Upload folder using huggingface_hub

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

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc8c146d474d7d98eec0071445bedeac8d9c45a697faa6d617d16720e6b0c15
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4a0dd5557f91ccc799fc03f1e1e12c90684fa91240a051b0ff939c70414034
+size 3855679144

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 8822848512
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2274 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.817204301075268,
+  "eval_steps": 500,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.030721966205837174,
+      "grad_norm": 5.377892017364502,
+      "learning_rate": 1.6460905349794242e-07,
+      "loss": 0.6829,
+      "step": 5
+    },
+    {
+      "epoch": 0.06144393241167435,
+      "grad_norm": 4.802157878875732,
+      "learning_rate": 3.7037037037037036e-07,
+      "loss": 0.6782,
+      "step": 10
+    },
+    {
+      "epoch": 0.09216589861751152,
+      "grad_norm": 4.367337226867676,
+      "learning_rate": 5.761316872427984e-07,
+      "loss": 0.6663,
+      "step": 15
+    },
+    {
+      "epoch": 0.1228878648233487,
+      "grad_norm": 3.747973918914795,
+      "learning_rate": 7.818930041152265e-07,
+      "loss": 0.655,
+      "step": 20
+    },
+    {
+      "epoch": 0.15360983102918588,
+      "grad_norm": 2.209118127822876,
+      "learning_rate": 9.876543209876544e-07,
+      "loss": 0.6173,
+      "step": 25
+    },
+    {
+      "epoch": 0.18433179723502305,
+      "grad_norm": 1.1678818464279175,
+      "learning_rate": 1.1934156378600823e-06,
+      "loss": 0.6048,
+      "step": 30
+    },
+    {
+      "epoch": 0.21505376344086022,
+      "grad_norm": 0.8436072468757629,
+      "learning_rate": 1.3991769547325104e-06,
+      "loss": 0.5856,
+      "step": 35
+    },
+    {
+      "epoch": 0.2457757296466974,
+      "grad_norm": 0.9035472273826599,
+      "learning_rate": 1.6049382716049383e-06,
+      "loss": 0.5731,
+      "step": 40
+    },
+    {
+      "epoch": 0.2764976958525346,
+      "grad_norm": 0.6879045963287354,
+      "learning_rate": 1.8106995884773665e-06,
+      "loss": 0.5672,
+      "step": 45
+    },
+    {
+      "epoch": 0.30721966205837176,
+      "grad_norm": 0.5572217106819153,
+      "learning_rate": 2.0164609053497946e-06,
+      "loss": 0.5652,
+      "step": 50
+    },
+    {
+      "epoch": 0.3379416282642089,
+      "grad_norm": 0.475868821144104,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.5569,
+      "step": 55
+    },
+    {
+      "epoch": 0.3686635944700461,
+      "grad_norm": 0.4037950932979584,
+      "learning_rate": 2.4279835390946504e-06,
+      "loss": 0.552,
+      "step": 60
+    },
+    {
+      "epoch": 0.39938556067588327,
+      "grad_norm": 0.3646543323993683,
+      "learning_rate": 2.6337448559670788e-06,
+      "loss": 0.5486,
+      "step": 65
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 0.3199547231197357,
+      "learning_rate": 2.8395061728395062e-06,
+      "loss": 0.548,
+      "step": 70
+    },
+    {
+      "epoch": 0.4608294930875576,
+      "grad_norm": 0.29529860615730286,
+      "learning_rate": 3.0452674897119346e-06,
+      "loss": 0.5412,
+      "step": 75
+    },
+    {
+      "epoch": 0.4915514592933948,
+      "grad_norm": 0.2877354025840759,
+      "learning_rate": 3.2510288065843625e-06,
+      "loss": 0.5384,
+      "step": 80
+    },
+    {
+      "epoch": 0.522273425499232,
+      "grad_norm": 0.27960506081581116,
+      "learning_rate": 3.4567901234567904e-06,
+      "loss": 0.5408,
+      "step": 85
+    },
+    {
+      "epoch": 0.5529953917050692,
+      "grad_norm": 0.3203478455543518,
+      "learning_rate": 3.6625514403292183e-06,
