Training in progress, step 520, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* 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
+checkpoint-520/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-520/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-520/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-520/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

checkpoint-520/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12552c83360cbb40b7a3c566e92efe5c9f577c79aed85bbd30d36bdda89cda26
+size 4967215360

checkpoint-520/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2424850b6570893df38c22b1d9af7dc852b1053913b4da209ba62a9803bd7cda
+size 3077766632

checkpoint-520/model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-520/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56effce03357eb73ff86ba34e53d20d383dae22898a61ff66a4e30743b2a99ef
+size 8172200510

checkpoint-520/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b083d9dde1f071db665fabbf1dcb68e9c94f9a61a816d0a9e4515374d00841e8
+size 14512

checkpoint-520/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a89185d5b4e3b18201a6667201b8f8cdd235301ef3dbaafd3091861a6445453d
+size 14512

checkpoint-520/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc5a935e08aec8834f6b14e299594966dcc654a63491495449bef863ea47f388
+size 1064

checkpoint-520/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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
+  }
+}

checkpoint-520/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-520/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-520/trainer_state.json

@@ -0,0 +1,3746 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 65,
+  "global_step": 520,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0019230769230769232,
+      "grad_norm": 3.5625,
+      "learning_rate": 0.0,
+      "loss": 1.1154,
+      "step": 1
+    },
+    {
+      "epoch": 0.0019230769230769232,
+      "eval_loss": 1.137184739112854,
+      "eval_runtime": 34.305,
+      "eval_samples_per_second": 68.299,
+      "eval_steps_per_second": 17.082,
+      "step": 1
+    },
+    {
+      "epoch": 0.0038461538461538464,
+      "grad_norm": 3.5,
+      "learning_rate": 1.9230769230769234e-07,
+      "loss": 1.1559,
+      "step": 2
+    },
+    {
+      "epoch": 0.0057692307692307696,
+      "grad_norm": 3.515625,
+      "learning_rate": 3.846153846153847e-07,
+      "loss": 1.1031,
+      "step": 3
+    },
+    {
+      "epoch": 0.007692307692307693,
+      "grad_norm": 3.6875,
+      "learning_rate": 5.76923076923077e-07,
+      "loss": 1.1168,
+      "step": 4
+    },
+    {
+      "epoch": 0.009615384615384616,
+      "grad_norm": 3.78125,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.0839,
+      "step": 5
+    },
+    {
+      "epoch": 0.011538461538461539,
+      "grad_norm": 3.546875,
+      "learning_rate": 9.615384615384617e-07,
+      "loss": 1.0938,
+      "step": 6
+    },
+    {
+      "epoch": 0.013461538461538462,
+      "grad_norm": 3.71875,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 1.1459,
+      "step": 7
+    },
+    {
+      "epoch": 0.015384615384615385,
+      "grad_norm": 3.671875,
+      "learning_rate": 1.3461538461538462e-06,
+      "loss": 1.0944,
+      "step": 8
+    },
+    {
+      "epoch": 0.01730769230769231,
+      "grad_norm": 3.65625,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 1.1185,
+      "step": 9
+    },
+    {
+      "epoch": 0.019230769230769232,
+      "grad_norm": 3.734375,
+      "learning_rate": 1.7307692307692308e-06,
+      "loss": 1.0774,
+      "step": 10
+    },
+    {
+      "epoch": 0.021153846153846155,
+      "grad_norm": 3.46875,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 1.1568,
+      "step": 11
+    },
+    {
+      "epoch": 0.023076923076923078,
+      "grad_norm": 3.515625,
+      "learning_rate": 2.1153846153846155e-06,
+      "loss": 1.086,
+      "step": 12
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 3.3125,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.0978,
+      "step": 13
+    },
+    {
+      "epoch": 0.026923076923076925,
+      "grad_norm": 3.359375,
+      "learning_rate": 2.5e-06,
+      "loss": 1.109,
+      "step": 14
+    },
+    {
+      "epoch": 0.028846153846153848,
+      "grad_norm": 2.953125,
+      "learning_rate": 2.6923076923076923e-06,
+      "loss": 1.0631,
+      "step": 15
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "grad_norm": 2.890625,
+      "learning_rate": 2.8846153846153845e-06,
+      "loss": 1.1241,
+      "step": 16
+    },
+    {
+      "epoch": 0.032692307692307694,
+      "grad_norm": 2.6875,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 1.0644,
+      "step": 17
+    },
+    {
+      "epoch": 0.03461538461538462,
+      "grad_norm": 2.640625,
+      "learning_rate": 3.2692307692307696e-06,
+      "loss": 1.0823,
+      "step": 18
+    },
+    {
+      "epoch": 0.03653846153846154,
+      "grad_norm": 2.703125,
+      "learning_rate": 3.4615384615384617e-06,
+      "loss": 1.0494,
+      "step": 19
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 2.375,
+      "learning_rate": 3.653846153846154e-06,
+      "loss": 1.0778,
+      "step": 20
+    },
+    {
+      "epoch": 0.04038461538461539,
+      "grad_norm": 2.359375,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.9911,
+      "step": 21
+    },
+    {
+      "epoch": 0.04230769230769231,
+      "grad_norm": 1.9296875,
+      "learning_rate": 4.0384615384615385e-06,
+      "loss": 1.1214,
+      "step": 22
+    },
+    {
+      "epoch": 0.04423076923076923,
+      "grad_norm": 1.859375,
+      "learning_rate": 4.230769230769231e-06,
+      "loss": 1.0294,
+      "step": 23
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 1.6796875,
+      "learning_rate": 4.423076923076924e-06,
+      "loss": 1.0473,
+      "step": 24
+    },
+    {
+      "epoch": 0.04807692307692308,
+      "grad_norm": 1.4765625,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 1.0562,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.4140625,
+      "learning_rate": 4.807692307692308e-06,
+      "loss": 1.0273,
+      "step": 26
+    },
+    {
+      "epoch": 0.051923076923076926,
+      "grad_norm": 1.2890625,
+      "learning_rate": 5e-06,
+      "loss": 1.0713,
+      "step": 27
+    },
+    {
+      "epoch": 0.05384615384615385,
+      "grad_norm": 1.2578125,
+      "learning_rate": 5.192307692307693e-06,
+      "loss": 1.0218,
+      "step": 28
+    },
+    {
+      "epoch": 0.05576923076923077,
+      "grad_norm": 1.2265625,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 1.0322,
+      "step": 29
+    },
+    {
+      "epoch": 0.057692307692307696,
+      "grad_norm": 1.125,
+      "learning_rate": 5.576923076923077e-06,
+      "loss": 0.9993,
+      "step": 30
+    },
+    {
+      "epoch": 0.05961538461538462,
+      "grad_norm": 1.1796875,
+      "learning_rate": 5.769230769230769e-06,
+      "loss": 0.9909,
+      "step": 31
+    },
+    {
+      "epoch": 0.06153846153846154,
+      "grad_norm": 1.078125,
+      "learning_rate": 5.961538461538462e-06,
+      "loss": 1.0497,
+      "step": 32
+    },
+    {
+      "epoch": 0.06346153846153846,
+      "grad_norm": 1.078125,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 1.0699,
+      "step": 33
+    },
+    {
+      "epoch": 0.06538461538461539,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6.3461538461538466e-06,
+      "loss": 1.0065,
+      "step": 34
+    },
+    {
+      "epoch": 0.0673076923076923,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.538461538461539e-06,
+      "loss": 0.9839,
+      "step": 35
+    },
+    {
+      "epoch": 0.06923076923076923,
+      "grad_norm": 1.421875,
+      "learning_rate": 6.730769230769232e-06,
+      "loss": 1.0069,
+      "step": 36
+    },
+    {
+      "epoch": 0.07115384615384615,
+      "grad_norm": 1.0546875,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 1.0441,
+      "step": 37
+    },
+    {
+      "epoch": 0.07307692307692308,
+      "grad_norm": 1.015625,
+      "learning_rate": 7.115384615384616e-06,
+      "loss": 0.9343,
+      "step": 38
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 1.0234375,
+      "learning_rate": 7.307692307692308e-06,
+      "loss": 0.9853,
+      "step": 39
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 0.98046875,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.9502,
+      "step": 40
+    },
+    {
+      "epoch": 0.07884615384615384,
+      "grad_norm": 0.984375,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.987,
+      "step": 41
+    },
+    {
+      "epoch": 0.08076923076923077,
+      "grad_norm": 1.0234375,
+      "learning_rate": 7.884615384615384e-06,
+      "loss": 1.009,
+      "step": 42
+    },
+    {
+      "epoch": 0.08269230769230769,
+      "grad_norm": 0.9765625,
+      "learning_rate": 8.076923076923077e-06,
+      "loss": 1.0174,
+      "step": 43
+    },
+    {
+      "epoch": 0.08461538461538462,
+      "grad_norm": 0.99609375,
+      "learning_rate": 8.26923076923077e-06,
+      "loss": 1.0515,
+      "step": 44
+    },
+    {
+      "epoch": 0.08653846153846154,
+      "grad_norm": 1.0234375,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 1.0196,
+      "step": 45
+    },
+    {
+      "epoch": 0.08846153846153847,
+      "grad_norm": 0.94921875,
+      "learning_rate": 8.653846153846155e-06,
+      "loss": 0.9957,
+      "step": 46
+    },
+    {
+      "epoch": 0.09038461538461538,
+      "grad_norm": 1.0078125,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 0.9422,
+      "step": 47
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.97265625,
+      "learning_rate": 9.03846153846154e-06,
+      "loss": 0.9527,
+      "step": 48
+    },
+    {
+      "epoch": 0.09423076923076923,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.9944,
+      "step": 49
+    },
+    {
+      "epoch": 0.09615384615384616,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.423076923076923e-06,
+      "loss": 0.9794,
+      "step": 50
+    },
+    {
+      "epoch": 0.09807692307692308,
+      "grad_norm": 1.03125,
+      "learning_rate": 9.615384615384616e-06,
+      "loss": 1.0226,
+      "step": 51
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.0,
+      "learning_rate": 9.807692307692308e-06,
+      "loss": 1.0325,
+      "step": 52
+    },
+    {
+      "epoch": 0.10192307692307692,
+      "grad_norm": 1.0234375,
+      "learning_rate": 1e-05,
+      "loss": 0.9893,
+      "step": 53
+    },
+    {
+      "epoch": 0.10384615384615385,
+      "grad_norm": 0.98046875,
+      "learning_rate": 9.999974723001716e-06,
+      "loss": 1.0543,
+      "step": 54
+    },
+    {
+      "epoch": 0.10576923076923077,
+      "grad_norm": 1.03125,
+      "learning_rate": 9.999898892262433e-06,
+      "loss": 1.0227,
+      "step": 55
+    },
+    {
+      "epoch": 0.1076923076923077,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.999772508548863e-06,
+      "loss": 1.067,
+      "step": 56
+    },
+    {
+      "epoch": 0.10961538461538461,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.999595573138845e-06,
+      "loss": 0.9794,
+      "step": 57
+    },
+    {
