    },
+    {
+      "epoch": 0.12465022768021246,
+      "grad_norm": 0.6804013252258301,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.7892,
+      "step": 8308
+    },
+    {
+      "epoch": 0.12511534047006398,
+      "grad_norm": 0.6824433207511902,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.7802,
+      "step": 8339
+    },
+    {
+      "epoch": 0.12558045325991554,
+      "grad_norm": 1.468239188194275,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.7869,
+      "step": 8370
+    },
+    {
+      "epoch": 0.12604556604976708,
+      "grad_norm": 0.5719156861305237,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.778,
+      "step": 8401
+    },
+    {
+      "epoch": 0.1265106788396186,
+      "grad_norm": 0.6709131002426147,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.7732,
+      "step": 8432
+    },
+    {
+      "epoch": 0.12697579162947015,
+      "grad_norm": 0.7485822439193726,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.7838,
+      "step": 8463
+    },
+    {
+      "epoch": 0.12744090441932168,
+      "grad_norm": 0.6957044005393982,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.7871,
+      "step": 8494
+    },
+    {
+      "epoch": 0.12790601720917322,
+      "grad_norm": 1.0035358667373657,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.7743,
+      "step": 8525
+    },
+    {
+      "epoch": 0.12837112999902475,
+      "grad_norm": 0.5898587107658386,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.7826,
+      "step": 8556
+    },
+    {
+      "epoch": 0.12883624278887632,
+      "grad_norm": 3.798095226287842,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.7808,
+      "step": 8587
+    },
+    {
+      "epoch": 0.12930135557872785,
+      "grad_norm": 0.6663601398468018,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.7849,
+      "step": 8618
+    },
+    {
+      "epoch": 0.12976646836857939,
+      "grad_norm": 0.7356058955192566,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.7798,
+      "step": 8649
+    },
+    {
+      "epoch": 0.13023158115843092,
+      "grad_norm": 0.6421476006507874,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.7704,
+      "step": 8680
+    },
+    {
+      "epoch": 0.13069669394828246,
+      "grad_norm": 0.5868635177612305,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.7759,
+      "step": 8711
+    },
+    {
+      "epoch": 0.131161806738134,
+      "grad_norm": 0.6703419089317322,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.781,
+      "step": 8742
+    },
+    {
+      "epoch": 0.13162691952798553,
+      "grad_norm": 0.751116931438446,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.768,
+      "step": 8773
+    },
+    {
+      "epoch": 0.1320920323178371,
+      "grad_norm": 0.9944510459899902,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.7783,
+      "step": 8804
+    },
+    {
+      "epoch": 0.13255714510768862,
+      "grad_norm": 0.6739645600318909,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.7745,
+      "step": 8835
+    },
+    {
+      "epoch": 0.13302225789754016,
+      "grad_norm": 0.612147867679596,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.7778,
+      "step": 8866
+    },
+    {
+      "epoch": 0.1334873706873917,
+      "grad_norm": 0.7233457565307617,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.7799,
+      "step": 8897
+    },
+    {
+      "epoch": 0.13395248347724323,
+      "grad_norm": 0.6210694909095764,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.7764,
+      "step": 8928
+    },
+    {
+      "epoch": 0.13441759626709476,
+      "grad_norm": 0.7104094624519348,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.776,
+      "step": 8959
+    },
+    {
+      "epoch": 0.1348827090569463,
+      "grad_norm": 0.6815863251686096,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.7799,
+      "step": 8990
+    },
+    {
+      "epoch": 0.13534782184679786,
+      "grad_norm": 0.660565972328186,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.7856,
+      "step": 9021
+    },
+    {
+      "epoch": 0.1358129346366494,
+      "grad_norm": 0.8271650671958923,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.7758,
+      "step": 9052
+    },
+    {
+      "epoch": 0.13627804742650093,
+      "grad_norm": 0.6217832565307617,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.7736,
+      "step": 9083
+    },
+    {
+      "epoch": 0.13674316021635247,
+      "grad_norm": 0.6582239270210266,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.7765,
+      "step": 9114
+    },
+    {
+      "epoch": 0.137208273006204,
+      "grad_norm": 0.758140504360199,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.7696,
+      "step": 9145
+    },
+    {
+      "epoch": 0.13767338579605554,
+      "grad_norm": 0.7370248436927795,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.7751,
+      "step": 9176
+    },
+    {
+      "epoch": 0.13813849858590707,
+      "grad_norm": 0.667799711227417,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.7686,
+      "step": 9207
+    },
+    {
+      "epoch": 0.13860361137575863,
+      "grad_norm": 0.6749032139778137,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.7656,
+      "step": 9238
+    },
+    {
+      "epoch": 0.13906872416561017,
+      "grad_norm": 0.7389397025108337,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.7733,
+      "step": 9269
+    },
+    {
+      "epoch": 0.1395338369554617,
+      "grad_norm": 0.8019024133682251,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.7704,
+      "step": 9300
+    },
+    {
+      "epoch": 0.13999894974531324,
+      "grad_norm": 0.6880025863647461,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.7745,
+      "step": 9331
+    },
+    {
+      "epoch": 0.14046406253516477,
+      "grad_norm": 0.7543455362319946,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.7616,
+      "step": 9362
+    },
+    {
+      "epoch": 0.1409291753250163,
+      "grad_norm": 0.6550135612487793,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.7698,
+      "step": 9393
+    },
+    {
+      "epoch": 0.14139428811486784,
+      "grad_norm": 0.7469960451126099,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.764,
+      "step": 9424
+    },
+    {
+      "epoch": 0.1418594009047194,
+      "grad_norm": 0.65736323595047,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.7625,
+      "step": 9455
+    },
+    {
+      "epoch": 0.14232451369457094,
+      "grad_norm": 0.7517855167388916,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.7727,
+      "step": 9486
+    },
+    {
+      "epoch": 0.14278962648442248,
+      "grad_norm": 0.5399331450462341,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.7625,
+      "step": 9517
+    },
+    {
+      "epoch": 0.143254739274274,
+      "grad_norm": 0.7568219900131226,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.7629,
+      "step": 9548
+    },
+    {
+      "epoch": 0.14371985206412555,
+      "grad_norm": 0.8380396962165833,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.765,
+      "step": 9579
+    },
+    {
+      "epoch": 0.14418496485397708,
+      "grad_norm": 0.657565176486969,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.7617,
+      "step": 9610
+    },
+    {
+      "epoch": 0.14465007764382862,
+      "grad_norm": 0.784701406955719,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.7662,
+      "step": 9641
+    },
+    {
+      "epoch": 0.14511519043368018,
+      "grad_norm": 0.6358653903007507,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.7668,
+      "step": 9672
+    },
+    {
+      "epoch": 0.14558030322353172,
+      "grad_norm": 0.6734030842781067,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.7587,
+      "step": 9703
+    },
+    {
+      "epoch": 0.14604541601338325,
+      "grad_norm": 0.693668007850647,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.7587,
+      "step": 9734
+    },
+    {
+      "epoch": 0.14651052880323479,
+      "grad_norm": 0.7010748982429504,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.7729,
+      "step": 9765
+    },
+    {
+      "epoch": 0.14697564159308632,
+      "grad_norm": 0.6210809946060181,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.7708,
+      "step": 9796
+    },
+    {
+      "epoch": 0.14744075438293786,
+      "grad_norm": 0.6918211579322815,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.7742,
+      "step": 9827
+    },
+    {
+      "epoch": 0.1479058671727894,
+      "grad_norm": 0.7196410298347473,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.7593,
+      "step": 9858
+    },
+    {
+      "epoch": 0.14837097996264095,
+      "grad_norm": 0.6762074828147888,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.7601,
+      "step": 9889
+    },
+    {
+      "epoch": 0.1488360927524925,
+      "grad_norm": 0.7633680701255798,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.7684,
+      "step": 9920
+    },
+    {
+      "epoch": 0.14930120554234402,
+      "grad_norm": 0.6944717168807983,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.7554,
+      "step": 9951
+    },
+    {
+      "epoch": 0.14976631833219556,
+      "grad_norm": 0.6295722126960754,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.7584,
+      "step": 9982
+    },
+    {
+      "epoch": 0.1502314311220471,
+      "grad_norm": 0.6174144744873047,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.7626,
+      "step": 10013
+    },
+    {
+      "epoch": 0.15069654391189863,
+      "grad_norm": 0.7596246600151062,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.7664,
+      "step": 10044
+    },
+    {
+      "epoch": 0.15116165670175016,
+      "grad_norm": 0.6924237012863159,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.7736,
+      "step": 10075
+    },
+    {
+      "epoch": 0.15162676949160173,
+      "grad_norm": 0.6916103363037109,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.7784,
+      "step": 10106
+    },
+    {
+      "epoch": 0.15209188228145326,
+      "grad_norm": 0.7141834497451782,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.7669,
+      "step": 10137
+    },
+    {
+      "epoch": 0.1525569950713048,
+      "grad_norm": 0.6703450679779053,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.7612,
+      "step": 10168
+    },
+    {
+      "epoch": 0.15302210786115633,
+      "grad_norm": 0.6729284524917603,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.7695,
+      "step": 10199
+    },
+    {
+      "epoch": 0.15348722065100787,
+      "grad_norm": 0.8227813243865967,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.7573,
+      "step": 10230
+    },
+    {
+      "epoch": 0.1539523334408594,
+      "grad_norm": 0.6902511715888977,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.7603,
+      "step": 10261
+    },
+    {
+      "epoch": 0.15441744623071094,
+      "grad_norm": 0.6204094290733337,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.7612,
+      "step": 10292
+    },
+    {
+      "epoch": 0.1548825590205625,
+      "grad_norm": 0.7256117463111877,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.7635,
+      "step": 10323
+    },
+    {
+      "epoch": 0.15534767181041403,
+      "grad_norm": 0.6088977456092834,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.7609,
+      "step": 10354
+    },
+    {
+      "epoch": 0.15581278460026557,
+      "grad_norm": 0.6714738607406616,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.7661,
+      "step": 10385
+    },
+    {
+      "epoch": 0.1562778973901171,
+      "grad_norm": 0.6832950711250305,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.7703,
+      "step": 10416
+    },
+    {
+      "epoch": 0.15674301017996864,
+      "grad_norm": 0.8103564381599426,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.7641,
+      "step": 10447
+    },
+    {
+      "epoch": 0.15720812296982017,
+      "grad_norm": 0.7727939486503601,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.7644,
+      "step": 10478
+    },
+    {
+      "epoch": 0.1576732357596717,
+      "grad_norm": 0.6045538187026978,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.7603,
+      "step": 10509
+    },
+    {
+      "epoch": 0.15813834854952327,
+      "grad_norm": 0.7199150323867798,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.7617,
+      "step": 10540
+    },
+    {
+      "epoch": 0.1586034613393748,
+      "grad_norm": 0.6426290273666382,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.765,
+      "step": 10571
+    },
+    {
+      "epoch": 0.15906857412922634,
+      "grad_norm": 0.6604538559913635,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.7512,
+      "step": 10602
+    },
+    {
+      "epoch": 0.15953368691907788,
+      "grad_norm": 0.6802282333374023,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.7528,
+      "step": 10633
+    },
+    {
+      "epoch": 0.1599987997089294,
+      "grad_norm": 0.5920473337173462,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.7645,
+      "step": 10664
+    },
+    {
+      "epoch": 0.16046391249878095,
+      "grad_norm": 0.70703125,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.7798,
+      "step": 10695
+    },
+    {
+      "epoch": 0.16092902528863248,
+      "grad_norm": 0.7090973258018494,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.7501,
