Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,27 @@
+{
+  "<+>": 151665,
+  "<->": 151666,
+  "</tool_call>": 151658,
+  "<extra>": 151667,
+  "<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
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "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": 4096,
+  "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_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fb2e3fc2360cf6eb364ef5495e7851d42efcd21cffeb69016d332a9c693e63
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc7f47e05608a50d710c7ada2b03cd5262f53d5d5674446afc4790ac55d571b
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4933b87f75a556b8ddcff21f69199cf9fb81970c8a667d50ba309b4e54bc8e
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d8aea02848c864d55c11286523912c816cdf7823a42ec409f33c26387447fb
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|video_pad|>",
+    "<|box_end|>",
+    "<+>",
+    "<|object_ref_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<->",
+    "<extra>",
+    "<|image_pad|>",
+    "<|object_ref_start|>",
+    "<|box_start|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|quad_start|>",
+    "<|vision_pad|>",
+    "<|quad_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291d05ad00455fef901f3c9cdbd95f896c591cdff089f3189f95d3171634563f
+size 11422540

tokenizer_config.json

@@ -0,0 +1,235 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<+>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<->",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<extra>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|video_pad|>",
+    "<|box_end|>",
+    "<+>",
+    "<|object_ref_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<->",
+    "<extra>",
+    "<|image_pad|>",
+    "<|object_ref_start|>",
+    "<|box_start|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|quad_start|>",
+    "<|vision_pad|>",
+    "<|quad_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2879 @@
+{
+  "best_global_step": 4000,
+  "best_metric": 0.7443897795757539,
+  "best_model_checkpoint": "/shared/sutd/tej/Finegrained_PRM/models/Qwen2_5_Math_7b_instruct_more_data_run1/checkpoint-4000",
+  "epoch": 0.8958880139982502,
+  "eval_steps": 1000,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 12.598268508911133,
+      "eval_runtime": 512.8513,
+      "eval_samples_per_second": 234.602,
+      "eval_steps_per_second": 14.663,
+      "eval_token_accuracy": 0.6931271686857003,
+      "step": 0
+    },
+    {
+      "epoch": 0.0022397200349956255,
+      "grad_norm": 74.01309967041016,
+      "learning_rate": 5.03919372900336e-08,
+      "loss": 12.6044,
+      "step": 10
+    },
+    {
+      "epoch": 0.004479440069991251,
+      "grad_norm": 69.36959838867188,
+      "learning_rate": 1.0638297872340426e-07,
+      "loss": 12.6075,
+      "step": 20
+    },
+    {
+      "epoch": 0.006719160104986877,
+      "grad_norm": 79.40869140625,
+      "learning_rate": 1.6237402015677493e-07,
+      "loss": 12.5963,
+      "step": 30
+    },
+    {
+      "epoch": 0.008958880139982502,
+      "grad_norm": 67.53589630126953,
+      "learning_rate": 2.1836506159014558e-07,
+      "loss": 12.5561,
+      "step": 40
+    },
+    {
+      "epoch": 0.011198600174978127,
+      "grad_norm": 77.55623626708984,
+      "learning_rate": 2.7435610302351626e-07,
+      "loss": 12.4879,
+      "step": 50
+    },
+    {
+      "epoch": 0.013438320209973754,
+      "grad_norm": 57.3841552734375,
+      "learning_rate": 3.303471444568869e-07,
+      "loss": 12.3546,
+      "step": 60
+    },
+    {
+      "epoch": 0.01567804024496938,
+      "grad_norm": 56.3227424621582,
+      "learning_rate": 3.863381858902576e-07,
+      "loss": 12.2106,
+      "step": 70
+    },
+    {
+      "epoch": 0.017917760279965004,
+      "grad_norm": 85.61465454101562,
+      "learning_rate": 4.423292273236283e-07,
+      "loss": 11.8673,
+      "step": 80
+    },
+    {
+      "epoch": 0.02015748031496063,
+      "grad_norm": 89.71321868896484,
+      "learning_rate": 4.98320268756999e-07,
+      "loss": 11.414,
+      "step": 90
+    },
+    {
+      "epoch": 0.022397200349956254,
+      "grad_norm": 133.00584411621094,
+      "learning_rate": 5.543113101903696e-07,
+      "loss": 10.6907,
+      "step": 100
+    },
+    {
+      "epoch": 0.024636920384951883,
+      "grad_norm": 126.6435775756836,
+      "learning_rate": 6.103023516237402e-07,
+      "loss": 9.8793,
+      "step": 110
+    },
+    {
+      "epoch": 0.026876640419947508,
+      "grad_norm": 129.69862365722656,
+      "learning_rate": 6.662933930571109e-07,
+      "loss": 9.3174,
+      "step": 120
+    },
+    {
+      "epoch": 0.029116360454943133,
+      "grad_norm": 139.8076629638672,
+      "learning_rate": 7.222844344904815e-07,
+      "loss": 8.8794,
+      "step": 130
+    },
+    {
+      "epoch": 0.03135608048993876,
+      "grad_norm": 139.58309936523438,
+      "learning_rate": 7.782754759238523e-07,
+      "loss": 8.5155,
+      "step": 140
+    },
+    {
+      "epoch": 0.03359580052493438,
+      "grad_norm": 161.12001037597656,
+      "learning_rate": 8.342665173572229e-07,
+      "loss": 8.1803,
+      "step": 150
+    },
+    {
+      "epoch": 0.03583552055993001,
+      "grad_norm": 145.7100830078125,
+      "learning_rate": 8.902575587905936e-07,
+      "loss": 7.8429,
+      "step": 160
+    },
+    {
+      "epoch": 0.03807524059492563,
+      "grad_norm": 141.91400146484375,
+      "learning_rate": 9.462486002239643e-07,
+      "loss": 7.5282,
+      "step": 170
+    },
+    {
+      "epoch": 0.04031496062992126,
+      "grad_norm": 160.6728973388672,
+      "learning_rate": 1.0022396416573349e-06,
+      "loss": 7.1987,
+      "step": 180
+    },
+    {
+      "epoch": 0.04255468066491688,
+      "grad_norm": 147.54306030273438,
+      "learning_rate": 1.0582306830907057e-06,
+      "loss": 6.8656,
+      "step": 190
+    },
+    {
+      "epoch": 0.04479440069991251,
+      "grad_norm": 170.87681579589844,
+      "learning_rate": 1.1142217245240761e-06,
+      "loss": 6.5252,
+      "step": 200
+    },
+    {
+      "epoch": 0.04703412073490813,
+      "grad_norm": 152.63320922851562,
+      "learning_rate": 1.170212765957447e-06,
+      "loss": 6.179,
+      "step": 210
+    },
+    {
+      "epoch": 0.049273840769903765,
+      "grad_norm": 149.25778198242188,
+      "learning_rate": 1.2262038073908176e-06,
+      "loss": 5.8261,
+      "step": 220
+    },
+    {
+      "epoch": 0.05151356080489939,
+      "grad_norm": 162.14759826660156,
+      "learning_rate": 1.2821948488241882e-06,
+      "loss": 5.4615,
+      "step": 230
+    },
+    {
+      "epoch": 0.053753280839895015,
+      "grad_norm": 150.42588806152344,
+      "learning_rate": 1.338185890257559e-06,
+      "loss": 5.0995,
+      "step": 240
+    },
+    {
+      "epoch": 0.05599300087489064,
+      "grad_norm": 180.09596252441406,
+      "learning_rate": 1.3941769316909296e-06,
+      "loss": 4.7214,
+      "step": 250
+    },
+    {
+      "epoch": 0.058232720909886265,
+      "grad_norm": 151.71328735351562,
+      "learning_rate": 1.4501679731243e-06,
+      "loss": 4.3411,
+      "step": 260
+    },
+    {
+      "epoch": 0.06047244094488189,
+      "grad_norm": 149.18179321289062,
+      "learning_rate": 1.506159014557671e-06,
+      "loss": 3.9648,
+      "step": 270
+    },
+    {
+      "epoch": 0.06271216097987752,
+      "grad_norm": 158.7989959716797,
+      "learning_rate": 1.5621500559910415e-06,
+      "loss": 3.5754,
+      "step": 280
+    },
+    {
+      "epoch": 0.06495188101487315,
+      "grad_norm": 142.4947509765625,
+      "learning_rate": 1.6181410974244121e-06,
+      "loss": 3.198,
+      "step": 290
+    },
+    {
+      "epoch": 0.06719160104986877,
+      "grad_norm": 172.62350463867188,
+      "learning_rate": 1.674132138857783e-06,
+      "loss": 2.8298,
+      "step": 300
+    },
+    {
+      "epoch": 0.0694313210848644,
+      "grad_norm": 133.85870361328125,
+      "learning_rate": 1.7301231802911536e-06,
+      "loss": 2.471,
+      "step": 310
+    },
+    {
+      "epoch": 0.07167104111986002,
+      "grad_norm": 118.70149230957031,
+      "learning_rate": 1.7861142217245242e-06,
+      "loss": 2.1336,
+      "step": 320
+    },
+    {
+      "epoch": 0.07391076115485565,
+      "grad_norm": 116.01596069335938,
+      "learning_rate": 1.8421052631578948e-06,
+      "loss": 1.8315,
+      "step": 330
+    },
+    {
+      "epoch": 0.07615048118985127,
+      "grad_norm": 91.01036071777344,
+      "learning_rate": 1.8980963045912657e-06,
+      "loss": 1.5717,
+      "step": 340
+    },
+    {
+      "epoch": 0.0783902012248469,
+      "grad_norm": 118.93321228027344,
+      "learning_rate": 1.954087346024636e-06,
+      "loss": 1.3266,
+      "step": 350
+    },
+    {
+      "epoch": 0.08062992125984252,
+      "grad_norm": 67.08316040039062,
+      "learning_rate": 2.010078387458007e-06,
+      "loss": 1.1372,
+      "step": 360
+    },
+    {
+      "epoch": 0.08286964129483815,
+      "grad_norm": 42.60381317138672,
+      "learning_rate": 2.0660694288913777e-06,
+      "loss": 0.9771,
+      "step": 370
+    },
+    {
+      "epoch": 0.08510936132983377,
+      "grad_norm": 46.03950500488281,
+      "learning_rate": 2.122060470324748e-06,
+      "loss": 0.8681,
+      "step": 380
+    },
+    {
+      "epoch": 0.0873490813648294,
+      "grad_norm": 23.767711639404297,