+      "loss": 0.5385,
+      "step": 90
+    },
+    {
+      "epoch": 0.5837173579109063,
+      "grad_norm": 0.293573260307312,
+      "learning_rate": 3.868312757201647e-06,
+      "loss": 0.5367,
+      "step": 95
+    },
+    {
+      "epoch": 0.6144393241167435,
+      "grad_norm": 0.2991442084312439,
+      "learning_rate": 4.074074074074074e-06,
+      "loss": 0.5318,
+      "step": 100
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.28697723150253296,
+      "learning_rate": 4.2798353909465025e-06,
+      "loss": 0.5325,
+      "step": 105
+    },
+    {
+      "epoch": 0.6758832565284179,
+      "grad_norm": 0.29979708790779114,
+      "learning_rate": 4.485596707818931e-06,
+      "loss": 0.5329,
+      "step": 110
+    },
+    {
+      "epoch": 0.706605222734255,
+      "grad_norm": 0.28516969084739685,
+      "learning_rate": 4.691358024691358e-06,
+      "loss": 0.5303,
+      "step": 115
+    },
+    {
+      "epoch": 0.7373271889400922,
+      "grad_norm": 0.2979312837123871,
+      "learning_rate": 4.897119341563787e-06,
+      "loss": 0.532,
+      "step": 120
+    },
+    {
+      "epoch": 0.7680491551459293,
+      "grad_norm": 0.29658472537994385,
+      "learning_rate": 5.102880658436214e-06,
+      "loss": 0.5361,
+      "step": 125
+    },
+    {
+      "epoch": 0.7987711213517665,
+      "grad_norm": 0.3170669972896576,
+      "learning_rate": 5.3086419753086425e-06,
+      "loss": 0.5307,
+      "step": 130
+    },
+    {
+      "epoch": 0.8294930875576036,
+      "grad_norm": 0.3079938590526581,
+      "learning_rate": 5.514403292181071e-06,
+      "loss": 0.5277,
+      "step": 135
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 0.33612361550331116,
+      "learning_rate": 5.720164609053498e-06,
+      "loss": 0.5298,
+      "step": 140
+    },
+    {
+      "epoch": 0.890937019969278,
+      "grad_norm": 0.3119032382965088,
+      "learning_rate": 5.925925925925926e-06,
+      "loss": 0.5248,
+      "step": 145
+    },
+    {
+      "epoch": 0.9216589861751152,
+      "grad_norm": 0.33814293146133423,
+      "learning_rate": 6.131687242798354e-06,
+      "loss": 0.5284,
+      "step": 150
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.322230726480484,
+      "learning_rate": 6.3374485596707825e-06,
+      "loss": 0.5281,
+      "step": 155
+    },
+    {
+      "epoch": 0.9831029185867896,
+      "grad_norm": 0.3144535720348358,
+      "learning_rate": 6.543209876543211e-06,
+      "loss": 0.5242,
+      "step": 160
+    },
+    {
+      "epoch": 1.012288786482335,
+      "grad_norm": 0.29515042901039124,
+      "learning_rate": 6.748971193415639e-06,
+      "loss": 0.5163,
+      "step": 165
+    },
+    {
+      "epoch": 1.043010752688172,
+      "grad_norm": 0.3272690176963806,
+      "learning_rate": 6.954732510288067e-06,
+      "loss": 0.5168,
+      "step": 170
+    },
+    {
+      "epoch": 1.0737327188940091,
+      "grad_norm": 0.38112202286720276,
+      "learning_rate": 7.160493827160494e-06,
+      "loss": 0.5175,
+      "step": 175
+    },
+    {
+      "epoch": 1.1044546850998465,
+      "grad_norm": 0.3627144992351532,
+      "learning_rate": 7.3662551440329225e-06,
+      "loss": 0.5146,
+      "step": 180
+    },
+    {
+      "epoch": 1.1351766513056836,
+      "grad_norm": 0.34759828448295593,
+      "learning_rate": 7.57201646090535e-06,
+      "loss": 0.5091,
+      "step": 185
+    },
+    {
+      "epoch": 1.1658986175115207,
+      "grad_norm": 0.32023346424102783,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.5154,
+      "step": 190
+    },
+    {
+      "epoch": 1.1966205837173578,
+      "grad_norm": 0.34595441818237305,
+      "learning_rate": 7.983539094650207e-06,
+      "loss": 0.514,
+      "step": 195