+      "step": 10726
+    },
+    {
+      "epoch": 0.16139413807848405,
+      "grad_norm": 0.6518564820289612,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.7646,
+      "step": 10757
+    },
+    {
+      "epoch": 0.16185925086833558,
+      "grad_norm": 0.7883148789405823,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.7464,
+      "step": 10788
+    },
+    {
+      "epoch": 0.16232436365818712,
+      "grad_norm": 0.701317310333252,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.7629,
+      "step": 10819
+    },
+    {
+      "epoch": 0.16278947644803865,
+      "grad_norm": 0.6755788922309875,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.7524,
+      "step": 10850
+    },
+    {
+      "epoch": 0.16325458923789019,
+      "grad_norm": 0.7258623242378235,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.7681,
+      "step": 10881
+    },
+    {
+      "epoch": 0.16371970202774172,
+      "grad_norm": 0.678916871547699,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.7572,
+      "step": 10912
+    },
+    {
+      "epoch": 0.16418481481759326,
+      "grad_norm": 0.6140801906585693,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.7573,
+      "step": 10943
+    },
+    {
+      "epoch": 0.16464992760744482,
+      "grad_norm": 0.8363719582557678,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.7541,
+      "step": 10974
+    },
+    {
+      "epoch": 0.16511504039729635,
+      "grad_norm": 0.8430968523025513,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.7621,
+      "step": 11005
+    },
+    {
+      "epoch": 0.1655801531871479,
+      "grad_norm": 0.7111339569091797,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.7581,
+      "step": 11036
+    },
+    {
+      "epoch": 0.16604526597699942,
+      "grad_norm": 0.6369599103927612,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.7543,
+      "step": 11067
+    },
+    {
+      "epoch": 0.16651037876685096,
+      "grad_norm": 0.6842892169952393,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.7599,
+      "step": 11098
+    },
+    {
+      "epoch": 0.1669754915567025,
+      "grad_norm": 0.6923761963844299,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.762,
+      "step": 11129
+    },
+    {
+      "epoch": 0.16744060434655403,
+      "grad_norm": 0.7744085788726807,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.748,
+      "step": 11160
+    },
+    {
+      "epoch": 0.1679057171364056,
+      "grad_norm": 0.6975285410881042,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.7518,
+      "step": 11191
+    },
+    {
+      "epoch": 0.16837082992625713,
+      "grad_norm": 0.5738661289215088,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.7508,
+      "step": 11222
+    },
+    {
+      "epoch": 0.16883594271610866,
+      "grad_norm": 0.5840383172035217,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.7591,
+      "step": 11253
+    },
+    {
+      "epoch": 0.1693010555059602,
+      "grad_norm": 0.7805384397506714,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.7519,
+      "step": 11284
+    },
+    {
+      "epoch": 0.16976616829581173,
+      "grad_norm": 0.7086957693099976,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.7638,
+      "step": 11315
+    },
+    {
+      "epoch": 0.17023128108566327,
+      "grad_norm": 0.7142307758331299,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.7489,
+      "step": 11346
+    },
+    {
+      "epoch": 0.1706963938755148,
+      "grad_norm": 0.6033651232719421,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.762,
+      "step": 11377
+    },
+    {
+      "epoch": 0.17116150666536636,
+      "grad_norm": 0.6250593066215515,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.7552,
+      "step": 11408
+    },
+    {
+      "epoch": 0.1716266194552179,
+      "grad_norm": 0.6813081502914429,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.7556,
+      "step": 11439
+    },
+    {
+      "epoch": 0.17209173224506943,
+      "grad_norm": 0.8393754363059998,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.7569,
+      "step": 11470
+    },
+    {
+      "epoch": 0.17255684503492097,
+      "grad_norm": 1.5094987154006958,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.7561,
+      "step": 11501
+    },
+    {
+      "epoch": 0.1730219578247725,
+      "grad_norm": 0.631462037563324,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.7558,
+      "step": 11532
+    },
+    {
+      "epoch": 0.17348707061462404,
+      "grad_norm": 0.7486265897750854,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.7569,
+      "step": 11563
+    },
+    {
+      "epoch": 0.17395218340447557,
+      "grad_norm": 0.9510587453842163,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.7503,
+      "step": 11594
+    },
+    {
+      "epoch": 0.17441729619432714,
+      "grad_norm": 0.5841720700263977,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.7555,
+      "step": 11625
+    },
+    {
+      "epoch": 0.17488240898417867,
+      "grad_norm": 0.5946236848831177,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.7484,
+      "step": 11656
+    },
+    {
+      "epoch": 0.1753475217740302,
+      "grad_norm": 0.8158132433891296,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.748,
+      "step": 11687
+    },
+    {
+      "epoch": 0.17581263456388174,
+      "grad_norm": 0.6327953338623047,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.7611,
+      "step": 11718
+    },
+    {
+      "epoch": 0.17627774735373328,
+      "grad_norm": 0.7370153069496155,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.7495,
+      "step": 11749
+    },
+    {
+      "epoch": 0.1767428601435848,
+      "grad_norm": 0.911038875579834,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.7604,
+      "step": 11780
+    },
+    {
+      "epoch": 0.17720797293343635,
+      "grad_norm": 0.7187597751617432,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.7448,
+      "step": 11811
+    },
+    {
+      "epoch": 0.1776730857232879,
+      "grad_norm": 0.6611767411231995,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.7486,
+      "step": 11842
+    },
+    {
+      "epoch": 0.17813819851313945,
+      "grad_norm": 0.725936770439148,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.7585,
+      "step": 11873
+    },
+    {
+      "epoch": 0.17860331130299098,
+      "grad_norm": 0.7662620544433594,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.7489,
+      "step": 11904
+    },
+    {
+      "epoch": 0.17906842409284252,
+      "grad_norm": 0.7236283421516418,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.7571,
+      "step": 11935
+    },
+    {
+      "epoch": 0.17953353688269405,
+      "grad_norm": 0.7157570123672485,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.7524,
+      "step": 11966
+    },
+    {
+      "epoch": 0.17999864967254559,
+      "grad_norm": 0.7178536653518677,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.7592,
+      "step": 11997
+    },
+    {
+      "epoch": 0.18046376246239712,
+      "grad_norm": 0.5687118768692017,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.7485,
+      "step": 12028
+    },
+    {
+      "epoch": 0.18092887525224868,
+      "grad_norm": 0.853602409362793,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.7578,
+      "step": 12059
+    },
+    {
+      "epoch": 0.18139398804210022,
+      "grad_norm": 0.7728062272071838,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.7463,
+      "step": 12090
+    },
+    {
+      "epoch": 0.18185910083195175,
+      "grad_norm": 0.6808280348777771,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.7513,
+      "step": 12121
+    },
+    {
+      "epoch": 0.1823242136218033,
+      "grad_norm": 0.730434775352478,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.7459,
+      "step": 12152
+    },
+    {
+      "epoch": 0.18278932641165482,
+      "grad_norm": 0.7605392336845398,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.7428,
+      "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:ee8c8c4b56f5ef244b7e4deb23b13b2d7ae50fce940e6c0d8a4ec3f3f25fa1a3
+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 sha256:2cd77b33bec3de91bc707e9cfa89950fd7ae1f58ea8382dda5b7de302aff1620
+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 sha256:4e13b2084c7a2ad41cfd8e3c90cd1075f2e2017af685da1ddae7d664a72c38ac
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f3af77599ad1da09c076f0116eb48314b17c28c4e10e1fad88cea6c9c634a9
+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 sha256:5cb253ac21ffc094220418a644dde15166c8dae7a18513bb3c7f6bc97754773c
+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": 0.22895552171401565,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000465112789851539,
+      "grad_norm": 2.768016815185547,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 1.3097,
+      "step": 31
+    },
+    {
+      "epoch": 0.000930225579703078,
+      "grad_norm": 1.7586184740066528,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 1.2415,
+      "step": 62
+    },
+    {
+      "epoch": 0.001395338369554617,
+      "grad_norm": 1.6319445371627808,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 1.1785,
+      "step": 93
+    },
+    {
+      "epoch": 0.001860451159406156,
+      "grad_norm": 1.667987585067749,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 1.165,
+      "step": 124
+    },
+    {
+      "epoch": 0.002325563949257695,
+      "grad_norm": 1.6823372840881348,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 1.1241,
+      "step": 155
+    },
+    {
+      "epoch": 0.002790676739109234,
+      "grad_norm": 1.7869504690170288,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 1.1232,
+      "step": 186
+    },
+    {
+      "epoch": 0.003255789528960773,
+      "grad_norm": 1.9446443319320679,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 1.108,
+      "step": 217
+    },
+    {
+      "epoch": 0.003720902318812312,
+      "grad_norm": 1.9483426809310913,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 1.118,
+      "step": 248
+    },
+    {
+      "epoch": 0.004186015108663851,
+      "grad_norm": 1.837703824043274,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 1.091,
+      "step": 279
+    },
+    {
+      "epoch": 0.00465112789851539,
+      "grad_norm": 1.9819648265838623,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 1.075,
+      "step": 310
+    },
+    {
+      "epoch": 0.005116240688366929,
+      "grad_norm": 1.9136595726013184,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 1.0668,
+      "step": 341
+    },
+    {
+      "epoch": 0.005581353478218468,
+      "grad_norm": 1.720566987991333,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 1.0769,
+      "step": 372
+    },
+    {
+      "epoch": 0.006046466268070007,
+      "grad_norm": 1.9698255062103271,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 1.0543,
+      "step": 403
+    },
+    {
+      "epoch": 0.006511579057921546,
+      "grad_norm": 1.665868878364563,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 1.0524,
+      "step": 434
+    },
+    {
+      "epoch": 0.006976691847773085,
+      "grad_norm": 1.9344353675842285,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 1.0518,
+      "step": 465
+    },
+    {
+      "epoch": 0.007441804637624624,
+      "grad_norm": 2.173403024673462,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 1.0476,
+      "step": 496
+    },
+    {
+      "epoch": 0.007906917427476163,
+      "grad_norm": 2.1878745555877686,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 1.0385,
+      "step": 527
+    },
+    {
+      "epoch": 0.008372030217327702,
+      "grad_norm": 1.8220405578613281,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 1.0374,
+      "step": 558
+    },
+    {
+      "epoch": 0.00883714300717924,
+      "grad_norm": 2.0194647312164307,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 1.0408,
+      "step": 589
+    },
+    {
+      "epoch": 0.00930225579703078,
+      "grad_norm": 1.9656147956848145,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 1.0252,
+      "step": 620
+    },
+    {
+      "epoch": 0.009767368586882319,
+      "grad_norm": 1.6676087379455566,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 1.0209,
+      "step": 651
+    },
+    {
+      "epoch": 0.010232481376733858,
+      "grad_norm": 1.8552638292312622,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 1.0077,
+      "step": 682
+    },
+    {
+      "epoch": 0.010697594166585398,
+      "grad_norm": 1.7905389070510864,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 1.0099,
+      "step": 713
+    },
+    {
+      "epoch": 0.011162706956436936,
+      "grad_norm": 1.8298577070236206,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 1.01,
+      "step": 744
+    },
+    {
+      "epoch": 0.011627819746288475,
+      "grad_norm": 1.6317881345748901,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 1.003,
+      "step": 775
+    },
+    {
+      "epoch": 0.012092932536140013,
+      "grad_norm": 1.9337595701217651,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 1.005,
+      "step": 806
+    },
+    {
+      "epoch": 0.012558045325991554,
+      "grad_norm": 1.655259132385254,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.992,
