Add files using upload-large-folder tool

.gitattributes

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

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d84bb669c93fa3d80fdd52e140f3376b330fa5fd7accb091bde321de9ac04831
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f76c9620a174ceb0540e5f2dbb22f89fbbe976e78f5fde97501f6e08f5e61c8
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad210af36ec349a5dba8aaf346e3243b3f42adb703cf8e7c7003c1b5317b47b
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51da41519a9d613d590d683c6c1ff5f906b0d60b55cbd877f8a5805d7e1bf8dc
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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
+    }
+  },
+  "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    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 10000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,3127 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 442,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004524886877828055,
+      "grad_norm": 3.2510592937469482,
+      "learning_rate": 4.524886877828055e-08,
+      "loss": 0.8401,
+      "step": 1
+    },
+    {
+      "epoch": 0.00904977375565611,
+      "grad_norm": 2.890446424484253,
+      "learning_rate": 9.04977375565611e-08,
+      "loss": 0.7699,
+      "step": 2
+    },
+    {
+      "epoch": 0.013574660633484163,
+      "grad_norm": 3.4535956382751465,
+      "learning_rate": 1.3574660633484163e-07,
+      "loss": 0.8325,
+      "step": 3
+    },
+    {
+      "epoch": 0.01809954751131222,
+      "grad_norm": 2.992128610610962,
+      "learning_rate": 1.809954751131222e-07,
+      "loss": 0.7607,
+      "step": 4
+    },
+    {
+      "epoch": 0.02262443438914027,
+      "grad_norm": 2.929943561553955,
+      "learning_rate": 2.2624434389140273e-07,
+      "loss": 0.7356,
+      "step": 5
+    },
+    {
+      "epoch": 0.027149321266968326,
+      "grad_norm": 3.091803550720215,
+      "learning_rate": 2.7149321266968326e-07,
+      "loss": 0.7924,
+      "step": 6
+    },
+    {
+      "epoch": 0.03167420814479638,
+      "grad_norm": 2.760162591934204,
+      "learning_rate": 3.167420814479638e-07,
+      "loss": 0.7152,
+      "step": 7
+    },
+    {
+      "epoch": 0.03619909502262444,
+      "grad_norm": 2.924128770828247,
+      "learning_rate": 3.619909502262444e-07,
+      "loss": 0.7361,
+      "step": 8
+    },
+    {
+      "epoch": 0.04072398190045249,
+      "grad_norm": 3.2693638801574707,
+      "learning_rate": 4.072398190045249e-07,
+      "loss": 0.8098,
+      "step": 9
+    },
+    {
+      "epoch": 0.04524886877828054,
+      "grad_norm": 2.807117462158203,
+      "learning_rate": 4.5248868778280546e-07,
+      "loss": 0.7414,
+      "step": 10
+    },
+    {
+      "epoch": 0.049773755656108594,
+      "grad_norm": 2.837460994720459,
+      "learning_rate": 4.977375565610859e-07,
+      "loss": 0.7736,
+      "step": 11
+    },
+    {
+      "epoch": 0.05429864253393665,
+      "grad_norm": 2.843400239944458,
+      "learning_rate": 5.429864253393665e-07,
+      "loss": 0.7254,
+      "step": 12
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 2.7627649307250977,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 0.7314,
+      "step": 13
+    },
+    {
+      "epoch": 0.06334841628959276,
+      "grad_norm": 2.5128955841064453,
+      "learning_rate": 6.334841628959276e-07,
+      "loss": 0.6816,
+      "step": 14
+    },
+    {
+      "epoch": 0.06787330316742081,
+      "grad_norm": 2.2178218364715576,
+      "learning_rate": 6.787330316742082e-07,
+      "loss": 0.687,
+      "step": 15
+    },
+    {
+      "epoch": 0.07239819004524888,
+      "grad_norm": 2.223222017288208,
+      "learning_rate": 7.239819004524888e-07,
+      "loss": 0.6834,
+      "step": 16
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 2.177546501159668,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 0.7176,
+      "step": 17
+    },
+    {
+      "epoch": 0.08144796380090498,
+      "grad_norm": 2.0788660049438477,
+      "learning_rate": 8.144796380090498e-07,
+      "loss": 0.6928,
+      "step": 18
+    },
+    {
+      "epoch": 0.08597285067873303,
+      "grad_norm": 2.013267993927002,
+      "learning_rate": 8.597285067873304e-07,
+      "loss": 0.7033,
+      "step": 19
+    },
+    {
+      "epoch": 0.09049773755656108,
+      "grad_norm": 1.640211820602417,
+      "learning_rate": 9.049773755656109e-07,
+      "loss": 0.7006,
+      "step": 20
+    },
+    {
+      "epoch": 0.09502262443438914,
+      "grad_norm": 1.2833340167999268,
+      "learning_rate": 9.502262443438914e-07,
+      "loss": 0.6464,
+      "step": 21
+    },
+    {
+      "epoch": 0.09954751131221719,
+      "grad_norm": 1.2619421482086182,
+      "learning_rate": 9.954751131221719e-07,
+      "loss": 0.6643,
+      "step": 22
+    },
+    {
+      "epoch": 0.10407239819004525,
+      "grad_norm": 1.2324565649032593,
+      "learning_rate": 1.0407239819004527e-06,
+      "loss": 0.6724,
+      "step": 23
+    },
+    {
+      "epoch": 0.1085972850678733,
+      "grad_norm": 1.1131088733673096,
+      "learning_rate": 1.085972850678733e-06,
+      "loss": 0.6059,
+      "step": 24
+    },
+    {
+      "epoch": 0.11312217194570136,
+      "grad_norm": 1.1473792791366577,
+      "learning_rate": 1.1312217194570136e-06,
+      "loss": 0.6494,
+      "step": 25
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 1.1130750179290771,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 0.6693,
+      "step": 26
+    },
+    {
+      "epoch": 0.12217194570135746,
+      "grad_norm": 1.1199308633804321,
+      "learning_rate": 1.2217194570135748e-06,
+      "loss": 0.7353,
+      "step": 27
+    },
+    {
+      "epoch": 0.12669683257918551,
+      "grad_norm": 1.094309687614441,
+      "learning_rate": 1.2669683257918552e-06,
+      "loss": 0.6729,
+      "step": 28
+    },
+    {
+      "epoch": 0.13122171945701358,
+      "grad_norm": 1.2093147039413452,
+      "learning_rate": 1.312217194570136e-06,
+      "loss": 0.6549,
+      "step": 29
+    },
+    {
+      "epoch": 0.13574660633484162,
+      "grad_norm": 1.2095019817352295,
+      "learning_rate": 1.3574660633484164e-06,
+      "loss": 0.6317,
+      "step": 30
+    },
+    {
+      "epoch": 0.14027149321266968,
+      "grad_norm": 1.43827223777771,
+      "learning_rate": 1.402714932126697e-06,
+      "loss": 0.6496,
+      "step": 31
+    },
+    {
+      "epoch": 0.14479638009049775,
+      "grad_norm": 1.4549624919891357,
+      "learning_rate": 1.4479638009049775e-06,
+      "loss": 0.6697,
+      "step": 32
+    },
+    {
+      "epoch": 0.1493212669683258,
+      "grad_norm": 1.165290117263794,
+      "learning_rate": 1.493212669683258e-06,
+      "loss": 0.6249,
+      "step": 33
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 1.257883906364441,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 0.6564,
+      "step": 34
+    },
+    {
+      "epoch": 0.1583710407239819,
+      "grad_norm": 1.027738094329834,
+      "learning_rate": 1.583710407239819e-06,
+      "loss": 0.5368,
+      "step": 35
+    },
+    {
+      "epoch": 0.16289592760180996,
+      "grad_norm": 0.9741559624671936,
+      "learning_rate": 1.6289592760180997e-06,
+      "loss": 0.6242,
+      "step": 36
+    },
+    {
+      "epoch": 0.167420814479638,
+      "grad_norm": 0.8538191318511963,
+      "learning_rate": 1.67420814479638e-06,
+      "loss": 0.6142,
+      "step": 37
+    },
+    {
+      "epoch": 0.17194570135746606,
+      "grad_norm": 0.6769871115684509,
+      "learning_rate": 1.7194570135746609e-06,
+      "loss": 0.5496,
+      "step": 38
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 0.6637622117996216,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 0.5751,
+      "step": 39
+    },
+    {
+      "epoch": 0.18099547511312217,
+      "grad_norm": 0.6483653783798218,
+      "learning_rate": 1.8099547511312218e-06,
+      "loss": 0.6127,
+      "step": 40
+    },
+    {
+      "epoch": 0.18552036199095023,
+      "grad_norm": 0.7997961044311523,
+      "learning_rate": 1.8552036199095024e-06,
+      "loss": 0.576,
+      "step": 41
+    },
+    {
+      "epoch": 0.19004524886877827,
+      "grad_norm": 0.7297148704528809,
+      "learning_rate": 1.9004524886877828e-06,
+      "loss": 0.6254,
+      "step": 42
+    },
+    {
+      "epoch": 0.19457013574660634,
+      "grad_norm": 0.6087789535522461,
+      "learning_rate": 1.9457013574660634e-06,
+      "loss": 0.5344,
+      "step": 43
+    },
+    {
+      "epoch": 0.19909502262443438,
+      "grad_norm": 0.7219811677932739,
+      "learning_rate": 1.9909502262443437e-06,
+      "loss": 0.5776,
+      "step": 44
+    },
+    {
+      "epoch": 0.20361990950226244,
+      "grad_norm": 0.7508623003959656,
+      "learning_rate": 2.0361990950226245e-06,
+      "loss": 0.5435,
+      "step": 45
+    },
+    {
+      "epoch": 0.2081447963800905,
+      "grad_norm": 0.6041704416275024,
+      "learning_rate": 2.0814479638009053e-06,
+      "loss": 0.5094,
+      "step": 46
+    },
+    {
+      "epoch": 0.21266968325791855,
+      "grad_norm": 0.6673488020896912,
+      "learning_rate": 2.1266968325791857e-06,
+      "loss": 0.556,
+      "step": 47
+    },
+    {
+      "epoch": 0.2171945701357466,
+      "grad_norm": 0.6235842704772949,
+      "learning_rate": 2.171945701357466e-06,
+      "loss": 0.5766,
+      "step": 48
+    },
+    {
+      "epoch": 0.22171945701357465,
+      "grad_norm": 0.5541844367980957,
+      "learning_rate": 2.2171945701357465e-06,
+      "loss": 0.5422,
+      "step": 49
+    },
+    {
+      "epoch": 0.22624434389140272,
+      "grad_norm": 0.6511553525924683,
+      "learning_rate": 2.2624434389140273e-06,
+      "loss": 0.6076,
+      "step": 50
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.5737389922142029,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 0.5804,