+      "learning_rate": 2.178051511758119e-06,
+      "loss": 0.7751,
+      "step": 390
+    },
+    {
+      "epoch": 0.08958880139982502,
+      "grad_norm": 45.41588592529297,
+      "learning_rate": 2.2340425531914894e-06,
+      "loss": 0.6874,
+      "step": 400
+    },
+    {
+      "epoch": 0.09182852143482065,
+      "grad_norm": 18.76463508605957,
+      "learning_rate": 2.2900335946248602e-06,
+      "loss": 0.6544,
+      "step": 410
+    },
+    {
+      "epoch": 0.09406824146981627,
+      "grad_norm": 21.69906234741211,
+      "learning_rate": 2.346024636058231e-06,
+      "loss": 0.5834,
+      "step": 420
+    },
+    {
+      "epoch": 0.0963079615048119,
+      "grad_norm": 29.034330368041992,
+      "learning_rate": 2.4020156774916015e-06,
+      "loss": 0.5398,
+      "step": 430
+    },
+    {
+      "epoch": 0.09854768153980753,
+      "grad_norm": 12.911064147949219,
+      "learning_rate": 2.4580067189249723e-06,
+      "loss": 0.4761,
+      "step": 440
+    },
+    {
+      "epoch": 0.10078740157480315,
+      "grad_norm": 32.778602600097656,
+      "learning_rate": 2.5139977603583427e-06,
+      "loss": 0.4394,
+      "step": 450
+    },
+    {
+      "epoch": 0.10302712160979878,
+      "grad_norm": 48.48755645751953,
+      "learning_rate": 2.5699888017917135e-06,
+      "loss": 0.4834,
+      "step": 460
+    },
+    {
+      "epoch": 0.1052668416447944,
+      "grad_norm": 24.921396255493164,
+      "learning_rate": 2.6259798432250844e-06,
+      "loss": 0.4231,
+      "step": 470
+    },
+    {
+      "epoch": 0.10750656167979003,
+      "grad_norm": 7.630334377288818,
+      "learning_rate": 2.6819708846584548e-06,
+      "loss": 0.3715,
+      "step": 480
+    },
+    {
+      "epoch": 0.10974628171478565,
+      "grad_norm": 36.03708267211914,
+      "learning_rate": 2.7379619260918256e-06,
+      "loss": 0.37,
+      "step": 490
+    },
+    {
+      "epoch": 0.11198600174978128,
+      "grad_norm": 33.10087585449219,
+      "learning_rate": 2.7939529675251964e-06,
+      "loss": 0.3522,
+      "step": 500
+    },
+    {
+      "epoch": 0.1142257217847769,
+      "grad_norm": 8.544207572937012,
+      "learning_rate": 2.849944008958567e-06,
+      "loss": 0.3339,
+      "step": 510
+    },
+    {
+      "epoch": 0.11646544181977253,
+      "grad_norm": 37.781951904296875,
+      "learning_rate": 2.9059350503919377e-06,
+      "loss": 0.325,
+      "step": 520
+    },
+    {
+      "epoch": 0.11870516185476815,
+      "grad_norm": 9.192522048950195,
+      "learning_rate": 2.9619260918253085e-06,
+      "loss": 0.3175,
+      "step": 530
+    },
+    {
+      "epoch": 0.12094488188976378,
+      "grad_norm": 35.02260208129883,
+      "learning_rate": 3.017917133258679e-06,
+      "loss": 0.3193,
+      "step": 540
+    },
+    {
+      "epoch": 0.1231846019247594,
+      "grad_norm": 4.580764293670654,
+      "learning_rate": 3.0739081746920498e-06,
+      "loss": 0.3122,
+      "step": 550
+    },
+    {
+      "epoch": 0.12542432195975503,
+      "grad_norm": 12.692420959472656,
+      "learning_rate": 3.1298992161254197e-06,
+      "loss": 0.3234,
+      "step": 560
+    },
+    {
+      "epoch": 0.12766404199475065,
+      "grad_norm": 5.639922618865967,
+      "learning_rate": 3.1858902575587906e-06,
+      "loss": 0.2774,
+      "step": 570
+    },
+    {
+      "epoch": 0.1299037620297463,
+      "grad_norm": 2.170525550842285,
+      "learning_rate": 3.241881298992162e-06,
+      "loss": 0.2828,
+      "step": 580
+    },
+    {
+      "epoch": 0.1321434820647419,
+      "grad_norm": 2.8537590503692627,
+      "learning_rate": 3.297872340425532e-06,
+      "loss": 0.2961,
+      "step": 590
+    },
+    {
+      "epoch": 0.13438320209973753,
+      "grad_norm": 4.110259532928467,
+      "learning_rate": 3.3538633818589027e-06,
+      "loss": 0.2664,
+      "step": 600
+    },
+    {
+      "epoch": 0.13662292213473315,
+      "grad_norm": 5.937915802001953,
+      "learning_rate": 3.4098544232922735e-06,
+      "loss": 0.3023,
+      "step": 610
+    },
+    {
+      "epoch": 0.1388626421697288,
+      "grad_norm": 14.195796012878418,
+      "learning_rate": 3.465845464725644e-06,
+      "loss": 0.2662,
+      "step": 620
+    },
+    {
+      "epoch": 0.1411023622047244,
+      "grad_norm": 8.165706634521484,
+      "learning_rate": 3.5218365061590147e-06,
+      "loss": 0.2909,
+      "step": 630
+    },
+    {
+      "epoch": 0.14334208223972003,
+      "grad_norm": 9.505974769592285,
+      "learning_rate": 3.5778275475923856e-06,
+      "loss": 0.277,
+      "step": 640
+    },
+    {
+      "epoch": 0.14558180227471565,
+      "grad_norm": 6.215830326080322,
+      "learning_rate": 3.633818589025756e-06,
+      "loss": 0.2649,
+      "step": 650
+    },
+    {
+      "epoch": 0.1478215223097113,
+      "grad_norm": 16.8066463470459,
+      "learning_rate": 3.689809630459127e-06,
+      "loss": 0.299,
+      "step": 660
+    },
+    {
+      "epoch": 0.1500612423447069,
+      "grad_norm": 8.53093147277832,
+      "learning_rate": 3.7458006718924976e-06,
+      "loss": 0.2673,
+      "step": 670
+    },
+    {
+      "epoch": 0.15230096237970253,
+      "grad_norm": 6.421195030212402,
+      "learning_rate": 3.801791713325868e-06,
+      "loss": 0.2792,
+      "step": 680
+    },
+    {
+      "epoch": 0.15454068241469815,
+      "grad_norm": 2.7667346000671387,
+      "learning_rate": 3.857782754759239e-06,
+      "loss": 0.2909,
+      "step": 690
+    },
+    {
+      "epoch": 0.1567804024496938,
+      "grad_norm": 10.2630033493042,
+      "learning_rate": 3.91377379619261e-06,
+      "loss": 0.2716,
+      "step": 700
+    },
+    {
+      "epoch": 0.1590201224846894,
+      "grad_norm": 1.535446286201477,
+      "learning_rate": 3.96976483762598e-06,
+      "loss": 0.2816,
+      "step": 710
+    },
+    {
+      "epoch": 0.16125984251968503,
+      "grad_norm": 9.585880279541016,
+      "learning_rate": 4.025755879059351e-06,
+      "loss": 0.2553,
+      "step": 720
+    },
+    {
+      "epoch": 0.16349956255468068,
+      "grad_norm": 14.28587818145752,
+      "learning_rate": 4.081746920492721e-06,
+      "loss": 0.2825,
+      "step": 730
+    },
+    {
+      "epoch": 0.1657392825896763,
+      "grad_norm": 4.546958923339844,
+      "learning_rate": 4.137737961926092e-06,
+      "loss": 0.2718,
+      "step": 740
+    },
+    {
+      "epoch": 0.1679790026246719,
+      "grad_norm": 2.867119312286377,
+      "learning_rate": 4.193729003359463e-06,
+      "loss": 0.2507,
+      "step": 750
+    },
+    {
+      "epoch": 0.17021872265966753,
+      "grad_norm": 14.170395851135254,
+      "learning_rate": 4.2497200447928334e-06,
+      "loss": 0.2677,
+      "step": 760
+    },
+    {
+      "epoch": 0.17245844269466318,
+      "grad_norm": 17.095518112182617,
+      "learning_rate": 4.305711086226204e-06,
+      "loss": 0.2506,
+      "step": 770
+    },
+    {
+      "epoch": 0.1746981627296588,
+      "grad_norm": 5.597836017608643,
+      "learning_rate": 4.361702127659575e-06,
+      "loss": 0.2871,
+      "step": 780
+    },
+    {
+      "epoch": 0.17693788276465441,
+      "grad_norm": 14.059051513671875,
+      "learning_rate": 4.417693169092945e-06,
+      "loss": 0.2731,
+      "step": 790
+    },
+    {
+      "epoch": 0.17917760279965003,
+      "grad_norm": 4.634145259857178,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 0.2461,
+      "step": 800
+    },
+    {
+      "epoch": 0.18141732283464568,
+      "grad_norm": 2.4694900512695312,
+      "learning_rate": 4.529675251959687e-06,
+      "loss": 0.2798,
+      "step": 810
+    },
+    {
+      "epoch": 0.1836570428696413,
+      "grad_norm": 2.7586958408355713,
+      "learning_rate": 4.585666293393058e-06,
+      "loss": 0.263,
+      "step": 820
+    },
+    {
+      "epoch": 0.18589676290463691,
+      "grad_norm": 1.317171335220337,
+      "learning_rate": 4.6416573348264284e-06,
+      "loss": 0.2602,
+      "step": 830
+    },
+    {
+      "epoch": 0.18813648293963253,
+      "grad_norm": 16.16120719909668,
+      "learning_rate": 4.697648376259799e-06,
+      "loss": 0.2567,
+      "step": 840
+    },
+    {
+      "epoch": 0.19037620297462818,
+      "grad_norm": 1.187530279159546,
+      "learning_rate": 4.753639417693169e-06,
+      "loss": 0.2715,
+      "step": 850
+    },
+    {
+      "epoch": 0.1926159230096238,
+      "grad_norm": 11.328052520751953,
+      "learning_rate": 4.80963045912654e-06,
+      "loss": 0.2785,
+      "step": 860
+    },
+    {
+      "epoch": 0.19485564304461941,
+      "grad_norm": 5.0461530685424805,
+      "learning_rate": 4.865621500559911e-06,
+      "loss": 0.2466,
+      "step": 870
+    },
+    {
+      "epoch": 0.19709536307961506,
+      "grad_norm": 2.635329246520996,
+      "learning_rate": 4.921612541993282e-06,
+      "loss": 0.2689,
+      "step": 880
+    },
+    {
+      "epoch": 0.19933508311461068,
+      "grad_norm": 18.956153869628906,
+      "learning_rate": 4.977603583426653e-06,
+      "loss": 0.2594,
+      "step": 890
+    },
+    {
+      "epoch": 0.2015748031496063,
+      "grad_norm": 1.4908218383789062,
+      "learning_rate": 5.033594624860023e-06,
+      "loss": 0.2559,
+      "step": 900
+    },
+    {
+      "epoch": 0.20381452318460191,
+      "grad_norm": 13.888111114501953,
+      "learning_rate": 5.089585666293394e-06,
+      "loss": 0.2859,
+      "step": 910
+    },
+    {
+      "epoch": 0.20605424321959756,