+      "step": 837
+    },
+    {
+      "epoch": 0.013023158115843092,
+      "grad_norm": 1.6854184865951538,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.9922,
+      "step": 868
+    },
+    {
+      "epoch": 0.01348827090569463,
+      "grad_norm": 1.7627979516983032,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.9828,
+      "step": 899
+    },
+    {
+      "epoch": 0.01395338369554617,
+      "grad_norm": 1.7015711069107056,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.9896,
+      "step": 930
+    },
+    {
+      "epoch": 0.01441849648539771,
+      "grad_norm": 1.6730037927627563,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.9847,
+      "step": 961
+    },
+    {
+      "epoch": 0.014883609275249248,
+      "grad_norm": 1.7218660116195679,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.9912,
+      "step": 992
+    },
+    {
+      "epoch": 0.015348722065100786,
+      "grad_norm": 1.5981271266937256,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.9791,
+      "step": 1023
+    },
+    {
+      "epoch": 0.015813834854952327,
+      "grad_norm": 2.0253615379333496,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.9693,
+      "step": 1054
+    },
+    {
+      "epoch": 0.016278947644803865,
+      "grad_norm": 1.62104070186615,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.9708,
+      "step": 1085
+    },
+    {
+      "epoch": 0.016744060434655404,
+      "grad_norm": 1.465540885925293,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.9603,
+      "step": 1116
+    },
+    {
+      "epoch": 0.017209173224506942,
+      "grad_norm": 1.3695433139801025,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.9643,
+      "step": 1147
+    },
+    {
+      "epoch": 0.01767428601435848,
+      "grad_norm": 1.5520803928375244,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.9652,
+      "step": 1178
+    },
+    {
+      "epoch": 0.018139398804210023,
+      "grad_norm": 1.5043976306915283,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.9609,
+      "step": 1209
+    },
+    {
+      "epoch": 0.01860451159406156,
+      "grad_norm": 1.5582523345947266,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.9549,
+      "step": 1240
+    },
+    {
+      "epoch": 0.0190696243839131,
+      "grad_norm": 1.5340025424957275,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.9596,
+      "step": 1271
+    },
+    {
+      "epoch": 0.019534737173764638,
+      "grad_norm": 1.2499620914459229,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.9499,
+      "step": 1302
+    },
+    {
+      "epoch": 0.019999849963616177,
+      "grad_norm": 1.3684868812561035,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.9499,
+      "step": 1333
+    },
+    {
+      "epoch": 0.020464962753467715,
+      "grad_norm": 1.3685338497161865,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.942,
+      "step": 1364
+    },
+    {
+      "epoch": 0.020930075543319254,
+      "grad_norm": 1.4686026573181152,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.9416,
+      "step": 1395
+    },
+    {
+      "epoch": 0.021395188333170796,
+      "grad_norm": 1.495653510093689,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.9439,
+      "step": 1426
+    },
+    {
+      "epoch": 0.021860301123022334,
+      "grad_norm": 1.2068424224853516,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.9509,
+      "step": 1457
+    },
+    {
+      "epoch": 0.022325413912873873,
+      "grad_norm": 1.6636161804199219,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.9343,
+      "step": 1488
+    },
+    {
+      "epoch": 0.02279052670272541,
+      "grad_norm": 1.2870069742202759,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.9407,
+      "step": 1519
+    },
+    {
+      "epoch": 0.02325563949257695,
+      "grad_norm": 1.5109976530075073,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.9395,
+      "step": 1550
+    },
+    {
+      "epoch": 0.023720752282428488,
+      "grad_norm": 1.5145201683044434,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.9293,
+      "step": 1581
+    },
+    {
+      "epoch": 0.024185865072280027,
+      "grad_norm": 1.4048824310302734,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.929,
+      "step": 1612
+    },
+    {
+      "epoch": 0.02465097786213157,
+      "grad_norm": 1.3233039379119873,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.9169,
+      "step": 1643
+    },
+    {
+      "epoch": 0.025116090651983107,
+      "grad_norm": 1.3225436210632324,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.9301,
+      "step": 1674
+    },
+    {
+      "epoch": 0.025581203441834646,
+      "grad_norm": 1.5295816659927368,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.9245,
+      "step": 1705
+    },
+    {
+      "epoch": 0.026046316231686184,
+      "grad_norm": 1.202820062637329,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.916,
+      "step": 1736
+    },
+    {
+      "epoch": 0.026511429021537723,
+      "grad_norm": 1.0473875999450684,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.9144,
+      "step": 1767
+    },
+    {
+      "epoch": 0.02697654181138926,
+      "grad_norm": 1.1044714450836182,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.9098,
+      "step": 1798
+    },
+    {
+      "epoch": 0.0274416546012408,
+      "grad_norm": 1.2836365699768066,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.9127,
+      "step": 1829
+    },
+    {
+      "epoch": 0.02790676739109234,
+      "grad_norm": 1.2214583158493042,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.9075,
+      "step": 1860
+    },
+    {
+      "epoch": 0.02837188018094388,
+      "grad_norm": 1.2603243589401245,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.8953,
+      "step": 1891
+    },
+    {
+      "epoch": 0.02883699297079542,
+      "grad_norm": 1.2945584058761597,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.903,
+      "step": 1922
+    },
+    {
+      "epoch": 0.029302105760646957,
+      "grad_norm": 1.0437217950820923,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.9013,
+      "step": 1953
+    },
+    {
+      "epoch": 0.029767218550498496,
+      "grad_norm": 1.5020360946655273,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.9078,
+      "step": 1984
+    },
+    {
+      "epoch": 0.030232331340350034,
+      "grad_norm": 1.097151517868042,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.9061,
+      "step": 2015
+    },
+    {
+      "epoch": 0.030697444130201573,
+      "grad_norm": 1.043756365776062,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.9005,
+      "step": 2046
+    },
+    {
+      "epoch": 0.031162556920053115,
+      "grad_norm": 1.3543506860733032,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.9024,
+      "step": 2077
+    },
+    {
+      "epoch": 0.03162766970990465,
+      "grad_norm": 2.175954818725586,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.89,
+      "step": 2108
+    },
+    {
+      "epoch": 0.03209278249975619,
+      "grad_norm": 3.4427719116210938,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.9204,
+      "step": 2139
+    },
+    {
+      "epoch": 0.03255789528960773,
+      "grad_norm": 4.699759006500244,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.9871,
+      "step": 2170
+    },
+    {
+      "epoch": 0.03302300807945927,
+      "grad_norm": 16.819217681884766,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.9176,
+      "step": 2201
+    },
+    {
+      "epoch": 0.03348812086931081,
+      "grad_norm": 3.4251508712768555,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.9154,
+      "step": 2232
+    },
+    {
+      "epoch": 0.03395323365916235,
+      "grad_norm": 1.1965570449829102,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.9446,
+      "step": 2263
+    },
+    {
+      "epoch": 0.034418346449013884,
+      "grad_norm": 5.077923774719238,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.9097,
+      "step": 2294
+    },
+    {
+      "epoch": 0.034883459238865426,
+      "grad_norm": 1.3503797054290771,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.9086,
+      "step": 2325
+    },
+    {
+      "epoch": 0.03534857202871696,
+      "grad_norm": 19.319576263427734,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.9072,
+      "step": 2356
+    },
+    {
+      "epoch": 0.0358136848185685,
+      "grad_norm": 1.2770804166793823,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.9093,
+      "step": 2387
+    },
+    {
+      "epoch": 0.036278797608420045,
+      "grad_norm": 1.0560117959976196,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.9032,
+      "step": 2418
+    },
+    {
+      "epoch": 0.03674391039827158,
+      "grad_norm": 1.1471630334854126,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.9002,
+      "step": 2449
+    },
+    {
+      "epoch": 0.03720902318812312,
+      "grad_norm": 1.1387799978256226,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.8875,
+      "step": 2480
+    },
+    {
+      "epoch": 0.03767413597797466,
+      "grad_norm": 2.4223828315734863,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.891,
+      "step": 2511
+    },
+    {
+      "epoch": 0.0381392487678262,
+      "grad_norm": 1.2967392206192017,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.8886,
+      "step": 2542
+    },
+    {
+      "epoch": 0.038604361557677734,
+      "grad_norm": 1.3206738233566284,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.8888,
+      "step": 2573
+    },
+    {
+      "epoch": 0.039069474347529276,
+      "grad_norm": 1.1495088338851929,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.8853,
+      "step": 2604
+    },
+    {
+      "epoch": 0.03953458713738082,
+      "grad_norm": 1.116990089416504,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.8776,
+      "step": 2635
+    },
+    {
+      "epoch": 0.03999969992723235,
+      "grad_norm": 1.0922496318817139,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.8921,
+      "step": 2666
+    },
+    {
+      "epoch": 0.040464812717083895,
+      "grad_norm": 1.0340460538864136,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.8782,
+      "step": 2697
+    },
+    {
+      "epoch": 0.04092992550693543,
+      "grad_norm": 1.066490888595581,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.8945,
+      "step": 2728
+    },
+    {
+      "epoch": 0.04139503829678697,
+      "grad_norm": 0.9310857057571411,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.8791,
+      "step": 2759
+    },
+    {
+      "epoch": 0.04186015108663851,
+      "grad_norm": 1.0934898853302002,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.8802,
+      "step": 2790
+    },
+    {
+      "epoch": 0.04232526387649005,
+      "grad_norm": 1.0999833345413208,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.8742,
+      "step": 2821
+    },
+    {
+      "epoch": 0.04279037666634159,
+      "grad_norm": 1.1188342571258545,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.8793,
+      "step": 2852
+    },
+    {
+      "epoch": 0.043255489456193126,
+      "grad_norm": 3.3688652515411377,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.8777,
+      "step": 2883
+    },
+    {
+      "epoch": 0.04372060224604467,
+      "grad_norm": 1.2814080715179443,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.8654,
+      "step": 2914
+    },
+    {
+      "epoch": 0.0441857150358962,
+      "grad_norm": 0.9839452505111694,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.8662,
+      "step": 2945
+    },
+    {
+      "epoch": 0.044650827825747745,
+      "grad_norm": 1.0929216146469116,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.8709,
+      "step": 2976
+    },
+    {
+      "epoch": 0.04511594061559928,
+      "grad_norm": 1.228953242301941,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.8618,
+      "step": 3007
+    },
+    {
+      "epoch": 0.04558105340545082,
+      "grad_norm": 0.9897522926330566,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.8671,
+      "step": 3038
+    },
+    {
+      "epoch": 0.046046166195302364,
+      "grad_norm": 1.0972915887832642,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.8629,
+      "step": 3069
+    },
+    {
+      "epoch": 0.0465112789851539,
+      "grad_norm": 1.1006323099136353,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.8613,
+      "step": 3100
+    },
+    {
+      "epoch": 0.04697639177500544,
+      "grad_norm": 1.2656612396240234,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.8852,
+      "step": 3131
+    },
+    {
+      "epoch": 0.047441504564856976,
+      "grad_norm": 0.9964312314987183,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.8767,
+      "step": 3162
+    },
+    {
+      "epoch": 0.04790661735470852,
+      "grad_norm": 0.9271666407585144,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.8542,
+      "step": 3193
+    },
+    {
+      "epoch": 0.04837173014456005,
+      "grad_norm": 1.241882562637329,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.8578,
+      "step": 3224
+    },
+    {
+      "epoch": 0.048836842934411595,
+      "grad_norm": 0.9396510720252991,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.8645,
+      "step": 3255
+    },
+    {
+      "epoch": 0.04930195572426314,