+      "epoch": 0.11153846153846154,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.999368087821337e-06,
+      "loss": 1.0166,
+      "step": 58
+    },
+    {
+      "epoch": 0.11346153846153846,
+      "grad_norm": 1.0546875,
+      "learning_rate": 9.999090054896397e-06,
+      "loss": 1.0092,
+      "step": 59
+    },
+    {
+      "epoch": 0.11538461538461539,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.99876147717516e-06,
+      "loss": 0.9518,
+      "step": 60
+    },
+    {
+      "epoch": 0.11730769230769231,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.99838235797981e-06,
+      "loss": 0.9558,
+      "step": 61
+    },
+    {
+      "epoch": 0.11923076923076924,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.997952701143547e-06,
+      "loss": 1.0134,
+      "step": 62
+    },
+    {
+      "epoch": 0.12115384615384615,
+      "grad_norm": 1.03125,
+      "learning_rate": 9.997472511010543e-06,
+      "loss": 0.8941,
+      "step": 63
+    },
+    {
+      "epoch": 0.12307692307692308,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.996941792435903e-06,
+      "loss": 0.9207,
+      "step": 64
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.996360550785619e-06,
+      "loss": 0.9351,
+      "step": 65
+    },
+    {
+      "epoch": 0.125,
+      "eval_loss": 1.0073611736297607,
+      "eval_runtime": 34.5277,
+      "eval_samples_per_second": 67.859,
+      "eval_steps_per_second": 16.972,
+      "step": 65
+    },
+    {
+      "epoch": 0.12692307692307692,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.995728791936505e-06,
+      "loss": 1.0024,
+      "step": 66
+    },
+    {
+      "epoch": 0.12884615384615383,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.995046522276152e-06,
+      "loss": 1.0015,
+      "step": 67
+    },
+    {
+      "epoch": 0.13076923076923078,
+      "grad_norm": 1.3359375,
+      "learning_rate": 9.994313748702848e-06,
+      "loss": 0.9595,
+      "step": 68
+    },
+    {
+      "epoch": 0.1326923076923077,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.993530478625524e-06,
+      "loss": 0.9331,
+      "step": 69
+    },
+    {
+      "epoch": 0.1346153846153846,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.992696719963662e-06,
+      "loss": 0.9174,
+      "step": 70
+    },
+    {
+      "epoch": 0.13653846153846153,
+      "grad_norm": 1.0546875,
+      "learning_rate": 9.99181248114723e-06,
+      "loss": 1.009,
+      "step": 71
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.990877771116588e-06,
+      "loss": 0.9661,
+      "step": 72
+    },
+    {
+      "epoch": 0.14038461538461539,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.989892599322404e-06,
+      "loss": 0.9398,
+      "step": 73
+    },
+    {
+      "epoch": 0.1423076923076923,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.988856975725551e-06,
+      "loss": 0.9973,
+      "step": 74
+    },
+    {
+      "epoch": 0.14423076923076922,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.987770910797014e-06,
+      "loss": 0.8935,
+      "step": 75
+    },
+    {
+      "epoch": 0.14615384615384616,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.986634415517774e-06,
+      "loss": 0.958,
+      "step": 76
+    },
+    {
+      "epoch": 0.14807692307692308,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.985447501378706e-06,
+      "loss": 0.9349,
+      "step": 77
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.984210180380464e-06,
+      "loss": 0.9474,
+      "step": 78
+    },
+    {
+      "epoch": 0.1519230769230769,
+      "grad_norm": 1.0234375,
+      "learning_rate": 9.98292246503335e-06,
+      "loss": 0.9704,
+      "step": 79
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.981584368357198e-06,
+      "loss": 0.9745,
+      "step": 80
+    },
+    {
+      "epoch": 0.15576923076923077,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.980195903881231e-06,
+      "loss": 0.9527,
+      "step": 81
+    },
+    {
+      "epoch": 0.1576923076923077,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.978757085643937e-06,
+      "loss": 0.9732,
+      "step": 82
+    },
+    {
+      "epoch": 0.1596153846153846,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.97726792819292e-06,
+      "loss": 0.9304,
+      "step": 83
+    },
+    {
+      "epoch": 0.16153846153846155,
+      "grad_norm": 1.03125,
+      "learning_rate": 9.975728446584748e-06,
+      "loss": 0.9999,
+      "step": 84
+    },
+    {
+      "epoch": 0.16346153846153846,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.974138656384815e-06,
+      "loss": 0.9477,
+      "step": 85
+    },
+    {
+      "epoch": 0.16538461538461538,
+      "grad_norm": 1.0234375,
+      "learning_rate": 9.97249857366717e-06,
+      "loss": 0.9661,
+      "step": 86
+    },
+    {
+      "epoch": 0.1673076923076923,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.970808215014357e-06,
+      "loss": 0.9763,
+      "step": 87
+    },
+    {
+      "epoch": 0.16923076923076924,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.969067597517255e-06,
+      "loss": 0.9292,
+      "step": 88
+    },
+    {
+      "epoch": 0.17115384615384616,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.967276738774897e-06,
+      "loss": 0.9083,
+      "step": 89
+    },
+    {
+      "epoch": 0.17307692307692307,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.9654356568943e-06,
+      "loss": 0.9764,
+      "step": 90
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.96354437049027e-06,
+      "loss": 0.9924,
+      "step": 91
+    },
+    {
+      "epoch": 0.17692307692307693,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.961602898685225e-06,
+      "loss": 0.9551,
+      "step": 92
+    },
+    {
+      "epoch": 0.17884615384615385,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.959611261108999e-06,
+      "loss": 1.0074,
+      "step": 93
+    },
+    {
+      "epoch": 0.18076923076923077,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.957569477898636e-06,
+      "loss": 1.0348,
+      "step": 94
+    },
+    {
+      "epoch": 0.18269230769230768,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.955477569698197e-06,
+      "loss": 0.9745,
+      "step": 95
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.95333555765855e-06,
+      "loss": 0.9278,
+      "step": 96
+    },
+    {
+      "epoch": 0.18653846153846154,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.951143463437145e-06,
+      "loss": 0.9497,
+      "step": 97
+    },
+    {
+      "epoch": 0.18846153846153846,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.948901309197807e-06,
+      "loss": 1.0283,
+      "step": 98
+    },
+    {
+      "epoch": 0.19038461538461537,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.946609117610508e-06,
+      "loss": 0.9384,
+      "step": 99
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 1.0546875,
+      "learning_rate": 9.94426691185114e-06,
+      "loss": 1.0316,
+      "step": 100
+    },
+    {
+      "epoch": 0.19423076923076923,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.94187471560127e-06,
+      "loss": 0.9401,
+      "step": 101
+    },
+    {
+      "epoch": 0.19615384615384615,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.939432553047919e-06,
+      "loss": 0.9112,
+      "step": 102
+    },
+    {
+      "epoch": 0.19807692307692307,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.936940448883299e-06,
+      "loss": 0.9085,
+      "step": 103
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.934398428304577e-06,
+      "loss": 0.9583,
+      "step": 104
+    },
+    {
+      "epoch": 0.20192307692307693,
+      "grad_norm": 1.1171875,
+      "learning_rate": 9.931806517013612e-06,
+      "loss": 0.9923,
+      "step": 105
+    },
+    {
+      "epoch": 0.20384615384615384,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.929164741216702e-06,
+      "loss": 0.9281,
+      "step": 106
+    },
+    {
+      "epoch": 0.20576923076923076,
+      "grad_norm": 2.03125,
+      "learning_rate": 9.926473127624306e-06,
+      "loss": 0.9767,
+      "step": 107
+    },
+    {
+      "epoch": 0.2076923076923077,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.923731703450794e-06,
+      "loss": 0.9255,
+      "step": 108
+    },
+    {
+      "epoch": 0.20961538461538462,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.920940496414153e-06,
+      "loss": 0.9394,
+      "step": 109
+    },
+    {
+      "epoch": 0.21153846153846154,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.91809953473572e-06,
+      "loss": 0.8881,
+      "step": 110
+    },
+    {
+      "epoch": 0.21346153846153845,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.915208847139883e-06,
+      "loss": 0.9327,
+      "step": 111
+    },
+    {
+      "epoch": 0.2153846153846154,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.912268462853811e-06,
+      "loss": 0.9637,
+      "step": 112
+    },
+    {
+      "epoch": 0.2173076923076923,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.909278411607134e-06,
+      "loss": 0.904,
+      "step": 113
+    },
+    {
+      "epoch": 0.21923076923076923,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.906238723631662e-06,
+      "loss": 1.0109,
+      "step": 114
+    },
+    {
+      "epoch": 0.22115384615384615,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.903149429661072e-06,
+      "loss": 0.9612,
+      "step": 115
+    },
+    {
+      "epoch": 0.2230769230769231,
+      "grad_norm": 1.140625,
+      "learning_rate": 9.90001056093059e-06,
+      "loss": 0.966,
+      "step": 116
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.896822149176695e-06,
+      "loss": 0.9076,
+      "step": 117
+    },
+    {
+      "epoch": 0.22692307692307692,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.893584226636773e-06,
+      "loss": 0.9435,
+      "step": 118
+    },
+    {
+      "epoch": 0.22884615384615384,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.89029682604881e-06,
+      "loss": 0.9738,
+      "step": 119
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.886959980651056e-06,
+      "loss": 1.0009,
+      "step": 120
+    },
+    {
+      "epoch": 0.2326923076923077,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.883573724181683e-06,
+      "loss": 0.9864,
+      "step": 121
+    },
+    {
+      "epoch": 0.23461538461538461,
+      "grad_norm": 1.125,
+      "learning_rate": 9.880138090878452e-06,
+      "loss": 0.9537,
+      "step": 122
+    },
+    {
+      "epoch": 0.23653846153846153,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.87665311547836e-06,
+      "loss": 1.0204,
+      "step": 123
+    },
+    {
+      "epoch": 0.23846153846153847,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.873118833217294e-06,
+      "loss": 0.9623,
+      "step": 124
+    },
+    {
+      "epoch": 0.2403846153846154,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.869535279829674e-06,
+      "loss": 0.9458,
+      "step": 125
+    },
+    {
+      "epoch": 0.2423076923076923,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.86590249154809e-06,