+      "grad_norm": 1.7197439670562744,
+      "learning_rate": 5.145576707726763e-06,
+      "loss": 0.2462,
+      "step": 920
+    },
+    {
+      "epoch": 0.20829396325459318,
+      "grad_norm": 1.1483347415924072,
+      "learning_rate": 5.201567749160134e-06,
+      "loss": 0.25,
+      "step": 930
+    },
+    {
+      "epoch": 0.2105336832895888,
+      "grad_norm": 10.579352378845215,
+      "learning_rate": 5.257558790593506e-06,
+      "loss": 0.2376,
+      "step": 940
+    },
+    {
+      "epoch": 0.21277340332458441,
+      "grad_norm": 2.291902542114258,
+      "learning_rate": 5.313549832026877e-06,
+      "loss": 0.2453,
+      "step": 950
+    },
+    {
+      "epoch": 0.21501312335958006,
+      "grad_norm": 5.439045429229736,
+      "learning_rate": 5.3695408734602476e-06,
+      "loss": 0.2984,
+      "step": 960
+    },
+    {
+      "epoch": 0.21725284339457568,
+      "grad_norm": 1.5583287477493286,
+      "learning_rate": 5.425531914893617e-06,
+      "loss": 0.256,
+      "step": 970
+    },
+    {
+      "epoch": 0.2194925634295713,
+      "grad_norm": 5.13300895690918,
+      "learning_rate": 5.4815229563269875e-06,
+      "loss": 0.259,
+      "step": 980
+    },
+    {
+      "epoch": 0.22173228346456694,
+      "grad_norm": 3.150655746459961,
+      "learning_rate": 5.537513997760358e-06,
+      "loss": 0.2447,
+      "step": 990
+    },
+    {
+      "epoch": 0.22397200349956256,
+      "grad_norm": 5.581788063049316,
+      "learning_rate": 5.593505039193729e-06,
+      "loss": 0.2388,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22397200349956256,
+      "eval_loss": 0.24665296077728271,
+      "eval_runtime": 508.3924,
+      "eval_samples_per_second": 236.66,
+      "eval_steps_per_second": 14.792,
+      "eval_token_accuracy": 0.6965583269229705,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22621172353455818,
+      "grad_norm": 6.410147666931152,
+      "learning_rate": 5.6494960806271e-06,
+      "loss": 0.2569,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2284514435695538,
+      "grad_norm": 8.687148094177246,
+      "learning_rate": 5.705487122060471e-06,
+      "loss": 0.2499,
+      "step": 1020
+    },
+    {
+      "epoch": 0.23069116360454944,
+      "grad_norm": 6.87606954574585,
+      "learning_rate": 5.761478163493841e-06,
+      "loss": 0.2555,
+      "step": 1030
+    },
+    {
+      "epoch": 0.23293088363954506,
+      "grad_norm": 1.6779398918151855,
+      "learning_rate": 5.817469204927212e-06,
+      "loss": 0.2556,
+      "step": 1040
+    },
+    {
+      "epoch": 0.23517060367454068,
+      "grad_norm": 7.228851318359375,
+      "learning_rate": 5.8734602463605825e-06,
+      "loss": 0.245,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2374103237095363,
+      "grad_norm": 5.364595890045166,
+      "learning_rate": 5.929451287793953e-06,
+      "loss": 0.2717,
+      "step": 1060
+    },
+    {
+      "epoch": 0.23965004374453194,
+      "grad_norm": 3.2734596729278564,
+      "learning_rate": 5.985442329227324e-06,
+      "loss": 0.2274,
+      "step": 1070
+    },
+    {
+      "epoch": 0.24188976377952756,
+      "grad_norm": 4.536466598510742,
+      "learning_rate": 6.041433370660694e-06,
+      "loss": 0.2561,
+      "step": 1080
+    },
+    {
+      "epoch": 0.24412948381452318,
+      "grad_norm": 7.9406280517578125,
+      "learning_rate": 6.097424412094065e-06,
+      "loss": 0.2428,
+      "step": 1090
+    },
+    {
+      "epoch": 0.2463692038495188,
+      "grad_norm": 6.413431644439697,
+      "learning_rate": 6.153415453527436e-06,
+      "loss": 0.2327,
+      "step": 1100
+    },
+    {
+      "epoch": 0.24860892388451444,
+      "grad_norm": 1.6045399904251099,
+      "learning_rate": 6.209406494960807e-06,
+      "loss": 0.2704,
+      "step": 1110
+    },
+    {
+      "epoch": 0.25084864391951006,
+      "grad_norm": 8.93922233581543,
+      "learning_rate": 6.2653975363941775e-06,
+      "loss": 0.2365,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2530883639545057,
+      "grad_norm": 6.114246845245361,
+      "learning_rate": 6.321388577827548e-06,
+      "loss": 0.2476,
+      "step": 1130
+    },
+    {
+      "epoch": 0.2553280839895013,
+      "grad_norm": 4.84804105758667,
+      "learning_rate": 6.377379619260918e-06,
+      "loss": 0.2411,
+      "step": 1140
+    },
+    {
+      "epoch": 0.2575678040244969,
+      "grad_norm": 2.421581506729126,
+      "learning_rate": 6.433370660694289e-06,
+      "loss": 0.2251,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2598075240594926,
+      "grad_norm": 13.80971622467041,
+      "learning_rate": 6.48936170212766e-06,
+      "loss": 0.2541,
+      "step": 1160
+    },
+    {
+      "epoch": 0.2620472440944882,
+      "grad_norm": 1.8289860486984253,
+      "learning_rate": 6.545352743561031e-06,
+      "loss": 0.2462,
+      "step": 1170
+    },
+    {
+      "epoch": 0.2642869641294838,
+      "grad_norm": 1.4232782125473022,
+      "learning_rate": 6.601343784994402e-06,
+      "loss": 0.2394,
+      "step": 1180
+    },
+    {
+      "epoch": 0.26652668416447944,
+      "grad_norm": 6.040958404541016,
+      "learning_rate": 6.6573348264277725e-06,
+      "loss": 0.2441,
+      "step": 1190
+    },
+    {
+      "epoch": 0.26876640419947506,
+      "grad_norm": 5.110551357269287,
+      "learning_rate": 6.7133258678611425e-06,
+      "loss": 0.2285,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2710061242344707,
+      "grad_norm": 14.493913650512695,
+      "learning_rate": 6.769316909294513e-06,
+      "loss": 0.2545,
+      "step": 1210
+    },
+    {
+      "epoch": 0.2732458442694663,
+      "grad_norm": 6.708395481109619,
+      "learning_rate": 6.825307950727884e-06,
+      "loss": 0.2399,
+      "step": 1220
+    },
+    {
+      "epoch": 0.2754855643044619,
+      "grad_norm": 7.098331451416016,
+      "learning_rate": 6.881298992161255e-06,
+      "loss": 0.2529,
+      "step": 1230
+    },
+    {
+      "epoch": 0.2777252843394576,
+      "grad_norm": 7.667686462402344,
+      "learning_rate": 6.937290033594626e-06,
+      "loss": 0.2265,
+      "step": 1240
+    },
+    {
+      "epoch": 0.2799650043744532,
+      "grad_norm": 3.293351411819458,
+      "learning_rate": 6.993281075027996e-06,
+      "loss": 0.212,
+      "step": 1250
+    },
+    {
+      "epoch": 0.2822047244094488,
+      "grad_norm": 6.79879093170166,
+      "learning_rate": 7.049272116461367e-06,
+      "loss": 0.2496,
+      "step": 1260
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 4.2775092124938965,
+      "learning_rate": 7.1052631578947375e-06,
+      "loss": 0.2219,
+      "step": 1270
+    },
+    {
+      "epoch": 0.28668416447944006,
+      "grad_norm": 2.1673076152801514,
+      "learning_rate": 7.161254199328108e-06,
+      "loss": 0.2374,
+      "step": 1280
+    },
+    {
+      "epoch": 0.2889238845144357,
+      "grad_norm": 5.312763214111328,
+      "learning_rate": 7.217245240761479e-06,
+      "loss": 0.2256,
+      "step": 1290
+    },
+    {
+      "epoch": 0.2911636045494313,
+      "grad_norm": 4.370241165161133,
+      "learning_rate": 7.27323628219485e-06,
+      "loss": 0.2357,
+      "step": 1300
+    },
+    {
+      "epoch": 0.29340332458442697,
+      "grad_norm": 3.1714890003204346,
+      "learning_rate": 7.32922732362822e-06,
+      "loss": 0.2557,
+      "step": 1310
+    },
+    {
+      "epoch": 0.2956430446194226,
+      "grad_norm": 2.53678297996521,
+      "learning_rate": 7.385218365061591e-06,
+      "loss": 0.2331,
+      "step": 1320
+    },
+    {
+      "epoch": 0.2978827646544182,
+      "grad_norm": 3.696383476257324,
+      "learning_rate": 7.441209406494962e-06,
+      "loss": 0.232,
+      "step": 1330
+    },
+    {
+      "epoch": 0.3001224846894138,
+      "grad_norm": 4.8781232833862305,
+      "learning_rate": 7.4972004479283325e-06,
+      "loss": 0.2306,
+      "step": 1340
+    },
+    {
+      "epoch": 0.30236220472440944,
+      "grad_norm": 1.83755362033844,
+      "learning_rate": 7.553191489361703e-06,
+      "loss": 0.2337,
+      "step": 1350
+    },
+    {
+      "epoch": 0.30460192475940506,
+      "grad_norm": 11.356858253479004,
+      "learning_rate": 7.609182530795074e-06,
+      "loss": 0.2459,
+      "step": 1360
+    },
+    {
+      "epoch": 0.3068416447944007,
+      "grad_norm": 8.49129581451416,
+      "learning_rate": 7.665173572228444e-06,
+      "loss": 0.2293,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3090813648293963,
+      "grad_norm": 2.2894465923309326,
+      "learning_rate": 7.721164613661814e-06,
+      "loss": 0.2383,
+      "step": 1380
+    },
+    {
+      "epoch": 0.311321084864392,
+      "grad_norm": 1.8182672262191772,
+      "learning_rate": 7.777155655095186e-06,
+      "loss": 0.241,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3135608048993876,
+      "grad_norm": 3.236206293106079,
+      "learning_rate": 7.833146696528556e-06,
+      "loss": 0.2285,
+      "step": 1400
+    },
+    {
+      "epoch": 0.3158005249343832,
+      "grad_norm": 1.631281852722168,
+      "learning_rate": 7.889137737961927e-06,
+      "loss": 0.2571,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3180402449693788,
+      "grad_norm": 8.107253074645996,
+      "learning_rate": 7.945128779395297e-06,
+      "loss": 0.2209,
+      "step": 1420
+    },
+    {
+      "epoch": 0.32027996500437445,
+      "grad_norm": 1.1233727931976318,