+      "grad_norm": 0.987626850605011,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.8613,
+      "step": 3286
+    },
+    {
+      "epoch": 0.04976706851411467,
+      "grad_norm": 0.9133639931678772,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.8601,
+      "step": 3317
+    },
+    {
+      "epoch": 0.050232181303966214,
+      "grad_norm": 0.784701943397522,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.849,
+      "step": 3348
+    },
+    {
+      "epoch": 0.05069729409381775,
+      "grad_norm": 0.9144874811172485,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.8591,
+      "step": 3379
+    },
+    {
+      "epoch": 0.05116240688366929,
+      "grad_norm": 0.8831948041915894,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.8579,
+      "step": 3410
+    },
+    {
+      "epoch": 0.051627519673520826,
+      "grad_norm": 0.9127451181411743,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.8632,
+      "step": 3441
+    },
+    {
+      "epoch": 0.05209263246337237,
+      "grad_norm": 0.939115047454834,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.8526,
+      "step": 3472
+    },
+    {
+      "epoch": 0.05255774525322391,
+      "grad_norm": 0.9380930066108704,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.8684,
+      "step": 3503
+    },
+    {
+      "epoch": 0.053022858043075445,
+      "grad_norm": 0.9686013460159302,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.8443,
+      "step": 3534
+    },
+    {
+      "epoch": 0.05348797083292699,
+      "grad_norm": 1.1282305717468262,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.8612,
+      "step": 3565
+    },
+    {
+      "epoch": 0.05395308362277852,
+      "grad_norm": 0.9129716753959656,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.8535,
+      "step": 3596
+    },
+    {
+      "epoch": 0.054418196412630064,
+      "grad_norm": 1.0998603105545044,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.8578,
+      "step": 3627
+    },
+    {
+      "epoch": 0.0548833092024816,
+      "grad_norm": 0.9199731945991516,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.8487,
+      "step": 3658
+    },
+    {
+      "epoch": 0.05534842199233314,
+      "grad_norm": 0.8940901160240173,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.8438,
+      "step": 3689
+    },
+    {
+      "epoch": 0.05581353478218468,
+      "grad_norm": 0.7387672066688538,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.848,
+      "step": 3720
+    },
+    {
+      "epoch": 0.05627864757203622,
+      "grad_norm": 1.0379717350006104,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.8433,
+      "step": 3751
+    },
+    {
+      "epoch": 0.05674376036188776,
+      "grad_norm": 1.020926594734192,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.8505,
+      "step": 3782
+    },
+    {
+      "epoch": 0.057208873151739295,
+      "grad_norm": 0.9726930856704712,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.8533,
+      "step": 3813
+    },
+    {
+      "epoch": 0.05767398594159084,
+      "grad_norm": 2.112886905670166,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.8416,
+      "step": 3844
+    },
+    {
+      "epoch": 0.05813909873144237,
+      "grad_norm": 0.9767888188362122,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.8453,
+      "step": 3875
+    },
+    {
+      "epoch": 0.058604211521293914,
+      "grad_norm": 1.101620078086853,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.8509,
+      "step": 3906
+    },
+    {
+      "epoch": 0.059069324311145456,
+      "grad_norm": 0.8144866824150085,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.847,
+      "step": 3937
+    },
+    {
+      "epoch": 0.05953443710099699,
+      "grad_norm": 0.9438722729682922,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.8319,
+      "step": 3968
+    },
+    {
+      "epoch": 0.05999954989084853,
+      "grad_norm": 1.0541943311691284,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.838,
+      "step": 3999
+    },
+    {
+      "epoch": 0.06046466268070007,
+      "grad_norm": 0.9656486511230469,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.8334,
+      "step": 4030
+    },
+    {
+      "epoch": 0.06092977547055161,
+      "grad_norm": 0.8693748116493225,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.8332,
+      "step": 4061
+    },
+    {
+      "epoch": 0.061394888260403145,
+      "grad_norm": 0.8312646746635437,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.8364,
+      "step": 4092
+    },
+    {
+      "epoch": 0.06186000105025469,
+      "grad_norm": 0.9871633648872375,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.8344,
+      "step": 4123
+    },
+    {
+      "epoch": 0.06232511384010623,
+      "grad_norm": 1.1861239671707153,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.8386,
+      "step": 4154
+    },
+    {
+      "epoch": 0.06279022662995777,
+      "grad_norm": 0.7850369215011597,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.8361,
+      "step": 4185
+    },
+    {
+      "epoch": 0.0632553394198093,
+      "grad_norm": 0.888320803642273,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.8309,
+      "step": 4216
+    },
+    {
+      "epoch": 0.06372045220966084,
+      "grad_norm": 1.0985304117202759,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.8289,
+      "step": 4247
+    },
+    {
+      "epoch": 0.06418556499951238,
+      "grad_norm": 0.980798065662384,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.8232,
+      "step": 4278
+    },
+    {
+      "epoch": 0.06465067778936393,
+      "grad_norm": 0.7904775142669678,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.8253,
+      "step": 4309
+    },
+    {
+      "epoch": 0.06511579057921546,
+      "grad_norm": 0.9444935321807861,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.8409,
+      "step": 4340
+    },
+    {
+      "epoch": 0.065580903369067,
+      "grad_norm": 0.9295307993888855,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.8429,
+      "step": 4371
+    },
+    {
+      "epoch": 0.06604601615891854,
+      "grad_norm": 0.9563235640525818,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.8203,
+      "step": 4402
+    },
+    {
+      "epoch": 0.06651112894877008,
+      "grad_norm": 0.7902786135673523,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.823,
+      "step": 4433
+    },
+    {
+      "epoch": 0.06697624173862161,
+      "grad_norm": 0.9005814790725708,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.8262,
+      "step": 4464
+    },
+    {
+      "epoch": 0.06744135452847315,
+      "grad_norm": 0.9644972085952759,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.8505,
+      "step": 4495
+    },
+    {
+      "epoch": 0.0679064673183247,
+      "grad_norm": 0.8087597489356995,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.8303,
+      "step": 4526
+    },
+    {
+      "epoch": 0.06837158010817623,
+      "grad_norm": 1.06015145778656,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.841,
+      "step": 4557
+    },
+    {
+      "epoch": 0.06883669289802777,
+      "grad_norm": 0.9413964152336121,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.8297,
+      "step": 4588
+    },
+    {
+      "epoch": 0.06930180568787932,
+      "grad_norm": 0.7894837260246277,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.8313,
+      "step": 4619
+    },
+    {
+      "epoch": 0.06976691847773085,
+      "grad_norm": 1.7959920167922974,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.8343,
+      "step": 4650
+    },
+    {
+      "epoch": 0.07023203126758239,
+      "grad_norm": 0.9917001128196716,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.8324,
+      "step": 4681
+    },
+    {
+      "epoch": 0.07069714405743392,
+      "grad_norm": 0.8763757944107056,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.8245,
+      "step": 4712
+    },
+    {
+      "epoch": 0.07116225684728547,
+      "grad_norm": 0.7827804684638977,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.8135,
+      "step": 4743
+    },
+    {
+      "epoch": 0.071627369637137,
+      "grad_norm": 0.7496729493141174,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.8218,
+      "step": 4774
+    },
+    {
+      "epoch": 0.07209248242698854,
+      "grad_norm": 0.9856346249580383,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.8206,
+      "step": 4805
+    },
+    {
+      "epoch": 0.07255759521684009,
+      "grad_norm": 0.8173674941062927,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.8174,
+      "step": 4836
+    },
+    {
+      "epoch": 0.07302270800669163,
+      "grad_norm": 0.943686842918396,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.8297,
+      "step": 4867
+    },
+    {
+      "epoch": 0.07348782079654316,
+      "grad_norm": 0.8119473457336426,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.8255,
+      "step": 4898
+    },
+    {
+      "epoch": 0.0739529335863947,
+      "grad_norm": 2.7093794345855713,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.8145,
+      "step": 4929
+    },
+    {
+      "epoch": 0.07441804637624624,
+      "grad_norm": 0.9842637777328491,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.8116,
+      "step": 4960
+    },
+    {
+      "epoch": 0.07488315916609778,
+      "grad_norm": 0.9502723813056946,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.8222,
+      "step": 4991
+    },
+    {
+      "epoch": 0.07534827195594931,
+      "grad_norm": 0.8006568551063538,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.8303,
+      "step": 5022
+    },
+    {
+      "epoch": 0.07581338474580086,
+      "grad_norm": 0.7108177542686462,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.8202,
+      "step": 5053
+    },
+    {
+      "epoch": 0.0762784975356524,
+      "grad_norm": 0.7464533448219299,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.8035,
+      "step": 5084
+    },
+    {
+      "epoch": 0.07674361032550393,
+      "grad_norm": 0.815014123916626,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.8161,
+      "step": 5115
+    },
+    {
+      "epoch": 0.07720872311535547,
+      "grad_norm": 0.8991546034812927,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.8013,
+      "step": 5146
+    },
+    {
+      "epoch": 0.07767383590520702,
+      "grad_norm": 1.0259745121002197,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.8069,
+      "step": 5177
+    },
+    {
+      "epoch": 0.07813894869505855,
+      "grad_norm": 0.8683953285217285,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.8053,
+      "step": 5208
+    },
+    {
+      "epoch": 0.07860406148491009,
+      "grad_norm": 0.6831669211387634,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.8183,
+      "step": 5239
+    },
+    {
+      "epoch": 0.07906917427476164,
+      "grad_norm": 1.005091667175293,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.8145,
+      "step": 5270
+    },
+    {
+      "epoch": 0.07953428706461317,
+      "grad_norm": 1.0526143312454224,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.8179,
+      "step": 5301
+    },
+    {
+      "epoch": 0.0799993998544647,
+      "grad_norm": 0.9000487327575684,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.8191,
+      "step": 5332
+    },
+    {
+      "epoch": 0.08046451264431624,
+      "grad_norm": 0.7542000412940979,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.8129,
+      "step": 5363
+    },
+    {
+      "epoch": 0.08092962543416779,
+      "grad_norm": 0.7871935963630676,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.8008,
+      "step": 5394
+    },
+    {
+      "epoch": 0.08139473822401933,
+      "grad_norm": 0.9389820098876953,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.8084,
+      "step": 5425
+    },
+    {
+      "epoch": 0.08185985101387086,
+      "grad_norm": 0.8348682522773743,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.8098,
+      "step": 5456
+    },
+    {
+      "epoch": 0.08232496380372241,
+      "grad_norm": 0.7959926724433899,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.8092,
+      "step": 5487
+    },
+    {
+      "epoch": 0.08279007659357394,
+      "grad_norm": 0.8719795346260071,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.812,
+      "step": 5518
+    },
+    {
+      "epoch": 0.08325518938342548,
+      "grad_norm": 0.7396957278251648,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.8052,
+      "step": 5549
+    },
+    {
+      "epoch": 0.08372030217327701,
+      "grad_norm": 0.7120716571807861,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.8198,
+      "step": 5580
+    },
+    {
+      "epoch": 0.08418541496312856,
+      "grad_norm": 0.6915568113327026,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.8167,
+      "step": 5611
+    },
+    {
+      "epoch": 0.0846505277529801,
+      "grad_norm": 0.7923029661178589,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.8102,
+      "step": 5642
+    },
+    {
+      "epoch": 0.08511564054283163,
+      "grad_norm": 0.9134017825126648,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.8044,
+      "step": 5673
+    },
+    {
+      "epoch": 0.08558075333268318,
+      "grad_norm": 0.6910101771354675,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.8033,
+      "step": 5704
+    },
+    {