+      "loss": 0.9223,
+      "step": 126
+    },
+    {
+      "epoch": 0.24423076923076922,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.862220505102933e-06,
+      "loss": 0.9847,
+      "step": 127
+    },
+    {
+      "epoch": 0.24615384615384617,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.858489357722028e-06,
+      "loss": 0.9633,
+      "step": 128
+    },
+    {
+      "epoch": 0.24807692307692308,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.896,
+      "step": 129
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.850879731549188e-06,
+      "loss": 0.8884,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.9758404493331909,
+      "eval_runtime": 34.4304,
+      "eval_samples_per_second": 68.05,
+      "eval_steps_per_second": 17.02,
+      "step": 130
+    },
+    {
+      "epoch": 0.2519230769230769,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.847001329696653e-06,
+      "loss": 0.9047,
+      "step": 131
+    },
+    {
+      "epoch": 0.25384615384615383,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.843073920786402e-06,
+      "loss": 0.979,
+      "step": 132
+    },
+    {
+      "epoch": 0.25576923076923075,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.839097544527674e-06,
+      "loss": 0.9224,
+      "step": 133
+    },
+    {
+      "epoch": 0.25769230769230766,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.835072241124815e-06,
+      "loss": 0.8739,
+      "step": 134
+    },
+    {
+      "epoch": 0.25961538461538464,
+      "grad_norm": 1.125,
+      "learning_rate": 9.830998051276858e-06,
+      "loss": 0.9326,
+      "step": 135
+    },
+    {
+      "epoch": 0.26153846153846155,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.82687501617712e-06,
+      "loss": 0.9303,
+      "step": 136
+    },
+    {
+      "epoch": 0.26346153846153847,
+      "grad_norm": 1.1171875,
+      "learning_rate": 9.822703177512783e-06,
+      "loss": 1.0002,
+      "step": 137
+    },
+    {
+      "epoch": 0.2653846153846154,
+      "grad_norm": 1.125,
+      "learning_rate": 9.818482577464466e-06,
+      "loss": 0.9562,
+      "step": 138
+    },
+    {
+      "epoch": 0.2673076923076923,
+      "grad_norm": 1.140625,
+      "learning_rate": 9.814213258705813e-06,
+      "loss": 0.9212,
+      "step": 139
+    },
+    {
+      "epoch": 0.2692307692307692,
+      "grad_norm": 1.125,
+      "learning_rate": 9.809895264403046e-06,
+      "loss": 0.9679,
+      "step": 140
+    },
+    {
+      "epoch": 0.27115384615384613,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.805528638214543e-06,
+      "loss": 0.9903,
+      "step": 141
+    },
+    {
+      "epoch": 0.27307692307692305,
+      "grad_norm": 1.1171875,
+      "learning_rate": 9.801113424290381e-06,
+      "loss": 0.9754,
+      "step": 142
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 1.125,
+      "learning_rate": 9.796649667271905e-06,
+      "loss": 0.8977,
+      "step": 143
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.792137412291265e-06,
+      "loss": 0.8798,
+      "step": 144
+    },
+    {
+      "epoch": 0.27884615384615385,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.787576704970965e-06,
+      "loss": 0.9382,
+      "step": 145
+    },
+    {
+      "epoch": 0.28076923076923077,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.7829675914234e-06,
+      "loss": 0.9692,
+      "step": 146
+    },
+    {
+      "epoch": 0.2826923076923077,
+      "grad_norm": 1.125,
+      "learning_rate": 9.778310118250397e-06,
+      "loss": 0.8939,
+      "step": 147
+    },
+    {
+      "epoch": 0.2846153846153846,
+      "grad_norm": 1.1640625,
+      "learning_rate": 9.77360433254273e-06,
+      "loss": 1.0047,
+      "step": 148
+    },
+    {
+      "epoch": 0.2865384615384615,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.768850281879651e-06,
+      "loss": 0.9484,
+      "step": 149
+    },
+    {
+      "epoch": 0.28846153846153844,
+      "grad_norm": 1.1171875,
+      "learning_rate": 9.764048014328417e-06,
+      "loss": 0.9004,
+      "step": 150
+    },
+    {
+      "epoch": 0.2903846153846154,
+      "grad_norm": 1.1171875,
+      "learning_rate": 9.759197578443787e-06,
+      "loss": 0.9281,
+      "step": 151
+    },
+    {
+      "epoch": 0.2923076923076923,
+      "grad_norm": 1.2109375,
+      "learning_rate": 9.754299023267548e-06,
+      "loss": 0.9638,
+      "step": 152
+    },
+    {
+      "epoch": 0.29423076923076924,
+      "grad_norm": 1.1640625,
+      "learning_rate": 9.74935239832801e-06,
+      "loss": 0.9366,
+      "step": 153
+    },
+    {
+      "epoch": 0.29615384615384616,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.7443577536395e-06,
+      "loss": 0.9125,
+      "step": 154
+    },
+    {
+      "epoch": 0.2980769230769231,
+      "grad_norm": 1.125,
+      "learning_rate": 9.739315139701868e-06,
+      "loss": 0.9226,
+      "step": 155
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.1484375,
+      "learning_rate": 9.734224607499978e-06,
+      "loss": 0.9384,
+      "step": 156
+    },
+    {
+      "epoch": 0.3019230769230769,
+      "grad_norm": 1.2890625,
+      "learning_rate": 9.729086208503174e-06,
+      "loss": 0.8788,
+      "step": 157
+    },
+    {
+      "epoch": 0.3038461538461538,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.723899994664779e-06,
+      "loss": 0.9672,
+      "step": 158
+    },
+    {
+      "epoch": 0.3057692307692308,
+      "grad_norm": 1.125,
+      "learning_rate": 9.71866601842156e-06,
+      "loss": 0.8889,
+      "step": 159
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.713384332693199e-06,
+      "loss": 0.8975,
+      "step": 160
+    },
+    {
+      "epoch": 0.3096153846153846,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.708054990881763e-06,
+      "loss": 0.9614,
+      "step": 161
+    },
+    {
+      "epoch": 0.31153846153846154,
+      "grad_norm": 1.125,
+      "learning_rate": 9.702678046871157e-06,
+      "loss": 0.9061,
+      "step": 162
+    },
+    {
+      "epoch": 0.31346153846153846,
+      "grad_norm": 1.1484375,
+      "learning_rate": 9.69725355502658e-06,
+      "loss": 0.9322,
+      "step": 163
+    },
+    {
+      "epoch": 0.3153846153846154,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.691781570193983e-06,
+      "loss": 0.9512,
+      "step": 164
+    },
+    {
+      "epoch": 0.3173076923076923,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.686262147699507e-06,
+      "loss": 1.0271,
+      "step": 165
+    },
+    {
+      "epoch": 0.3192307692307692,
+      "grad_norm": 1.125,
+      "learning_rate": 9.680695343348923e-06,
+      "loss": 0.9529,
+      "step": 166
+    },
+    {
+      "epoch": 0.3211538461538462,
+      "grad_norm": 1.203125,
+      "learning_rate": 9.675081213427076e-06,
+      "loss": 0.9636,
+      "step": 167
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.669419814697303e-06,
+      "loss": 0.8879,
+      "step": 168
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 1.125,
+      "learning_rate": 9.663711204400872e-06,
+      "loss": 0.8889,
+      "step": 169
+    },
+    {
+      "epoch": 0.3269230769230769,
+      "grad_norm": 1.0546875,
+      "learning_rate": 9.657955440256396e-06,
+      "loss": 0.9735,
+      "step": 170
+    },
+    {
+      "epoch": 0.32884615384615384,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.65215258045925e-06,
+      "loss": 1.0088,
+      "step": 171
+    },
+    {
+      "epoch": 0.33076923076923076,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.64630268368099e-06,
+      "loss": 0.9318,
+      "step": 172
+    },
+    {
+      "epoch": 0.3326923076923077,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.640405809068743e-06,
+      "loss": 0.9902,
+      "step": 173
+    },
+    {
+      "epoch": 0.3346153846153846,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.634462016244625e-06,
+      "loss": 0.9315,
+      "step": 174
+    },
+    {
+      "epoch": 0.33653846153846156,
+      "grad_norm": 1.0546875,
+      "learning_rate": 9.628471365305134e-06,
+      "loss": 0.931,
+      "step": 175
+    },
+    {
+      "epoch": 0.3384615384615385,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.622433916820539e-06,
+      "loss": 0.9167,
+      "step": 176
+    },
+    {
+      "epoch": 0.3403846153846154,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.616349731834271e-06,
+      "loss": 0.9214,
+      "step": 177
+    },
+    {
+      "epoch": 0.3423076923076923,
+      "grad_norm": 1.1171875,
+      "learning_rate": 9.610218871862303e-06,
+      "loss": 0.945,
+      "step": 178
+    },
+    {
+      "epoch": 0.34423076923076923,
+      "grad_norm": 1.1171875,
+      "learning_rate": 9.604041398892528e-06,
+      "loss": 0.9445,
+      "step": 179
+    },
+    {
+      "epoch": 0.34615384615384615,
+      "grad_norm": 1.140625,
+      "learning_rate": 9.597817375384138e-06,
+      "loss": 1.0135,
+      "step": 180
+    },
+    {
+      "epoch": 0.34807692307692306,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.591546864266983e-06,
+      "loss": 0.9393,
+      "step": 181
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.1171875,
+      "learning_rate": 9.585229928940944e-06,
+      "loss": 0.9273,
+      "step": 182
+    },
+    {
+      "epoch": 0.35192307692307695,
+      "grad_norm": 1.1171875,
+      "learning_rate": 9.578866633275289e-06,
+      "loss": 1.0091,
+      "step": 183
+    },
+    {
+      "epoch": 0.35384615384615387,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.572457041608018e-06,
+      "loss": 0.9301,
+      "step": 184
+    },
+    {
+      "epoch": 0.3557692307692308,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.56600121874523e-06,
+      "loss": 0.991,
+      "step": 185
+    },
+    {
+      "epoch": 0.3576923076923077,
+      "grad_norm": 1.125,
+      "learning_rate": 9.55949922996045e-06,
+      "loss": 0.8897,
+      "step": 186
+    },
+    {
+      "epoch": 0.3596153846153846,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.55295114099399e-06,
+      "loss": 0.8844,
+      "step": 187
+    },
+    {
+      "epoch": 0.36153846153846153,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.546357018052254e-06,
+      "loss": 0.9226,
+      "step": 188
+    },
+    {
+      "epoch": 0.36346153846153845,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.539716927807102e-06,
+      "loss": 0.9273,
+      "step": 189
+    },
+    {
+      "epoch": 0.36538461538461536,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.533030937395151e-06,
+      "loss": 0.9116,
+      "step": 190
+    },
+    {
+      "epoch": 0.36730769230769234,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.526299114417108e-06,
+      "loss": 0.9732,
+      "step": 191
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.519521526937087e-06,
+      "loss": 0.918,
+      "step": 192
+    },
+    {
+      "epoch": 0.37115384615384617,
+      "grad_norm": 1.03125,
+      "learning_rate": 9.512698243481914e-06,
+      "loss": 0.9045,
+      "step": 193
+    },
+    {
+      "epoch": 0.3730769230769231,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.505829333040437e-06,