+    },
+    {
+      "epoch": 1.2273425499231951,
+      "grad_norm": 0.35786375403404236,
+      "learning_rate": 8.189300411522634e-06,
+      "loss": 0.515,
+      "step": 200
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "grad_norm": 0.3521522283554077,
+      "learning_rate": 8.395061728395062e-06,
+      "loss": 0.5096,
+      "step": 205
+    },
+    {
+      "epoch": 1.2887864823348694,
+      "grad_norm": 0.3382728397846222,
+      "learning_rate": 8.60082304526749e-06,
+      "loss": 0.5092,
+      "step": 210
+    },
+    {
+      "epoch": 1.3195084485407067,
+      "grad_norm": 0.3584599494934082,
+      "learning_rate": 8.806584362139918e-06,
+      "loss": 0.5088,
+      "step": 215
+    },
+    {
+      "epoch": 1.3502304147465438,
+      "grad_norm": 0.3886154294013977,
+      "learning_rate": 9.012345679012346e-06,
+      "loss": 0.5103,
+      "step": 220
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 0.35392460227012634,
+      "learning_rate": 9.218106995884775e-06,
+      "loss": 0.5122,
+      "step": 225
+    },
+    {
+      "epoch": 1.411674347158218,
+      "grad_norm": 0.3449483811855316,
+      "learning_rate": 9.423868312757202e-06,
+      "loss": 0.5101,
+      "step": 230
+    },
+    {
+      "epoch": 1.4423963133640554,
+      "grad_norm": 0.40504640340805054,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 0.5079,
+      "step": 235
+    },
+    {
+      "epoch": 1.4731182795698925,
+      "grad_norm": 0.3839814066886902,
+      "learning_rate": 9.835390946502057e-06,
+      "loss": 0.5075,
+      "step": 240
+    },
+    {
+      "epoch": 1.5038402457757296,
+      "grad_norm": 0.3998360335826874,
+      "learning_rate": 9.999994841278135e-06,
+      "loss": 0.5117,
+      "step": 245
+    },
+    {
+      "epoch": 1.5345622119815667,
+      "grad_norm": 0.3241407573223114,
+      "learning_rate": 9.99981428713058e-06,
+      "loss": 0.5116,
+      "step": 250
+    },
+    {
+      "epoch": 1.565284178187404,
+      "grad_norm": 0.3408064544200897,
+      "learning_rate": 9.999375807534642e-06,
+      "loss": 0.5086,
+      "step": 255
+    },
+    {
+      "epoch": 1.5960061443932412,
+      "grad_norm": 0.3956799805164337,
+      "learning_rate": 9.998679425110168e-06,
+      "loss": 0.5057,
+      "step": 260
+    },
+    {
+      "epoch": 1.6267281105990783,
+      "grad_norm": 0.34674304723739624,
+      "learning_rate": 9.997725175781445e-06,
+      "loss": 0.5042,
+      "step": 265
+    },
+    {
+      "epoch": 1.6574500768049156,
+      "grad_norm": 0.33803871273994446,
+      "learning_rate": 9.996513108775338e-06,
+      "loss": 0.5094,
+      "step": 270
+    },
+    {
+      "epoch": 1.6881720430107527,
+      "grad_norm": 0.3286557197570801,
+      "learning_rate": 9.995043286618752e-06,
+      "loss": 0.5082,
+      "step": 275
+    },
+    {
+      "epoch": 1.7188940092165899,
+      "grad_norm": 0.4859721064567566,
+      "learning_rate": 9.993315785135417e-06,
+      "loss": 0.5062,
+      "step": 280
+    },
+    {
+      "epoch": 1.7496159754224272,
+      "grad_norm": 0.39187705516815186,
+      "learning_rate": 9.991330693441956e-06,
+      "loss": 0.5004,
+      "step": 285
+    },
+    {
+      "epoch": 1.780337941628264,
+      "grad_norm": 0.3706142008304596,
+      "learning_rate": 9.989088113943309e-06,
+      "loss": 0.5074,
+      "step": 290
+    },
+    {
+      "epoch": 1.8110599078341014,
+      "grad_norm": 0.36376601457595825,
+      "learning_rate": 9.986588162327436e-06,
+      "loss": 0.5043,
+      "step": 295
+    },
+    {
+      "epoch": 1.8417818740399385,
+      "grad_norm": 0.3372829854488373,
+      "learning_rate": 9.983830967559355e-06,
+      "loss": 0.505,
+      "step": 300