+      "epoch": 0.08604586612253472,
+      "grad_norm": 1.0083701610565186,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.7984,
+      "step": 5735
+    },
+    {
+      "epoch": 0.08651097891238625,
+      "grad_norm": 0.7578200697898865,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.8028,
+      "step": 5766
+    },
+    {
+      "epoch": 0.08697609170223779,
+      "grad_norm": 0.6932199001312256,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.7913,
+      "step": 5797
+    },
+    {
+      "epoch": 0.08744120449208934,
+      "grad_norm": 0.8898211717605591,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.8087,
+      "step": 5828
+    },
+    {
+      "epoch": 0.08790631728194087,
+      "grad_norm": 0.8452892303466797,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.798,
+      "step": 5859
+    },
+    {
+      "epoch": 0.0883714300717924,
+      "grad_norm": 0.7200170159339905,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.8033,
+      "step": 5890
+    },
+    {
+      "epoch": 0.08883654286164396,
+      "grad_norm": 0.9801698923110962,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.801,
+      "step": 5921
+    },
+    {
+      "epoch": 0.08930165565149549,
+      "grad_norm": 0.6971285939216614,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.8004,
+      "step": 5952
+    },
+    {
+      "epoch": 0.08976676844134703,
+      "grad_norm": 0.6692901253700256,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.8079,
+      "step": 5983
+    },
+    {
+      "epoch": 0.09023188123119856,
+      "grad_norm": 0.7357479929924011,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.8047,
+      "step": 6014
+    },
+    {
+      "epoch": 0.09069699402105011,
+      "grad_norm": 0.9808568358421326,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.7943,
+      "step": 6045
+    },
+    {
+      "epoch": 0.09116210681090164,
+      "grad_norm": 0.8038450479507446,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.7962,
+      "step": 6076
+    },
+    {
+      "epoch": 0.09162721960075318,
+      "grad_norm": 1.1002798080444336,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.8133,
+      "step": 6107
+    },
+    {
+      "epoch": 0.09209233239060473,
+      "grad_norm": 0.8928295373916626,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.7968,
+      "step": 6138
+    },
+    {
+      "epoch": 0.09255744518045626,
+      "grad_norm": 0.8596677184104919,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.8087,
+      "step": 6169
+    },
+    {
+      "epoch": 0.0930225579703078,
+      "grad_norm": 1.0481047630310059,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.7874,
+      "step": 6200
+    },
+    {
+      "epoch": 0.09348767076015933,
+      "grad_norm": 0.7633193731307983,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.7945,
+      "step": 6231
+    },
+    {
+      "epoch": 0.09395278355001088,
+      "grad_norm": 0.6666761040687561,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.7999,
+      "step": 6262
+    },
+    {
+      "epoch": 0.09441789633986242,
+      "grad_norm": 0.7834581732749939,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.8004,
+      "step": 6293
+    },
+    {
+      "epoch": 0.09488300912971395,
+      "grad_norm": 0.8548229932785034,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.7983,
+      "step": 6324
+    },
+    {
+      "epoch": 0.0953481219195655,
+      "grad_norm": 0.8321638703346252,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.8103,
+      "step": 6355
+    },
+    {
+      "epoch": 0.09581323470941704,
+      "grad_norm": 0.8134599924087524,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.8042,
+      "step": 6386
+    },
+    {
+      "epoch": 0.09627834749926857,
+      "grad_norm": 0.9421968460083008,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.8028,
+      "step": 6417
+    },
+    {
+      "epoch": 0.0967434602891201,
+      "grad_norm": 0.6998574137687683,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.809,
+      "step": 6448
+    },
+    {
+      "epoch": 0.09720857307897166,
+      "grad_norm": 0.7347880005836487,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.8115,
+      "step": 6479
+    },
+    {
+      "epoch": 0.09767368586882319,
+      "grad_norm": 0.8895875811576843,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.8023,
+      "step": 6510
+    },
+    {
+      "epoch": 0.09813879865867473,
+      "grad_norm": 0.588324785232544,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.7958,
+      "step": 6541
+    },
+    {
+      "epoch": 0.09860391144852627,
+      "grad_norm": 0.8145986199378967,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.8018,
+      "step": 6572
+    },
+    {
+      "epoch": 0.09906902423837781,
+      "grad_norm": 0.659679651260376,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.7904,
+      "step": 6603
+    },
+    {
+      "epoch": 0.09953413702822934,
+      "grad_norm": 0.7664335370063782,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.7953,
+      "step": 6634
+    },
+    {
+      "epoch": 0.09999924981808088,
+      "grad_norm": 0.630374550819397,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.7834,
+      "step": 6665
+    },
+    {
+      "epoch": 0.10046436260793243,
+      "grad_norm": 0.8089181780815125,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.7939,
+      "step": 6696
+    },
+    {
+      "epoch": 0.10092947539778396,
+      "grad_norm": 0.7410175204277039,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.7997,
+      "step": 6727
+    },
+    {
+      "epoch": 0.1013945881876355,
+      "grad_norm": 0.8867741823196411,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.7876,
+      "step": 6758
+    },
+    {
+      "epoch": 0.10185970097748705,
+      "grad_norm": 0.8592618107795715,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.7915,
+      "step": 6789
+    },
+    {
+      "epoch": 0.10232481376733858,
+      "grad_norm": 0.7498304843902588,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.7953,
+      "step": 6820
+    },
+    {
+      "epoch": 0.10278992655719012,
+      "grad_norm": 0.7439833879470825,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.7932,
+      "step": 6851
+    },
+    {
+      "epoch": 0.10325503934704165,
+      "grad_norm": 0.7184897065162659,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.7905,
+      "step": 6882
+    },
+    {
+      "epoch": 0.1037201521368932,
+      "grad_norm": 0.7455788254737854,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.7822,
+      "step": 6913
+    },
+    {
+      "epoch": 0.10418526492674474,
+      "grad_norm": 0.7429169416427612,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.7895,
+      "step": 6944
+    },
+    {
+      "epoch": 0.10465037771659627,
+      "grad_norm": 0.708569347858429,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.7922,
+      "step": 6975
+    },
+    {
+      "epoch": 0.10511549050644782,
+      "grad_norm": 0.6906721591949463,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.7932,
+      "step": 7006
+    },
+    {
+      "epoch": 0.10558060329629936,
+      "grad_norm": 0.7495471835136414,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.7849,
+      "step": 7037
+    },
+    {
+      "epoch": 0.10604571608615089,
+      "grad_norm": 0.7219502329826355,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.7842,
+      "step": 7068
+    },
+    {
+      "epoch": 0.10651082887600243,
+      "grad_norm": 0.7211415767669678,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.7822,
+      "step": 7099
+    },
+    {
+      "epoch": 0.10697594166585397,
+      "grad_norm": 0.7900408506393433,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.7956,
+      "step": 7130
+    },
+    {
+      "epoch": 0.10744105445570551,
+      "grad_norm": 0.8071913123130798,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.7884,
+      "step": 7161
+    },
+    {
+      "epoch": 0.10790616724555704,
+      "grad_norm": 0.6667525172233582,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.7815,
+      "step": 7192
+    },
+    {
+      "epoch": 0.1083712800354086,
+      "grad_norm": 0.8470203280448914,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.793,
+      "step": 7223
+    },
+    {
+      "epoch": 0.10883639282526013,
+      "grad_norm": 0.7718335390090942,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.787,
+      "step": 7254
+    },
+    {
+      "epoch": 0.10930150561511166,
+      "grad_norm": 0.67174232006073,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.7859,
+      "step": 7285
+    },
+    {
+      "epoch": 0.1097666184049632,
+      "grad_norm": 0.9030664563179016,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.785,
+      "step": 7316
+    },
+    {
+      "epoch": 0.11023173119481475,
+      "grad_norm": 0.6775389313697815,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.7835,
+      "step": 7347
+    },
+    {
+      "epoch": 0.11069684398466628,
+      "grad_norm": 0.6373648643493652,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.7816,
+      "step": 7378
+    },
+    {
+      "epoch": 0.11116195677451782,
+      "grad_norm": 0.7260624170303345,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.7878,
+      "step": 7409
+    },
+    {
+      "epoch": 0.11162706956436937,
+      "grad_norm": 0.7170141935348511,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.7754,
+      "step": 7440
+    },
+    {
+      "epoch": 0.1120921823542209,
+      "grad_norm": 0.7276513576507568,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.7854,
+      "step": 7471
+    },
+    {
+      "epoch": 0.11255729514407244,
+      "grad_norm": 0.7349756956100464,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.791,
+      "step": 7502
+    },
+    {
+      "epoch": 0.11302240793392397,
+      "grad_norm": 0.8739349246025085,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.7926,
+      "step": 7533
+    },
+    {
+      "epoch": 0.11348752072377552,
+      "grad_norm": 0.7612133622169495,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.7954,
+      "step": 7564
+    },
+    {
+      "epoch": 0.11395263351362706,
+      "grad_norm": 0.7819641828536987,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.7813,
+      "step": 7595
+    },
+    {
+      "epoch": 0.11441774630347859,
+      "grad_norm": 0.789462685585022,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.7982,
+      "step": 7626
+    },
+    {
+      "epoch": 0.11488285909333014,
+      "grad_norm": 0.677481472492218,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.778,
+      "step": 7657
+    },
+    {
+      "epoch": 0.11534797188318167,
+      "grad_norm": 0.8899239301681519,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.7841,
+      "step": 7688
+    },
+    {
+      "epoch": 0.11581308467303321,
+      "grad_norm": 0.9114879369735718,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.7962,
+      "step": 7719
+    },
+    {
+      "epoch": 0.11627819746288474,
+      "grad_norm": 0.7342079877853394,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.784,
+      "step": 7750
+    },
+    {
+      "epoch": 0.1167433102527363,
+      "grad_norm": 0.7678495049476624,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.7831,
+      "step": 7781
+    },
+    {
+      "epoch": 0.11720842304258783,
+      "grad_norm": 0.8216970562934875,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.7782,
+      "step": 7812
+    },
+    {
+      "epoch": 0.11767353583243936,
+      "grad_norm": 0.8297589421272278,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.7851,
+      "step": 7843
+    },
+    {
+      "epoch": 0.11813864862229091,
+      "grad_norm": 0.6707519292831421,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.7801,
+      "step": 7874
+    },
+    {
+      "epoch": 0.11860376141214245,
+      "grad_norm": 0.6816626787185669,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.7872,
+      "step": 7905
+    },
+    {
+      "epoch": 0.11906887420199398,
+      "grad_norm": 0.9005252122879028,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.7936,
+      "step": 7936
+    },
+    {
+      "epoch": 0.11953398699184552,
+      "grad_norm": 0.8328778147697449,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.7786,
+      "step": 7967
+    },
+    {
+      "epoch": 0.11999909978169707,
+      "grad_norm": 0.8410969376564026,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.7848,
+      "step": 7998
+    },
+    {
+      "epoch": 0.1204642125715486,
+      "grad_norm": 0.7608590722084045,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.7834,
+      "step": 8029
+    },
+    {
+      "epoch": 0.12092932536140014,
+      "grad_norm": 0.8817543983459473,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.7852,
+      "step": 8060
+    },
+    {
+      "epoch": 0.12139443815125169,
+      "grad_norm": 0.7609240412712097,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.7766,
+      "step": 8091
+    },
+    {
+      "epoch": 0.12185955094110322,
+      "grad_norm": 1.1703492403030396,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.7844,
+      "step": 8122
+    },
+    {
+      "epoch": 0.12232466373095476,
+      "grad_norm": 0.7617055773735046,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.7806,