+      "step": 51
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.45331427454948425,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 0.4903,
+      "step": 52
+    },
+    {
+      "epoch": 0.2398190045248869,
+      "grad_norm": 0.5451053977012634,
+      "learning_rate": 2.3981900452488693e-06,
+      "loss": 0.5716,
+      "step": 53
+    },
+    {
+      "epoch": 0.24434389140271492,
+      "grad_norm": 0.5204625725746155,
+      "learning_rate": 2.4434389140271496e-06,
+      "loss": 0.5129,
+      "step": 54
+    },
+    {
+      "epoch": 0.248868778280543,
+      "grad_norm": 0.4971032440662384,
+      "learning_rate": 2.48868778280543e-06,
+      "loss": 0.5389,
+      "step": 55
+    },
+    {
+      "epoch": 0.25339366515837103,
+      "grad_norm": 0.5272262096405029,
+      "learning_rate": 2.5339366515837104e-06,
+      "loss": 0.5235,
+      "step": 56
+    },
+    {
+      "epoch": 0.2579185520361991,
+      "grad_norm": 0.5696743130683899,
+      "learning_rate": 2.5791855203619916e-06,
+      "loss": 0.508,
+      "step": 57
+    },
+    {
+      "epoch": 0.26244343891402716,
+      "grad_norm": 0.5246968269348145,
+      "learning_rate": 2.624434389140272e-06,
+      "loss": 0.5625,
+      "step": 58
+    },
+    {
+      "epoch": 0.2669683257918552,
+      "grad_norm": 0.5081693530082703,
+      "learning_rate": 2.6696832579185524e-06,
+      "loss": 0.501,
+      "step": 59
+    },
+    {
+      "epoch": 0.27149321266968324,
+      "grad_norm": 0.48727846145629883,
+      "learning_rate": 2.7149321266968327e-06,
+      "loss": 0.5259,
+      "step": 60
+    },
+    {
+      "epoch": 0.27601809954751133,
+      "grad_norm": 0.4420638084411621,
+      "learning_rate": 2.7601809954751135e-06,
+      "loss": 0.5165,
+      "step": 61
+    },
+    {
+      "epoch": 0.28054298642533937,
+      "grad_norm": 0.4388761818408966,
+      "learning_rate": 2.805429864253394e-06,
+      "loss": 0.4902,
+      "step": 62
+    },
+    {
+      "epoch": 0.2850678733031674,
+      "grad_norm": 0.42472442984580994,
+      "learning_rate": 2.8506787330316743e-06,
+      "loss": 0.4561,
+      "step": 63
+    },
+    {
+      "epoch": 0.2895927601809955,
+      "grad_norm": 0.4837457239627838,
+      "learning_rate": 2.895927601809955e-06,
+      "loss": 0.5295,
+      "step": 64
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.4987254738807678,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.515,
+      "step": 65
+    },
+    {
+      "epoch": 0.2986425339366516,
+      "grad_norm": 0.4454256594181061,
+      "learning_rate": 2.986425339366516e-06,
+      "loss": 0.5238,
+      "step": 66
+    },
+    {
+      "epoch": 0.3031674208144796,
+      "grad_norm": 0.5037821531295776,
+      "learning_rate": 3.0316742081447962e-06,
+      "loss": 0.5527,
+      "step": 67
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.4538140296936035,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.4905,
+      "step": 68
+    },
+    {
+      "epoch": 0.31221719457013575,
+      "grad_norm": 0.5122717022895813,
+      "learning_rate": 3.122171945701358e-06,
+      "loss": 0.5493,
+      "step": 69
+    },
+    {
+      "epoch": 0.3167420814479638,
+      "grad_norm": 0.44596371054649353,
+      "learning_rate": 3.167420814479638e-06,
+      "loss": 0.5484,
+      "step": 70
+    },
+    {
+      "epoch": 0.3212669683257919,
+      "grad_norm": 0.4473898410797119,
+      "learning_rate": 3.212669683257919e-06,
+      "loss": 0.5218,
+      "step": 71
+    },
+    {
+      "epoch": 0.3257918552036199,
+      "grad_norm": 0.3825899064540863,
+      "learning_rate": 3.2579185520361994e-06,
+      "loss": 0.4883,
+      "step": 72
+    },
+    {
+      "epoch": 0.33031674208144796,
+      "grad_norm": 0.40941205620765686,
+      "learning_rate": 3.3031674208144797e-06,
+      "loss": 0.4127,
+      "step": 73
+    },
+    {
+      "epoch": 0.334841628959276,
+      "grad_norm": 0.42915788292884827,
+      "learning_rate": 3.34841628959276e-06,
+      "loss": 0.5194,
+      "step": 74
+    },
+    {
+      "epoch": 0.3393665158371041,
+      "grad_norm": 0.44509854912757874,
+      "learning_rate": 3.3936651583710413e-06,
+      "loss": 0.4664,
+      "step": 75
+    },
+    {
+      "epoch": 0.3438914027149321,
+      "grad_norm": 0.41393935680389404,
+      "learning_rate": 3.4389140271493217e-06,
+      "loss": 0.5213,
+      "step": 76
+    },
+    {
+      "epoch": 0.34841628959276016,
+      "grad_norm": 0.4840753674507141,
+      "learning_rate": 3.484162895927602e-06,
+      "loss": 0.5456,
+      "step": 77
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 0.39024800062179565,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 0.446,
+      "step": 78
+    },
+    {
+      "epoch": 0.3574660633484163,
+      "grad_norm": 0.4665883481502533,
+      "learning_rate": 3.5746606334841633e-06,
+      "loss": 0.504,
+      "step": 79
+    },
+    {
+      "epoch": 0.36199095022624433,
+      "grad_norm": 0.38244664669036865,
+      "learning_rate": 3.6199095022624436e-06,
+      "loss": 0.4656,
+      "step": 80
+    },
+    {
+      "epoch": 0.3665158371040724,
+      "grad_norm": 0.39441755414009094,
+      "learning_rate": 3.665158371040724e-06,
+      "loss": 0.4861,
+      "step": 81
+    },
+    {
+      "epoch": 0.37104072398190047,
+      "grad_norm": 0.41697946190834045,
+      "learning_rate": 3.710407239819005e-06,
+      "loss": 0.4678,
+      "step": 82
+    },
+    {
+      "epoch": 0.3755656108597285,
+      "grad_norm": 0.4145350456237793,
+      "learning_rate": 3.755656108597285e-06,
+      "loss": 0.4501,
+      "step": 83
+    },
+    {
+      "epoch": 0.38009049773755654,
+      "grad_norm": 0.42326846718788147,
+      "learning_rate": 3.8009049773755656e-06,
+      "loss": 0.4617,
+      "step": 84
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.44864463806152344,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.5503,
+      "step": 85
+    },
+    {
+      "epoch": 0.3891402714932127,
+      "grad_norm": 0.4511263072490692,
+      "learning_rate": 3.891402714932127e-06,
+      "loss": 0.4581,
+      "step": 86
+    },
+    {
+      "epoch": 0.3936651583710407,
+      "grad_norm": 0.5121440291404724,
+      "learning_rate": 3.9366515837104075e-06,
+      "loss": 0.4622,
+      "step": 87
+    },
+    {
+      "epoch": 0.39819004524886875,
+      "grad_norm": 0.45248016715049744,
+      "learning_rate": 3.9819004524886875e-06,
+      "loss": 0.5035,
+      "step": 88
+    },
+    {
+      "epoch": 0.40271493212669685,
+      "grad_norm": 0.4109788239002228,
+      "learning_rate": 4.027149321266969e-06,
+      "loss": 0.4743,
+      "step": 89
+    },
+    {
+      "epoch": 0.4072398190045249,
+      "grad_norm": 0.4233633577823639,
+      "learning_rate": 4.072398190045249e-06,
+      "loss": 0.4829,
+      "step": 90
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 0.47834792733192444,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 0.5588,
+      "step": 91
+    },
+    {
+      "epoch": 0.416289592760181,
+      "grad_norm": 0.4849421977996826,
+      "learning_rate": 4.162895927601811e-06,
+      "loss": 0.4738,
+      "step": 92
+    },
+    {
+      "epoch": 0.42081447963800905,
+      "grad_norm": 0.4980224370956421,
+      "learning_rate": 4.208144796380091e-06,
+      "loss": 0.5288,
+      "step": 93
+    },
+    {
+      "epoch": 0.4253393665158371,
+      "grad_norm": 0.42526569962501526,
+      "learning_rate": 4.2533936651583714e-06,
+      "loss": 0.4128,
+      "step": 94
+    },
+    {
+      "epoch": 0.4298642533936652,
+      "grad_norm": 0.483390748500824,
+      "learning_rate": 4.298642533936652e-06,
+      "loss": 0.4445,
+      "step": 95
+    },
+    {
+      "epoch": 0.4343891402714932,
+      "grad_norm": 0.4766150116920471,
+      "learning_rate": 4.343891402714932e-06,
+      "loss": 0.5001,
+      "step": 96
+    },
+    {
+      "epoch": 0.43891402714932126,
+      "grad_norm": 0.5314707159996033,
+      "learning_rate": 4.389140271493213e-06,
+      "loss": 0.4891,
+      "step": 97
+    },
+    {
+      "epoch": 0.4434389140271493,
+      "grad_norm": 0.44213107228279114,
+      "learning_rate": 4.434389140271493e-06,
+      "loss": 0.5129,
+      "step": 98
+    },
+    {
+      "epoch": 0.4479638009049774,
+      "grad_norm": 0.43551620841026306,
+      "learning_rate": 4.479638009049775e-06,
+      "loss": 0.4557,
+      "step": 99
+    },
+    {
+      "epoch": 0.45248868778280543,
+      "grad_norm": 0.4333869516849518,
+      "learning_rate": 4.5248868778280546e-06,
+      "loss": 0.4746,
+      "step": 100
+    },
+    {
+      "epoch": 0.45701357466063347,
+      "grad_norm": 0.42583024501800537,
+      "learning_rate": 4.570135746606335e-06,
+      "loss": 0.45,
+      "step": 101
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.48476096987724304,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.5087,
+      "step": 102
+    },
+    {
+      "epoch": 0.4660633484162896,
+      "grad_norm": 0.4503658413887024,
+      "learning_rate": 4.660633484162896e-06,
+      "loss": 0.4574,
+      "step": 103
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.43352094292640686,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 0.4494,
+      "step": 104
+    },
+    {
+      "epoch": 0.4751131221719457,
+      "grad_norm": 0.4933190643787384,
+      "learning_rate": 4.751131221719457e-06,
+      "loss": 0.4441,
+      "step": 105
+    },
+    {
+      "epoch": 0.4796380090497738,
+      "grad_norm": 0.4639478325843811,
+      "learning_rate": 4.7963800904977385e-06,
+      "loss": 0.4721,
+      "step": 106
+    },
+    {
+      "epoch": 0.4841628959276018,
+      "grad_norm": 0.4035486876964569,
+      "learning_rate": 4.8416289592760185e-06,
+      "loss": 0.4574,
+      "step": 107
+    },
+    {
+      "epoch": 0.48868778280542985,