+      "loss": 0.9189,
+      "step": 194
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.498914865062831e-06,
+      "loss": 0.9853,
+      "step": 195
+    },
+    {
+      "epoch": 0.375,
+      "eval_loss": 0.9608431458473206,
+      "eval_runtime": 34.5143,
+      "eval_samples_per_second": 67.885,
+      "eval_steps_per_second": 16.978,
+      "step": 195
+    },
+    {
+      "epoch": 0.3769230769230769,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.491954909459895e-06,
+      "loss": 0.9078,
+      "step": 196
+    },
+    {
+      "epoch": 0.37884615384615383,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.484949536602343e-06,
+      "loss": 0.8859,
+      "step": 197
+    },
+    {
+      "epoch": 0.38076923076923075,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.477898817320094e-06,
+      "loss": 0.9183,
+      "step": 198
+    },
+    {
+      "epoch": 0.38269230769230766,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.470802822901558e-06,
+      "loss": 0.918,
+      "step": 199
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.463661625092907e-06,
+      "loss": 0.9444,
+      "step": 200
+    },
+    {
+      "epoch": 0.38653846153846155,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.45647529609736e-06,
+      "loss": 0.8958,
+      "step": 201
+    },
+    {
+      "epoch": 0.38846153846153847,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.44924390857445e-06,
+      "loss": 0.9071,
+      "step": 202
+    },
+    {
+      "epoch": 0.3903846153846154,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.44196753563928e-06,
+      "loss": 0.962,
+      "step": 203
+    },
+    {
+      "epoch": 0.3923076923076923,
+      "grad_norm": 1.0546875,
+      "learning_rate": 9.434646250861801e-06,
+      "loss": 0.9814,
+      "step": 204
+    },
+    {
+      "epoch": 0.3942307692307692,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.427280128266049e-06,
+      "loss": 0.9873,
+      "step": 205
+    },
+    {
+      "epoch": 0.39615384615384613,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.419869242329417e-06,
+      "loss": 0.9034,
+      "step": 206
+    },
+    {
+      "epoch": 0.39807692307692305,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.412413667981884e-06,
+      "loss": 0.8953,
+      "step": 207
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.404913480605264e-06,
+      "loss": 1.0005,
+      "step": 208
+    },
+    {
+      "epoch": 0.40192307692307694,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.397368756032445e-06,
+      "loss": 0.9455,
+      "step": 209
+    },
+    {
+      "epoch": 0.40384615384615385,
+      "grad_norm": 1.0234375,
+      "learning_rate": 9.389779570546628e-06,
+      "loss": 0.9336,
+      "step": 210
+    },
+    {
+      "epoch": 0.40576923076923077,
+      "grad_norm": 1.1953125,
+      "learning_rate": 9.38214600088054e-06,
+      "loss": 0.8907,
+      "step": 211
+    },
+    {
+      "epoch": 0.4076923076923077,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.374468124215676e-06,
+      "loss": 0.8735,
+      "step": 212
+    },
+    {
+      "epoch": 0.4096153846153846,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.366746018181503e-06,
+      "loss": 0.9682,
+      "step": 213
+    },
+    {
+      "epoch": 0.4115384615384615,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.358979760854686e-06,
+      "loss": 0.9069,
+      "step": 214
+    },
+    {
+      "epoch": 0.41346153846153844,
+      "grad_norm": 0.99609375,
+      "learning_rate": 9.351169430758293e-06,
+      "loss": 0.9371,
+      "step": 215
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.343315106861008e-06,
+      "loss": 0.9691,
+      "step": 216
+    },
+    {
+      "epoch": 0.4173076923076923,
+      "grad_norm": 1.0234375,
+      "learning_rate": 9.33541686857632e-06,
+      "loss": 0.9521,
+      "step": 217
+    },
+    {
+      "epoch": 0.41923076923076924,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.327474795761734e-06,
+      "loss": 0.9503,
+      "step": 218
+    },
+    {
+      "epoch": 0.42115384615384616,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.31948896871795e-06,
+      "loss": 0.9311,
+      "step": 219
+    },
+    {
+      "epoch": 0.4230769230769231,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.311459468188066e-06,
+      "loss": 0.8998,
+      "step": 220
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.303386375356752e-06,
+      "loss": 0.8776,
+      "step": 221
+    },
+    {
+      "epoch": 0.4269230769230769,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.295269771849426e-06,
+      "loss": 0.9003,
+      "step": 222
+    },
+    {
+      "epoch": 0.4288461538461538,
+      "grad_norm": 0.98046875,
+      "learning_rate": 9.28710973973144e-06,
+      "loss": 0.9597,
+      "step": 223
+    },
+    {
+      "epoch": 0.4307692307692308,
+      "grad_norm": 0.96875,
+      "learning_rate": 9.278906361507238e-06,
+      "loss": 0.8842,
+      "step": 224
+    },
+    {
+      "epoch": 0.4326923076923077,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.270659720119533e-06,
+      "loss": 0.9524,
+      "step": 225
+    },
+    {
+      "epoch": 0.4346153846153846,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.262369898948462e-06,
+      "loss": 0.9271,
+      "step": 226
+    },
+    {
+      "epoch": 0.43653846153846154,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.254036981810741e-06,
+      "loss": 0.9627,
+      "step": 227
+    },
+    {
+      "epoch": 0.43846153846153846,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.245661052958823e-06,
+      "loss": 0.9305,
+      "step": 228
+    },
+    {
+      "epoch": 0.4403846153846154,
+      "grad_norm": 1.03125,
+      "learning_rate": 9.237242197080045e-06,
+      "loss": 0.9855,
+      "step": 229
+    },
+    {
+      "epoch": 0.4423076923076923,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.22878049929577e-06,
+      "loss": 0.9237,
+      "step": 230
+    },
+    {
+      "epoch": 0.4442307692307692,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.220276045160524e-06,
+      "loss": 0.9733,
+      "step": 231
+    },
+    {
+      "epoch": 0.4461538461538462,
+      "grad_norm": 0.9765625,
+      "learning_rate": 9.211728920661136e-06,
+      "loss": 0.9613,
+      "step": 232
+    },
+    {
+      "epoch": 0.4480769230769231,
+      "grad_norm": 0.9609375,
+      "learning_rate": 9.203139212215868e-06,
+      "loss": 0.9317,
+      "step": 233
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.99609375,
+      "learning_rate": 9.19450700667354e-06,
+      "loss": 0.9067,
+      "step": 234
+    },
+    {
+      "epoch": 0.4519230769230769,
+      "grad_norm": 0.9296875,
+      "learning_rate": 9.185832391312644e-06,
+      "loss": 0.9088,
+      "step": 235
+    },
+    {
+      "epoch": 0.45384615384615384,
+      "grad_norm": 0.953125,
+      "learning_rate": 9.17711545384048e-06,
+      "loss": 0.9359,
+      "step": 236
+    },
+    {
+      "epoch": 0.45576923076923076,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.168356282392253e-06,
+      "loss": 0.96,
+      "step": 237
+    },
+    {
+      "epoch": 0.4576923076923077,
+      "grad_norm": 0.90234375,
+      "learning_rate": 9.159554965530184e-06,
+      "loss": 0.9193,
+      "step": 238
+    },
+    {
+      "epoch": 0.4596153846153846,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.150711592242627e-06,
+      "loss": 0.9439,
+      "step": 239
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.14182625194315e-06,
+      "loss": 0.8804,
+      "step": 240
+    },
+    {
+      "epoch": 0.4634615384615385,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.132899034469648e-06,
+      "loss": 0.916,
+      "step": 241
+    },
+    {
+      "epoch": 0.4653846153846154,
+      "grad_norm": 0.98828125,
+      "learning_rate": 9.123930030083425e-06,
+      "loss": 0.8793,
+      "step": 242
+    },
+    {
+      "epoch": 0.4673076923076923,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.114919329468283e-06,
+      "loss": 0.9162,
+      "step": 243
+    },
+    {
+      "epoch": 0.46923076923076923,
+      "grad_norm": 0.98046875,
+      "learning_rate": 9.10586702372961e-06,
+      "loss": 0.9098,
+      "step": 244
+    },
+    {
+      "epoch": 0.47115384615384615,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.09677320439345e-06,
+      "loss": 0.9219,
+      "step": 245
+    },
+    {
+      "epoch": 0.47307692307692306,
+      "grad_norm": 0.921875,
+      "learning_rate": 9.087637963405586e-06,
+      "loss": 0.9554,
+      "step": 246
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.9140625,
+      "learning_rate": 9.07846139313061e-06,
+      "loss": 0.9994,
+      "step": 247
+    },
+    {
+      "epoch": 0.47692307692307695,
+      "grad_norm": 0.96875,
+      "learning_rate": 9.069243586350976e-06,
+      "loss": 0.9052,
+      "step": 248
+    },
+    {
+      "epoch": 0.47884615384615387,
+      "grad_norm": 0.94921875,
+      "learning_rate": 9.059984636266082e-06,
+      "loss": 0.9232,
+      "step": 249
+    },
+    {
+      "epoch": 0.4807692307692308,
+      "grad_norm": 0.97265625,
+      "learning_rate": 9.050684636491317e-06,
+      "loss": 0.8964,
+      "step": 250
+    },
+    {
+      "epoch": 0.4826923076923077,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.041343681057106e-06,
+      "loss": 0.9386,
+      "step": 251
+    },
+    {
+      "epoch": 0.4846153846153846,
+      "grad_norm": 0.8984375,
+      "learning_rate": 9.03196186440798e-06,
+      "loss": 0.9078,
+      "step": 252
+    },
+    {
+      "epoch": 0.48653846153846153,
+      "grad_norm": 0.96875,
+      "learning_rate": 9.022539281401601e-06,
+      "loss": 0.9056,
+      "step": 253
+    },
+    {
+      "epoch": 0.48846153846153845,
+      "grad_norm": 0.8671875,
+      "learning_rate": 9.013076027307817e-06,
+      "loss": 0.8973,
+      "step": 254
+    },
+    {
+      "epoch": 0.49038461538461536,
+      "grad_norm": 0.921875,
+      "learning_rate": 9.00357219780769e-06,
+      "loss": 0.9663,
+      "step": 255
+    },
+    {
+      "epoch": 0.49230769230769234,
+      "grad_norm": 0.90234375,
+      "learning_rate": 8.994027888992533e-06,
+      "loss": 0.8857,
+      "step": 256
+    },
+    {
+      "epoch": 0.49423076923076925,
+      "grad_norm": 0.9921875,
+      "learning_rate": 8.984443197362938e-06,
+      "loss": 0.9815,
+      "step": 257
+    },
+    {
+      "epoch": 0.49615384615384617,
+      "grad_norm": 0.91015625,
+      "learning_rate": 8.974818219827796e-06,
+      "loss": 0.9693,
+      "step": 258
+    },
+    {
+      "epoch": 0.4980769230769231,
+      "grad_norm": 1.2265625,
+      "learning_rate": 8.965153053703325e-06,
+      "loss": 0.8971,
+      "step": 259
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.94140625,
+      "learning_rate": 8.955447796712083e-06,
+      "loss": 0.8998,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.9489682912826538,
+      "eval_runtime": 34.8214,
+      "eval_samples_per_second": 67.286,