+      "step": 8153
+    },
+    {
+      "epoch": 0.12278977652080629,
+      "grad_norm": 0.7049508690834045,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.7807,
+      "step": 8184
+    },
+    {
+      "epoch": 0.12325488931065784,
+      "grad_norm": 0.7807313203811646,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.7825,
+      "step": 8215
+    },
+    {
+      "epoch": 0.12372000210050937,
+      "grad_norm": 0.9308986067771912,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.7803,
+      "step": 8246
+    },
+    {
+      "epoch": 0.12418511489036091,
+      "grad_norm": 0.7101467251777649,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.7762,
+      "step": 8277
+    },
+    {
+      "epoch": 0.12465022768021246,
+      "grad_norm": 0.6804013252258301,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.7892,
+      "step": 8308
+    },
+    {
+      "epoch": 0.12511534047006398,
+      "grad_norm": 0.6824433207511902,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.7802,
+      "step": 8339
+    },
+    {
+      "epoch": 0.12558045325991554,
+      "grad_norm": 1.468239188194275,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.7869,
+      "step": 8370
+    },
+    {
+      "epoch": 0.12604556604976708,
+      "grad_norm": 0.5719156861305237,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.778,
+      "step": 8401
+    },
+    {
+      "epoch": 0.1265106788396186,
+      "grad_norm": 0.6709131002426147,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.7732,
+      "step": 8432
+    },
+    {
+      "epoch": 0.12697579162947015,
+      "grad_norm": 0.7485822439193726,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.7838,
+      "step": 8463
+    },
+    {
+      "epoch": 0.12744090441932168,
+      "grad_norm": 0.6957044005393982,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.7871,
+      "step": 8494
+    },
+    {
+      "epoch": 0.12790601720917322,
+      "grad_norm": 1.0035358667373657,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.7743,
+      "step": 8525
+    },
+    {
+      "epoch": 0.12837112999902475,
+      "grad_norm": 0.5898587107658386,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.7826,
+      "step": 8556
+    },
+    {
+      "epoch": 0.12883624278887632,
+      "grad_norm": 3.798095226287842,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.7808,
+      "step": 8587
+    },
+    {
+      "epoch": 0.12930135557872785,
+      "grad_norm": 0.6663601398468018,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.7849,
+      "step": 8618
+    },
+    {
+      "epoch": 0.12976646836857939,
+      "grad_norm": 0.7356058955192566,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.7798,
+      "step": 8649
+    },
+    {
+      "epoch": 0.13023158115843092,
+      "grad_norm": 0.6421476006507874,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.7704,
+      "step": 8680
+    },
+    {
+      "epoch": 0.13069669394828246,
+      "grad_norm": 0.5868635177612305,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.7759,
+      "step": 8711
+    },
+    {
+      "epoch": 0.131161806738134,
+      "grad_norm": 0.6703419089317322,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.781,
+      "step": 8742
+    },
+    {
+      "epoch": 0.13162691952798553,
+      "grad_norm": 0.751116931438446,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.768,
+      "step": 8773
+    },
+    {
+      "epoch": 0.1320920323178371,
+      "grad_norm": 0.9944510459899902,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.7783,
+      "step": 8804
+    },
+    {
+      "epoch": 0.13255714510768862,
+      "grad_norm": 0.6739645600318909,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.7745,
+      "step": 8835
+    },
+    {
+      "epoch": 0.13302225789754016,
+      "grad_norm": 0.612147867679596,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.7778,
+      "step": 8866
+    },
+    {
+      "epoch": 0.1334873706873917,
+      "grad_norm": 0.7233457565307617,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.7799,
+      "step": 8897
+    },
+    {
+      "epoch": 0.13395248347724323,
+      "grad_norm": 0.6210694909095764,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.7764,
+      "step": 8928
+    },
+    {
+      "epoch": 0.13441759626709476,
+      "grad_norm": 0.7104094624519348,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.776,
+      "step": 8959
+    },
+    {
+      "epoch": 0.1348827090569463,
+      "grad_norm": 0.6815863251686096,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.7799,
+      "step": 8990
+    },
+    {
+      "epoch": 0.13534782184679786,
+      "grad_norm": 0.660565972328186,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.7856,
+      "step": 9021
+    },
+    {
+      "epoch": 0.1358129346366494,
+      "grad_norm": 0.8271650671958923,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.7758,
+      "step": 9052
+    },
+    {
+      "epoch": 0.13627804742650093,
+      "grad_norm": 0.6217832565307617,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.7736,
+      "step": 9083
+    },
+    {
+      "epoch": 0.13674316021635247,
+      "grad_norm": 0.6582239270210266,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.7765,
+      "step": 9114
+    },
+    {
+      "epoch": 0.137208273006204,
+      "grad_norm": 0.758140504360199,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.7696,
+      "step": 9145
+    },
+    {
+      "epoch": 0.13767338579605554,
+      "grad_norm": 0.7370248436927795,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.7751,
+      "step": 9176
+    },
+    {
+      "epoch": 0.13813849858590707,
+      "grad_norm": 0.667799711227417,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.7686,
+      "step": 9207
+    },
+    {
+      "epoch": 0.13860361137575863,
+      "grad_norm": 0.6749032139778137,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.7656,
+      "step": 9238
+    },
+    {
+      "epoch": 0.13906872416561017,
+      "grad_norm": 0.7389397025108337,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.7733,
+      "step": 9269
+    },
+    {
+      "epoch": 0.1395338369554617,
+      "grad_norm": 0.8019024133682251,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.7704,
+      "step": 9300
+    },
+    {
+      "epoch": 0.13999894974531324,
+      "grad_norm": 0.6880025863647461,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.7745,
+      "step": 9331
+    },
+    {
+      "epoch": 0.14046406253516477,
+      "grad_norm": 0.7543455362319946,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.7616,
+      "step": 9362
+    },
+    {
+      "epoch": 0.1409291753250163,
+      "grad_norm": 0.6550135612487793,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.7698,
+      "step": 9393
+    },
+    {
+      "epoch": 0.14139428811486784,
+      "grad_norm": 0.7469960451126099,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.764,
+      "step": 9424
+    },
+    {
+      "epoch": 0.1418594009047194,
+      "grad_norm": 0.65736323595047,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.7625,
+      "step": 9455
+    },
+    {
+      "epoch": 0.14232451369457094,
+      "grad_norm": 0.7517855167388916,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.7727,
+      "step": 9486
+    },
+    {
+      "epoch": 0.14278962648442248,
+      "grad_norm": 0.5399331450462341,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.7625,
+      "step": 9517
+    },
+    {
+      "epoch": 0.143254739274274,
+      "grad_norm": 0.7568219900131226,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.7629,
+      "step": 9548
+    },
+    {
+      "epoch": 0.14371985206412555,
+      "grad_norm": 0.8380396962165833,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.765,
+      "step": 9579
+    },
+    {
+      "epoch": 0.14418496485397708,
+      "grad_norm": 0.657565176486969,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.7617,
+      "step": 9610
+    },
+    {
+      "epoch": 0.14465007764382862,
+      "grad_norm": 0.784701406955719,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.7662,
+      "step": 9641
+    },
+    {
+      "epoch": 0.14511519043368018,
+      "grad_norm": 0.6358653903007507,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.7668,
+      "step": 9672
+    },
+    {
+      "epoch": 0.14558030322353172,
+      "grad_norm": 0.6734030842781067,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.7587,
+      "step": 9703
+    },
+    {
+      "epoch": 0.14604541601338325,
+      "grad_norm": 0.693668007850647,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.7587,
+      "step": 9734
+    },
+    {
+      "epoch": 0.14651052880323479,
+      "grad_norm": 0.7010748982429504,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.7729,
+      "step": 9765
+    },
+    {
+      "epoch": 0.14697564159308632,
+      "grad_norm": 0.6210809946060181,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.7708,
+      "step": 9796
+    },
+    {
+      "epoch": 0.14744075438293786,
+      "grad_norm": 0.6918211579322815,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.7742,
+      "step": 9827
+    },
+    {
+      "epoch": 0.1479058671727894,
+      "grad_norm": 0.7196410298347473,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.7593,
+      "step": 9858
+    },
+    {
+      "epoch": 0.14837097996264095,
+      "grad_norm": 0.6762074828147888,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.7601,
+      "step": 9889
+    },
+    {
+      "epoch": 0.1488360927524925,
+      "grad_norm": 0.7633680701255798,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.7684,
+      "step": 9920
+    },
+    {
+      "epoch": 0.14930120554234402,
+      "grad_norm": 0.6944717168807983,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.7554,
+      "step": 9951
+    },
+    {
+      "epoch": 0.14976631833219556,
+      "grad_norm": 0.6295722126960754,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.7584,
+      "step": 9982
+    },
+    {
+      "epoch": 0.1502314311220471,
+      "grad_norm": 0.6174144744873047,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.7626,
+      "step": 10013
+    },
+    {
+      "epoch": 0.15069654391189863,
+      "grad_norm": 0.7596246600151062,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.7664,
+      "step": 10044
+    },
+    {
+      "epoch": 0.15116165670175016,
+      "grad_norm": 0.6924237012863159,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.7736,
+      "step": 10075
+    },
+    {
+      "epoch": 0.15162676949160173,
+      "grad_norm": 0.6916103363037109,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.7784,
+      "step": 10106
+    },
+    {
+      "epoch": 0.15209188228145326,
+      "grad_norm": 0.7141834497451782,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.7669,
+      "step": 10137
+    },
+    {
+      "epoch": 0.1525569950713048,
+      "grad_norm": 0.6703450679779053,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.7612,
+      "step": 10168
+    },
+    {
+      "epoch": 0.15302210786115633,
+      "grad_norm": 0.6729284524917603,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.7695,
+      "step": 10199
+    },
+    {
+      "epoch": 0.15348722065100787,
+      "grad_norm": 0.8227813243865967,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.7573,
+      "step": 10230
+    },
+    {
+      "epoch": 0.1539523334408594,
+      "grad_norm": 0.6902511715888977,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.7603,
+      "step": 10261
+    },
+    {
+      "epoch": 0.15441744623071094,
+      "grad_norm": 0.6204094290733337,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.7612,
+      "step": 10292
+    },
+    {
+      "epoch": 0.1548825590205625,
+      "grad_norm": 0.7256117463111877,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.7635,
+      "step": 10323
+    },
+    {
+      "epoch": 0.15534767181041403,
+      "grad_norm": 0.6088977456092834,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.7609,
+      "step": 10354
+    },
+    {
+      "epoch": 0.15581278460026557,
+      "grad_norm": 0.6714738607406616,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.7661,
+      "step": 10385
+    },
+    {
+      "epoch": 0.1562778973901171,
+      "grad_norm": 0.6832950711250305,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.7703,
+      "step": 10416
+    },
+    {
+      "epoch": 0.15674301017996864,
+      "grad_norm": 0.8103564381599426,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.7641,
+      "step": 10447
+    },
+    {
+      "epoch": 0.15720812296982017,
+      "grad_norm": 0.7727939486503601,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.7644,
+      "step": 10478
+    },
+    {
+      "epoch": 0.1576732357596717,
+      "grad_norm": 0.6045538187026978,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.7603,
+      "step": 10509
+    },
+    {
+      "epoch": 0.15813834854952327,
+      "grad_norm": 0.7199150323867798,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.7617,
+      "step": 10540
+    },
+    {
+      "epoch": 0.1586034613393748,
+      "grad_norm": 0.6426290273666382,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.765,
+      "step": 10571
+    },
+    {
+      "epoch": 0.15906857412922634,