+      "learning_rate": 8.001119820828667e-06,
+      "loss": 0.2427,
+      "step": 1430
+    },
+    {
+      "epoch": 0.32251968503937006,
+      "grad_norm": 8.097697257995605,
+      "learning_rate": 8.057110862262039e-06,
+      "loss": 0.2452,
+      "step": 1440
+    },
+    {
+      "epoch": 0.3247594050743657,
+      "grad_norm": 2.3983142375946045,
+      "learning_rate": 8.113101903695409e-06,
+      "loss": 0.2186,
+      "step": 1450
+    },
+    {
+      "epoch": 0.32699912510936135,
+      "grad_norm": 12.040475845336914,
+      "learning_rate": 8.16909294512878e-06,
+      "loss": 0.2438,
+      "step": 1460
+    },
+    {
+      "epoch": 0.329238845144357,
+      "grad_norm": 1.604379653930664,
+      "learning_rate": 8.22508398656215e-06,
+      "loss": 0.2395,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3314785651793526,
+      "grad_norm": 3.6802425384521484,
+      "learning_rate": 8.28107502799552e-06,
+      "loss": 0.2417,
+      "step": 1480
+    },
+    {
+      "epoch": 0.3337182852143482,
+      "grad_norm": 1.3274339437484741,
+      "learning_rate": 8.337066069428892e-06,
+      "loss": 0.2333,
+      "step": 1490
+    },
+    {
+      "epoch": 0.3359580052493438,
+      "grad_norm": 2.7458624839782715,
+      "learning_rate": 8.393057110862262e-06,
+      "loss": 0.2099,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33819772528433945,
+      "grad_norm": 2.586228847503662,
+      "learning_rate": 8.449048152295634e-06,
+      "loss": 0.2487,
+      "step": 1510
+    },
+    {
+      "epoch": 0.34043744531933506,
+      "grad_norm": 4.21591329574585,
+      "learning_rate": 8.505039193729004e-06,
+      "loss": 0.2232,
+      "step": 1520
+    },
+    {
+      "epoch": 0.3426771653543307,
+      "grad_norm": 10.471442222595215,
+      "learning_rate": 8.561030235162374e-06,
+      "loss": 0.243,
+      "step": 1530
+    },
+    {
+      "epoch": 0.34491688538932636,
+      "grad_norm": 2.1316909790039062,
+      "learning_rate": 8.617021276595746e-06,
+      "loss": 0.2245,
+      "step": 1540
+    },
+    {
+      "epoch": 0.347156605424322,
+      "grad_norm": 2.768832206726074,
+      "learning_rate": 8.673012318029116e-06,
+      "loss": 0.231,
+      "step": 1550
+    },
+    {
+      "epoch": 0.3493963254593176,
+      "grad_norm": 1.221541404724121,
+      "learning_rate": 8.729003359462487e-06,
+      "loss": 0.227,
+      "step": 1560
+    },
+    {
+      "epoch": 0.3516360454943132,
+      "grad_norm": 7.449015140533447,
+      "learning_rate": 8.784994400895857e-06,
+      "loss": 0.2445,
+      "step": 1570
+    },
+    {
+      "epoch": 0.35387576552930883,
+      "grad_norm": 3.9796910285949707,
+      "learning_rate": 8.840985442329229e-06,
+      "loss": 0.2312,
+      "step": 1580
+    },
+    {
+      "epoch": 0.35611548556430445,
+      "grad_norm": 4.768671989440918,
+      "learning_rate": 8.896976483762599e-06,
+      "loss": 0.2371,
+      "step": 1590
+    },
+    {
+      "epoch": 0.35835520559930006,
+      "grad_norm": 2.461826801300049,
+      "learning_rate": 8.952967525195969e-06,
+      "loss": 0.2342,
+      "step": 1600
+    },
+    {
+      "epoch": 0.36059492563429574,
+      "grad_norm": 15.604554176330566,
+      "learning_rate": 9.00895856662934e-06,
+      "loss": 0.2639,
+      "step": 1610
+    },
+    {
+      "epoch": 0.36283464566929136,
+      "grad_norm": 10.057650566101074,
+      "learning_rate": 9.06494960806271e-06,
+      "loss": 0.2364,
+      "step": 1620
+    },
+    {
+      "epoch": 0.365074365704287,
+      "grad_norm": 1.363266110420227,
+      "learning_rate": 9.120940649496082e-06,
+      "loss": 0.2284,
+      "step": 1630
+    },
+    {
+      "epoch": 0.3673140857392826,
+      "grad_norm": 6.2388763427734375,
+      "learning_rate": 9.176931690929452e-06,
+      "loss": 0.2363,
+      "step": 1640
+    },
+    {
+      "epoch": 0.3695538057742782,
+      "grad_norm": 5.490090370178223,
+      "learning_rate": 9.232922732362822e-06,
+      "loss": 0.2274,
+      "step": 1650
+    },
+    {
+      "epoch": 0.37179352580927383,
+      "grad_norm": 4.038967132568359,
+      "learning_rate": 9.288913773796194e-06,
+      "loss": 0.2431,
+      "step": 1660
+    },
+    {
+      "epoch": 0.37403324584426945,
+      "grad_norm": 2.4451630115509033,
+      "learning_rate": 9.344904815229564e-06,
+      "loss": 0.2269,
+      "step": 1670
+    },
+    {
+      "epoch": 0.37627296587926506,
+      "grad_norm": 7.310824871063232,
+      "learning_rate": 9.400895856662936e-06,
+      "loss": 0.2338,
+      "step": 1680
+    },
+    {
+      "epoch": 0.37851268591426074,
+      "grad_norm": 3.421902656555176,
+      "learning_rate": 9.456886898096306e-06,
+      "loss": 0.225,
+      "step": 1690
+    },
+    {
+      "epoch": 0.38075240594925636,
+      "grad_norm": 2.0587453842163086,
+      "learning_rate": 9.512877939529676e-06,
+      "loss": 0.2229,
+      "step": 1700
+    },
+    {
+      "epoch": 0.382992125984252,
+      "grad_norm": 7.844244956970215,
+      "learning_rate": 9.568868980963046e-06,
+      "loss": 0.2471,
+      "step": 1710
+    },
+    {
+      "epoch": 0.3852318460192476,
+      "grad_norm": 2.0231168270111084,
+      "learning_rate": 9.624860022396417e-06,
+      "loss": 0.2265,
+      "step": 1720
+    },
+    {
+      "epoch": 0.3874715660542432,
+      "grad_norm": 4.695873737335205,
+      "learning_rate": 9.680851063829787e-06,
+      "loss": 0.2319,
+      "step": 1730
+    },
+    {
+      "epoch": 0.38971128608923883,
+      "grad_norm": 4.3562703132629395,
+      "learning_rate": 9.736842105263159e-06,
+      "loss": 0.2402,
+      "step": 1740
+    },
+    {
+      "epoch": 0.39195100612423445,
+      "grad_norm": 3.8503875732421875,
+      "learning_rate": 9.79283314669653e-06,
+      "loss": 0.2172,
+      "step": 1750
+    },
+    {
+      "epoch": 0.3941907261592301,
+      "grad_norm": 1.6659972667694092,
+      "learning_rate": 9.848824188129899e-06,
+      "loss": 0.2556,
+      "step": 1760
+    },
+    {
+      "epoch": 0.39643044619422574,
+      "grad_norm": 8.133085250854492,
+      "learning_rate": 9.90481522956327e-06,
+      "loss": 0.2404,
+      "step": 1770
+    },
+    {
+      "epoch": 0.39867016622922136,
+      "grad_norm": 1.0106691122055054,
+      "learning_rate": 9.96080627099664e-06,
+      "loss": 0.2221,
+      "step": 1780
+    },
+    {
+      "epoch": 0.400909886264217,
+      "grad_norm": 4.416316986083984,
+      "learning_rate": 9.999999140094955e-06,
+      "loss": 0.2338,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4031496062992126,
+      "grad_norm": 2.253812074661255,
+      "learning_rate": 9.999983852902361e-06,
+      "loss": 0.224,
+      "step": 1800
+    },
+    {
+      "epoch": 0.4053893263342082,
+      "grad_norm": 3.477606773376465,
+      "learning_rate": 9.999949456775993e-06,
+      "loss": 0.2328,
+      "step": 1810
+    },
+    {
+      "epoch": 0.40762904636920383,
+      "grad_norm": 4.672702789306641,
+      "learning_rate": 9.9998959518473e-06,
+      "loss": 0.2336,
+      "step": 1820
+    },
+    {
+      "epoch": 0.4098687664041995,
+      "grad_norm": 1.8212214708328247,
+      "learning_rate": 9.999823338320772e-06,
+      "loss": 0.2283,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4121084864391951,
+      "grad_norm": 2.800435781478882,
+      "learning_rate": 9.99973161647392e-06,
+      "loss": 0.2379,
+      "step": 1840
+    },
+    {
+      "epoch": 0.41434820647419074,
+      "grad_norm": 7.563694477081299,
+      "learning_rate": 9.999620786657289e-06,
+      "loss": 0.2188,
+      "step": 1850
+    },
+    {
+      "epoch": 0.41658792650918636,
+      "grad_norm": 13.088976860046387,
+      "learning_rate": 9.999490849294448e-06,
+      "loss": 0.2567,
+      "step": 1860
+    },
+    {
+      "epoch": 0.418827646544182,
+      "grad_norm": 1.8773629665374756,
+      "learning_rate": 9.99934180488199e-06,
+      "loss": 0.2316,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4210673665791776,
+      "grad_norm": 3.4965360164642334,
+      "learning_rate": 9.999173653989533e-06,
+      "loss": 0.2355,
+      "step": 1880
+    },
+    {
+      "epoch": 0.4233070866141732,
+      "grad_norm": 3.4962074756622314,
+      "learning_rate": 9.998986397259716e-06,
+      "loss": 0.229,
+      "step": 1890
+    },
+    {
+      "epoch": 0.42554680664916883,
+      "grad_norm": 1.0358535051345825,
+      "learning_rate": 9.998780035408198e-06,
+      "loss": 0.2235,
+      "step": 1900
+    },
+    {
+      "epoch": 0.4277865266841645,
+      "grad_norm": 15.394458770751953,
+      "learning_rate": 9.998554569223652e-06,
+      "loss": 0.2484,
+      "step": 1910
+    },
+    {
+      "epoch": 0.4300262467191601,
+      "grad_norm": 2.1868062019348145,
+      "learning_rate": 9.998309999567764e-06,
+      "loss": 0.2382,
+      "step": 1920
+    },
+    {
+      "epoch": 0.43226596675415574,
+      "grad_norm": 3.1081955432891846,
+      "learning_rate": 9.99804632737523e-06,
+      "loss": 0.229,
+      "step": 1930
+    },
+    {
+      "epoch": 0.43450568678915136,
+      "grad_norm": 1.4906216859817505,
+      "learning_rate": 9.997763553653752e-06,
+      "loss": 0.2319,
+      "step": 1940
+    },
+    {
+      "epoch": 0.436745406824147,
+      "grad_norm": 3.580657482147217,
+      "learning_rate": 9.997461679484034e-06,
+      "loss": 0.2156,
+      "step": 1950