+      "grad_norm": 0.47403860092163086,
+      "learning_rate": 4.886877828054299e-06,
+      "loss": 0.4516,
+      "step": 108
+    },
+    {
+      "epoch": 0.49321266968325794,
+      "grad_norm": 0.48216933012008667,
+      "learning_rate": 4.93212669683258e-06,
+      "loss": 0.4521,
+      "step": 109
+    },
+    {
+      "epoch": 0.497737556561086,
+      "grad_norm": 0.43759751319885254,
+      "learning_rate": 4.97737556561086e-06,
+      "loss": 0.4409,
+      "step": 110
+    },
+    {
+      "epoch": 0.502262443438914,
+      "grad_norm": 0.4080127775669098,
+      "learning_rate": 5.022624434389141e-06,
+      "loss": 0.4762,
+      "step": 111
+    },
+    {
+      "epoch": 0.5067873303167421,
+      "grad_norm": 0.5794436931610107,
+      "learning_rate": 5.067873303167421e-06,
+      "loss": 0.4954,
+      "step": 112
+    },
+    {
+      "epoch": 0.5113122171945701,
+      "grad_norm": 0.5085976123809814,
+      "learning_rate": 5.1131221719457016e-06,
+      "loss": 0.4635,
+      "step": 113
+    },
+    {
+      "epoch": 0.5158371040723982,
+      "grad_norm": 0.41183438897132874,
+      "learning_rate": 5.158371040723983e-06,
+      "loss": 0.46,
+      "step": 114
+    },
+    {
+      "epoch": 0.5203619909502263,
+      "grad_norm": 0.4061497747898102,
+      "learning_rate": 5.203619909502263e-06,
+      "loss": 0.4559,
+      "step": 115
+    },
+    {
+      "epoch": 0.5248868778280543,
+      "grad_norm": 0.4753948748111725,
+      "learning_rate": 5.248868778280544e-06,
+      "loss": 0.4398,
+      "step": 116
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 0.47879111766815186,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 0.4709,
+      "step": 117
+    },
+    {
+      "epoch": 0.5339366515837104,
+      "grad_norm": 0.4345899820327759,
+      "learning_rate": 5.339366515837105e-06,
+      "loss": 0.4576,
+      "step": 118
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 0.4419268071651459,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 0.4489,
+      "step": 119
+    },
+    {
+      "epoch": 0.5429864253393665,
+      "grad_norm": 0.46015602350234985,
+      "learning_rate": 5.4298642533936655e-06,
+      "loss": 0.4463,
+      "step": 120
+    },
+    {
+      "epoch": 0.5475113122171946,
+      "grad_norm": 0.4941313862800598,
+      "learning_rate": 5.475113122171946e-06,
+      "loss": 0.5041,
+      "step": 121
+    },
+    {
+      "epoch": 0.5520361990950227,
+      "grad_norm": 0.4165358245372772,
+      "learning_rate": 5.520361990950227e-06,
+      "loss": 0.4749,
+      "step": 122
+    },
+    {
+      "epoch": 0.5565610859728507,
+      "grad_norm": 0.4693758189678192,
+      "learning_rate": 5.565610859728508e-06,
+      "loss": 0.4536,
+      "step": 123
+    },
+    {
+      "epoch": 0.5610859728506787,
+      "grad_norm": 0.4350532293319702,
+      "learning_rate": 5.610859728506788e-06,
+      "loss": 0.5089,
+      "step": 124
+    },
+    {
+      "epoch": 0.5656108597285068,
+      "grad_norm": 0.45343929529190063,
+      "learning_rate": 5.656108597285069e-06,
+      "loss": 0.4014,
+      "step": 125
+    },
+    {
+      "epoch": 0.5701357466063348,
+      "grad_norm": 0.507248044013977,
+      "learning_rate": 5.7013574660633486e-06,
+      "loss": 0.4932,
+      "step": 126
+    },
+    {
+      "epoch": 0.5746606334841629,
+      "grad_norm": 0.48399487137794495,
+      "learning_rate": 5.746606334841629e-06,
+      "loss": 0.5221,
+      "step": 127
+    },
+    {
+      "epoch": 0.579185520361991,
+      "grad_norm": 0.39801326394081116,
+      "learning_rate": 5.79185520361991e-06,
+      "loss": 0.4325,
+      "step": 128
+    },
+    {
+      "epoch": 0.583710407239819,
+      "grad_norm": 0.4183308780193329,
+      "learning_rate": 5.837104072398191e-06,
+      "loss": 0.4293,
+      "step": 129
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.4360859990119934,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.4135,
+      "step": 130
+    },
+    {
+      "epoch": 0.5927601809954751,
+      "grad_norm": 0.4908457398414612,
+      "learning_rate": 5.927601809954752e-06,
+      "loss": 0.4765,
+      "step": 131
+    },
+    {
+      "epoch": 0.5972850678733032,
+      "grad_norm": 0.4215766489505768,
+      "learning_rate": 5.972850678733032e-06,
+      "loss": 0.4622,
+      "step": 132
+    },
+    {
+      "epoch": 0.6018099547511312,
+      "grad_norm": 0.4052114188671112,
+      "learning_rate": 6.0180995475113125e-06,
+      "loss": 0.4317,
+      "step": 133
+    },
+    {
+      "epoch": 0.6063348416289592,
+      "grad_norm": 0.46360260248184204,
+      "learning_rate": 6.0633484162895924e-06,
+      "loss": 0.4827,
+      "step": 134
+    },
+    {
+      "epoch": 0.6108597285067874,
+      "grad_norm": 0.40575292706489563,
+      "learning_rate": 6.108597285067874e-06,
+      "loss": 0.4281,
+      "step": 135
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.5005738139152527,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.5005,
+      "step": 136
+    },
+    {
+      "epoch": 0.6199095022624435,
+      "grad_norm": 0.451043963432312,
+      "learning_rate": 6.199095022624435e-06,
+      "loss": 0.4006,
+      "step": 137
+    },
+    {
+      "epoch": 0.6244343891402715,
+      "grad_norm": 0.4629691541194916,
+      "learning_rate": 6.244343891402716e-06,
+      "loss": 0.4941,
+      "step": 138
+    },
+    {
+      "epoch": 0.6289592760180995,
+      "grad_norm": 0.4519931375980377,
+      "learning_rate": 6.2895927601809956e-06,
+      "loss": 0.4438,
+      "step": 139
+    },
+    {
+      "epoch": 0.6334841628959276,
+      "grad_norm": 0.4885016679763794,
+      "learning_rate": 6.334841628959276e-06,
+      "loss": 0.4642,
+      "step": 140
+    },
+    {
+      "epoch": 0.6380090497737556,
+      "grad_norm": 0.4142250418663025,
+      "learning_rate": 6.380090497737556e-06,
+      "loss": 0.4164,
+      "step": 141
+    },
+    {
+      "epoch": 0.6425339366515838,
+      "grad_norm": 0.4803358316421509,
+      "learning_rate": 6.425339366515838e-06,
+      "loss": 0.4564,
+      "step": 142
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 0.47766202688217163,
+      "learning_rate": 6.470588235294119e-06,
+      "loss": 0.4106,
+      "step": 143
+    },
+    {
+      "epoch": 0.6515837104072398,
+      "grad_norm": 0.449381947517395,
+      "learning_rate": 6.515837104072399e-06,
+      "loss": 0.4301,
+      "step": 144
+    },
+    {
+      "epoch": 0.6561085972850679,
+      "grad_norm": 0.3938814103603363,
+      "learning_rate": 6.5610859728506795e-06,
+      "loss": 0.4916,
+      "step": 145
+    },
+    {
+      "epoch": 0.6606334841628959,
+      "grad_norm": 0.39036545157432556,
+      "learning_rate": 6.6063348416289595e-06,
+      "loss": 0.4538,
+      "step": 146
+    },
+    {
+      "epoch": 0.665158371040724,
+      "grad_norm": 0.4129018485546112,
+      "learning_rate": 6.65158371040724e-06,
+      "loss": 0.4414,
+      "step": 147
+    },
+    {
+      "epoch": 0.669683257918552,
+      "grad_norm": 0.4925534725189209,
+      "learning_rate": 6.69683257918552e-06,
+      "loss": 0.4393,
+      "step": 148
+    },
+    {
+      "epoch": 0.6742081447963801,
+      "grad_norm": 0.4131447374820709,
+      "learning_rate": 6.742081447963802e-06,
+      "loss": 0.4944,
+      "step": 149
+    },
+    {
+      "epoch": 0.6787330316742082,
+      "grad_norm": 0.4236401319503784,
+      "learning_rate": 6.787330316742083e-06,
+      "loss": 0.4603,
+      "step": 150
+    },
+    {
+      "epoch": 0.6832579185520362,
+      "grad_norm": 0.4191535413265228,
+      "learning_rate": 6.832579185520363e-06,
+      "loss": 0.4195,
+      "step": 151
+    },
+    {
+      "epoch": 0.6877828054298643,
+      "grad_norm": 0.36520934104919434,
+      "learning_rate": 6.8778280542986434e-06,
+      "loss": 0.4602,
+      "step": 152
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.5145202875137329,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 0.508,
+      "step": 153
+    },
+    {
+      "epoch": 0.6968325791855203,
+      "grad_norm": 0.5549051761627197,
+      "learning_rate": 6.968325791855204e-06,
+      "loss": 0.4974,
+      "step": 154
+    },
+    {
+      "epoch": 0.7013574660633484,
+      "grad_norm": 0.42621299624443054,
+      "learning_rate": 7.013574660633484e-06,
+      "loss": 0.4783,
+      "step": 155
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.562082052230835,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 0.519,
+      "step": 156
+    },
+    {
+      "epoch": 0.7104072398190046,
+      "grad_norm": 0.4220001697540283,
+      "learning_rate": 7.104072398190046e-06,
+      "loss": 0.4909,
+      "step": 157
+    },
+    {
+      "epoch": 0.7149321266968326,
+      "grad_norm": 0.450371652841568,
+      "learning_rate": 7.1493212669683265e-06,
+      "loss": 0.441,
+      "step": 158
+    },
+    {
+      "epoch": 0.7194570135746606,
+      "grad_norm": 0.4640924036502838,
+      "learning_rate": 7.1945701357466065e-06,
+      "loss": 0.4315,
+      "step": 159
+    },
+    {
+      "epoch": 0.7239819004524887,
+      "grad_norm": 0.417269229888916,
+      "learning_rate": 7.239819004524887e-06,
+      "loss": 0.4071,
+      "step": 160
+    },
+    {
+      "epoch": 0.7285067873303167,
+      "grad_norm": 0.5066007971763611,
+      "learning_rate": 7.285067873303168e-06,
+      "loss": 0.4618,
+      "step": 161
+    },
+    {
+      "epoch": 0.7330316742081447,
+      "grad_norm": 0.412210613489151,
+      "learning_rate": 7.330316742081448e-06,
+      "loss": 0.4871,
+      "step": 162
+    },
+    {
+      "epoch": 0.7375565610859729,
+      "grad_norm": 0.41878026723861694,
+      "learning_rate": 7.37556561085973e-06,
+      "loss": 0.437,
+      "step": 163
+    },
+    {
+      "epoch": 0.7420814479638009,
+      "grad_norm": 0.48414674401283264,