+      "eval_steps_per_second": 16.829,
+      "step": 260
+    },
+    {
+      "epoch": 0.5019230769230769,
+      "grad_norm": 0.9609375,
+      "learning_rate": 8.94570254698197e-06,
+      "loss": 0.9153,
+      "step": 261
+    },
+    {
+      "epoch": 0.5038461538461538,
+      "grad_norm": 0.94140625,
+      "learning_rate": 8.935917403045251e-06,
+      "loss": 0.9449,
+      "step": 262
+    },
+    {
+      "epoch": 0.5057692307692307,
+      "grad_norm": 0.91796875,
+      "learning_rate": 8.926092463837557e-06,
+      "loss": 0.9087,
+      "step": 263
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.890625,
+      "learning_rate": 8.916227828696873e-06,
+      "loss": 0.8946,
+      "step": 264
+    },
+    {
+      "epoch": 0.5096153846153846,
+      "grad_norm": 0.8671875,
+      "learning_rate": 8.906323597362547e-06,
+      "loss": 0.9261,
+      "step": 265
+    },
+    {
+      "epoch": 0.5115384615384615,
+      "grad_norm": 0.8828125,
+      "learning_rate": 8.896379869974273e-06,
+      "loss": 0.8826,
+      "step": 266
+    },
+    {
+      "epoch": 0.5134615384615384,
+      "grad_norm": 0.9609375,
+      "learning_rate": 8.886396747071085e-06,
+      "loss": 0.9224,
+      "step": 267
+    },
+    {
+      "epoch": 0.5153846153846153,
+      "grad_norm": 0.84765625,
+      "learning_rate": 8.876374329590331e-06,
+      "loss": 0.8849,
+      "step": 268
+    },
+    {
+      "epoch": 0.5173076923076924,
+      "grad_norm": 0.890625,
+      "learning_rate": 8.866312718866669e-06,
+      "loss": 0.9516,
+      "step": 269
+    },
+    {
+      "epoch": 0.5192307692307693,
+      "grad_norm": 0.921875,
+      "learning_rate": 8.85621201663102e-06,
+      "loss": 0.9049,
+      "step": 270
+    },
+    {
+      "epoch": 0.5211538461538462,
+      "grad_norm": 0.8125,
+      "learning_rate": 8.846072325009562e-06,
+      "loss": 0.8953,
+      "step": 271
+    },
+    {
+      "epoch": 0.5230769230769231,
+      "grad_norm": 0.8046875,
+      "learning_rate": 8.83589374652268e-06,
+      "loss": 0.8507,
+      "step": 272
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.8359375,
+      "learning_rate": 8.825676384083936e-06,
+      "loss": 0.8904,
+      "step": 273
+    },
+    {
+      "epoch": 0.5269230769230769,
+      "grad_norm": 0.83203125,
+      "learning_rate": 8.815420340999034e-06,
+      "loss": 0.9469,
+      "step": 274
+    },
+    {
+      "epoch": 0.5288461538461539,
+      "grad_norm": 0.90234375,
+      "learning_rate": 8.805125720964766e-06,
+      "loss": 0.9144,
+      "step": 275
+    },
+    {
+      "epoch": 0.5307692307692308,
+      "grad_norm": 0.828125,
+      "learning_rate": 8.79479262806797e-06,
+      "loss": 0.8757,
+      "step": 276
+    },
+    {
+      "epoch": 0.5326923076923077,
+      "grad_norm": 0.83203125,
+      "learning_rate": 8.784421166784476e-06,
+      "loss": 0.8781,
+      "step": 277
+    },
+    {
+      "epoch": 0.5346153846153846,
+      "grad_norm": 0.89453125,
+      "learning_rate": 8.774011441978046e-06,
+      "loss": 0.9348,
+      "step": 278
+    },
+    {
+      "epoch": 0.5365384615384615,
+      "grad_norm": 0.9296875,
+      "learning_rate": 8.763563558899317e-06,
+      "loss": 0.9949,
+      "step": 279
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 0.8359375,
+      "learning_rate": 8.75307762318474e-06,
+      "loss": 0.9171,
+      "step": 280
+    },
+    {
+      "epoch": 0.5403846153846154,
+      "grad_norm": 0.890625,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 1.0024,
+      "step": 281
+    },
+    {
+      "epoch": 0.5423076923076923,
+      "grad_norm": 0.82421875,
+      "learning_rate": 8.731992018316478e-06,
+      "loss": 0.8619,
+      "step": 282
+    },
+    {
+      "epoch": 0.5442307692307692,
+      "grad_norm": 0.7890625,
+      "learning_rate": 8.721392562355113e-06,
+      "loss": 0.955,
+      "step": 283
+    },
+    {
+      "epoch": 0.5461538461538461,
+      "grad_norm": 1.046875,
+      "learning_rate": 8.71075548014038e-06,
+      "loss": 0.9189,
+      "step": 284
+    },
+    {
+      "epoch": 0.5480769230769231,
+      "grad_norm": 0.9140625,
+      "learning_rate": 8.700080879221689e-06,
+      "loss": 0.9118,
+      "step": 285
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.8203125,
+      "learning_rate": 8.689368867527781e-06,
+      "loss": 0.8916,
+      "step": 286
+    },
+    {
+      "epoch": 0.551923076923077,
+      "grad_norm": 0.86328125,
+      "learning_rate": 8.67861955336566e-06,
+      "loss": 0.8934,
+      "step": 287
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.875,
+      "learning_rate": 8.667833045419483e-06,
+      "loss": 0.8921,
+      "step": 288
+    },
+    {
+      "epoch": 0.5557692307692308,
+      "grad_norm": 0.87890625,
+      "learning_rate": 8.657009452749466e-06,
+      "loss": 1.0005,
+      "step": 289
+    },
+    {
+      "epoch": 0.5576923076923077,
+      "grad_norm": 0.85546875,
+      "learning_rate": 8.646148884790786e-06,
+      "loss": 0.8828,
+      "step": 290
+    },
+    {
+      "epoch": 0.5596153846153846,
+      "grad_norm": 0.82421875,
+      "learning_rate": 8.635251451352463e-06,
+      "loss": 0.8704,
+      "step": 291
+    },
+    {
+      "epoch": 0.5615384615384615,
+      "grad_norm": 0.7890625,
+      "learning_rate": 8.624317262616261e-06,
+      "loss": 0.9182,
+      "step": 292
+    },
+    {
+      "epoch": 0.5634615384615385,
+      "grad_norm": 0.86328125,
+      "learning_rate": 8.613346429135567e-06,
+      "loss": 0.9128,
+      "step": 293
+    },
+    {
+      "epoch": 0.5653846153846154,
+      "grad_norm": 0.83984375,
+      "learning_rate": 8.602339061834278e-06,
+      "loss": 0.9893,
+      "step": 294
+    },
+    {
+      "epoch": 0.5673076923076923,
+      "grad_norm": 0.84375,
+      "learning_rate": 8.591295272005674e-06,
+      "loss": 0.9299,
+      "step": 295
+    },
+    {
+      "epoch": 0.5692307692307692,
+      "grad_norm": 0.77734375,
+      "learning_rate": 8.5802151713113e-06,
+      "loss": 0.894,
+      "step": 296
+    },
+    {
+      "epoch": 0.5711538461538461,
+      "grad_norm": 0.8359375,
+      "learning_rate": 8.569098871779828e-06,
+      "loss": 0.9472,
+      "step": 297
+    },
+    {
+      "epoch": 0.573076923076923,
+      "grad_norm": 0.828125,
+      "learning_rate": 8.557946485805932e-06,
+      "loss": 0.919,
+      "step": 298
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.8046875,
+      "learning_rate": 8.546758126149148e-06,
+      "loss": 0.882,
+      "step": 299
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 0.88671875,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.8685,
+      "step": 300
+    },
+    {
+      "epoch": 0.5788461538461539,
+      "grad_norm": 0.85546875,
+      "learning_rate": 8.524273938642539e-06,
+      "loss": 0.8966,
+      "step": 301
+    },
+    {
+      "epoch": 0.5807692307692308,
+      "grad_norm": 0.796875,
+      "learning_rate": 8.512978338125818e-06,
+      "loss": 0.9205,
+      "step": 302
+    },
+    {
+      "epoch": 0.5826923076923077,
+      "grad_norm": 0.83984375,
+      "learning_rate": 8.501647218590127e-06,
+      "loss": 0.9815,
+      "step": 303
+    },
+    {
+      "epoch": 0.5846153846153846,
+      "grad_norm": 0.80859375,
+      "learning_rate": 8.490280694602142e-06,
+      "loss": 0.9317,
+      "step": 304
+    },
+    {
+      "epoch": 0.5865384615384616,
+      "grad_norm": 0.7890625,
+      "learning_rate": 8.478878881086505e-06,
+      "loss": 0.9498,
+      "step": 305
+    },
+    {
+      "epoch": 0.5884615384615385,
+      "grad_norm": 0.7578125,
+      "learning_rate": 8.467441893324667e-06,
+      "loss": 0.9088,
+      "step": 306
+    },
+    {
+      "epoch": 0.5903846153846154,
+      "grad_norm": 0.81640625,
+      "learning_rate": 8.455969846953711e-06,
+      "loss": 0.8728,
+      "step": 307
+    },
+    {
+      "epoch": 0.5923076923076923,
+      "grad_norm": 0.8046875,
+      "learning_rate": 8.444462857965198e-06,
+      "loss": 0.9345,
+      "step": 308
+    },
+    {
+      "epoch": 0.5942307692307692,
+      "grad_norm": 0.8046875,
+      "learning_rate": 8.432921042703985e-06,
+      "loss": 0.8951,
+      "step": 309
+    },
+    {
+      "epoch": 0.5961538461538461,
+      "grad_norm": 0.8046875,
+      "learning_rate": 8.42134451786705e-06,
+      "loss": 1.005,
+      "step": 310
+    },
+    {
+      "epoch": 0.5980769230769231,
+      "grad_norm": 0.7734375,
+      "learning_rate": 8.409733400502311e-06,
+      "loss": 0.919,
+      "step": 311
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.81640625,
+      "learning_rate": 8.398087808007447e-06,
+      "loss": 0.882,
+      "step": 312
+    },
+    {
+      "epoch": 0.6019230769230769,
+      "grad_norm": 0.84375,
+      "learning_rate": 8.386407858128707e-06,
+      "loss": 0.9254,
+      "step": 313
+    },
+    {
+      "epoch": 0.6038461538461538,
+      "grad_norm": 0.77734375,
+      "learning_rate": 8.374693668959717e-06,
+      "loss": 0.9312,
+      "step": 314
+    },
+    {
+      "epoch": 0.6057692307692307,
+      "grad_norm": 0.77734375,
+      "learning_rate": 8.362945358940295e-06,
+      "loss": 0.9124,
+      "step": 315
+    },
+    {
+      "epoch": 0.6076923076923076,
+      "grad_norm": 0.765625,
+      "learning_rate": 8.351163046855246e-06,
+      "loss": 0.9181,
+      "step": 316
+    },
+    {
+      "epoch": 0.6096153846153847,
+      "grad_norm": 0.77734375,
+      "learning_rate": 8.339346851833163e-06,
+      "loss": 0.9124,
+      "step": 317
+    },
+    {
+      "epoch": 0.6115384615384616,
+      "grad_norm": 0.78515625,
+      "learning_rate": 8.327496893345223e-06,
+      "loss": 0.9282,
+      "step": 318
+    },
+    {
+      "epoch": 0.6134615384615385,
+      "grad_norm": 0.7421875,
+      "learning_rate": 8.315613291203977e-06,
+      "loss": 0.9125,
+      "step": 319
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.7734375,
+      "learning_rate": 8.303696165562141e-06,
+      "loss": 0.9366,
+      "step": 320
+    },
+    {
+      "epoch": 0.6173076923076923,
+      "grad_norm": 0.78515625,
+      "learning_rate": 8.291745636911382e-06,
+      "loss": 0.9808,
+      "step": 321
+    },
+    {
+      "epoch": 0.6192307692307693,
+      "grad_norm": 0.74609375,
+      "learning_rate": 8.279761826081096e-06,
+      "loss": 0.9105,
+      "step": 322
+    },
+    {
+      "epoch": 0.6211538461538462,
+      "grad_norm": 0.79296875,
+      "learning_rate": 8.26774485423719e-06,
+      "loss": 0.9444,
+      "step": 323
+    },
+    {
+      "epoch": 0.6230769230769231,
+      "grad_norm": 0.79296875,
+      "learning_rate": 8.255694842880854e-06,
+      "loss": 0.8981,
+      "step": 324
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.76171875,
+      "learning_rate": 8.243611913847337e-06,
+      "loss": 0.8919,
+      "step": 325
+    },
+    {
+      "epoch": 0.625,
+      "eval_loss": 0.9419646263122559,
+      "eval_runtime": 34.6043,
+      "eval_samples_per_second": 67.708,
+      "eval_steps_per_second": 16.934,
+      "step": 325
+    },
+    {
+      "epoch": 0.6269230769230769,
+      "grad_norm": 0.76171875,