+      "grad_norm": 0.6604538559913635,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.7512,
+      "step": 10602
+    },
+    {
+      "epoch": 0.15953368691907788,
+      "grad_norm": 0.6802282333374023,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.7528,
+      "step": 10633
+    },
+    {
+      "epoch": 0.1599987997089294,
+      "grad_norm": 0.5920473337173462,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.7645,
+      "step": 10664
+    },
+    {
+      "epoch": 0.16046391249878095,
+      "grad_norm": 0.70703125,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.7798,
+      "step": 10695
+    },
+    {
+      "epoch": 0.16092902528863248,
+      "grad_norm": 0.7090973258018494,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.7501,
+      "step": 10726
+    },
+    {
+      "epoch": 0.16139413807848405,
+      "grad_norm": 0.6518564820289612,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.7646,
+      "step": 10757
+    },
+    {
+      "epoch": 0.16185925086833558,
+      "grad_norm": 0.7883148789405823,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.7464,
+      "step": 10788
+    },
+    {
+      "epoch": 0.16232436365818712,
+      "grad_norm": 0.701317310333252,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.7629,
+      "step": 10819
+    },
+    {
+      "epoch": 0.16278947644803865,
+      "grad_norm": 0.6755788922309875,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.7524,
+      "step": 10850
+    },
+    {
+      "epoch": 0.16325458923789019,
+      "grad_norm": 0.7258623242378235,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.7681,
+      "step": 10881
+    },
+    {
+      "epoch": 0.16371970202774172,
+      "grad_norm": 0.678916871547699,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.7572,
+      "step": 10912
+    },
+    {
+      "epoch": 0.16418481481759326,
+      "grad_norm": 0.6140801906585693,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.7573,
+      "step": 10943
+    },
+    {
+      "epoch": 0.16464992760744482,
+      "grad_norm": 0.8363719582557678,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.7541,
+      "step": 10974
+    },
+    {
+      "epoch": 0.16511504039729635,
+      "grad_norm": 0.8430968523025513,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.7621,
+      "step": 11005
+    },
+    {
+      "epoch": 0.1655801531871479,
+      "grad_norm": 0.7111339569091797,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.7581,
+      "step": 11036
+    },
+    {
+      "epoch": 0.16604526597699942,
+      "grad_norm": 0.6369599103927612,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.7543,
+      "step": 11067
+    },
+    {
+      "epoch": 0.16651037876685096,
+      "grad_norm": 0.6842892169952393,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.7599,
+      "step": 11098
+    },
+    {
+      "epoch": 0.1669754915567025,
+      "grad_norm": 0.6923761963844299,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.762,
+      "step": 11129
+    },
+    {
+      "epoch": 0.16744060434655403,
+      "grad_norm": 0.7744085788726807,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.748,
+      "step": 11160
+    },
+    {
+      "epoch": 0.1679057171364056,
+      "grad_norm": 0.6975285410881042,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.7518,
+      "step": 11191
+    },
+    {
+      "epoch": 0.16837082992625713,
+      "grad_norm": 0.5738661289215088,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.7508,
+      "step": 11222
+    },
+    {
+      "epoch": 0.16883594271610866,
+      "grad_norm": 0.5840383172035217,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.7591,
+      "step": 11253
+    },
+    {
+      "epoch": 0.1693010555059602,
+      "grad_norm": 0.7805384397506714,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.7519,
+      "step": 11284
+    },
+    {
+      "epoch": 0.16976616829581173,
+      "grad_norm": 0.7086957693099976,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.7638,
+      "step": 11315
+    },
+    {
+      "epoch": 0.17023128108566327,
+      "grad_norm": 0.7142307758331299,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.7489,
+      "step": 11346
+    },
+    {
+      "epoch": 0.1706963938755148,
+      "grad_norm": 0.6033651232719421,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.762,
+      "step": 11377
+    },
+    {
+      "epoch": 0.17116150666536636,
+      "grad_norm": 0.6250593066215515,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.7552,
+      "step": 11408
+    },
+    {
+      "epoch": 0.1716266194552179,
+      "grad_norm": 0.6813081502914429,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.7556,
+      "step": 11439
+    },
+    {
+      "epoch": 0.17209173224506943,
+      "grad_norm": 0.8393754363059998,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.7569,
+      "step": 11470
+    },
+    {
+      "epoch": 0.17255684503492097,
+      "grad_norm": 1.5094987154006958,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.7561,
+      "step": 11501
+    },
+    {
+      "epoch": 0.1730219578247725,
+      "grad_norm": 0.631462037563324,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.7558,
+      "step": 11532
+    },
+    {
+      "epoch": 0.17348707061462404,
+      "grad_norm": 0.7486265897750854,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.7569,
+      "step": 11563
+    },
+    {
+      "epoch": 0.17395218340447557,
+      "grad_norm": 0.9510587453842163,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.7503,
+      "step": 11594
+    },
+    {
+      "epoch": 0.17441729619432714,
+      "grad_norm": 0.5841720700263977,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.7555,
+      "step": 11625
+    },
+    {
+      "epoch": 0.17488240898417867,
+      "grad_norm": 0.5946236848831177,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.7484,
+      "step": 11656
+    },
+    {
+      "epoch": 0.1753475217740302,
+      "grad_norm": 0.8158132433891296,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.748,
+      "step": 11687
+    },
+    {
+      "epoch": 0.17581263456388174,
+      "grad_norm": 0.6327953338623047,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.7611,
+      "step": 11718
+    },
+    {
+      "epoch": 0.17627774735373328,
+      "grad_norm": 0.7370153069496155,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.7495,
+      "step": 11749
+    },
+    {
+      "epoch": 0.1767428601435848,
+      "grad_norm": 0.911038875579834,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.7604,
+      "step": 11780
+    },
+    {
+      "epoch": 0.17720797293343635,
+      "grad_norm": 0.7187597751617432,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.7448,
+      "step": 11811
+    },
+    {
+      "epoch": 0.1776730857232879,
+      "grad_norm": 0.6611767411231995,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.7486,
+      "step": 11842
+    },
+    {
+      "epoch": 0.17813819851313945,
+      "grad_norm": 0.725936770439148,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.7585,
+      "step": 11873
+    },
+    {
+      "epoch": 0.17860331130299098,
+      "grad_norm": 0.7662620544433594,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.7489,
+      "step": 11904
+    },
+    {
+      "epoch": 0.17906842409284252,
+      "grad_norm": 0.7236283421516418,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.7571,
+      "step": 11935
+    },
+    {
+      "epoch": 0.17953353688269405,
+      "grad_norm": 0.7157570123672485,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.7524,
+      "step": 11966
+    },
+    {
+      "epoch": 0.17999864967254559,
+      "grad_norm": 0.7178536653518677,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.7592,
+      "step": 11997
+    },
+    {
+      "epoch": 0.18046376246239712,
+      "grad_norm": 0.5687118768692017,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.7485,
+      "step": 12028
+    },
+    {
+      "epoch": 0.18092887525224868,
+      "grad_norm": 0.853602409362793,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.7578,
+      "step": 12059
+    },
+    {
+      "epoch": 0.18139398804210022,
+      "grad_norm": 0.7728062272071838,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.7463,
+      "step": 12090
+    },
+    {
+      "epoch": 0.18185910083195175,
+      "grad_norm": 0.6808280348777771,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.7513,
+      "step": 12121
+    },
+    {
+      "epoch": 0.1823242136218033,
+      "grad_norm": 0.730434775352478,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.7459,
+      "step": 12152
+    },
+    {
+      "epoch": 0.18278932641165482,
+      "grad_norm": 0.7605392336845398,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.7428,
+      "step": 12183
+    },
+    {
+      "epoch": 0.18325443920150636,
+      "grad_norm": 0.6910775303840637,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 0.7433,
+      "step": 12214
+    },
+    {
+      "epoch": 0.1837195519913579,
+      "grad_norm": 0.7537398338317871,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 0.7492,
+      "step": 12245
+    },
+    {
+      "epoch": 0.18418466478120946,
+      "grad_norm": 6.885498523712158,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 0.7657,
+      "step": 12276
+    },
+    {
+      "epoch": 0.184649777571061,
+      "grad_norm": 0.7328066229820251,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 0.7481,
+      "step": 12307
+    },
+    {
+      "epoch": 0.18511489036091253,
+      "grad_norm": 0.7026427388191223,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 0.7496,
+      "step": 12338
+    },
+    {
+      "epoch": 0.18558000315076406,
+      "grad_norm": 0.6714969277381897,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 0.753,
+      "step": 12369
+    },
+    {
+      "epoch": 0.1860451159406156,
+      "grad_norm": 0.6818881034851074,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 0.7481,
+      "step": 12400
+    },
+    {
+      "epoch": 0.18651022873046713,
+      "grad_norm": 0.752812385559082,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 0.7499,
+      "step": 12431
+    },
+    {
+      "epoch": 0.18697534152031867,
+      "grad_norm": 0.6960272789001465,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 0.7439,
+      "step": 12462
+    },
+    {
+      "epoch": 0.18744045431017023,
+      "grad_norm": 0.6496702432632446,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 0.7501,
+      "step": 12493
+    },
+    {
+      "epoch": 0.18790556710002176,
+      "grad_norm": 0.5779111981391907,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 0.7529,
+      "step": 12524
+    },
+    {
+      "epoch": 0.1883706798898733,
+      "grad_norm": 0.9846493601799011,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 0.7523,
+      "step": 12555
+    },
+    {
+      "epoch": 0.18883579267972483,
+      "grad_norm": 0.7048613429069519,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 0.7448,
+      "step": 12586
+    },
+    {
+      "epoch": 0.18930090546957637,
+      "grad_norm": 0.7556883096694946,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 0.7452,
+      "step": 12617
+    },
+    {
+      "epoch": 0.1897660182594279,
+      "grad_norm": 0.6527885794639587,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 0.7577,
+      "step": 12648
+    },
+    {
+      "epoch": 0.19023113104927944,
+      "grad_norm": 0.6012036800384521,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 0.7495,
+      "step": 12679
+    },
+    {
+      "epoch": 0.190696243839131,
+      "grad_norm": 0.6436840891838074,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 0.7528,
+      "step": 12710
+    },
+    {
+      "epoch": 0.19116135662898254,
+      "grad_norm": 0.6732128262519836,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 0.753,
+      "step": 12741
+    },
+    {
+      "epoch": 0.19162646941883407,
+      "grad_norm": 0.6353326439857483,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 0.7486,
+      "step": 12772
+    },
+    {
+      "epoch": 0.1920915822086856,
+      "grad_norm": 0.5631440877914429,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 0.7514,
+      "step": 12803
+    },
+    {
+      "epoch": 0.19255669499853714,
+      "grad_norm": 0.6583711504936218,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 0.7433,
+      "step": 12834
+    },
+    {
+      "epoch": 0.19302180778838868,
+      "grad_norm": 0.6780082583427429,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 0.7454,
+      "step": 12865
+    },
+    {
+      "epoch": 0.1934869205782402,
+      "grad_norm": 0.6170808672904968,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 0.7483,
+      "step": 12896
+    },
+    {
+      "epoch": 0.19395203336809178,
+      "grad_norm": 0.6318443417549133,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 0.7468,
+      "step": 12927
+    },
+    {
+      "epoch": 0.1944171461579433,
+      "grad_norm": 0.6315960884094238,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 0.7555,
+      "step": 12958
+    },
+    {
+      "epoch": 0.19488225894779485,
+      "grad_norm": 0.6713199615478516,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 0.7434,
+      "step": 12989
+    },
+    {
+      "epoch": 0.19534737173764638,
+      "grad_norm": 0.6113536953926086,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 0.7507,