+      "learning_rate": 7.42081447963801e-06,
+      "loss": 0.4682,
+      "step": 164
+    },
+    {
+      "epoch": 0.746606334841629,
+      "grad_norm": 0.45116230845451355,
+      "learning_rate": 7.4660633484162904e-06,
+      "loss": 0.4137,
+      "step": 165
+    },
+    {
+      "epoch": 0.751131221719457,
+      "grad_norm": 0.4211224615573883,
+      "learning_rate": 7.51131221719457e-06,
+      "loss": 0.4063,
+      "step": 166
+    },
+    {
+      "epoch": 0.755656108597285,
+      "grad_norm": 0.46173834800720215,
+      "learning_rate": 7.556561085972851e-06,
+      "loss": 0.4924,
+      "step": 167
+    },
+    {
+      "epoch": 0.7601809954751131,
+      "grad_norm": 0.4191412925720215,
+      "learning_rate": 7.601809954751131e-06,
+      "loss": 0.4572,
+      "step": 168
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 0.4505658745765686,
+      "learning_rate": 7.647058823529411e-06,
+      "loss": 0.4481,
+      "step": 169
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.5168994069099426,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.4449,
+      "step": 170
+    },
+    {
+      "epoch": 0.7737556561085973,
+      "grad_norm": 0.5589344501495361,
+      "learning_rate": 7.737556561085974e-06,
+      "loss": 0.4761,
+      "step": 171
+    },
+    {
+      "epoch": 0.7782805429864253,
+      "grad_norm": 0.4831865429878235,
+      "learning_rate": 7.782805429864253e-06,
+      "loss": 0.4805,
+      "step": 172
+    },
+    {
+      "epoch": 0.7828054298642534,
+      "grad_norm": 0.46204084157943726,
+      "learning_rate": 7.828054298642534e-06,
+      "loss": 0.4535,
+      "step": 173
+    },
+    {
+      "epoch": 0.7873303167420814,
+      "grad_norm": 0.44106197357177734,
+      "learning_rate": 7.873303167420815e-06,
+      "loss": 0.4072,
+      "step": 174
+    },
+    {
+      "epoch": 0.7918552036199095,
+      "grad_norm": 0.5106877088546753,
+      "learning_rate": 7.918552036199096e-06,
+      "loss": 0.4125,
+      "step": 175
+    },
+    {
+      "epoch": 0.7963800904977375,
+      "grad_norm": 0.5074198842048645,
+      "learning_rate": 7.963800904977375e-06,
+      "loss": 0.434,
+      "step": 176
+    },
+    {
+      "epoch": 0.8009049773755657,
+      "grad_norm": 0.40606701374053955,
+      "learning_rate": 8.009049773755657e-06,
+      "loss": 0.4624,
+      "step": 177
+    },
+    {
+      "epoch": 0.8054298642533937,
+      "grad_norm": 0.5007057189941406,
+      "learning_rate": 8.054298642533938e-06,
+      "loss": 0.4476,
+      "step": 178
+    },
+    {
+      "epoch": 0.8099547511312217,
+      "grad_norm": 0.5165268778800964,
+      "learning_rate": 8.099547511312217e-06,
+      "loss": 0.4746,
+      "step": 179
+    },
+    {
+      "epoch": 0.8144796380090498,
+      "grad_norm": 0.46993181109428406,
+      "learning_rate": 8.144796380090498e-06,
+      "loss": 0.4432,
+      "step": 180
+    },
+    {
+      "epoch": 0.8190045248868778,
+      "grad_norm": 0.5677555799484253,
+      "learning_rate": 8.190045248868779e-06,
+      "loss": 0.4422,
+      "step": 181
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.5643273591995239,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 0.5143,
+      "step": 182
+    },
+    {
+      "epoch": 0.8280542986425339,
+      "grad_norm": 0.5022807717323303,
+      "learning_rate": 8.280542986425339e-06,
+      "loss": 0.4544,
+      "step": 183
+    },
+    {
+      "epoch": 0.832579185520362,
+      "grad_norm": 0.49226853251457214,
+      "learning_rate": 8.325791855203621e-06,
+      "loss": 0.4637,
+      "step": 184
+    },
+    {
+      "epoch": 0.8371040723981901,
+      "grad_norm": 0.48023420572280884,
+      "learning_rate": 8.371040723981902e-06,
+      "loss": 0.4264,
+      "step": 185
+    },
+    {
+      "epoch": 0.8416289592760181,
+      "grad_norm": 0.5742875337600708,
+      "learning_rate": 8.416289592760181e-06,
+      "loss": 0.4761,
+      "step": 186
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 0.5855184197425842,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 0.4668,
+      "step": 187
+    },
+    {
+      "epoch": 0.8506787330316742,
+      "grad_norm": 0.5004088282585144,
+      "learning_rate": 8.506787330316743e-06,
+      "loss": 0.4354,
+      "step": 188
+    },
+    {
+      "epoch": 0.8552036199095022,
+      "grad_norm": 0.5111898183822632,
+      "learning_rate": 8.552036199095024e-06,
+      "loss": 0.4494,
+      "step": 189
+    },
+    {
+      "epoch": 0.8597285067873304,
+      "grad_norm": 0.5159589052200317,
+      "learning_rate": 8.597285067873304e-06,
+      "loss": 0.493,
+      "step": 190
+    },
+    {
+      "epoch": 0.8642533936651584,
+      "grad_norm": 0.5572559833526611,
+      "learning_rate": 8.642533936651585e-06,
+      "loss": 0.4845,
+      "step": 191
+    },
+    {
+      "epoch": 0.8687782805429864,
+      "grad_norm": 0.47993189096450806,
+      "learning_rate": 8.687782805429864e-06,
+      "loss": 0.4709,
+      "step": 192
+    },
+    {
+      "epoch": 0.8733031674208145,
+      "grad_norm": 0.4479634463787079,
+      "learning_rate": 8.733031674208145e-06,
+      "loss": 0.4192,
+      "step": 193
+    },
+    {
+      "epoch": 0.8778280542986425,
+      "grad_norm": 0.48463767766952515,
+      "learning_rate": 8.778280542986426e-06,
+      "loss": 0.4468,
+      "step": 194
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.4300975203514099,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.4546,
+      "step": 195
+    },
+    {
+      "epoch": 0.8868778280542986,
+      "grad_norm": 0.43377694487571716,
+      "learning_rate": 8.868778280542986e-06,
+      "loss": 0.4517,
+      "step": 196
+    },
+    {
+      "epoch": 0.8914027149321267,
+      "grad_norm": 0.4832284152507782,
+      "learning_rate": 8.914027149321268e-06,
+      "loss": 0.4296,
+      "step": 197
+    },
+    {
+      "epoch": 0.8959276018099548,
+      "grad_norm": 0.47211429476737976,
+      "learning_rate": 8.95927601809955e-06,
+      "loss": 0.4487,
+      "step": 198
+    },
+    {
+      "epoch": 0.9004524886877828,
+      "grad_norm": 0.4101850688457489,
+      "learning_rate": 9.004524886877828e-06,
+      "loss": 0.4392,
+      "step": 199
+    },
+    {
+      "epoch": 0.9049773755656109,
+      "grad_norm": 0.5208500623703003,
+      "learning_rate": 9.049773755656109e-06,
+      "loss": 0.4276,
+      "step": 200
+    },
+    {
+      "epoch": 0.9095022624434389,
+      "grad_norm": 0.49378854036331177,
+      "learning_rate": 9.09502262443439e-06,
+      "loss": 0.454,
+      "step": 201
+    },
+    {
+      "epoch": 0.9140271493212669,
+      "grad_norm": 0.4764745831489563,
+      "learning_rate": 9.14027149321267e-06,
+      "loss": 0.4176,
+      "step": 202
+    },
+    {
+      "epoch": 0.918552036199095,
+      "grad_norm": 0.45192357897758484,
+      "learning_rate": 9.18552036199095e-06,
+      "loss": 0.4762,
+      "step": 203
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.4330678880214691,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.4158,
+      "step": 204
+    },
+    {
+      "epoch": 0.9276018099547512,
+      "grad_norm": 0.5406427383422852,
+      "learning_rate": 9.276018099547513e-06,
+      "loss": 0.4351,
+      "step": 205
+    },
+    {
+      "epoch": 0.9321266968325792,
+      "grad_norm": 0.4686480760574341,
+      "learning_rate": 9.321266968325792e-06,
+      "loss": 0.4683,
+      "step": 206
+    },
+    {
+      "epoch": 0.9366515837104072,
+      "grad_norm": 0.430961549282074,
+      "learning_rate": 9.366515837104073e-06,
+      "loss": 0.4077,
+      "step": 207
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.4596535563468933,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 0.4357,
+      "step": 208
+    },
+    {
+      "epoch": 0.9457013574660633,
+      "grad_norm": 0.49825915694236755,
+      "learning_rate": 9.457013574660635e-06,
+      "loss": 0.4438,
+      "step": 209
+    },
+    {
+      "epoch": 0.9502262443438914,
+      "grad_norm": 0.4968724846839905,
+      "learning_rate": 9.502262443438914e-06,
+      "loss": 0.4391,
+      "step": 210
+    },
+    {
+      "epoch": 0.9547511312217195,
+      "grad_norm": 0.5227912664413452,
+      "learning_rate": 9.547511312217196e-06,
+      "loss": 0.4682,
+      "step": 211
+    },
+    {
+      "epoch": 0.9592760180995475,
+      "grad_norm": 0.593227744102478,
+      "learning_rate": 9.592760180995477e-06,
+      "loss": 0.4375,
+      "step": 212
+    },
+    {
+      "epoch": 0.9638009049773756,
+      "grad_norm": 0.46191665530204773,
+      "learning_rate": 9.638009049773756e-06,
+      "loss": 0.4469,
+      "step": 213
+    },
+    {
+      "epoch": 0.9683257918552036,
+      "grad_norm": 0.49439120292663574,
+      "learning_rate": 9.683257918552037e-06,
+      "loss": 0.4167,
+      "step": 214
+    },
+    {
+      "epoch": 0.9728506787330317,
+      "grad_norm": 0.5323225855827332,
+      "learning_rate": 9.728506787330318e-06,
+      "loss": 0.462,
+      "step": 215
+    },
+    {
+      "epoch": 0.9773755656108597,
+      "grad_norm": 0.40613311529159546,
+      "learning_rate": 9.773755656108599e-06,
+      "loss": 0.3551,
+      "step": 216
+    },
+    {
+      "epoch": 0.9819004524886877,
+      "grad_norm": 0.523820161819458,
+      "learning_rate": 9.819004524886878e-06,
+      "loss": 0.4303,
+      "step": 217
+    },
+    {
+      "epoch": 0.9864253393665159,
+      "grad_norm": 0.4367105960845947,
+      "learning_rate": 9.86425339366516e-06,
+      "loss": 0.4617,
+      "step": 218
+    },
+    {
+      "epoch": 0.9909502262443439,
+      "grad_norm": 0.474623441696167,
+      "learning_rate": 9.90950226244344e-06,
+      "loss": 0.4098,
+      "step": 219
+    },
+    {
+      "epoch": 0.995475113122172,
+      "grad_norm": 0.5020592212677002,
+      "learning_rate": 9.95475113122172e-06,