+      "learning_rate": 8.231496189304704e-06,
+      "loss": 0.8434,
+      "step": 326
+    },
+    {
+      "epoch": 0.6288461538461538,
+      "grad_norm": 0.8671875,
+      "learning_rate": 8.21934779175262e-06,
+      "loss": 0.912,
+      "step": 327
+    },
+    {
+      "epoch": 0.6307692307692307,
+      "grad_norm": 0.7890625,
+      "learning_rate": 8.207166844021093e-06,
+      "loss": 0.9085,
+      "step": 328
+    },
+    {
+      "epoch": 0.6326923076923077,
+      "grad_norm": 0.77734375,
+      "learning_rate": 8.19495346926924e-06,
+      "loss": 0.9301,
+      "step": 329
+    },
+    {
+      "epoch": 0.6346153846153846,
+      "grad_norm": 0.75,
+      "learning_rate": 8.182707790984043e-06,
+      "loss": 0.9023,
+      "step": 330
+    },
+    {
+      "epoch": 0.6365384615384615,
+      "grad_norm": 0.76953125,
+      "learning_rate": 8.170429932979097e-06,
+      "loss": 0.9363,
+      "step": 331
+    },
+    {
+      "epoch": 0.6384615384615384,
+      "grad_norm": 0.76953125,
+      "learning_rate": 8.15812001939336e-06,
+      "loss": 0.927,
+      "step": 332
+    },
+    {
+      "epoch": 0.6403846153846153,
+      "grad_norm": 0.8671875,
+      "learning_rate": 8.145778174689897e-06,
+      "loss": 0.9826,
+      "step": 333
+    },
+    {
+      "epoch": 0.6423076923076924,
+      "grad_norm": 0.8125,
+      "learning_rate": 8.133404523654626e-06,
+      "loss": 0.922,
+      "step": 334
+    },
+    {
+      "epoch": 0.6442307692307693,
+      "grad_norm": 0.7578125,
+      "learning_rate": 8.120999191395048e-06,
+      "loss": 0.9405,
+      "step": 335
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.78515625,
+      "learning_rate": 8.108562303338987e-06,
+      "loss": 0.8947,
+      "step": 336
+    },
+    {
+      "epoch": 0.6480769230769231,
+      "grad_norm": 0.74609375,
+      "learning_rate": 8.096093985233323e-06,
+      "loss": 0.9109,
+      "step": 337
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.8125,
+      "learning_rate": 8.083594363142717e-06,
+      "loss": 0.9111,
+      "step": 338
+    },
+    {
+      "epoch": 0.6519230769230769,
+      "grad_norm": 0.78515625,
+      "learning_rate": 8.071063563448341e-06,
+      "loss": 0.8957,
+      "step": 339
+    },
+    {
+      "epoch": 0.6538461538461539,
+      "grad_norm": 0.74609375,
+      "learning_rate": 8.058501712846594e-06,
+      "loss": 0.9003,
+      "step": 340
+    },
+    {
+      "epoch": 0.6557692307692308,
+      "grad_norm": 0.7890625,
+      "learning_rate": 8.045908938347828e-06,
+      "loss": 0.9372,
+      "step": 341
+    },
+    {
+      "epoch": 0.6576923076923077,
+      "grad_norm": 0.75390625,
+      "learning_rate": 8.03328536727506e-06,
+      "loss": 0.8854,
+      "step": 342
+    },
+    {
+      "epoch": 0.6596153846153846,
+      "grad_norm": 0.77734375,
+      "learning_rate": 8.020631127262681e-06,
+      "loss": 0.9505,
+      "step": 343
+    },
+    {
+      "epoch": 0.6615384615384615,
+      "grad_norm": 0.765625,
+      "learning_rate": 8.007946346255176e-06,
+      "loss": 0.9581,
+      "step": 344
+    },
+    {
+      "epoch": 0.6634615384615384,
+      "grad_norm": 0.83984375,
+      "learning_rate": 7.995231152505815e-06,
+      "loss": 0.9068,
+      "step": 345
+    },
+    {
+      "epoch": 0.6653846153846154,
+      "grad_norm": 0.78125,
+      "learning_rate": 7.982485674575373e-06,
+      "loss": 0.9159,
+      "step": 346
+    },
+    {
+      "epoch": 0.6673076923076923,
+      "grad_norm": 0.765625,
+      "learning_rate": 7.96971004133082e-06,
+      "loss": 0.9015,
+      "step": 347
+    },
+    {
+      "epoch": 0.6692307692307692,
+      "grad_norm": 0.796875,
+      "learning_rate": 7.95690438194402e-06,
+      "loss": 0.9531,
+      "step": 348
+    },
+    {
+      "epoch": 0.6711538461538461,
+      "grad_norm": 0.8046875,
+      "learning_rate": 7.944068825890424e-06,
+      "loss": 0.8971,
+      "step": 349
+    },
+    {
+      "epoch": 0.6730769230769231,
+      "grad_norm": 0.83203125,
+      "learning_rate": 7.931203502947762e-06,
+      "loss": 0.868,
+      "step": 350
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.734375,
+      "learning_rate": 7.918308543194735e-06,
+      "loss": 0.9151,
+      "step": 351
+    },
+    {
+      "epoch": 0.676923076923077,
+      "grad_norm": 0.77734375,
+      "learning_rate": 7.905384077009693e-06,
+      "loss": 0.9949,
+      "step": 352
+    },
+    {
+      "epoch": 0.6788461538461539,
+      "grad_norm": 0.77734375,
+      "learning_rate": 7.892430235069317e-06,
+      "loss": 0.9025,
+      "step": 353
+    },
+    {
+      "epoch": 0.6807692307692308,
+      "grad_norm": 0.76171875,
+      "learning_rate": 7.879447148347307e-06,
+      "loss": 0.8969,
+      "step": 354
+    },
+    {
+      "epoch": 0.6826923076923077,
+      "grad_norm": 0.8828125,
+      "learning_rate": 7.866434948113046e-06,
+      "loss": 0.9086,
+      "step": 355
+    },
+    {
+      "epoch": 0.6846153846153846,
+      "grad_norm": 0.78125,
+      "learning_rate": 7.853393765930279e-06,
+      "loss": 0.865,
+      "step": 356
+    },
+    {
+      "epoch": 0.6865384615384615,
+      "grad_norm": 0.78515625,
+      "learning_rate": 7.84032373365578e-06,
+      "loss": 0.9514,
+      "step": 357
+    },
+    {
+      "epoch": 0.6884615384615385,
+      "grad_norm": 0.7421875,
+      "learning_rate": 7.827224983438024e-06,
+      "loss": 0.8866,
+      "step": 358
+    },
+    {
+      "epoch": 0.6903846153846154,
+      "grad_norm": 0.8671875,
+      "learning_rate": 7.814097647715848e-06,
+      "loss": 0.8856,
+      "step": 359
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.78125,
+      "learning_rate": 7.800941859217103e-06,
+      "loss": 0.8864,
+      "step": 360
+    },
+    {
+      "epoch": 0.6942307692307692,
+      "grad_norm": 0.75390625,
+      "learning_rate": 7.787757750957335e-06,
+      "loss": 0.9212,
+      "step": 361
+    },
+    {
+      "epoch": 0.6961538461538461,
+      "grad_norm": 0.796875,
+      "learning_rate": 7.77454545623841e-06,
+      "loss": 0.9006,
+      "step": 362
+    },
+    {
+      "epoch": 0.698076923076923,
+      "grad_norm": 0.7578125,
+      "learning_rate": 7.761305108647188e-06,
+      "loss": 0.9427,
+      "step": 363
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.78125,
+      "learning_rate": 7.74803684205417e-06,
+      "loss": 0.9583,
+      "step": 364
+    },
+    {
+      "epoch": 0.7019230769230769,
+      "grad_norm": 0.80078125,
+      "learning_rate": 7.734740790612137e-06,
+      "loss": 0.9303,
+      "step": 365
+    },
+    {
+      "epoch": 0.7038461538461539,
+      "grad_norm": 0.796875,
+      "learning_rate": 7.72141708875479e-06,
+      "loss": 0.9017,
+      "step": 366
+    },
+    {
+      "epoch": 0.7057692307692308,
+      "grad_norm": 0.7421875,
+      "learning_rate": 7.708065871195413e-06,
+      "loss": 0.9247,
+      "step": 367
+    },
+    {
+      "epoch": 0.7076923076923077,
+      "grad_norm": 0.7109375,
+      "learning_rate": 7.694687272925487e-06,
+      "loss": 0.8598,
+      "step": 368
+    },
+    {
+      "epoch": 0.7096153846153846,
+      "grad_norm": 0.73046875,
+      "learning_rate": 7.681281429213328e-06,
+      "loss": 0.9719,
+      "step": 369
+    },
+    {
+      "epoch": 0.7115384615384616,
+      "grad_norm": 0.76171875,
+      "learning_rate": 7.667848475602735e-06,
+      "loss": 0.9588,
+      "step": 370
+    },
+    {
+      "epoch": 0.7134615384615385,
+      "grad_norm": 0.73046875,
+      "learning_rate": 7.654388547911605e-06,
+      "loss": 0.8185,
+      "step": 371
+    },
+    {
+      "epoch": 0.7153846153846154,
+      "grad_norm": 0.73046875,
+      "learning_rate": 7.640901782230567e-06,
+      "loss": 0.93,
+      "step": 372
+    },
+    {
+      "epoch": 0.7173076923076923,
+      "grad_norm": 0.734375,
+      "learning_rate": 7.627388314921602e-06,
+      "loss": 0.9846,
+      "step": 373
+    },
+    {
+      "epoch": 0.7192307692307692,
+      "grad_norm": 0.74609375,
+      "learning_rate": 7.613848282616665e-06,
+      "loss": 0.9807,
+      "step": 374
+    },
+    {
+      "epoch": 0.7211538461538461,
+      "grad_norm": 0.75390625,
+      "learning_rate": 7.600281822216307e-06,
+      "loss": 0.9011,
+      "step": 375
+    },
+    {
+      "epoch": 0.7230769230769231,
+      "grad_norm": 0.74609375,
+      "learning_rate": 7.586689070888284e-06,
+      "loss": 0.8961,
+      "step": 376
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.7890625,
+      "learning_rate": 7.5730701660661795e-06,
+      "loss": 0.9279,
+      "step": 377
+    },
+    {
+      "epoch": 0.7269230769230769,
+      "grad_norm": 0.74609375,
+      "learning_rate": 7.559425245448006e-06,
+      "loss": 0.9177,
+      "step": 378
+    },
+    {
+      "epoch": 0.7288461538461538,
+      "grad_norm": 0.734375,
+      "learning_rate": 7.5457544469948164e-06,
+      "loss": 0.9309,
+      "step": 379
+    },
+    {
+      "epoch": 0.7307692307692307,
+      "grad_norm": 0.75,
+      "learning_rate": 7.532057908929311e-06,
+      "loss": 0.8937,
+      "step": 380
+    },
+    {
+      "epoch": 0.7326923076923076,
+      "grad_norm": 0.78515625,
+      "learning_rate": 7.5183357697344395e-06,
+      "loss": 0.895,
+      "step": 381
+    },
+    {
+      "epoch": 0.7346153846153847,
+      "grad_norm": 0.7421875,
+      "learning_rate": 7.504588168151994e-06,
+      "loss": 0.9167,
+      "step": 382
+    },
+    {
+      "epoch": 0.7365384615384616,
+      "grad_norm": 0.7421875,
+      "learning_rate": 7.4908152431812175e-06,
+      "loss": 0.921,
+      "step": 383
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.75390625,
+      "learning_rate": 7.477017134077389e-06,
+      "loss": 0.8987,
+      "step": 384
+    },
+    {
+      "epoch": 0.7403846153846154,
+      "grad_norm": 0.7578125,
+      "learning_rate": 7.4631939803504215e-06,
+      "loss": 0.8866,
+      "step": 385
+    },
+    {
+      "epoch": 0.7423076923076923,
+      "grad_norm": 0.73828125,
+      "learning_rate": 7.449345921763449e-06,
+      "loss": 0.8745,
+      "step": 386
+    },
+    {
+      "epoch": 0.7442307692307693,
+      "grad_norm": 0.75390625,
+      "learning_rate": 7.435473098331411e-06,
+      "loss": 0.865,
+      "step": 387
+    },
+    {
+      "epoch": 0.7461538461538462,
+      "grad_norm": 0.78125,
+      "learning_rate": 7.421575650319641e-06,
+      "loss": 0.8841,
+      "step": 388
+    },
+    {
+      "epoch": 0.7480769230769231,
+      "grad_norm": 0.765625,
+      "learning_rate": 7.407653718242449e-06,
+      "loss": 0.9637,
+      "step": 389
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.70703125,
+      "learning_rate": 7.393707442861693e-06,
+      "loss": 0.914,
+      "step": 390
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.9376137256622314,
+      "eval_runtime": 34.5412,
+      "eval_samples_per_second": 67.832,
+      "eval_steps_per_second": 16.965,
+      "step": 390
+    },
+    {
+      "epoch": 0.7519230769230769,
+      "grad_norm": 0.74609375,
+      "learning_rate": 7.379736965185369e-06,
+      "loss": 0.9394,