+    },
+    {
+      "epoch": 0.4389851268591426,
+      "grad_norm": 9.583480834960938,
+      "learning_rate": 9.997140706019779e-06,
+      "loss": 0.237,
+      "step": 1960
+    },
+    {
+      "epoch": 0.4412248468941382,
+      "grad_norm": 5.272135257720947,
+      "learning_rate": 9.996800634487685e-06,
+      "loss": 0.227,
+      "step": 1970
+    },
+    {
+      "epoch": 0.4434645669291339,
+      "grad_norm": 2.0222976207733154,
+      "learning_rate": 9.996441466187434e-06,
+      "loss": 0.2317,
+      "step": 1980
+    },
+    {
+      "epoch": 0.4457042869641295,
+      "grad_norm": 1.1668893098831177,
+      "learning_rate": 9.996063202491698e-06,
+      "loss": 0.232,
+      "step": 1990
+    },
+    {
+      "epoch": 0.4479440069991251,
+      "grad_norm": 10.037023544311523,
+      "learning_rate": 9.995665844846119e-06,
+      "loss": 0.2207,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4479440069991251,
+      "eval_loss": 0.23211318254470825,
+      "eval_runtime": 506.8766,
+      "eval_samples_per_second": 237.367,
+      "eval_steps_per_second": 14.836,
+      "eval_token_accuracy": 0.6974161164822881,
+      "step": 2000
+    },
+    {
+      "epoch": 0.45018372703412074,
+      "grad_norm": 2.2029612064361572,
+      "learning_rate": 9.995249394769327e-06,
+      "loss": 0.2383,
+      "step": 2010
+    },
+    {
+      "epoch": 0.45242344706911636,
+      "grad_norm": 9.830987930297852,
+      "learning_rate": 9.994813853852903e-06,
+      "loss": 0.2207,
+      "step": 2020
+    },
+    {
+      "epoch": 0.454663167104112,
+      "grad_norm": 1.8869295120239258,
+      "learning_rate": 9.9943592237614e-06,
+      "loss": 0.2264,
+      "step": 2030
+    },
+    {
+      "epoch": 0.4569028871391076,
+      "grad_norm": 1.761500597000122,
+      "learning_rate": 9.993885506232324e-06,
+      "loss": 0.2285,
+      "step": 2040
+    },
+    {
+      "epoch": 0.4591426071741032,
+      "grad_norm": 4.521030426025391,
+      "learning_rate": 9.993392703076126e-06,
+      "loss": 0.2236,
+      "step": 2050
+    },
+    {
+      "epoch": 0.4613823272090989,
+      "grad_norm": 1.2697912454605103,
+      "learning_rate": 9.9928808161762e-06,
+      "loss": 0.2341,
+      "step": 2060
+    },
+    {
+      "epoch": 0.4636220472440945,
+      "grad_norm": 3.4168875217437744,
+      "learning_rate": 9.992349847488878e-06,
+      "loss": 0.2126,
+      "step": 2070
+    },
+    {
+      "epoch": 0.4658617672790901,
+      "grad_norm": 5.974389553070068,
+      "learning_rate": 9.991799799043413e-06,
+      "loss": 0.2372,
+      "step": 2080
+    },
+    {
+      "epoch": 0.46810148731408574,
+      "grad_norm": 1.9752360582351685,
+      "learning_rate": 9.991230672941982e-06,
+      "loss": 0.2288,
+      "step": 2090
+    },
+    {
+      "epoch": 0.47034120734908136,
+      "grad_norm": 1.7691487073898315,
+      "learning_rate": 9.990642471359668e-06,
+      "loss": 0.2142,
+      "step": 2100
+    },
+    {
+      "epoch": 0.472580927384077,
+      "grad_norm": 4.6645731925964355,
+      "learning_rate": 9.990035196544461e-06,
+      "loss": 0.2403,
+      "step": 2110
+    },
+    {
+      "epoch": 0.4748206474190726,
+      "grad_norm": 2.952207565307617,
+      "learning_rate": 9.989408850817243e-06,
+      "loss": 0.2269,
+      "step": 2120
+    },
+    {
+      "epoch": 0.47706036745406827,
+      "grad_norm": 1.3406009674072266,
+      "learning_rate": 9.988763436571783e-06,
+      "loss": 0.2302,
+      "step": 2130
+    },
+    {
+      "epoch": 0.4793000874890639,
+      "grad_norm": 1.8972488641738892,
+      "learning_rate": 9.98809895627472e-06,
+      "loss": 0.2271,
+      "step": 2140
+    },
+    {
+      "epoch": 0.4815398075240595,
+      "grad_norm": 2.660292863845825,
+      "learning_rate": 9.987415412465568e-06,
+      "loss": 0.2278,
+      "step": 2150
+    },
+    {
+      "epoch": 0.4837795275590551,
+      "grad_norm": 2.4427502155303955,
+      "learning_rate": 9.986712807756695e-06,
+      "loss": 0.2633,
+      "step": 2160
+    },
+    {
+      "epoch": 0.48601924759405074,
+      "grad_norm": 5.147864818572998,
+      "learning_rate": 9.98599114483331e-06,
+      "loss": 0.23,
+      "step": 2170
+    },
+    {
+      "epoch": 0.48825896762904636,
+      "grad_norm": 5.563263893127441,
+      "learning_rate": 9.98525042645347e-06,
+      "loss": 0.2378,
+      "step": 2180
+    },
+    {
+      "epoch": 0.490498687664042,
+      "grad_norm": 6.136834621429443,
+      "learning_rate": 9.984490655448049e-06,
+      "loss": 0.2303,
+      "step": 2190
+    },
+    {
+      "epoch": 0.4927384076990376,
+      "grad_norm": 2.446849822998047,
+      "learning_rate": 9.983711834720738e-06,
+      "loss": 0.2234,
+      "step": 2200
+    },
+    {
+      "epoch": 0.49497812773403327,
+      "grad_norm": 4.507411956787109,
+      "learning_rate": 9.982913967248035e-06,
+      "loss": 0.2462,
+      "step": 2210
+    },
+    {
+      "epoch": 0.4972178477690289,
+      "grad_norm": 1.4177577495574951,
+      "learning_rate": 9.982097056079228e-06,
+      "loss": 0.2254,
+      "step": 2220
+    },
+    {
+      "epoch": 0.4994575678040245,
+      "grad_norm": 7.209784030914307,
+      "learning_rate": 9.981261104336389e-06,
+      "loss": 0.2264,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5016972878390201,
+      "grad_norm": 18.120464324951172,
+      "learning_rate": 9.980406115214353e-06,
+      "loss": 0.2385,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5039370078740157,
+      "grad_norm": 1.6847277879714966,
+      "learning_rate": 9.979532091980723e-06,
+      "loss": 0.2201,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5061767279090114,
+      "grad_norm": 2.8450379371643066,
+      "learning_rate": 9.97863903797584e-06,
+      "loss": 0.2419,
+      "step": 2260
+    },
+    {
+      "epoch": 0.508416447944007,
+      "grad_norm": 4.046864032745361,
+      "learning_rate": 9.97772695661277e-06,
+      "loss": 0.2259,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5106561679790026,
+      "grad_norm": 1.2429368495941162,
+      "learning_rate": 9.976795851377312e-06,
+      "loss": 0.2272,
+      "step": 2280
+    },
+    {
+      "epoch": 0.5128958880139982,
+      "grad_norm": 3.9099016189575195,
+      "learning_rate": 9.975845725827959e-06,
+      "loss": 0.232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.5151356080489938,
+      "grad_norm": 1.1243308782577515,
+      "learning_rate": 9.9748765835959e-06,
+      "loss": 0.2198,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5173753280839894,
+      "grad_norm": 5.873220443725586,
+      "learning_rate": 9.973888428385006e-06,
+      "loss": 0.2435,
+      "step": 2310
+    },
+    {
+      "epoch": 0.5196150481189852,
+      "grad_norm": 1.5939319133758545,
+      "learning_rate": 9.972881263971803e-06,
+      "loss": 0.2246,
+      "step": 2320
+    },
+    {
+      "epoch": 0.5218547681539808,
+      "grad_norm": 4.427680969238281,
+      "learning_rate": 9.971855094205473e-06,
+      "loss": 0.2324,
+      "step": 2330
+    },
+    {
+      "epoch": 0.5240944881889764,
+      "grad_norm": 2.819718360900879,
+      "learning_rate": 9.97080992300783e-06,
+      "loss": 0.2497,
+      "step": 2340
+    },
+    {
+      "epoch": 0.526334208223972,
+      "grad_norm": 2.0332233905792236,
+      "learning_rate": 9.969745754373311e-06,
+      "loss": 0.2225,
+      "step": 2350
+    },
+    {
+      "epoch": 0.5285739282589677,
+      "grad_norm": 12.013405799865723,
+      "learning_rate": 9.968662592368952e-06,
+      "loss": 0.2445,
+      "step": 2360
+    },
+    {
+      "epoch": 0.5308136482939633,
+      "grad_norm": 10.702028274536133,
+      "learning_rate": 9.967560441134381e-06,
+      "loss": 0.2164,
+      "step": 2370
+    },
+    {
+      "epoch": 0.5330533683289589,
+      "grad_norm": 5.7824907302856445,
+      "learning_rate": 9.966439304881798e-06,
+      "loss": 0.2213,
+      "step": 2380
+    },
+    {
+      "epoch": 0.5352930883639545,
+      "grad_norm": 5.64496374130249,
+      "learning_rate": 9.965299187895962e-06,
+      "loss": 0.2288,
+      "step": 2390
+    },
+    {
+      "epoch": 0.5375328083989501,
+      "grad_norm": 1.3699864149093628,
+      "learning_rate": 9.964140094534169e-06,
+      "loss": 0.2322,
+      "step": 2400
+    },
+    {
+      "epoch": 0.5397725284339457,
+      "grad_norm": 4.486180305480957,
+      "learning_rate": 9.962962029226244e-06,
+      "loss": 0.2296,
+      "step": 2410
+    },
+    {
+      "epoch": 0.5420122484689414,
+      "grad_norm": 2.6139583587646484,
+      "learning_rate": 9.961764996474514e-06,
+      "loss": 0.2161,
+      "step": 2420
+    },
+    {
+      "epoch": 0.544251968503937,
+      "grad_norm": 1.0381577014923096,
+      "learning_rate": 9.960549000853799e-06,
+      "loss": 0.2275,
+      "step": 2430
+    },
+    {
+      "epoch": 0.5464916885389326,
+      "grad_norm": 2.3962111473083496,
+      "learning_rate": 9.959314047011389e-06,
+      "loss": 0.23,
+      "step": 2440
+    },
+    {
+      "epoch": 0.5487314085739282,
+      "grad_norm": 1.2226966619491577,
+      "learning_rate": 9.958060139667027e-06,
+      "loss": 0.2163,
+      "step": 2450
+    },
+    {
+      "epoch": 0.5509711286089238,
+      "grad_norm": 6.7834062576293945,
+      "learning_rate": 9.9567872836129e-06,
+      "loss": 0.2324,
+      "step": 2460
+    },
+    {