+      "loss": 0.3816,
+      "step": 220
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4186856150627136,
+      "learning_rate": 1e-05,
+      "loss": 0.4303,
+      "step": 221
+    },
+    {
+      "epoch": 1.004524886877828,
+      "grad_norm": 0.5000538229942322,
+      "learning_rate": 9.999993763081091e-06,
+      "loss": 0.4021,
+      "step": 222
+    },
+    {
+      "epoch": 1.009049773755656,
+      "grad_norm": 0.4233403205871582,
+      "learning_rate": 9.999975052339923e-06,
+      "loss": 0.3917,
+      "step": 223
+    },
+    {
+      "epoch": 1.0135746606334841,
+      "grad_norm": 0.44955193996429443,
+      "learning_rate": 9.999943867823174e-06,
+      "loss": 0.4112,
+      "step": 224
+    },
+    {
+      "epoch": 1.0180995475113122,
+      "grad_norm": 0.5060259699821472,
+      "learning_rate": 9.999900209608642e-06,
+      "loss": 0.3585,
+      "step": 225
+    },
+    {
+      "epoch": 1.0226244343891402,
+      "grad_norm": 0.46285244822502136,
+      "learning_rate": 9.999844077805245e-06,
+      "loss": 0.3972,
+      "step": 226
+    },
+    {
+      "epoch": 1.0271493212669682,
+      "grad_norm": 0.519055962562561,
+      "learning_rate": 9.999775472553019e-06,
+      "loss": 0.3439,
+      "step": 227
+    },
+    {
+      "epoch": 1.0316742081447963,
+      "grad_norm": 0.49448850750923157,
+      "learning_rate": 9.999694394023119e-06,
+      "loss": 0.3777,
+      "step": 228
+    },
+    {
+      "epoch": 1.0361990950226245,
+      "grad_norm": 0.502755343914032,
+      "learning_rate": 9.999600842417815e-06,
+      "loss": 0.3685,
+      "step": 229
+    },
+    {
+      "epoch": 1.0407239819004526,
+      "grad_norm": 0.5343412756919861,
+      "learning_rate": 9.999494817970498e-06,
+      "loss": 0.3402,
+      "step": 230
+    },
+    {
+      "epoch": 1.0452488687782806,
+      "grad_norm": 0.5237849354743958,
+      "learning_rate": 9.999376320945673e-06,
+      "loss": 0.3453,
+      "step": 231
+    },
+    {
+      "epoch": 1.0497737556561086,
+      "grad_norm": 0.5596418380737305,
+      "learning_rate": 9.999245351638964e-06,
+      "loss": 0.3945,
+      "step": 232
+    },
+    {
+      "epoch": 1.0542986425339367,
+      "grad_norm": 0.3989311456680298,
+      "learning_rate": 9.999101910377107e-06,
+      "loss": 0.3383,
+      "step": 233
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 0.4172278642654419,
+      "learning_rate": 9.998945997517957e-06,
+      "loss": 0.392,
+      "step": 234
+    },
+    {
+      "epoch": 1.0633484162895928,
+      "grad_norm": 0.5389004349708557,
+      "learning_rate": 9.998777613450478e-06,
+      "loss": 0.3883,
+      "step": 235
+    },
+    {
+      "epoch": 1.0678733031674208,
+      "grad_norm": 0.5382748246192932,
+      "learning_rate": 9.998596758594752e-06,
+      "loss": 0.3582,
+      "step": 236
+    },
+    {
+      "epoch": 1.0723981900452488,
+      "grad_norm": 0.5459226965904236,
+      "learning_rate": 9.998403433401969e-06,
+      "loss": 0.4137,
+      "step": 237
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 0.48526811599731445,
+      "learning_rate": 9.998197638354428e-06,
+      "loss": 0.3618,
+      "step": 238
+    },
+    {
+      "epoch": 1.081447963800905,
+      "grad_norm": 0.47047311067581177,
+      "learning_rate": 9.997979373965542e-06,
+      "loss": 0.3097,
+      "step": 239
+    },
+    {
+      "epoch": 1.085972850678733,
+      "grad_norm": 0.5708703398704529,
+      "learning_rate": 9.997748640779829e-06,
+      "loss": 0.4371,
+      "step": 240
+    },
+    {
+      "epoch": 1.090497737556561,
+      "grad_norm": 0.5245316028594971,
+      "learning_rate": 9.997505439372914e-06,
+      "loss": 0.3988,
+      "step": 241
+    },
+    {
+      "epoch": 1.0950226244343892,
+      "grad_norm": 0.5281980633735657,
+      "learning_rate": 9.997249770351531e-06,
+      "loss": 0.414,
+      "step": 242
+    },
+    {
+      "epoch": 1.0995475113122173,
+      "grad_norm": 0.6034480333328247,
+      "learning_rate": 9.99698163435351e-06,
+      "loss": 0.4268,
+      "step": 243
+    },
+    {
+      "epoch": 1.1040723981900453,
+      "grad_norm": 0.479973703622818,
+      "learning_rate": 9.996701032047795e-06,
+      "loss": 0.4261,
+      "step": 244
+    },
+    {
+      "epoch": 1.1085972850678734,
+      "grad_norm": 0.4137464165687561,
+      "learning_rate": 9.996407964134416e-06,
+      "loss": 0.369,
+      "step": 245
+    },
+    {
+      "epoch": 1.1131221719457014,
+      "grad_norm": 0.7938151359558105,
+      "learning_rate": 9.996102431344514e-06,
+      "loss": 0.4152,
+      "step": 246
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.5222673416137695,
+      "learning_rate": 9.99578443444032e-06,
+      "loss": 0.3956,
+      "step": 247
+    },
+    {
+      "epoch": 1.1221719457013575,
+      "grad_norm": 0.41782158613204956,
+      "learning_rate": 9.995453974215164e-06,
+      "loss": 0.3423,
+      "step": 248
+    },
+    {
+      "epoch": 1.1266968325791855,
+      "grad_norm": 0.6398916244506836,
+      "learning_rate": 9.995111051493468e-06,
+      "loss": 0.3975,
+      "step": 249
+    },
+    {
+      "epoch": 1.1312217194570136,
+      "grad_norm": 0.5231488943099976,
+      "learning_rate": 9.99475566713074e-06,
+      "loss": 0.4051,
+      "step": 250
+    },
+    {
+      "epoch": 1.1357466063348416,
+      "grad_norm": 0.48015347123146057,
+      "learning_rate": 9.994387822013586e-06,
+      "loss": 0.4183,
+      "step": 251
+    },
+    {
+      "epoch": 1.1402714932126696,
+      "grad_norm": 0.44875526428222656,
+      "learning_rate": 9.994007517059693e-06,
+      "loss": 0.37,
+      "step": 252
+    },
+    {
+      "epoch": 1.1447963800904977,
+      "grad_norm": 0.6783897876739502,
+      "learning_rate": 9.993614753217833e-06,
+      "loss": 0.4063,
+      "step": 253
+    },
+    {
+      "epoch": 1.1493212669683257,
+      "grad_norm": 0.5309958457946777,
+      "learning_rate": 9.99320953146786e-06,
+      "loss": 0.3896,
+      "step": 254
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 0.5052987933158875,
+      "learning_rate": 9.992791852820709e-06,
+      "loss": 0.4243,
+      "step": 255
+    },
+    {
+      "epoch": 1.1583710407239818,
+      "grad_norm": 0.47427037358283997,
+      "learning_rate": 9.992361718318393e-06,
+      "loss": 0.3601,
+      "step": 256
+    },
+    {
+      "epoch": 1.16289592760181,
+      "grad_norm": 0.4682779312133789,
+      "learning_rate": 9.991919129033994e-06,
+      "loss": 0.3564,
+      "step": 257
+    },
+    {
+      "epoch": 1.167420814479638,
+      "grad_norm": 0.5049699544906616,
+      "learning_rate": 9.991464086071669e-06,
+      "loss": 0.3362,
+      "step": 258
+    },
+    {
+      "epoch": 1.1719457013574661,
+      "grad_norm": 0.43032440543174744,
+      "learning_rate": 9.990996590566648e-06,
+      "loss": 0.3884,
+      "step": 259
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.48647770285606384,
+      "learning_rate": 9.990516643685222e-06,
+      "loss": 0.3797,
+      "step": 260
+    },
+    {
+      "epoch": 1.1809954751131222,
+      "grad_norm": 0.6087546944618225,
+      "learning_rate": 9.990024246624745e-06,
+      "loss": 0.4037,
+      "step": 261
+    },
+    {
+      "epoch": 1.1855203619909502,
+      "grad_norm": 0.4716806709766388,
+      "learning_rate": 9.989519400613636e-06,
+      "loss": 0.4145,
+      "step": 262
+    },
+    {
+      "epoch": 1.1900452488687783,
+      "grad_norm": 0.47347491979599,
+      "learning_rate": 9.989002106911368e-06,
+      "loss": 0.3781,
+      "step": 263
+    },
+    {
+      "epoch": 1.1945701357466063,
+      "grad_norm": 0.6511465907096863,
+      "learning_rate": 9.988472366808468e-06,
+      "loss": 0.4168,
+      "step": 264
+    },
+    {
+      "epoch": 1.1990950226244343,
+      "grad_norm": 0.4355635941028595,
+      "learning_rate": 9.987930181626515e-06,
+      "loss": 0.3703,
+      "step": 265
+    },
+    {
+      "epoch": 1.2036199095022624,
+      "grad_norm": 0.4431900382041931,
+      "learning_rate": 9.987375552718133e-06,
+      "loss": 0.4355,
+      "step": 266
+    },
+    {
+      "epoch": 1.2081447963800904,
+      "grad_norm": 0.4137621223926544,
+      "learning_rate": 9.986808481466994e-06,
+      "loss": 0.3837,
+      "step": 267
+    },
+    {
+      "epoch": 1.2126696832579185,
+      "grad_norm": 0.49528124928474426,
+      "learning_rate": 9.98622896928781e-06,
+      "loss": 0.3732,
+      "step": 268
+    },
+    {
+      "epoch": 1.2171945701357467,
+      "grad_norm": 0.45777904987335205,
+      "learning_rate": 9.985637017626326e-06,
+      "loss": 0.4144,
+      "step": 269
+    },
+    {
+      "epoch": 1.2217194570135748,
+      "grad_norm": 0.5112358331680298,
+      "learning_rate": 9.985032627959325e-06,
+      "loss": 0.4616,
+      "step": 270
+    },
+    {
+      "epoch": 1.2262443438914028,
+      "grad_norm": 0.5006369948387146,
+      "learning_rate": 9.984415801794622e-06,
+      "loss": 0.4317,
+      "step": 271
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.48134738206863403,
+      "learning_rate": 9.983786540671052e-06,
+      "loss": 0.3928,
+      "step": 272
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 0.4563564956188202,
+      "learning_rate": 9.983144846158472e-06,
+      "loss": 0.3907,
+      "step": 273
+    },
+    {
+      "epoch": 1.239819004524887,
+      "grad_norm": 0.43982940912246704,
+      "learning_rate": 9.982490719857766e-06,
+      "loss": 0.41,
+      "step": 274
+    },
+    {
+      "epoch": 1.244343891402715,
+      "grad_norm": 0.4124949872493744,
+      "learning_rate": 9.981824163400827e-06,
+      "loss": 0.3775,
+      "step": 275
+    },
+    {
+      "epoch": 1.248868778280543,
+      "grad_norm": 0.44366535544395447,
+      "learning_rate": 9.981145178450555e-06,
+      "loss": 0.3958,