+      "step": 391
+    },
+    {
+      "epoch": 0.7538461538461538,
+      "grad_norm": 0.77734375,
+      "learning_rate": 7.365742426466169e-06,
+      "loss": 0.9122,
+      "step": 392
+    },
+    {
+      "epoch": 0.7557692307692307,
+      "grad_norm": 0.73046875,
+      "learning_rate": 7.3517239682000675e-06,
+      "loss": 0.9033,
+      "step": 393
+    },
+    {
+      "epoch": 0.7576923076923077,
+      "grad_norm": 0.97265625,
+      "learning_rate": 7.337681732124882e-06,
+      "loss": 0.8908,
+      "step": 394
+    },
+    {
+      "epoch": 0.7596153846153846,
+      "grad_norm": 0.734375,
+      "learning_rate": 7.323615860218844e-06,
+      "loss": 0.8938,
+      "step": 395
+    },
+    {
+      "epoch": 0.7615384615384615,
+      "grad_norm": 0.75390625,
+      "learning_rate": 7.30952649469916e-06,
+      "loss": 0.9013,
+      "step": 396
+    },
+    {
+      "epoch": 0.7634615384615384,
+      "grad_norm": 0.75390625,
+      "learning_rate": 7.295413778020579e-06,
+      "loss": 0.9203,
+      "step": 397
+    },
+    {
+      "epoch": 0.7653846153846153,
+      "grad_norm": 0.76171875,
+      "learning_rate": 7.281277852873947e-06,
+      "loss": 0.9713,
+      "step": 398
+    },
+    {
+      "epoch": 0.7673076923076924,
+      "grad_norm": 0.7890625,
+      "learning_rate": 7.267118862184767e-06,
+      "loss": 0.9376,
+      "step": 399
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.765625,
+      "learning_rate": 7.252936949111749e-06,
+      "loss": 0.9329,
+      "step": 400
+    },
+    {
+      "epoch": 0.7711538461538462,
+      "grad_norm": 0.734375,
+      "learning_rate": 7.2387322570453724e-06,
+      "loss": 0.8421,
+      "step": 401
+    },
+    {
+      "epoch": 0.7730769230769231,
+      "grad_norm": 0.75,
+      "learning_rate": 7.224504929606429e-06,
+      "loss": 0.8929,
+      "step": 402
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.75390625,
+      "learning_rate": 7.210255110644569e-06,
+      "loss": 0.9063,
+      "step": 403
+    },
+    {
+      "epoch": 0.7769230769230769,
+      "grad_norm": 0.7265625,
+      "learning_rate": 7.195982944236853e-06,
+      "loss": 0.9735,
+      "step": 404
+    },
+    {
+      "epoch": 0.7788461538461539,
+      "grad_norm": 0.7109375,
+      "learning_rate": 7.181688574686292e-06,
+      "loss": 0.8794,
+      "step": 405
+    },
+    {
+      "epoch": 0.7807692307692308,
+      "grad_norm": 0.75,
+      "learning_rate": 7.167372146520386e-06,
+      "loss": 0.8891,
+      "step": 406
+    },
+    {
+      "epoch": 0.7826923076923077,
+      "grad_norm": 0.71484375,
+      "learning_rate": 7.15303380448967e-06,
+      "loss": 0.8951,
+      "step": 407
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.78125,
+      "learning_rate": 7.138673693566241e-06,
+      "loss": 0.897,
+      "step": 408
+    },
+    {
+      "epoch": 0.7865384615384615,
+      "grad_norm": 0.796875,
+      "learning_rate": 7.1242919589422974e-06,
+      "loss": 0.9431,
+      "step": 409
+    },
+    {
+      "epoch": 0.7884615384615384,
+      "grad_norm": 0.74609375,
+      "learning_rate": 7.1098887460286745e-06,
+      "loss": 0.8704,
+      "step": 410
+    },
+    {
+      "epoch": 0.7903846153846154,
+      "grad_norm": 0.765625,
+      "learning_rate": 7.095464200453366e-06,
+      "loss": 0.9813,
+      "step": 411
+    },
+    {
+      "epoch": 0.7923076923076923,
+      "grad_norm": 0.734375,
+      "learning_rate": 7.081018468060057e-06,
+      "loss": 0.8657,
+      "step": 412
+    },
+    {
+      "epoch": 0.7942307692307692,
+      "grad_norm": 0.7578125,
+      "learning_rate": 7.066551694906651e-06,
+      "loss": 0.9216,
+      "step": 413
+    },
+    {
+      "epoch": 0.7961538461538461,
+      "grad_norm": 0.734375,
+      "learning_rate": 7.052064027263785e-06,
+      "loss": 0.9203,
+      "step": 414
+    },
+    {
+      "epoch": 0.7980769230769231,
+      "grad_norm": 0.73828125,
+      "learning_rate": 7.0375556116133605e-06,
+      "loss": 0.9002,
+      "step": 415
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.73046875,
+      "learning_rate": 7.023026594647057e-06,
+      "loss": 0.9279,
+      "step": 416
+    },
+    {
+      "epoch": 0.801923076923077,
+      "grad_norm": 0.71875,
+      "learning_rate": 7.008477123264849e-06,
+      "loss": 0.8851,
+      "step": 417
+    },
+    {
+      "epoch": 0.8038461538461539,
+      "grad_norm": 0.72265625,
+      "learning_rate": 6.9939073445735205e-06,
+      "loss": 0.8718,
+      "step": 418
+    },
+    {
+      "epoch": 0.8057692307692308,
+      "grad_norm": 0.703125,
+      "learning_rate": 6.9793174058851805e-06,
+      "loss": 0.8874,
+      "step": 419
+    },
+    {
+      "epoch": 0.8076923076923077,
+      "grad_norm": 0.73828125,
+      "learning_rate": 6.964707454715772e-06,
+      "loss": 0.8747,
+      "step": 420
+    },
+    {
+      "epoch": 0.8096153846153846,
+      "grad_norm": 0.7578125,
+      "learning_rate": 6.9500776387835785e-06,
+      "loss": 0.9146,
+      "step": 421
+    },
+    {
+      "epoch": 0.8115384615384615,
+      "grad_norm": 0.78515625,
+      "learning_rate": 6.935428106007734e-06,
+      "loss": 0.9598,
+      "step": 422
+    },
+    {
+      "epoch": 0.8134615384615385,
+      "grad_norm": 0.75390625,
+      "learning_rate": 6.920759004506723e-06,
+      "loss": 0.873,
+      "step": 423
+    },
+    {
+      "epoch": 0.8153846153846154,
+      "grad_norm": 0.80859375,
+      "learning_rate": 6.906070482596887e-06,
+      "loss": 0.9395,
+      "step": 424
+    },
+    {
+      "epoch": 0.8173076923076923,
+      "grad_norm": 0.71484375,
+      "learning_rate": 6.891362688790925e-06,
+      "loss": 0.8713,
+      "step": 425
+    },
+    {
+      "epoch": 0.8192307692307692,
+      "grad_norm": 0.7109375,
+      "learning_rate": 6.876635771796386e-06,
+      "loss": 0.8427,
+      "step": 426
+    },
+    {
+      "epoch": 0.8211538461538461,
+      "grad_norm": 0.75,
+      "learning_rate": 6.8618898805141744e-06,
+      "loss": 0.9148,
+      "step": 427
+    },
+    {
+      "epoch": 0.823076923076923,
+      "grad_norm": 0.74609375,
+      "learning_rate": 6.847125164037036e-06,
+      "loss": 0.8788,
+      "step": 428
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.72265625,
+      "learning_rate": 6.832341771648057e-06,
+      "loss": 0.8523,
+      "step": 429
+    },
+    {
+      "epoch": 0.8269230769230769,
+      "grad_norm": 0.7265625,
+      "learning_rate": 6.817539852819149e-06,
+      "loss": 0.869,
+      "step": 430
+    },
+    {
+      "epoch": 0.8288461538461539,
+      "grad_norm": 0.6953125,
+      "learning_rate": 6.802719557209547e-06,
+      "loss": 0.8934,
+      "step": 431
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.7265625,
+      "learning_rate": 6.787881034664283e-06,
+      "loss": 0.9127,
+      "step": 432
+    },
+    {
+      "epoch": 0.8326923076923077,
+      "grad_norm": 0.7421875,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.9617,
+      "step": 433
+    },
+    {
+      "epoch": 0.8346153846153846,
+      "grad_norm": 0.7421875,
+      "learning_rate": 6.758149909066832e-06,
+      "loss": 0.8918,
+      "step": 434
+    },
+    {
+      "epoch": 0.8365384615384616,
+      "grad_norm": 0.7734375,
+      "learning_rate": 6.743257606620094e-06,
+      "loss": 0.9721,
+      "step": 435
+    },
+    {
+      "epoch": 0.8384615384615385,
+      "grad_norm": 0.734375,
+      "learning_rate": 6.728347678445539e-06,
+      "loss": 0.9183,
+      "step": 436
+    },
+    {
+      "epoch": 0.8403846153846154,
+      "grad_norm": 0.7265625,
+      "learning_rate": 6.713420275294467e-06,
+      "loss": 0.8995,
+      "step": 437
+    },
+    {
+      "epoch": 0.8423076923076923,
+      "grad_norm": 0.75,
+      "learning_rate": 6.69847554809485e-06,
+      "loss": 0.879,
+      "step": 438
+    },
+    {
+      "epoch": 0.8442307692307692,
+      "grad_norm": 0.7421875,
+      "learning_rate": 6.683513647949826e-06,
+      "loss": 0.927,
+      "step": 439
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 0.75390625,
+      "learning_rate": 6.668534726136166e-06,
+      "loss": 0.9,
+      "step": 440
+    },
+    {
+      "epoch": 0.8480769230769231,
+      "grad_norm": 0.74609375,
+      "learning_rate": 6.653538934102743e-06,
+      "loss": 0.8526,
+      "step": 441
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.75,
+      "learning_rate": 6.638526423468999e-06,
+      "loss": 0.8354,
+      "step": 442
+    },
+    {
+      "epoch": 0.8519230769230769,
+      "grad_norm": 0.75,
+      "learning_rate": 6.6234973460234184e-06,
+      "loss": 0.8852,
+      "step": 443
+    },
+    {
+      "epoch": 0.8538461538461538,
+      "grad_norm": 0.75,
+      "learning_rate": 6.608451853721985e-06,
+      "loss": 0.9275,
+      "step": 444
+    },
+    {
+      "epoch": 0.8557692307692307,
+      "grad_norm": 0.72265625,
+      "learning_rate": 6.593390098686653e-06,
+      "loss": 0.9023,
+      "step": 445
+    },
+    {
+      "epoch": 0.8576923076923076,
+      "grad_norm": 0.75,
+      "learning_rate": 6.578312233203804e-06,
+      "loss": 0.8804,
+      "step": 446
+    },
+    {
+      "epoch": 0.8596153846153847,
+      "grad_norm": 0.7109375,
+      "learning_rate": 6.563218409722712e-06,
+      "loss": 0.9229,
+      "step": 447
+    },
+    {
+      "epoch": 0.8615384615384616,
+      "grad_norm": 0.71484375,
+      "learning_rate": 6.548108780853995e-06,
+      "loss": 0.8995,
+      "step": 448
+    },
+    {
+      "epoch": 0.8634615384615385,
+      "grad_norm": 0.703125,
+      "learning_rate": 6.532983499368078e-06,
+      "loss": 0.8847,
+      "step": 449
+    },
+    {
+      "epoch": 0.8653846153846154,
+      "grad_norm": 0.71484375,
+      "learning_rate": 6.5178427181936485e-06,
+      "loss": 0.923,
+      "step": 450
+    },
+    {
+      "epoch": 0.8673076923076923,
+      "grad_norm": 0.73828125,
+      "learning_rate": 6.502686590416105e-06,
+      "loss": 0.8987,
+      "step": 451
+    },
+    {
+      "epoch": 0.8692307692307693,
+      "grad_norm": 0.7109375,
+      "learning_rate": 6.487515269276015e-06,
+      "loss": 0.9345,
+      "step": 452
+    },
+    {
+      "epoch": 0.8711538461538462,
+      "grad_norm": 0.74609375,
+      "learning_rate": 6.472328908167562e-06,
+      "loss": 0.8575,
+      "step": 453
+    },
+    {
+      "epoch": 0.8730769230769231,
+      "grad_norm": 0.734375,
+      "learning_rate": 6.457127660636994e-06,
+      "loss": 0.9209,
+      "step": 454
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.74609375,
+      "learning_rate": 6.441911680381074e-06,
+      "loss": 0.8873,
+      "step": 455
+    },
+    {
+      "epoch": 0.875,
+      "eval_loss": 0.9346491098403931,
+      "eval_runtime": 34.5947,
+      "eval_samples_per_second": 67.727,
+      "eval_steps_per_second": 16.939,
+      "step": 455
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.73046875,
+      "learning_rate": 6.426681121245527e-06,
+      "loss": 0.9187,
+      "step": 456
+    },
+    {
+      "epoch": 0.8788461538461538,
+      "grad_norm": 0.77734375,
+      "learning_rate": 6.411436137223479e-06,