+      "epoch": 0.5532108486439196,
+      "grad_norm": 7.556985378265381,
+      "learning_rate": 9.955495483713604e-06,
+      "loss": 0.2186,
+      "step": 2470
+    },
+    {
+      "epoch": 0.5554505686789152,
+      "grad_norm": 6.278934955596924,
+      "learning_rate": 9.954184744906139e-06,
+      "loss": 0.232,
+      "step": 2480
+    },
+    {
+      "epoch": 0.5576902887139108,
+      "grad_norm": 1.6271597146987915,
+      "learning_rate": 9.95285507219989e-06,
+      "loss": 0.2324,
+      "step": 2490
+    },
+    {
+      "epoch": 0.5599300087489064,
+      "grad_norm": 3.6434125900268555,
+      "learning_rate": 9.951506470676592e-06,
+      "loss": 0.2182,
+      "step": 2500
+    },
+    {
+      "epoch": 0.562169728783902,
+      "grad_norm": 1.8215718269348145,
+      "learning_rate": 9.950138945490335e-06,
+      "loss": 0.2353,
+      "step": 2510
+    },
+    {
+      "epoch": 0.5644094488188977,
+      "grad_norm": 3.433577299118042,
+      "learning_rate": 9.948752501867522e-06,
+      "loss": 0.2257,
+      "step": 2520
+    },
+    {
+      "epoch": 0.5666491688538933,
+      "grad_norm": 4.02660608291626,
+      "learning_rate": 9.947347145106865e-06,
+      "loss": 0.2192,
+      "step": 2530
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 1.360437273979187,
+      "learning_rate": 9.945922880579351e-06,
+      "loss": 0.2199,
+      "step": 2540
+    },
+    {
+      "epoch": 0.5711286089238845,
+      "grad_norm": 1.155464768409729,
+      "learning_rate": 9.944479713728237e-06,
+      "loss": 0.1921,
+      "step": 2550
+    },
+    {
+      "epoch": 0.5733683289588801,
+      "grad_norm": 7.086646556854248,
+      "learning_rate": 9.943017650069013e-06,
+      "loss": 0.242,
+      "step": 2560
+    },
+    {
+      "epoch": 0.5756080489938757,
+      "grad_norm": 4.299362659454346,
+      "learning_rate": 9.941536695189396e-06,
+      "loss": 0.228,
+      "step": 2570
+    },
+    {
+      "epoch": 0.5778477690288714,
+      "grad_norm": 8.915771484375,
+      "learning_rate": 9.940036854749297e-06,
+      "loss": 0.2308,
+      "step": 2580
+    },
+    {
+      "epoch": 0.580087489063867,
+      "grad_norm": 2.6741573810577393,
+      "learning_rate": 9.938518134480803e-06,
+      "loss": 0.2398,
+      "step": 2590
+    },
+    {
+      "epoch": 0.5823272090988626,
+      "grad_norm": 2.5663797855377197,
+      "learning_rate": 9.93698054018816e-06,
+      "loss": 0.2077,
+      "step": 2600
+    },
+    {
+      "epoch": 0.5845669291338582,
+      "grad_norm": 2.6795785427093506,
+      "learning_rate": 9.935424077747744e-06,
+      "loss": 0.2367,
+      "step": 2610
+    },
+    {
+      "epoch": 0.5868066491688539,
+      "grad_norm": 3.2071633338928223,
+      "learning_rate": 9.933848753108041e-06,
+      "loss": 0.2106,
+      "step": 2620
+    },
+    {
+      "epoch": 0.5890463692038496,
+      "grad_norm": 3.1179144382476807,
+      "learning_rate": 9.932254572289626e-06,
+      "loss": 0.2446,
+      "step": 2630
+    },
+    {
+      "epoch": 0.5912860892388452,
+      "grad_norm": 1.6278126239776611,
+      "learning_rate": 9.930641541385138e-06,
+      "loss": 0.2211,
+      "step": 2640
+    },
+    {
+      "epoch": 0.5935258092738408,
+      "grad_norm": 5.3661885261535645,
+      "learning_rate": 9.929009666559255e-06,
+      "loss": 0.2107,
+      "step": 2650
+    },
+    {
+      "epoch": 0.5957655293088364,
+      "grad_norm": 6.771117210388184,
+      "learning_rate": 9.927358954048676e-06,
+      "loss": 0.2399,
+      "step": 2660
+    },
+    {
+      "epoch": 0.598005249343832,
+      "grad_norm": 2.178788185119629,
+      "learning_rate": 9.925689410162095e-06,
+      "loss": 0.21,
+      "step": 2670
+    },
+    {
+      "epoch": 0.6002449693788277,
+      "grad_norm": 8.165093421936035,
+      "learning_rate": 9.92400104128017e-06,
+      "loss": 0.2246,
+      "step": 2680
+    },
+    {
+      "epoch": 0.6024846894138233,
+      "grad_norm": 3.471679449081421,
+      "learning_rate": 9.922293853855509e-06,
+      "loss": 0.2131,
+      "step": 2690
+    },
+    {
+      "epoch": 0.6047244094488189,
+      "grad_norm": 2.9488112926483154,
+      "learning_rate": 9.92056785441264e-06,
+      "loss": 0.2245,
+      "step": 2700
+    },
+    {
+      "epoch": 0.6069641294838145,
+      "grad_norm": 5.4626145362854,
+      "learning_rate": 9.918823049547984e-06,
+      "loss": 0.2444,
+      "step": 2710
+    },
+    {
+      "epoch": 0.6092038495188101,
+      "grad_norm": 1.8659770488739014,
+      "learning_rate": 9.917059445929838e-06,
+      "loss": 0.2226,
+      "step": 2720
+    },
+    {
+      "epoch": 0.6114435695538057,
+      "grad_norm": 2.041576385498047,
+      "learning_rate": 9.915277050298336e-06,
+      "loss": 0.2401,
+      "step": 2730
+    },
+    {
+      "epoch": 0.6136832895888014,
+      "grad_norm": 7.602120399475098,
+      "learning_rate": 9.913475869465442e-06,
+      "loss": 0.2105,
+      "step": 2740
+    },
+    {
+      "epoch": 0.615923009623797,
+      "grad_norm": 1.5145801305770874,
+      "learning_rate": 9.911655910314901e-06,
+      "loss": 0.2168,
+      "step": 2750
+    },
+    {
+      "epoch": 0.6181627296587926,
+      "grad_norm": 2.4858598709106445,
+      "learning_rate": 9.909817179802234e-06,
+      "loss": 0.2363,
+      "step": 2760
+    },
+    {
+      "epoch": 0.6204024496937883,
+      "grad_norm": 2.1684751510620117,
+      "learning_rate": 9.907959684954702e-06,
+      "loss": 0.2234,
+      "step": 2770
+    },
+    {
+      "epoch": 0.622642169728784,
+      "grad_norm": 1.7832976579666138,
+      "learning_rate": 9.906083432871273e-06,
+      "loss": 0.2282,
+      "step": 2780
+    },
+    {
+      "epoch": 0.6248818897637796,
+      "grad_norm": 6.974465370178223,
+      "learning_rate": 9.90418843072261e-06,
+      "loss": 0.2264,
+      "step": 2790
+    },
+    {
+      "epoch": 0.6271216097987752,
+      "grad_norm": 4.383815765380859,
+      "learning_rate": 9.902274685751027e-06,
+      "loss": 0.2145,
+      "step": 2800
+    },
+    {
+      "epoch": 0.6293613298337708,
+      "grad_norm": 1.6938287019729614,
+      "learning_rate": 9.900342205270475e-06,
+      "loss": 0.2388,
+      "step": 2810
+    },
+    {
+      "epoch": 0.6316010498687664,
+      "grad_norm": 14.980836868286133,
+      "learning_rate": 9.898390996666502e-06,
+      "loss": 0.2289,
+      "step": 2820
+    },
+    {
+      "epoch": 0.633840769903762,
+      "grad_norm": 6.246406555175781,
+      "learning_rate": 9.89642106739624e-06,
+      "loss": 0.2319,
+      "step": 2830
+    },
+    {
+      "epoch": 0.6360804899387577,
+      "grad_norm": 7.479663848876953,
+      "learning_rate": 9.894432424988363e-06,
+      "loss": 0.2224,
+      "step": 2840
+    },
+    {
+      "epoch": 0.6383202099737533,
+      "grad_norm": 6.564876556396484,
+      "learning_rate": 9.892425077043058e-06,
+      "loss": 0.2185,
+      "step": 2850
+    },
+    {
+      "epoch": 0.6405599300087489,
+      "grad_norm": 5.287945747375488,
+      "learning_rate": 9.89039903123201e-06,
+      "loss": 0.2352,
+      "step": 2860
+    },
+    {
+      "epoch": 0.6427996500437445,
+      "grad_norm": 1.6189258098602295,
+      "learning_rate": 9.888354295298356e-06,
+      "loss": 0.2107,
+      "step": 2870
+    },
+    {
+      "epoch": 0.6450393700787401,
+      "grad_norm": 1.7470353841781616,
+      "learning_rate": 9.88629087705667e-06,
+      "loss": 0.2284,
+      "step": 2880
+    },
+    {
+      "epoch": 0.6472790901137357,
+      "grad_norm": 6.374598503112793,
+      "learning_rate": 9.884208784392917e-06,
+      "loss": 0.2295,
+      "step": 2890
+    },
+    {
+      "epoch": 0.6495188101487314,
+      "grad_norm": 3.07970929145813,
+      "learning_rate": 9.882108025264442e-06,
+      "loss": 0.2199,
+      "step": 2900
+    },
+    {
+      "epoch": 0.651758530183727,
+      "grad_norm": 5.308441638946533,
+      "learning_rate": 9.87998860769992e-06,
+      "loss": 0.2246,
+      "step": 2910
+    },
+    {
+      "epoch": 0.6539982502187227,
+      "grad_norm": 8.279508590698242,
+      "learning_rate": 9.877850539799341e-06,
+      "loss": 0.2222,
+      "step": 2920
+    },
+    {
+      "epoch": 0.6562379702537183,
+      "grad_norm": 6.9987006187438965,
+      "learning_rate": 9.87569382973397e-06,
+      "loss": 0.2319,
+      "step": 2930
+    },
+    {
+      "epoch": 0.658477690288714,
+      "grad_norm": 4.786025524139404,
+      "learning_rate": 9.873518485746321e-06,
+      "loss": 0.2257,
+      "step": 2940
+    },
+    {
+      "epoch": 0.6607174103237096,
+      "grad_norm": 3.0393166542053223,
+      "learning_rate": 9.871324516150123e-06,
+      "loss": 0.2153,
+      "step": 2950
+    },
+    {
+      "epoch": 0.6629571303587052,
+      "grad_norm": 3.177739143371582,
+      "learning_rate": 9.869111929330282e-06,
+      "loss": 0.2232,
+      "step": 2960
+    },
+    {
+      "epoch": 0.6651968503937008,
+      "grad_norm": 2.291867971420288,
+      "learning_rate": 9.866880733742865e-06,
+      "loss": 0.212,
+      "step": 2970
+    },
+    {
+      "epoch": 0.6674365704286964,
+      "grad_norm": 3.9312686920166016,
+      "learning_rate": 9.864630937915052e-06,
+      "loss": 0.2262,
+      "step": 2980
+    },
+    {
+      "epoch": 0.669676290463692,
+      "grad_norm": 2.110924482345581,
+      "learning_rate": 9.862362550445108e-06,
+      "loss": 0.2274,