+      "step": 276
+    },
+    {
+      "epoch": 1.253393665158371,
+      "grad_norm": 0.4540594220161438,
+      "learning_rate": 9.980453766700861e-06,
+      "loss": 0.4276,
+      "step": 277
+    },
+    {
+      "epoch": 1.257918552036199,
+      "grad_norm": 0.4591408967971802,
+      "learning_rate": 9.979749929876658e-06,
+      "loss": 0.3899,
+      "step": 278
+    },
+    {
+      "epoch": 1.262443438914027,
+      "grad_norm": 0.4709743857383728,
+      "learning_rate": 9.979033669733855e-06,
+      "loss": 0.4155,
+      "step": 279
+    },
+    {
+      "epoch": 1.2669683257918551,
+      "grad_norm": 0.5153703689575195,
+      "learning_rate": 9.978304988059352e-06,
+      "loss": 0.355,
+      "step": 280
+    },
+    {
+      "epoch": 1.2714932126696832,
+      "grad_norm": 0.5748324990272522,
+      "learning_rate": 9.977563886671043e-06,
+      "loss": 0.3903,
+      "step": 281
+    },
+    {
+      "epoch": 1.2760180995475112,
+      "grad_norm": 0.42208483815193176,
+      "learning_rate": 9.976810367417801e-06,
+      "loss": 0.3711,
+      "step": 282
+    },
+    {
+      "epoch": 1.2805429864253393,
+      "grad_norm": 0.4175834059715271,
+      "learning_rate": 9.976044432179486e-06,
+      "loss": 0.3714,
+      "step": 283
+    },
+    {
+      "epoch": 1.2850678733031673,
+      "grad_norm": 0.48363685607910156,
+      "learning_rate": 9.975266082866923e-06,
+      "loss": 0.359,
+      "step": 284
+    },
+    {
+      "epoch": 1.2895927601809956,
+      "grad_norm": 0.4426751732826233,
+      "learning_rate": 9.974475321421918e-06,
+      "loss": 0.3497,
+      "step": 285
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 0.49176037311553955,
+      "learning_rate": 9.973672149817232e-06,
+      "loss": 0.4077,
+      "step": 286
+    },
+    {
+      "epoch": 1.2986425339366516,
+      "grad_norm": 0.47568652033805847,
+      "learning_rate": 9.972856570056594e-06,
+      "loss": 0.3892,
+      "step": 287
+    },
+    {
+      "epoch": 1.3031674208144797,
+      "grad_norm": 0.484466552734375,
+      "learning_rate": 9.972028584174687e-06,
+      "loss": 0.4417,
+      "step": 288
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "grad_norm": 0.41258934140205383,
+      "learning_rate": 9.971188194237141e-06,
+      "loss": 0.3803,
+      "step": 289
+    },
+    {
+      "epoch": 1.3122171945701357,
+      "grad_norm": 0.463830828666687,
+      "learning_rate": 9.970335402340534e-06,
+      "loss": 0.4389,
+      "step": 290
+    },
+    {
+      "epoch": 1.3167420814479638,
+      "grad_norm": 0.425300270318985,
+      "learning_rate": 9.969470210612384e-06,
+      "loss": 0.4108,
+      "step": 291
+    },
+    {
+      "epoch": 1.3212669683257918,
+      "grad_norm": 0.5346444249153137,
+      "learning_rate": 9.968592621211146e-06,
+      "loss": 0.3969,
+      "step": 292
+    },
+    {
+      "epoch": 1.3257918552036199,
+      "grad_norm": 0.4658094644546509,
+      "learning_rate": 9.967702636326195e-06,
+      "loss": 0.4434,
+      "step": 293
+    },
+    {
+      "epoch": 1.330316742081448,
+      "grad_norm": 0.48898160457611084,
+      "learning_rate": 9.966800258177842e-06,
+      "loss": 0.4164,
+      "step": 294
+    },
+    {
+      "epoch": 1.334841628959276,
+      "grad_norm": 0.5616970062255859,
+      "learning_rate": 9.96588548901731e-06,
+      "loss": 0.4472,
+      "step": 295
+    },
+    {
+      "epoch": 1.3393665158371042,
+      "grad_norm": 0.43943265080451965,
+      "learning_rate": 9.964958331126735e-06,
+      "loss": 0.4284,
+      "step": 296
+    },
+    {
+      "epoch": 1.3438914027149322,
+      "grad_norm": 0.5051960945129395,
+      "learning_rate": 9.964018786819158e-06,
+      "loss": 0.3999,
+      "step": 297
+    },
+    {
+      "epoch": 1.3484162895927603,
+      "grad_norm": 0.5062891840934753,
+      "learning_rate": 9.963066858438525e-06,
+      "loss": 0.4063,
+      "step": 298
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 0.5116050243377686,
+      "learning_rate": 9.96210254835968e-06,
+      "loss": 0.3752,
+      "step": 299
+    },
+    {
+      "epoch": 1.3574660633484164,
+      "grad_norm": 0.4431830048561096,
+      "learning_rate": 9.961125858988348e-06,
+      "loss": 0.3763,
+      "step": 300
+    },
+    {
+      "epoch": 1.3619909502262444,
+      "grad_norm": 0.4586993455886841,
+      "learning_rate": 9.96013679276114e-06,
+      "loss": 0.3983,
+      "step": 301
+    },
+    {
+      "epoch": 1.3665158371040724,
+      "grad_norm": 0.4054921567440033,
+      "learning_rate": 9.959135352145552e-06,
+      "loss": 0.3679,
+      "step": 302
+    },
+    {
+      "epoch": 1.3710407239819005,
+      "grad_norm": 0.4635688066482544,
+      "learning_rate": 9.958121539639945e-06,
+      "loss": 0.3835,
+      "step": 303
+    },
+    {
+      "epoch": 1.3755656108597285,
+      "grad_norm": 0.4249536395072937,
+      "learning_rate": 9.95709535777354e-06,
+      "loss": 0.3947,
+      "step": 304
+    },
+    {
+      "epoch": 1.3800904977375565,
+      "grad_norm": 0.43373027443885803,
+      "learning_rate": 9.956056809106426e-06,
+      "loss": 0.3603,
+      "step": 305
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.45955413579940796,
+      "learning_rate": 9.955005896229543e-06,
+      "loss": 0.3909,
+      "step": 306
+    },
+    {
+      "epoch": 1.3891402714932126,
+      "grad_norm": 0.44556981325149536,
+      "learning_rate": 9.95394262176467e-06,
+      "loss": 0.3668,
+      "step": 307
+    },
+    {
+      "epoch": 1.3936651583710407,
+      "grad_norm": 0.4461539685726166,
+      "learning_rate": 9.952866988364431e-06,
+      "loss": 0.3902,
+      "step": 308
+    },
+    {
+      "epoch": 1.3981900452488687,
+      "grad_norm": 0.4445544481277466,
+      "learning_rate": 9.951778998712282e-06,
+      "loss": 0.407,
+      "step": 309
+    },
+    {
+      "epoch": 1.4027149321266967,
+      "grad_norm": 0.40608200430870056,
+      "learning_rate": 9.950678655522505e-06,
+      "loss": 0.3472,
+      "step": 310
+    },
+    {
+      "epoch": 1.4072398190045248,
+      "grad_norm": 0.4478733241558075,
+      "learning_rate": 9.9495659615402e-06,
+      "loss": 0.4088,
+      "step": 311
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.5241243243217468,
+      "learning_rate": 9.948440919541277e-06,
+      "loss": 0.3937,
+      "step": 312
+    },
+    {
+      "epoch": 1.416289592760181,
+      "grad_norm": 0.44417575001716614,
+      "learning_rate": 9.947303532332457e-06,
+      "loss": 0.3508,
+      "step": 313
+    },
+    {
+      "epoch": 1.420814479638009,
+      "grad_norm": 0.46424350142478943,
+      "learning_rate": 9.946153802751257e-06,
+      "loss": 0.4189,
+      "step": 314
+    },
+    {
+      "epoch": 1.4253393665158371,
+      "grad_norm": 0.41135942935943604,
+      "learning_rate": 9.944991733665986e-06,
+      "loss": 0.3924,
+      "step": 315
+    },
+    {
+      "epoch": 1.4298642533936652,
+      "grad_norm": 0.4415293037891388,
+      "learning_rate": 9.943817327975732e-06,
+      "loss": 0.3657,
+      "step": 316
+    },
+    {
+      "epoch": 1.4343891402714932,
+      "grad_norm": 0.40911784768104553,
+      "learning_rate": 9.942630588610368e-06,
+      "loss": 0.383,
+      "step": 317
+    },
+    {
+      "epoch": 1.4389140271493213,
+      "grad_norm": 0.43340831995010376,
+      "learning_rate": 9.94143151853053e-06,
+      "loss": 0.3657,
+      "step": 318
+    },
+    {
+      "epoch": 1.4434389140271493,
+      "grad_norm": 0.46907198429107666,
+      "learning_rate": 9.940220120727624e-06,
+      "loss": 0.4239,
+      "step": 319
+    },
+    {
+      "epoch": 1.4479638009049773,
+      "grad_norm": 0.4872211813926697,
+      "learning_rate": 9.938996398223802e-06,
+      "loss": 0.4008,
+      "step": 320
+    },
+    {
+      "epoch": 1.4524886877828054,
+      "grad_norm": 0.46110352873802185,
+      "learning_rate": 9.937760354071966e-06,
+      "loss": 0.3792,
+      "step": 321
+    },
+    {
+      "epoch": 1.4570135746606334,
+      "grad_norm": 0.46933513879776,
+      "learning_rate": 9.936511991355764e-06,
+      "loss": 0.3626,
+      "step": 322
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.47610121965408325,
+      "learning_rate": 9.935251313189564e-06,
+      "loss": 0.4133,
+      "step": 323
+    },
+    {
+      "epoch": 1.4660633484162897,
+      "grad_norm": 0.4467121660709381,
+      "learning_rate": 9.933978322718472e-06,
+      "loss": 0.4247,
+      "step": 324
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.4571016728878021,
+      "learning_rate": 9.932693023118299e-06,
+      "loss": 0.4107,
+      "step": 325
+    },
+    {
+      "epoch": 1.4751131221719458,
+      "grad_norm": 0.533100962638855,
+      "learning_rate": 9.931395417595568e-06,
+      "loss": 0.4091,
+      "step": 326
+    },
+    {
+      "epoch": 1.4796380090497738,
+      "grad_norm": 0.4366355538368225,
+      "learning_rate": 9.930085509387509e-06,
+      "loss": 0.3467,
+      "step": 327
+    },
+    {
+      "epoch": 1.4841628959276019,
+      "grad_norm": 0.41149038076400757,
+      "learning_rate": 9.92876330176203e-06,
+      "loss": 0.387,
+      "step": 328
+    },
+    {
+      "epoch": 1.48868778280543,
+      "grad_norm": 0.4341404438018799,
+      "learning_rate": 9.927428798017738e-06,
+      "loss": 0.4285,
+      "step": 329
+    },
+    {
+      "epoch": 1.493212669683258,
+      "grad_norm": 0.46218249201774597,
+      "learning_rate": 9.926082001483909e-06,
+      "loss": 0.4224,
+      "step": 330
+    },
+    {
+      "epoch": 1.497737556561086,
+      "grad_norm": 0.42733314633369446,
+      "learning_rate": 9.924722915520484e-06,
+      "loss": 0.375,
+      "step": 331
+    },
+    {
+      "epoch": 1.502262443438914,
+      "grad_norm": 0.4854833781719208,
+      "learning_rate": 9.92335154351807e-06,