+      "step": 13020
+    },
+    {
+      "epoch": 0.19581248452749792,
+      "grad_norm": 0.6978309750556946,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 0.7517,
+      "step": 13051
+    },
+    {
+      "epoch": 0.19627759731734945,
+      "grad_norm": 0.5803030729293823,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 0.7435,
+      "step": 13082
+    },
+    {
+      "epoch": 0.19674271010720099,
+      "grad_norm": 0.6192615032196045,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 0.741,
+      "step": 13113
+    },
+    {
+      "epoch": 0.19720782289705255,
+      "grad_norm": 0.6736807227134705,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 0.745,
+      "step": 13144
+    },
+    {
+      "epoch": 0.19767293568690408,
+      "grad_norm": 0.6507841348648071,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 0.7519,
+      "step": 13175
+    },
+    {
+      "epoch": 0.19813804847675562,
+      "grad_norm": 0.8572797775268555,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 0.7469,
+      "step": 13206
+    },
+    {
+      "epoch": 0.19860316126660715,
+      "grad_norm": 0.666427731513977,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 0.7468,
+      "step": 13237
+    },
+    {
+      "epoch": 0.1990682740564587,
+      "grad_norm": 2.855318069458008,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 0.7531,
+      "step": 13268
+    },
+    {
+      "epoch": 0.19953338684631022,
+      "grad_norm": 0.6657108664512634,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 0.7533,
+      "step": 13299
+    },
+    {
+      "epoch": 0.19999849963616176,
+      "grad_norm": 0.6588160991668701,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 0.7485,
+      "step": 13330
+    },
+    {
+      "epoch": 0.20046361242601332,
+      "grad_norm": 0.7666765451431274,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 0.7487,
+      "step": 13361
+    },
+    {
+      "epoch": 0.20092872521586486,
+      "grad_norm": 0.5730627775192261,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 0.7537,
+      "step": 13392
+    },
+    {
+      "epoch": 0.2013938380057164,
+      "grad_norm": 0.7242007851600647,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 0.7466,
+      "step": 13423
+    },
+    {
+      "epoch": 0.20185895079556793,
+      "grad_norm": 0.6119891405105591,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 0.7481,
+      "step": 13454
+    },
+    {
+      "epoch": 0.20232406358541946,
+      "grad_norm": 0.6716734766960144,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 0.7488,
+      "step": 13485
+    },
+    {
+      "epoch": 0.202789176375271,
+      "grad_norm": 0.6604441404342651,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 0.7492,
+      "step": 13516
+    },
+    {
+      "epoch": 0.20325428916512253,
+      "grad_norm": 0.6652749180793762,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 0.7308,
+      "step": 13547
+    },
+    {
+      "epoch": 0.2037194019549741,
+      "grad_norm": 0.7707824110984802,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 0.7406,
+      "step": 13578
+    },
+    {
+      "epoch": 0.20418451474482563,
+      "grad_norm": 0.6316570043563843,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 0.7448,
+      "step": 13609
+    },
+    {
+      "epoch": 0.20464962753467716,
+      "grad_norm": 0.7021921277046204,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 0.7496,
+      "step": 13640
+    },
+    {
+      "epoch": 0.2051147403245287,
+      "grad_norm": 0.6538084745407104,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 0.7398,
+      "step": 13671
+    },
+    {
+      "epoch": 0.20557985311438023,
+      "grad_norm": 0.686916172504425,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 0.7442,
+      "step": 13702
+    },
+    {
+      "epoch": 0.20604496590423177,
+      "grad_norm": 0.6664201021194458,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 0.7443,
+      "step": 13733
+    },
+    {
+      "epoch": 0.2065100786940833,
+      "grad_norm": 0.6051350831985474,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 0.7461,
+      "step": 13764
+    },
+    {
+      "epoch": 0.20697519148393487,
+      "grad_norm": 0.6227654814720154,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 0.7364,
+      "step": 13795
+    },
+    {
+      "epoch": 0.2074403042737864,
+      "grad_norm": 0.6357854008674622,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 0.7398,
+      "step": 13826
+    },
+    {
+      "epoch": 0.20790541706363794,
+      "grad_norm": 0.6361419558525085,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 0.7492,
+      "step": 13857
+    },
+    {
+      "epoch": 0.20837052985348947,
+      "grad_norm": 0.6335052251815796,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 0.742,
+      "step": 13888
+    },
+    {
+      "epoch": 0.208835642643341,
+      "grad_norm": 0.7693495750427246,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 0.7439,
+      "step": 13919
+    },
+    {
+      "epoch": 0.20930075543319254,
+      "grad_norm": 0.8410791158676147,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 0.7316,
+      "step": 13950
+    },
+    {
+      "epoch": 0.20976586822304408,
+      "grad_norm": 0.6099753975868225,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 0.7444,
+      "step": 13981
+    },
+    {
+      "epoch": 0.21023098101289564,
+      "grad_norm": 0.6221752762794495,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 0.7359,
+      "step": 14012
+    },
+    {
+      "epoch": 0.21069609380274718,
+      "grad_norm": 0.6333944201469421,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 0.751,
+      "step": 14043
+    },
+    {
+      "epoch": 0.2111612065925987,
+      "grad_norm": 0.7014179229736328,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 0.7376,
+      "step": 14074
+    },
+    {
+      "epoch": 0.21162631938245025,
+      "grad_norm": 0.5648131966590881,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 0.7465,
+      "step": 14105
+    },
+    {
+      "epoch": 0.21209143217230178,
+      "grad_norm": 0.6424175500869751,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 0.7433,
+      "step": 14136
+    },
+    {
+      "epoch": 0.21255654496215332,
+      "grad_norm": 0.5607630610466003,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 0.7381,
+      "step": 14167
+    },
+    {
+      "epoch": 0.21302165775200485,
+      "grad_norm": 0.6301280856132507,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 0.7339,
+      "step": 14198
+    },
+    {
+      "epoch": 0.2134867705418564,
+      "grad_norm": 0.7305763959884644,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 0.7401,
+      "step": 14229
+    },
+    {
+      "epoch": 0.21395188333170795,
+      "grad_norm": 0.7338880896568298,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 0.7488,
+      "step": 14260
+    },
+    {
+      "epoch": 0.21441699612155948,
+      "grad_norm": 0.5389525890350342,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 0.7385,
+      "step": 14291
+    },
+    {
+      "epoch": 0.21488210891141102,
+      "grad_norm": 0.6449492573738098,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 0.7437,
+      "step": 14322
+    },
+    {
+      "epoch": 0.21534722170126255,
+      "grad_norm": 0.6714854836463928,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 0.735,
+      "step": 14353
+    },
+    {
+      "epoch": 0.2158123344911141,
+      "grad_norm": 0.6901969909667969,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 0.7358,
+      "step": 14384
+    },
+    {
+      "epoch": 0.21627744728096562,
+      "grad_norm": 0.6448566317558289,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 0.7438,
+      "step": 14415
+    },
+    {
+      "epoch": 0.2167425600708172,
+      "grad_norm": 0.5600573420524597,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 0.7297,
+      "step": 14446
+    },
+    {
+      "epoch": 0.21720767286066872,
+      "grad_norm": 0.5650613307952881,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 0.7419,
+      "step": 14477
+    },
+    {
+      "epoch": 0.21767278565052026,
+      "grad_norm": 0.574630856513977,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 0.7373,
+      "step": 14508
+    },
+    {
+      "epoch": 0.2181378984403718,
+      "grad_norm": 0.570468008518219,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 0.74,
+      "step": 14539
+    },
+    {
+      "epoch": 0.21860301123022333,
+      "grad_norm": 0.6052928566932678,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 0.7396,
+      "step": 14570
+    },
+    {
+      "epoch": 0.21906812402007486,
+      "grad_norm": 0.6222713589668274,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 0.7419,
+      "step": 14601
+    },
+    {
+      "epoch": 0.2195332368099264,
+      "grad_norm": 0.6853971481323242,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 0.7458,
+      "step": 14632
+    },
+    {
+      "epoch": 0.21999834959977796,
+      "grad_norm": 0.7226673364639282,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 0.7482,
+      "step": 14663
+    },
+    {
+      "epoch": 0.2204634623896295,
+      "grad_norm": 0.7071784138679504,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 0.7388,
+      "step": 14694
+    },
+    {
+      "epoch": 0.22092857517948103,
+      "grad_norm": 0.7203782200813293,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 0.7328,
+      "step": 14725
+    },
+    {
+      "epoch": 0.22139368796933256,
+      "grad_norm": 0.6478374600410461,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 0.7518,
+      "step": 14756
+    },
+    {
+      "epoch": 0.2218588007591841,
+      "grad_norm": 1.1449323892593384,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 0.7424,
+      "step": 14787
+    },
+    {
+      "epoch": 0.22232391354903563,
+      "grad_norm": 0.6048957109451294,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 0.7427,
+      "step": 14818
+    },
+    {
+      "epoch": 0.22278902633888717,
+      "grad_norm": 0.6361618041992188,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 0.7374,
+      "step": 14849
+    },
+    {
+      "epoch": 0.22325413912873873,
+      "grad_norm": 0.6137757301330566,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 0.7401,
+      "step": 14880
+    },
+    {
+      "epoch": 0.22371925191859027,
+      "grad_norm": 0.7561056613922119,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 0.7355,
+      "step": 14911
+    },
+    {
+      "epoch": 0.2241843647084418,
+      "grad_norm": 0.6654713153839111,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 0.7306,
+      "step": 14942
+    },
+    {
+      "epoch": 0.22464947749829334,
+      "grad_norm": 1.9415818452835083,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 0.747,
+      "step": 14973
+    },
+    {
+      "epoch": 0.22511459028814487,
+      "grad_norm": 0.5493363738059998,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 0.7354,
+      "step": 15004
+    },
+    {
+      "epoch": 0.2255797030779964,
+      "grad_norm": 0.6092799305915833,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 0.7379,
+      "step": 15035
+    },
+    {
+      "epoch": 0.22604481586784794,
+      "grad_norm": 0.7052552103996277,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 0.739,
+      "step": 15066
+    },
+    {
+      "epoch": 0.2265099286576995,
+      "grad_norm": 0.6495633721351624,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 0.7382,
+      "step": 15097
+    },
+    {
+      "epoch": 0.22697504144755104,
+      "grad_norm": 0.6802439093589783,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 0.742,
+      "step": 15128
+    },
+    {
+      "epoch": 0.22744015423740258,
+      "grad_norm": 0.6225425004959106,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 0.7346,
+      "step": 15159
+    },
+    {
+      "epoch": 0.2279052670272541,
+      "grad_norm": 0.5513209104537964,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 0.7356,
+      "step": 15190
+    },
+    {
+      "epoch": 0.22837037981710565,
+      "grad_norm": 0.6840267777442932,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 0.7446,
+      "step": 15221
+    },
+    {
+      "epoch": 0.22883549260695718,
+      "grad_norm": 0.6213731169700623,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 0.7299,
+      "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:ee8c8c4b56f5ef244b7e4deb23b13b2d7ae50fce940e6c0d8a4ec3f3f25fa1a3
+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:ed361d4fa578fdbeeb816e56a68a4a65c369b62a0456ad2ded5defc6be2d5f6b
+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:d39bdb6e4a71c7dc4e9d684e29725e8889ad7e421e47d4f7f5d7137ab0df4ac7
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34784c4222ee23f5487edbd2175706e78d672048e0c575a5cb4becab9f83959
+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:a45b3c36a474fb5839471c234607fbdbcfce7f71c4eef4ff68d1e3407407e7fb
+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:ee8c8c4b56f5ef244b7e4deb23b13b2d7ae50fce940e6c0d8a4ec3f3f25fa1a3
+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:c1328ca7a55c33f44f019a9112d010c27b0834cfca77844d56d633d67cdf15b9
+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