+      "step": 2990
+    },
+    {
+      "epoch": 0.6719160104986877,
+      "grad_norm": 1.4342049360275269,
+      "learning_rate": 9.860075580002359e-06,
+      "loss": 0.2171,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6719160104986877,
+      "eval_loss": 0.21779567003250122,
+      "eval_runtime": 508.7876,
+      "eval_samples_per_second": 236.476,
+      "eval_steps_per_second": 14.78,
+      "eval_token_accuracy": 0.7062596501325423,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6741557305336833,
+      "grad_norm": 1.5321989059448242,
+      "learning_rate": 9.857770035327142e-06,
+      "loss": 0.2255,
+      "step": 3010
+    },
+    {
+      "epoch": 0.6763954505686789,
+      "grad_norm": 9.719202041625977,
+      "learning_rate": 9.85544592523079e-06,
+      "loss": 0.2185,
+      "step": 3020
+    },
+    {
+      "epoch": 0.6786351706036745,
+      "grad_norm": 8.409933090209961,
+      "learning_rate": 9.853103258595581e-06,
+      "loss": 0.2295,
+      "step": 3030
+    },
+    {
+      "epoch": 0.6808748906386701,
+      "grad_norm": 1.9369258880615234,
+      "learning_rate": 9.85074204437472e-06,
+      "loss": 0.2283,
+      "step": 3040
+    },
+    {
+      "epoch": 0.6831146106736657,
+      "grad_norm": 2.4668948650360107,
+      "learning_rate": 9.848362291592288e-06,
+      "loss": 0.2123,
+      "step": 3050
+    },
+    {
+      "epoch": 0.6853543307086614,
+      "grad_norm": 2.983069658279419,
+      "learning_rate": 9.845964009343228e-06,
+      "loss": 0.2315,
+      "step": 3060
+    },
+    {
+      "epoch": 0.6875940507436571,
+      "grad_norm": 3.6539225578308105,
+      "learning_rate": 9.843547206793289e-06,
+      "loss": 0.2202,
+      "step": 3070
+    },
+    {
+      "epoch": 0.6898337707786527,
+      "grad_norm": 9.64335823059082,
+      "learning_rate": 9.841111893179006e-06,
+      "loss": 0.2149,
+      "step": 3080
+    },
+    {
+      "epoch": 0.6920734908136483,
+      "grad_norm": 11.048383712768555,
+      "learning_rate": 9.838658077807657e-06,
+      "loss": 0.2334,
+      "step": 3090
+    },
+    {
+      "epoch": 0.694313210848644,
+      "grad_norm": 7.029510021209717,
+      "learning_rate": 9.836185770057234e-06,
+      "loss": 0.2093,
+      "step": 3100
+    },
+    {
+      "epoch": 0.6965529308836396,
+      "grad_norm": 2.615210771560669,
+      "learning_rate": 9.833694979376398e-06,
+      "loss": 0.2294,
+      "step": 3110
+    },
+    {
+      "epoch": 0.6987926509186352,
+      "grad_norm": 9.237405776977539,
+      "learning_rate": 9.831185715284452e-06,
+      "loss": 0.2225,
+      "step": 3120
+    },
+    {
+      "epoch": 0.7010323709536308,
+      "grad_norm": 2.880690097808838,
+      "learning_rate": 9.828657987371301e-06,
+      "loss": 0.2291,
+      "step": 3130
+    },
+    {
+      "epoch": 0.7032720909886264,
+      "grad_norm": 4.929702281951904,
+      "learning_rate": 9.826111805297409e-06,
+      "loss": 0.2338,
+      "step": 3140
+    },
+    {
+      "epoch": 0.705511811023622,
+      "grad_norm": 1.8025418519973755,
+      "learning_rate": 9.823547178793775e-06,
+      "loss": 0.2087,
+      "step": 3150
+    },
+    {
+      "epoch": 0.7077515310586177,
+      "grad_norm": 10.105000495910645,
+      "learning_rate": 9.820964117661888e-06,
+      "loss": 0.2376,
+      "step": 3160
+    },
+    {
+      "epoch": 0.7099912510936133,
+      "grad_norm": 10.464491844177246,
+      "learning_rate": 9.818362631773685e-06,
+      "loss": 0.2162,
+      "step": 3170
+    },
+    {
+      "epoch": 0.7122309711286089,
+      "grad_norm": 1.2578132152557373,
+      "learning_rate": 9.815742731071524e-06,
+      "loss": 0.2297,
+      "step": 3180
+    },
+    {
+      "epoch": 0.7144706911636045,
+      "grad_norm": 7.663752555847168,
+      "learning_rate": 9.813104425568138e-06,
+      "loss": 0.2151,
+      "step": 3190
+    },
+    {
+      "epoch": 0.7167104111986001,
+      "grad_norm": 3.7501728534698486,
+      "learning_rate": 9.810447725346604e-06,
+      "loss": 0.2226,
+      "step": 3200
+    },
+    {
+      "epoch": 0.7189501312335957,
+      "grad_norm": 7.99606466293335,
+      "learning_rate": 9.807772640560292e-06,
+      "loss": 0.2327,
+      "step": 3210
+    },
+    {
+      "epoch": 0.7211898512685915,
+      "grad_norm": 4.222293376922607,
+      "learning_rate": 9.805079181432842e-06,
+      "loss": 0.2206,
+      "step": 3220
+    },
+    {
+      "epoch": 0.7234295713035871,
+      "grad_norm": 6.806760311126709,
+      "learning_rate": 9.802367358258114e-06,
+      "loss": 0.2147,
+      "step": 3230
+    },
+    {
+      "epoch": 0.7256692913385827,
+      "grad_norm": 4.147646427154541,
+      "learning_rate": 9.799637181400147e-06,
+      "loss": 0.2097,
+      "step": 3240
+    },
+    {
+      "epoch": 0.7279090113735783,
+      "grad_norm": 1.1662570238113403,
+      "learning_rate": 9.796888661293133e-06,
+      "loss": 0.2096,
+      "step": 3250
+    },
+    {
+      "epoch": 0.730148731408574,
+      "grad_norm": 6.412913799285889,
+      "learning_rate": 9.794121808441361e-06,
+      "loss": 0.2361,
+      "step": 3260
+    },
+    {
+      "epoch": 0.7323884514435696,
+      "grad_norm": 1.2370624542236328,
+      "learning_rate": 9.791336633419189e-06,
+      "loss": 0.2041,
+      "step": 3270
+    },
+    {
+      "epoch": 0.7346281714785652,
+      "grad_norm": 0.9865597486495972,
+      "learning_rate": 9.788533146870995e-06,
+      "loss": 0.2199,
+      "step": 3280
+    },
+    {
+      "epoch": 0.7368678915135608,
+      "grad_norm": 4.455222129821777,
+      "learning_rate": 9.78571135951114e-06,
+      "loss": 0.22,
+      "step": 3290
+    },
+    {
+      "epoch": 0.7391076115485564,
+      "grad_norm": 4.656614780426025,
+      "learning_rate": 9.782871282123932e-06,
+      "loss": 0.2182,
+      "step": 3300
+    },
+    {
+      "epoch": 0.741347331583552,
+      "grad_norm": 3.1240029335021973,
+      "learning_rate": 9.780012925563573e-06,
+      "loss": 0.2307,
+      "step": 3310
+    },
+    {
+      "epoch": 0.7435870516185477,
+      "grad_norm": 3.156013011932373,
+      "learning_rate": 9.777136300754129e-06,
+      "loss": 0.2141,
+      "step": 3320
+    },
+    {
+      "epoch": 0.7458267716535433,
+      "grad_norm": 4.594078540802002,
+      "learning_rate": 9.774241418689481e-06,
+      "loss": 0.2338,
+      "step": 3330
+    },
+    {
+      "epoch": 0.7480664916885389,
+      "grad_norm": 6.030776023864746,
+      "learning_rate": 9.771328290433287e-06,
+      "loss": 0.222,
+      "step": 3340
+    },
+    {
+      "epoch": 0.7503062117235345,
+      "grad_norm": 3.0741419792175293,
+      "learning_rate": 9.768396927118939e-06,
+      "loss": 0.2051,
+      "step": 3350
+    },
+    {
+      "epoch": 0.7525459317585301,
+      "grad_norm": 1.915945053100586,
+      "learning_rate": 9.76544733994952e-06,
+      "loss": 0.2241,
+      "step": 3360
+    },
+    {
+      "epoch": 0.7547856517935259,
+      "grad_norm": 6.906998634338379,
+      "learning_rate": 9.762479540197753e-06,
+      "loss": 0.2111,
+      "step": 3370
+    },
+    {
+      "epoch": 0.7570253718285215,
+      "grad_norm": 1.6207234859466553,
+      "learning_rate": 9.75949353920598e-06,
+      "loss": 0.2209,
+      "step": 3380
+    },
+    {
+      "epoch": 0.7592650918635171,
+      "grad_norm": 1.919848084449768,
+      "learning_rate": 9.756489348386093e-06,
+      "loss": 0.2238,
+      "step": 3390
+    },
+    {
+      "epoch": 0.7615048118985127,
+      "grad_norm": 1.796086072921753,
+      "learning_rate": 9.753466979219507e-06,
+      "loss": 0.2103,
+      "step": 3400
+    },
+    {
+      "epoch": 0.7637445319335083,
+      "grad_norm": 1.6984485387802124,
+      "learning_rate": 9.75042644325711e-06,
+      "loss": 0.2229,
+      "step": 3410
+    },
+    {
+      "epoch": 0.765984251968504,
+      "grad_norm": 4.693706035614014,
+      "learning_rate": 9.747367752119216e-06,
+      "loss": 0.222,
+      "step": 3420
+    },
+    {
+      "epoch": 0.7682239720034996,
+      "grad_norm": 3.6621434688568115,
+      "learning_rate": 9.744290917495535e-06,
+      "loss": 0.2253,
+      "step": 3430
+    },
+    {
+      "epoch": 0.7704636920384952,
+      "grad_norm": 4.475337505340576,
+      "learning_rate": 9.741195951145105e-06,
+      "loss": 0.2198,
+      "step": 3440
+    },
+    {
+      "epoch": 0.7727034120734908,
+      "grad_norm": 6.554020404815674,
+      "learning_rate": 9.738082864896267e-06,
+      "loss": 0.2082,
+      "step": 3450
+    },
+    {
+      "epoch": 0.7749431321084864,
+      "grad_norm": 1.775171160697937,
+      "learning_rate": 9.734951670646612e-06,
+      "loss": 0.2345,
+      "step": 3460
+    },
+    {
+      "epoch": 0.777182852143482,
+      "grad_norm": 10.973596572875977,
+      "learning_rate": 9.731802380362936e-06,
+      "loss": 0.2201,
+      "step": 3470
+    },
+    {
+      "epoch": 0.7794225721784777,
+      "grad_norm": 3.4094762802124023,
+      "learning_rate": 9.728635006081191e-06,
+      "loss": 0.2299,
+      "step": 3480
+    },
+    {
+      "epoch": 0.7816622922134733,
+      "grad_norm": 3.6424269676208496,
+      "learning_rate": 9.725449559906448e-06,
+      "loss": 0.2235,
+      "step": 3490
+    },
+    {
+      "epoch": 0.7839020122484689,
+      "grad_norm": 4.4308319091796875,
+      "learning_rate": 9.72224605401284e-06,
+      "loss": 0.2117,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7861417322834645,