+      "loss": 0.4287,
+      "step": 332
+    },
+    {
+      "epoch": 1.506787330316742,
+      "grad_norm": 0.4013662040233612,
+      "learning_rate": 9.92196788889792e-06,
+      "loss": 0.3262,
+      "step": 333
+    },
+    {
+      "epoch": 1.51131221719457,
+      "grad_norm": 0.4636831283569336,
+      "learning_rate": 9.92057195511193e-06,
+      "loss": 0.4486,
+      "step": 334
+    },
+    {
+      "epoch": 1.5158371040723981,
+      "grad_norm": 0.3883086144924164,
+      "learning_rate": 9.919163745642633e-06,
+      "loss": 0.3536,
+      "step": 335
+    },
+    {
+      "epoch": 1.5203619909502262,
+      "grad_norm": 0.47283634543418884,
+      "learning_rate": 9.91774326400318e-06,
+      "loss": 0.3475,
+      "step": 336
+    },
+    {
+      "epoch": 1.5248868778280542,
+      "grad_norm": 0.5383743047714233,
+      "learning_rate": 9.916310513737345e-06,
+      "loss": 0.5013,
+      "step": 337
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 0.4297215938568115,
+      "learning_rate": 9.91486549841951e-06,
+      "loss": 0.3726,
+      "step": 338
+    },
+    {
+      "epoch": 1.5339366515837103,
+      "grad_norm": 0.5066801905632019,
+      "learning_rate": 9.913408221654647e-06,
+      "loss": 0.3823,
+      "step": 339
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.4163861870765686,
+      "learning_rate": 9.911938687078324e-06,
+      "loss": 0.3728,
+      "step": 340
+    },
+    {
+      "epoch": 1.5429864253393664,
+      "grad_norm": 0.46085265278816223,
+      "learning_rate": 9.91045689835669e-06,
+      "loss": 0.3822,
+      "step": 341
+    },
+    {
+      "epoch": 1.5475113122171946,
+      "grad_norm": 0.4126754105091095,
+      "learning_rate": 9.908962859186465e-06,
+      "loss": 0.3634,
+      "step": 342
+    },
+    {
+      "epoch": 1.5520361990950227,
+      "grad_norm": 0.4993842542171478,
+      "learning_rate": 9.907456573294924e-06,
+      "loss": 0.3835,
+      "step": 343
+    },
+    {
+      "epoch": 1.5565610859728507,
+      "grad_norm": 0.4884220063686371,
+      "learning_rate": 9.905938044439904e-06,
+      "loss": 0.436,
+      "step": 344
+    },
+    {
+      "epoch": 1.5610859728506787,
+      "grad_norm": 0.3982529044151306,
+      "learning_rate": 9.90440727640978e-06,
+      "loss": 0.389,
+      "step": 345
+    },
+    {
+      "epoch": 1.5656108597285068,
+      "grad_norm": 0.4887678921222687,
+      "learning_rate": 9.902864273023465e-06,
+      "loss": 0.344,
+      "step": 346
+    },
+    {
+      "epoch": 1.5701357466063348,
+      "grad_norm": 0.4793776869773865,
+      "learning_rate": 9.901309038130392e-06,
+      "loss": 0.4078,
+      "step": 347
+    },
+    {
+      "epoch": 1.5746606334841629,
+      "grad_norm": 0.44910818338394165,
+      "learning_rate": 9.89974157561051e-06,
+      "loss": 0.3894,
+      "step": 348
+    },
+    {
+      "epoch": 1.5791855203619911,
+      "grad_norm": 0.45025259256362915,
+      "learning_rate": 9.898161889374272e-06,
+      "loss": 0.4182,
+      "step": 349
+    },
+    {
+      "epoch": 1.5837104072398192,
+      "grad_norm": 0.45233941078186035,
+      "learning_rate": 9.896569983362632e-06,
+      "loss": 0.3846,
+      "step": 350
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 0.4646618664264679,
+      "learning_rate": 9.894965861547023e-06,
+      "loss": 0.364,
+      "step": 351
+    },
+    {
+      "epoch": 1.5927601809954752,
+      "grad_norm": 0.44090190529823303,
+      "learning_rate": 9.893349527929357e-06,
+      "loss": 0.3949,
+      "step": 352
+    },
+    {
+      "epoch": 1.5972850678733033,
+      "grad_norm": 0.5286484360694885,
+      "learning_rate": 9.891720986542011e-06,
+      "loss": 0.4311,
+      "step": 353
+    },
+    {
+      "epoch": 1.6018099547511313,
+      "grad_norm": 0.44429534673690796,
+      "learning_rate": 9.890080241447816e-06,
+      "loss": 0.3906,
+      "step": 354
+    },
+    {
+      "epoch": 1.6063348416289593,
+      "grad_norm": 0.5068367123603821,
+      "learning_rate": 9.888427296740054e-06,
+      "loss": 0.4052,
+      "step": 355
+    },
+    {
+      "epoch": 1.6108597285067874,
+      "grad_norm": 0.507785975933075,
+      "learning_rate": 9.886762156542428e-06,
+      "loss": 0.4063,
+      "step": 356
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "grad_norm": 0.49715733528137207,
+      "learning_rate": 9.885084825009085e-06,
+      "loss": 0.3965,
+      "step": 357
+    },
+    {
+      "epoch": 1.6199095022624435,
+      "grad_norm": 0.4482433497905731,
+      "learning_rate": 9.883395306324575e-06,
+      "loss": 0.4066,
+      "step": 358
+    },
+    {
+      "epoch": 1.6244343891402715,
+      "grad_norm": 0.41335636377334595,
+      "learning_rate": 9.881693604703853e-06,
+      "loss": 0.3674,
+      "step": 359
+    },
+    {
+      "epoch": 1.6289592760180995,
+      "grad_norm": 0.5023950934410095,
+      "learning_rate": 9.87997972439227e-06,
+      "loss": 0.3444,
+      "step": 360
+    },
+    {
+      "epoch": 1.6334841628959276,
+      "grad_norm": 0.5373045802116394,
+      "learning_rate": 9.878253669665557e-06,
+      "loss": 0.3853,
+      "step": 361
+    },
+    {
+      "epoch": 1.6380090497737556,
+      "grad_norm": 0.4574486315250397,
+      "learning_rate": 9.876515444829822e-06,
+      "loss": 0.4254,
+      "step": 362
+    },
+    {
+      "epoch": 1.6425339366515836,
+      "grad_norm": 0.5090571045875549,
+      "learning_rate": 9.874765054221532e-06,
+      "loss": 0.391,
+      "step": 363
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.4528499245643616,
+      "learning_rate": 9.873002502207502e-06,
+      "loss": 0.4292,
+      "step": 364
+    },
+    {
+      "epoch": 1.6515837104072397,
+      "grad_norm": 0.4229438304901123,
+      "learning_rate": 9.871227793184893e-06,
+      "loss": 0.3829,
+      "step": 365
+    },
+    {
+      "epoch": 1.6561085972850678,
+      "grad_norm": 0.4995672404766083,
+      "learning_rate": 9.869440931581186e-06,
+      "loss": 0.3534,
+      "step": 366
+    },
+    {
+      "epoch": 1.6606334841628958,
+      "grad_norm": 0.527503490447998,
+      "learning_rate": 9.867641921854192e-06,
+      "loss": 0.4057,
+      "step": 367
+    },
+    {
+      "epoch": 1.6651583710407238,
+      "grad_norm": 0.4658501446247101,
+      "learning_rate": 9.865830768492019e-06,
+      "loss": 0.4088,
+      "step": 368
+    },
+    {
+      "epoch": 1.6696832579185519,
+      "grad_norm": 0.5441451668739319,
+      "learning_rate": 9.864007476013075e-06,
+      "loss": 0.4149,
+      "step": 369
+    },
+    {
+      "epoch": 1.6742081447963801,
+      "grad_norm": 0.48692771792411804,
+      "learning_rate": 9.862172048966048e-06,
+      "loss": 0.3818,
+      "step": 370
+    },
+    {
+      "epoch": 1.6787330316742082,
+      "grad_norm": 0.40074610710144043,
+      "learning_rate": 9.860324491929905e-06,
+      "loss": 0.3657,
+      "step": 371
+    },
+    {
+      "epoch": 1.6832579185520362,
+      "grad_norm": 0.4921663999557495,
+      "learning_rate": 9.858464809513867e-06,
+      "loss": 0.4022,
+      "step": 372
+    },
+    {
+      "epoch": 1.6877828054298643,
+      "grad_norm": 0.46872252225875854,
+      "learning_rate": 9.856593006357415e-06,
+      "loss": 0.4099,
+      "step": 373
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.5141183137893677,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.3961,
+      "step": 374
+    },
+    {
+      "epoch": 1.6968325791855203,
+      "grad_norm": 0.46619221568107605,
+      "learning_rate": 9.852813056532345e-06,
+      "loss": 0.3172,
+      "step": 375
+    },
+    {
+      "epoch": 1.7013574660633484,
+      "grad_norm": 0.5484828352928162,
+      "learning_rate": 9.85090491929382e-06,
+      "loss": 0.4182,
+      "step": 376
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.5394891500473022,
+      "learning_rate": 9.848984680175049e-06,
+      "loss": 0.3898,
+      "step": 377
+    },
+    {
+      "epoch": 1.7104072398190047,
+      "grad_norm": 0.48792046308517456,
+      "learning_rate": 9.84705234396658e-06,
+      "loss": 0.3373,
+      "step": 378
+    },
+    {
+      "epoch": 1.7149321266968327,
+      "grad_norm": 0.3987761437892914,
+      "learning_rate": 9.845107915489143e-06,
+      "loss": 0.334,
+      "step": 379
+    },
+    {
+      "epoch": 1.7194570135746607,
+      "grad_norm": 0.525193452835083,
+      "learning_rate": 9.843151399593636e-06,
+      "loss": 0.3718,
+      "step": 380
+    },
+    {
+      "epoch": 1.7239819004524888,
+      "grad_norm": 0.48990345001220703,
+      "learning_rate": 9.84118280116111e-06,
+      "loss": 0.3763,
+      "step": 381
+    },
+    {
+      "epoch": 1.7285067873303168,
+      "grad_norm": 0.4889325797557831,
+      "learning_rate": 9.839202125102761e-06,
+      "loss": 0.3785,
+      "step": 382
+    },
+    {
+      "epoch": 1.7330316742081449,
+      "grad_norm": 0.5154342651367188,
+      "learning_rate": 9.837209376359918e-06,
+      "loss": 0.3883,
+      "step": 383
+    },
+    {
+      "epoch": 1.737556561085973,
+      "grad_norm": 0.5224171280860901,
+      "learning_rate": 9.835204559904021e-06,
+      "loss": 0.3666,
+      "step": 384
+    },
+    {
+      "epoch": 1.742081447963801,
+      "grad_norm": 0.5012906193733215,
+      "learning_rate": 9.833187680736624e-06,
+      "loss": 0.4093,
+      "step": 385
+    },
+    {
+      "epoch": 1.746606334841629,
+      "grad_norm": 0.5155039429664612,
+      "learning_rate": 9.831158743889373e-06,
+      "loss": 0.3768,
+      "step": 386
+    },
+    {
+      "epoch": 1.751131221719457,
+      "grad_norm": 0.44377192854881287,
+      "learning_rate": 9.829117754423991e-06,
+      "loss": 0.4136,
+      "step": 387
+    },
+    {
+      "epoch": 1.755656108597285,
+      "grad_norm": 0.6181144714355469,
+      "learning_rate": 9.827064717432272e-06,