+      "loss": 0.9509,
+      "step": 457
+    },
+    {
+      "epoch": 0.8807692307692307,
+      "grad_norm": 0.75,
+      "learning_rate": 6.396176882453902e-06,
+      "loss": 0.9401,
+      "step": 458
+    },
+    {
+      "epoch": 0.8826923076923077,
+      "grad_norm": 0.73828125,
+      "learning_rate": 6.38090351122006e-06,
+      "loss": 0.8767,
+      "step": 459
+    },
+    {
+      "epoch": 0.8846153846153846,
+      "grad_norm": 0.72265625,
+      "learning_rate": 6.365616177947945e-06,
+      "loss": 0.8637,
+      "step": 460
+    },
+    {
+      "epoch": 0.8865384615384615,
+      "grad_norm": 0.74609375,
+      "learning_rate": 6.350315037204714e-06,
+      "loss": 0.9081,
+      "step": 461
+    },
+    {
+      "epoch": 0.8884615384615384,
+      "grad_norm": 0.73828125,
+      "learning_rate": 6.335000243697134e-06,
+      "loss": 0.9054,
+      "step": 462
+    },
+    {
+      "epoch": 0.8903846153846153,
+      "grad_norm": 0.73046875,
+      "learning_rate": 6.319671952270004e-06,
+      "loss": 0.9045,
+      "step": 463
+    },
+    {
+      "epoch": 0.8923076923076924,
+      "grad_norm": 0.71484375,
+      "learning_rate": 6.304330317904605e-06,
+      "loss": 0.9227,
+      "step": 464
+    },
+    {
+      "epoch": 0.8942307692307693,
+      "grad_norm": 0.69921875,
+      "learning_rate": 6.288975495717124e-06,
+      "loss": 0.8882,
+      "step": 465
+    },
+    {
+      "epoch": 0.8961538461538462,
+      "grad_norm": 0.76171875,
+      "learning_rate": 6.273607640957085e-06,
+      "loss": 0.9967,
+      "step": 466
+    },
+    {
+      "epoch": 0.8980769230769231,
+      "grad_norm": 0.73046875,
+      "learning_rate": 6.258226909005783e-06,
+      "loss": 0.9474,
+      "step": 467
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.7578125,
+      "learning_rate": 6.2428334553747135e-06,
+      "loss": 0.912,
+      "step": 468
+    },
+    {
+      "epoch": 0.9019230769230769,
+      "grad_norm": 0.74609375,
+      "learning_rate": 6.227427435703997e-06,
+      "loss": 0.9355,
+      "step": 469
+    },
+    {
+      "epoch": 0.9038461538461539,
+      "grad_norm": 0.75,
+      "learning_rate": 6.212009005760805e-06,
+      "loss": 0.9328,
+      "step": 470
+    },
+    {
+      "epoch": 0.9057692307692308,
+      "grad_norm": 0.74609375,
+      "learning_rate": 6.1965783214377895e-06,
+      "loss": 0.9323,
+      "step": 471
+    },
+    {
+      "epoch": 0.9076923076923077,
+      "grad_norm": 0.71484375,
+      "learning_rate": 6.181135538751504e-06,
+      "loss": 0.8865,
+      "step": 472
+    },
+    {
+      "epoch": 0.9096153846153846,
+      "grad_norm": 0.73046875,
+      "learning_rate": 6.165680813840822e-06,
+      "loss": 0.9123,
+      "step": 473
+    },
+    {
+      "epoch": 0.9115384615384615,
+      "grad_norm": 0.73828125,
+      "learning_rate": 6.150214302965368e-06,
+      "loss": 0.9209,
+      "step": 474
+    },
+    {
+      "epoch": 0.9134615384615384,
+      "grad_norm": 0.7109375,
+      "learning_rate": 6.134736162503929e-06,
+      "loss": 0.9377,
+      "step": 475
+    },
+    {
+      "epoch": 0.9153846153846154,
+      "grad_norm": 0.734375,
+      "learning_rate": 6.119246548952877e-06,
+      "loss": 0.9317,
+      "step": 476
+    },
+    {
+      "epoch": 0.9173076923076923,
+      "grad_norm": 0.71484375,
+      "learning_rate": 6.103745618924587e-06,
+      "loss": 0.8839,
+      "step": 477
+    },
+    {
+      "epoch": 0.9192307692307692,
+      "grad_norm": 0.71484375,
+      "learning_rate": 6.088233529145849e-06,
+      "loss": 0.8823,
+      "step": 478
+    },
+    {
+      "epoch": 0.9211538461538461,
+      "grad_norm": 0.7421875,
+      "learning_rate": 6.072710436456293e-06,
+      "loss": 0.9031,
+      "step": 479
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.7109375,
+      "learning_rate": 6.057176497806791e-06,
+      "loss": 0.9132,
+      "step": 480
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.7734375,
+      "learning_rate": 6.041631870257882e-06,
+      "loss": 0.8772,
+      "step": 481
+    },
+    {
+      "epoch": 0.926923076923077,
+      "grad_norm": 0.73046875,
+      "learning_rate": 6.026076710978172e-06,
+      "loss": 0.901,
+      "step": 482
+    },
+    {
+      "epoch": 0.9288461538461539,
+      "grad_norm": 0.74609375,
+      "learning_rate": 6.010511177242757e-06,
+      "loss": 0.9196,
+      "step": 483
+    },
+    {
+      "epoch": 0.9307692307692308,
+      "grad_norm": 0.73046875,
+      "learning_rate": 5.994935426431627e-06,
+      "loss": 0.9718,
+      "step": 484
+    },
+    {
+      "epoch": 0.9326923076923077,
+      "grad_norm": 0.76953125,
+      "learning_rate": 5.979349616028067e-06,
+      "loss": 0.963,
+      "step": 485
+    },
+    {
+      "epoch": 0.9346153846153846,
+      "grad_norm": 0.70703125,
+      "learning_rate": 5.963753903617084e-06,
+      "loss": 0.9048,
+      "step": 486
+    },
+    {
+      "epoch": 0.9365384615384615,
+      "grad_norm": 0.7578125,
+      "learning_rate": 5.948148446883794e-06,
+      "loss": 0.9705,
+      "step": 487
+    },
+    {
+      "epoch": 0.9384615384615385,
+      "grad_norm": 0.71484375,
+      "learning_rate": 5.932533403611835e-06,
+      "loss": 0.8878,
+      "step": 488
+    },
+    {
+      "epoch": 0.9403846153846154,
+      "grad_norm": 0.73046875,
+      "learning_rate": 5.916908931681781e-06,
+      "loss": 0.9049,
+      "step": 489
+    },
+    {
+      "epoch": 0.9423076923076923,
+      "grad_norm": 0.703125,
+      "learning_rate": 5.90127518906953e-06,
+      "loss": 0.8733,
+      "step": 490
+    },
+    {
+      "epoch": 0.9442307692307692,
+      "grad_norm": 0.69921875,
+      "learning_rate": 5.885632333844714e-06,
+      "loss": 0.8896,
+      "step": 491
+    },
+    {
+      "epoch": 0.9461538461538461,
+      "grad_norm": 0.7109375,
+      "learning_rate": 5.8699805241691065e-06,
+      "loss": 0.9191,
+      "step": 492
+    },
+    {
+      "epoch": 0.948076923076923,
+      "grad_norm": 0.69921875,
+      "learning_rate": 5.854319918295012e-06,
+      "loss": 0.8721,
+      "step": 493
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.73828125,
+      "learning_rate": 5.838650674563674e-06,
+      "loss": 0.8746,
+      "step": 494
+    },
+    {
+      "epoch": 0.9519230769230769,
+      "grad_norm": 0.74609375,
+      "learning_rate": 5.82297295140367e-06,
+      "loss": 0.9072,
+      "step": 495
+    },
+    {
+      "epoch": 0.9538461538461539,
+      "grad_norm": 0.74609375,
+      "learning_rate": 5.807286907329315e-06,
+      "loss": 0.8981,
+      "step": 496
+    },
+    {
+      "epoch": 0.9557692307692308,
+      "grad_norm": 0.734375,
+      "learning_rate": 5.79159270093905e-06,
+      "loss": 0.9358,
+      "step": 497
+    },
+    {
+      "epoch": 0.9576923076923077,
+      "grad_norm": 0.7109375,
+      "learning_rate": 5.7758904909138495e-06,
+      "loss": 0.915,
+      "step": 498
+    },
+    {
+      "epoch": 0.9596153846153846,
+      "grad_norm": 0.72265625,
+      "learning_rate": 5.760180436015604e-06,
+      "loss": 0.8652,
+      "step": 499
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 0.7265625,
+      "learning_rate": 5.74446269508553e-06,
+      "loss": 0.8926,
+      "step": 500
+    },
+    {
+      "epoch": 0.9634615384615385,
+      "grad_norm": 0.71484375,
+      "learning_rate": 5.7287374270425475e-06,
+      "loss": 0.8889,
+      "step": 501
+    },
+    {
+      "epoch": 0.9653846153846154,
+      "grad_norm": 0.703125,
+      "learning_rate": 5.7130047908816884e-06,
+      "loss": 0.9027,
+      "step": 502
+    },
+    {
+      "epoch": 0.9673076923076923,
+      "grad_norm": 0.7421875,
+      "learning_rate": 5.69726494567248e-06,
+      "loss": 0.9419,
+      "step": 503
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.73046875,
+      "learning_rate": 5.681518050557336e-06,
+      "loss": 0.9396,
+      "step": 504
+    },
+    {
+      "epoch": 0.9711538461538461,
+      "grad_norm": 0.71875,
+      "learning_rate": 5.6657642647499545e-06,
+      "loss": 0.8828,
+      "step": 505
+    },
+    {
+      "epoch": 0.9730769230769231,
+      "grad_norm": 0.765625,
+      "learning_rate": 5.650003747533701e-06,
+      "loss": 0.944,
+      "step": 506
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.73046875,
+      "learning_rate": 5.6342366582600035e-06,
+      "loss": 0.9072,
+      "step": 507
+    },
+    {
+      "epoch": 0.9769230769230769,
+      "grad_norm": 0.7265625,
+      "learning_rate": 5.61846315634674e-06,
+      "loss": 0.9015,
+      "step": 508
+    },
+    {
+      "epoch": 0.9788461538461538,
+      "grad_norm": 0.7265625,
+      "learning_rate": 5.6026834012766155e-06,
+      "loss": 0.9117,
+      "step": 509
+    },
+    {
+      "epoch": 0.9807692307692307,
+      "grad_norm": 0.75,
+      "learning_rate": 5.586897552595573e-06,
+      "loss": 0.971,
+      "step": 510
+    },
+    {
+      "epoch": 0.9826923076923076,
+      "grad_norm": 0.73828125,
+      "learning_rate": 5.571105769911159e-06,
+      "loss": 0.8729,
+      "step": 511
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "grad_norm": 0.72265625,
+      "learning_rate": 5.555308212890917e-06,
+      "loss": 0.9132,
+      "step": 512
+    },
+    {
+      "epoch": 0.9865384615384616,
+      "grad_norm": 0.72265625,
+      "learning_rate": 5.539505041260779e-06,
+      "loss": 0.8606,
+      "step": 513
+    },
+    {
+      "epoch": 0.9884615384615385,
+      "grad_norm": 0.703125,
+      "learning_rate": 5.523696414803438e-06,
+      "loss": 0.8937,
+      "step": 514
+    },
+    {
+      "epoch": 0.9903846153846154,
+      "grad_norm": 0.73046875,
+      "learning_rate": 5.507882493356745e-06,
+      "loss": 0.913,
+      "step": 515
+    },
+    {
+      "epoch": 0.9923076923076923,
+      "grad_norm": 4.5625,
+      "learning_rate": 5.49206343681209e-06,
+      "loss": 0.862,
+      "step": 516
+    },
+    {
+      "epoch": 0.9942307692307693,
+      "grad_norm": 0.703125,
+      "learning_rate": 5.476239405112775e-06,
+      "loss": 0.8662,
+      "step": 517
+    },
+    {
+      "epoch": 0.9961538461538462,
+      "grad_norm": 0.73046875,
+      "learning_rate": 5.460410558252408e-06,
+      "loss": 0.8443,
+      "step": 518
+    },
+    {
+      "epoch": 0.9980769230769231,
+      "grad_norm": 0.7578125,
+      "learning_rate": 5.444577056273284e-06,
+      "loss": 0.9569,
+      "step": 519
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.73828125,
+      "learning_rate": 5.428739059264767e-06,
+      "loss": 0.8854,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9325999617576599,
+      "eval_runtime": 34.5297,
+      "eval_samples_per_second": 67.855,
+      "eval_steps_per_second": 16.971,
+      "step": 520
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1040,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 520,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.971810321620009e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-520/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0615dd190e3cad06c1c45c1f3f829927e89a7869d28d503cafc3ceb762da2c
+size 10808