+      "grad_norm": 5.900296688079834,
+      "learning_rate": 9.719024500643526e-06,
+      "loss": 0.2298,
+      "step": 3510
+    },
+    {
+      "epoch": 0.7883814523184602,
+      "grad_norm": 4.9092020988464355,
+      "learning_rate": 9.715784912110632e-06,
+      "loss": 0.2181,
+      "step": 3520
+    },
+    {
+      "epoch": 0.7906211723534559,
+      "grad_norm": 3.5412979125976562,
+      "learning_rate": 9.712527300795218e-06,
+      "loss": 0.2213,
+      "step": 3530
+    },
+    {
+      "epoch": 0.7928608923884515,
+      "grad_norm": 2.001018524169922,
+      "learning_rate": 9.709251679147217e-06,
+      "loss": 0.2176,
+      "step": 3540
+    },
+    {
+      "epoch": 0.7951006124234471,
+      "grad_norm": 1.459351897239685,
+      "learning_rate": 9.705958059685399e-06,
+      "loss": 0.212,
+      "step": 3550
+    },
+    {
+      "epoch": 0.7973403324584427,
+      "grad_norm": 2.8420157432556152,
+      "learning_rate": 9.702646454997315e-06,
+      "loss": 0.2299,
+      "step": 3560
+    },
+    {
+      "epoch": 0.7995800524934383,
+      "grad_norm": 3.9574944972991943,
+      "learning_rate": 9.699316877739253e-06,
+      "loss": 0.204,
+      "step": 3570
+    },
+    {
+      "epoch": 0.801819772528434,
+      "grad_norm": 1.4476044178009033,
+      "learning_rate": 9.695969340636189e-06,
+      "loss": 0.2102,
+      "step": 3580
+    },
+    {
+      "epoch": 0.8040594925634296,
+      "grad_norm": 2.721195936203003,
+      "learning_rate": 9.692603856481736e-06,
+      "loss": 0.2274,
+      "step": 3590
+    },
+    {
+      "epoch": 0.8062992125984252,
+      "grad_norm": 3.3109710216522217,
+      "learning_rate": 9.689220438138099e-06,
+      "loss": 0.2086,
+      "step": 3600
+    },
+    {
+      "epoch": 0.8085389326334208,
+      "grad_norm": 6.931108474731445,
+      "learning_rate": 9.685819098536024e-06,
+      "loss": 0.223,
+      "step": 3610
+    },
+    {
+      "epoch": 0.8107786526684164,
+      "grad_norm": 5.233217239379883,
+      "learning_rate": 9.682399850674745e-06,
+      "loss": 0.2303,
+      "step": 3620
+    },
+    {
+      "epoch": 0.813018372703412,
+      "grad_norm": 1.7679535150527954,
+      "learning_rate": 9.678962707621944e-06,
+      "loss": 0.2211,
+      "step": 3630
+    },
+    {
+      "epoch": 0.8152580927384077,
+      "grad_norm": 2.661332368850708,
+      "learning_rate": 9.675507682513687e-06,
+      "loss": 0.2066,
+      "step": 3640
+    },
+    {
+      "epoch": 0.8174978127734033,
+      "grad_norm": 0.9035616517066956,
+      "learning_rate": 9.67203478855439e-06,
+      "loss": 0.2112,
+      "step": 3650
+    },
+    {
+      "epoch": 0.819737532808399,
+      "grad_norm": 4.500796318054199,
+      "learning_rate": 9.668544039016754e-06,
+      "loss": 0.2215,
+      "step": 3660
+    },
+    {
+      "epoch": 0.8219772528433946,
+      "grad_norm": 1.4607346057891846,
+      "learning_rate": 9.665035447241721e-06,
+      "loss": 0.2043,
+      "step": 3670
+    },
+    {
+      "epoch": 0.8242169728783902,
+      "grad_norm": 1.0367200374603271,
+      "learning_rate": 9.661509026638427e-06,
+      "loss": 0.2284,
+      "step": 3680
+    },
+    {
+      "epoch": 0.8264566929133859,
+      "grad_norm": 7.388817310333252,
+      "learning_rate": 9.657964790684143e-06,
+      "loss": 0.2177,
+      "step": 3690
+    },
+    {
+      "epoch": 0.8286964129483815,
+      "grad_norm": 6.648113250732422,
+      "learning_rate": 9.654402752924223e-06,
+      "loss": 0.2108,
+      "step": 3700
+    },
+    {
+      "epoch": 0.8309361329833771,
+      "grad_norm": 3.2974541187286377,
+      "learning_rate": 9.650822926972064e-06,
+      "loss": 0.2163,
+      "step": 3710
+    },
+    {
+      "epoch": 0.8331758530183727,
+      "grad_norm": 1.5554214715957642,
+      "learning_rate": 9.647225326509037e-06,
+      "loss": 0.2127,
+      "step": 3720
+    },
+    {
+      "epoch": 0.8354155730533683,
+      "grad_norm": 1.1680930852890015,
+      "learning_rate": 9.643609965284452e-06,
+      "loss": 0.21,
+      "step": 3730
+    },
+    {
+      "epoch": 0.837655293088364,
+      "grad_norm": 3.262380599975586,
+      "learning_rate": 9.639976857115492e-06,
+      "loss": 0.2234,
+      "step": 3740
+    },
+    {
+      "epoch": 0.8398950131233596,
+      "grad_norm": 1.6106623411178589,
+      "learning_rate": 9.636326015887167e-06,
+      "loss": 0.2102,
+      "step": 3750
+    },
+    {
+      "epoch": 0.8421347331583552,
+      "grad_norm": 3.9737660884857178,
+      "learning_rate": 9.632657455552258e-06,
+      "loss": 0.214,
+      "step": 3760
+    },
+    {
+      "epoch": 0.8443744531933508,
+      "grad_norm": 5.535833358764648,
+      "learning_rate": 9.628971190131266e-06,
+      "loss": 0.2171,
+      "step": 3770
+    },
+    {
+      "epoch": 0.8466141732283464,
+      "grad_norm": 1.5001612901687622,
+      "learning_rate": 9.625267233712357e-06,
+      "loss": 0.2084,
+      "step": 3780
+    },
+    {
+      "epoch": 0.848853893263342,
+      "grad_norm": 3.5858755111694336,
+      "learning_rate": 9.621545600451308e-06,
+      "loss": 0.2122,
+      "step": 3790
+    },
+    {
+      "epoch": 0.8510936132983377,
+      "grad_norm": 2.433242082595825,
+      "learning_rate": 9.617806304571455e-06,
+      "loss": 0.203,
+      "step": 3800
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.7443480491638184,
+      "learning_rate": 9.614049360363632e-06,
+      "loss": 0.2245,
+      "step": 3810
+    },
+    {
+      "epoch": 0.855573053368329,
+      "grad_norm": 10.19050407409668,
+      "learning_rate": 9.610274782186128e-06,
+      "loss": 0.2178,
+      "step": 3820
+    },
+    {
+      "epoch": 0.8578127734033246,
+      "grad_norm": 4.910433769226074,
+      "learning_rate": 9.606482584464622e-06,
+      "loss": 0.219,
+      "step": 3830
+    },
+    {
+      "epoch": 0.8600524934383202,
+      "grad_norm": 4.34425687789917,
+      "learning_rate": 9.602672781692133e-06,
+      "loss": 0.2109,
+      "step": 3840
+    },
+    {
+      "epoch": 0.8622922134733159,
+      "grad_norm": 1.3024218082427979,
+      "learning_rate": 9.598845388428957e-06,
+      "loss": 0.1945,
+      "step": 3850
+    },
+    {
+      "epoch": 0.8645319335083115,
+      "grad_norm": 3.875014066696167,
+      "learning_rate": 9.59500041930263e-06,
+      "loss": 0.2177,
+      "step": 3860
+    },
+    {
+      "epoch": 0.8667716535433071,
+      "grad_norm": 6.025304317474365,
+      "learning_rate": 9.591137889007843e-06,
+      "loss": 0.2087,
+      "step": 3870
+    },
+    {
+      "epoch": 0.8690113735783027,
+      "grad_norm": 1.9392833709716797,
+      "learning_rate": 9.587257812306417e-06,
+      "loss": 0.2315,
+      "step": 3880
+    },
+    {
+      "epoch": 0.8712510936132983,
+      "grad_norm": 1.3517054319381714,
+      "learning_rate": 9.583360204027224e-06,
+      "loss": 0.2164,
+      "step": 3890
+    },
+    {
+      "epoch": 0.873490813648294,
+      "grad_norm": 2.300626039505005,
+      "learning_rate": 9.579445079066136e-06,
+      "loss": 0.2034,
+      "step": 3900
+    },
+    {
+      "epoch": 0.8757305336832896,
+      "grad_norm": 6.352007865905762,
+      "learning_rate": 9.57551245238598e-06,
+      "loss": 0.2157,
+      "step": 3910
+    },
+    {
+      "epoch": 0.8779702537182852,
+      "grad_norm": 8.510796546936035,
+      "learning_rate": 9.571562339016463e-06,
+      "loss": 0.2137,
+      "step": 3920
+    },
+    {
+      "epoch": 0.8802099737532808,
+      "grad_norm": 1.9818949699401855,
+      "learning_rate": 9.567594754054122e-06,
+      "loss": 0.2188,
+      "step": 3930
+    },
+    {
+      "epoch": 0.8824496937882764,
+      "grad_norm": 5.979051113128662,
+      "learning_rate": 9.563609712662274e-06,
+      "loss": 0.2103,
+      "step": 3940
+    },
+    {
+      "epoch": 0.884689413823272,
+      "grad_norm": 4.557352066040039,
+      "learning_rate": 9.559607230070943e-06,
+      "loss": 0.2065,
+      "step": 3950
+    },
+    {
+      "epoch": 0.8869291338582678,
+      "grad_norm": 1.7298095226287842,
+      "learning_rate": 9.555587321576816e-06,
+      "loss": 0.2199,
+      "step": 3960
+    },
+    {
+      "epoch": 0.8891688538932634,
+      "grad_norm": 7.868046760559082,
+      "learning_rate": 9.551550002543172e-06,
+      "loss": 0.2195,
+      "step": 3970
+    },
+    {
+      "epoch": 0.891408573928259,
+      "grad_norm": 4.001582145690918,
+      "learning_rate": 9.547495288399837e-06,
+      "loss": 0.2244,
+      "step": 3980
+    },
+    {
+      "epoch": 0.8936482939632546,
+      "grad_norm": 5.262408256530762,
+      "learning_rate": 9.543423194643113e-06,
+      "loss": 0.21,
+      "step": 3990
+    },
+    {
+      "epoch": 0.8958880139982502,
+      "grad_norm": 1.7287728786468506,
+      "learning_rate": 9.539333736835723e-06,
+      "loss": 0.2081,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8958880139982502,
+      "eval_loss": 0.21423038840293884,
+      "eval_runtime": 508.214,
+      "eval_samples_per_second": 236.743,
+      "eval_steps_per_second": 14.797,
+      "eval_token_accuracy": 0.7443897795757539,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 17856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8984694308677353e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f9ce7a88c83e56706349177602a9159f64407953ba60193107c05d465599cd
+size 6712