+      "loss": 0.4698,
+      "step": 388
+    },
+    {
+      "epoch": 1.760180995475113,
+      "grad_norm": 0.5261528491973877,
+      "learning_rate": 9.82499963803607e-06,
+      "loss": 0.3924,
+      "step": 389
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.43123725056648254,
+      "learning_rate": 9.822922521387277e-06,
+      "loss": 0.4207,
+      "step": 390
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "grad_norm": 0.4998953342437744,
+      "learning_rate": 9.820833372667813e-06,
+      "loss": 0.3933,
+      "step": 391
+    },
+    {
+      "epoch": 1.7737556561085972,
+      "grad_norm": 0.5654891133308411,
+      "learning_rate": 9.81873219708962e-06,
+      "loss": 0.3732,
+      "step": 392
+    },
+    {
+      "epoch": 1.7782805429864252,
+      "grad_norm": 0.4899405539035797,
+      "learning_rate": 9.816618999894645e-06,
+      "loss": 0.3752,
+      "step": 393
+    },
+    {
+      "epoch": 1.7828054298642533,
+      "grad_norm": 0.5240674614906311,
+      "learning_rate": 9.81449378635482e-06,
+      "loss": 0.4596,
+      "step": 394
+    },
+    {
+      "epoch": 1.7873303167420813,
+      "grad_norm": 0.46099403500556946,
+      "learning_rate": 9.81235656177206e-06,
+      "loss": 0.3748,
+      "step": 395
+    },
+    {
+      "epoch": 1.7918552036199094,
+      "grad_norm": 0.46495547890663147,
+      "learning_rate": 9.810207331478247e-06,
+      "loss": 0.4091,
+      "step": 396
+    },
+    {
+      "epoch": 1.7963800904977374,
+      "grad_norm": 0.5413225293159485,
+      "learning_rate": 9.808046100835207e-06,
+      "loss": 0.3903,
+      "step": 397
+    },
+    {
+      "epoch": 1.8009049773755657,
+      "grad_norm": 0.5968965888023376,
+      "learning_rate": 9.80587287523471e-06,
+      "loss": 0.3925,
+      "step": 398
+    },
+    {
+      "epoch": 1.8054298642533937,
+      "grad_norm": 0.46063658595085144,
+      "learning_rate": 9.803687660098446e-06,
+      "loss": 0.4055,
+      "step": 399
+    },
+    {
+      "epoch": 1.8099547511312217,
+      "grad_norm": 0.4856792390346527,
+      "learning_rate": 9.801490460878023e-06,
+      "loss": 0.3594,
+      "step": 400
+    },
+    {
+      "epoch": 1.8144796380090498,
+      "grad_norm": 0.4093053638935089,
+      "learning_rate": 9.79928128305494e-06,
+      "loss": 0.353,
+      "step": 401
+    },
+    {
+      "epoch": 1.8190045248868778,
+      "grad_norm": 0.5286359786987305,
+      "learning_rate": 9.797060132140584e-06,
+      "loss": 0.3798,
+      "step": 402
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 0.49250075221061707,
+      "learning_rate": 9.794827013676206e-06,
+      "loss": 0.412,
+      "step": 403
+    },
+    {
+      "epoch": 1.8280542986425339,
+      "grad_norm": 0.43814513087272644,
+      "learning_rate": 9.792581933232924e-06,
+      "loss": 0.386,
+      "step": 404
+    },
+    {
+      "epoch": 1.8325791855203621,
+      "grad_norm": 0.4019566774368286,
+      "learning_rate": 9.790324896411684e-06,
+      "loss": 0.3668,
+      "step": 405
+    },
+    {
+      "epoch": 1.8371040723981902,
+      "grad_norm": 0.44960689544677734,
+      "learning_rate": 9.788055908843275e-06,
+      "loss": 0.3761,
+      "step": 406
+    },
+    {
+      "epoch": 1.8416289592760182,
+      "grad_norm": 0.40887507796287537,
+      "learning_rate": 9.78577497618829e-06,
+      "loss": 0.3824,
+      "step": 407
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.5183314085006714,
+      "learning_rate": 9.783482104137127e-06,
+      "loss": 0.3466,
+      "step": 408
+    },
+    {
+      "epoch": 1.8506787330316743,
+      "grad_norm": 0.4178057312965393,
+      "learning_rate": 9.781177298409969e-06,
+      "loss": 0.3428,
+      "step": 409
+    },
+    {
+      "epoch": 1.8552036199095023,
+      "grad_norm": 0.45295459032058716,
+      "learning_rate": 9.778860564756769e-06,
+      "loss": 0.3886,
+      "step": 410
+    },
+    {
+      "epoch": 1.8597285067873304,
+      "grad_norm": 0.5001879334449768,
+      "learning_rate": 9.776531908957241e-06,
+      "loss": 0.4219,
+      "step": 411
+    },
+    {
+      "epoch": 1.8642533936651584,
+      "grad_norm": 0.47920331358909607,
+      "learning_rate": 9.77419133682084e-06,
+      "loss": 0.4203,
+      "step": 412
+    },
+    {
+      "epoch": 1.8687782805429864,
+      "grad_norm": 0.48827502131462097,
+      "learning_rate": 9.771838854186748e-06,
+      "loss": 0.4053,
+      "step": 413
+    },
+    {
+      "epoch": 1.8733031674208145,
+      "grad_norm": 0.42105311155319214,
+      "learning_rate": 9.769474466923864e-06,
+      "loss": 0.3749,
+      "step": 414
+    },
+    {
+      "epoch": 1.8778280542986425,
+      "grad_norm": 0.41811907291412354,
+      "learning_rate": 9.76709818093078e-06,
+      "loss": 0.3489,
+      "step": 415
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.42248275876045227,
+      "learning_rate": 9.764710002135784e-06,
+      "loss": 0.4341,
+      "step": 416
+    },
+    {
+      "epoch": 1.8868778280542986,
+      "grad_norm": 0.4599759578704834,
+      "learning_rate": 9.762309936496824e-06,
+      "loss": 0.3931,
+      "step": 417
+    },
+    {
+      "epoch": 1.8914027149321266,
+      "grad_norm": 0.47709447145462036,
+      "learning_rate": 9.759897990001504e-06,
+      "loss": 0.3697,
+      "step": 418
+    },
+    {
+      "epoch": 1.8959276018099547,
+      "grad_norm": 0.44299864768981934,
+      "learning_rate": 9.757474168667072e-06,
+      "loss": 0.4235,
+      "step": 419
+    },
+    {
+      "epoch": 1.9004524886877827,
+      "grad_norm": 0.45147445797920227,
+      "learning_rate": 9.7550384785404e-06,
+      "loss": 0.3915,
+      "step": 420
+    },
+    {
+      "epoch": 1.9049773755656108,
+      "grad_norm": 0.4743190109729767,
+      "learning_rate": 9.752590925697964e-06,
+      "loss": 0.4003,
+      "step": 421
+    },
+    {
+      "epoch": 1.9095022624434388,
+      "grad_norm": 0.515183687210083,
+      "learning_rate": 9.750131516245844e-06,
+      "loss": 0.4147,
+      "step": 422
+    },
+    {
+      "epoch": 1.9140271493212668,
+      "grad_norm": 0.4393065273761749,
+      "learning_rate": 9.747660256319695e-06,
+      "loss": 0.4065,
+      "step": 423
+    },
+    {
+      "epoch": 1.9185520361990949,
+      "grad_norm": 0.4030460715293884,
+      "learning_rate": 9.745177152084733e-06,
+      "loss": 0.3824,
+      "step": 424
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.47524887323379517,
+      "learning_rate": 9.742682209735727e-06,
+      "loss": 0.4089,
+      "step": 425
+    },
+    {
+      "epoch": 1.9276018099547512,
+      "grad_norm": 0.4686073660850525,
+      "learning_rate": 9.74017543549698e-06,
+      "loss": 0.3935,
+      "step": 426
+    },
+    {
+      "epoch": 1.9321266968325792,
+      "grad_norm": 0.3981013894081116,
+      "learning_rate": 9.737656835622312e-06,
+      "loss": 0.3755,
+      "step": 427
+    },
+    {
+      "epoch": 1.9366515837104072,
+      "grad_norm": 0.46402475237846375,
+      "learning_rate": 9.73512641639504e-06,
+      "loss": 0.3673,
+      "step": 428
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.502984881401062,
+      "learning_rate": 9.732584184127973e-06,
+      "loss": 0.3981,
+      "step": 429
+    },
+    {
+      "epoch": 1.9457013574660633,
+      "grad_norm": 0.42585644125938416,
+      "learning_rate": 9.730030145163392e-06,
+      "loss": 0.4047,
+      "step": 430
+    },
+    {
+      "epoch": 1.9502262443438914,
+      "grad_norm": 0.39187467098236084,
+      "learning_rate": 9.72746430587303e-06,
+      "loss": 0.391,
+      "step": 431
+    },
+    {
+      "epoch": 1.9547511312217196,
+      "grad_norm": 0.3843924105167389,
+      "learning_rate": 9.724886672658056e-06,
+      "loss": 0.4038,
+      "step": 432
+    },
+    {
+      "epoch": 1.9592760180995477,
+      "grad_norm": 0.47524020075798035,
+      "learning_rate": 9.72229725194907e-06,
+      "loss": 0.4075,
+      "step": 433
+    },
+    {
+      "epoch": 1.9638009049773757,
+      "grad_norm": 0.46401557326316833,
+      "learning_rate": 9.719696050206072e-06,
+      "loss": 0.3564,
+      "step": 434
+    },
+    {
+      "epoch": 1.9683257918552037,
+      "grad_norm": 0.4504929482936859,
+      "learning_rate": 9.717083073918459e-06,
+      "loss": 0.401,
+      "step": 435
+    },
+    {
+      "epoch": 1.9728506787330318,
+      "grad_norm": 0.4272751212120056,
+      "learning_rate": 9.714458329604997e-06,
+      "loss": 0.4096,
+      "step": 436
+    },
+    {
+      "epoch": 1.9773755656108598,
+      "grad_norm": 0.4029974341392517,
+      "learning_rate": 9.711821823813812e-06,
+      "loss": 0.4362,
+      "step": 437
+    },
+    {
+      "epoch": 1.9819004524886878,
+      "grad_norm": 0.4730750322341919,
+      "learning_rate": 9.709173563122377e-06,
+      "loss": 0.3892,
+      "step": 438
+    },
+    {
+      "epoch": 1.9864253393665159,
+      "grad_norm": 0.4282892644405365,
+      "learning_rate": 9.706513554137482e-06,
+      "loss": 0.4198,
+      "step": 439
+    },
+    {
+      "epoch": 1.990950226244344,
+      "grad_norm": 0.4743562340736389,
+      "learning_rate": 9.703841803495234e-06,
+      "loss": 0.4141,
+      "step": 440
+    },
+    {
+      "epoch": 1.995475113122172,
+      "grad_norm": 0.4112869203090668,
+      "learning_rate": 9.701158317861031e-06,
+      "loss": 0.3836,
+      "step": 441
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.41886061429977417,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.3317,
+      "step": 442
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2210,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 442,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 90814059528192.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3043921de5ed0b9eee1ff8eb6ce6ddc9116b2cac0d219cd3f349af26a1ec10ae
+size 7672