+    },
+    {
+      "epoch": 1.8725038402457757,
+      "grad_norm": 0.3605220913887024,
+      "learning_rate": 9.98081667187449e-06,
+      "loss": 0.506,
+      "step": 305
+    },
+    {
+      "epoch": 1.903225806451613,
+      "grad_norm": 0.37473252415657043,
+      "learning_rate": 9.977545430771332e-06,
+      "loss": 0.5065,
+      "step": 310
+    },
+    {
+      "epoch": 1.93394777265745,
+      "grad_norm": 0.3622889816761017,
+      "learning_rate": 9.974017413003407e-06,
+      "loss": 0.5049,
+      "step": 315
+    },
+    {
+      "epoch": 1.9646697388632872,
+      "grad_norm": 0.36003556847572327,
+      "learning_rate": 9.970232800570594e-06,
+      "loss": 0.5042,
+      "step": 320
+    },
+    {
+      "epoch": 1.9953917050691246,
+      "grad_norm": 0.35878923535346985,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 0.498,
+      "step": 325
+    },
+    {
+      "epoch": 2.02457757296467,
+      "grad_norm": 0.3277081847190857,
+      "learning_rate": 9.961894585884472e-06,
+      "loss": 0.4833,
+      "step": 330
+    },
+    {
+      "epoch": 2.055299539170507,
+      "grad_norm": 0.35245636105537415,
+      "learning_rate": 9.957341413774693e-06,
+      "loss": 0.4823,
+      "step": 335
+    },
+    {
+      "epoch": 2.086021505376344,
+      "grad_norm": 0.3628138601779938,
+      "learning_rate": 9.952532507264892e-06,
+      "loss": 0.4789,
+      "step": 340
+    },
+    {
+      "epoch": 2.1167434715821813,
+      "grad_norm": 0.36662936210632324,
+      "learning_rate": 9.947468114432156e-06,
+      "loss": 0.4876,
+      "step": 345
+    },
+    {
+      "epoch": 2.1474654377880182,
+      "grad_norm": 0.3806234896183014,
+      "learning_rate": 9.942148496533348e-06,
+      "loss": 0.4797,
+      "step": 350
+    },
+    {
+      "epoch": 2.1781874039938556,
+      "grad_norm": 0.3836243152618408,
+      "learning_rate": 9.936573927991631e-06,
+      "loss": 0.4823,
+      "step": 355
+    },
+    {
+      "epoch": 2.208909370199693,
+      "grad_norm": 0.3716926872730255,
+      "learning_rate": 9.930744696382298e-06,
+      "loss": 0.4846,
+      "step": 360
+    },
+    {
+      "epoch": 2.23963133640553,
+      "grad_norm": 0.3589572608470917,
+      "learning_rate": 9.924661102417959e-06,
+      "loss": 0.4794,
+      "step": 365
+    },
+    {
+      "epoch": 2.270353302611367,
+      "grad_norm": 0.44799497723579407,
+      "learning_rate": 9.918323459933006e-06,
+      "loss": 0.4849,
+      "step": 370
+    },
+    {
+      "epoch": 2.3010752688172045,
+      "grad_norm": 0.35237064957618713,
+      "learning_rate": 9.911732095867443e-06,
+      "loss": 0.4819,
+      "step": 375
+    },
+    {
+      "epoch": 2.3317972350230414,
+      "grad_norm": 0.3844442665576935,
+      "learning_rate": 9.904887350250002e-06,
+      "loss": 0.4828,
+      "step": 380
+    },
+    {
+      "epoch": 2.3625192012288787,
+      "grad_norm": 0.34357205033302307,
+      "learning_rate": 9.897789576180617e-06,
+      "loss": 0.4795,
+      "step": 385
+    },
+    {
+      "epoch": 2.3932411674347156,
+      "grad_norm": 0.34739232063293457,
+      "learning_rate": 9.8904391398122e-06,
+      "loss": 0.4817,
+      "step": 390
+    },
+    {
+      "epoch": 2.423963133640553,
+      "grad_norm": 0.3262459337711334,
+      "learning_rate": 9.882836420331753e-06,
+      "loss": 0.4807,
+      "step": 395
+    },
+    {
+      "epoch": 2.4546850998463903,
+      "grad_norm": 0.32715994119644165,
+      "learning_rate": 9.87498180994081e-06,
+      "loss": 0.4825,
+      "step": 400
+    },
+    {
+      "epoch": 2.485407066052227,
+      "grad_norm": 0.3524874150753021,
+      "learning_rate": 9.8668757138352e-06,
+      "loss": 0.4832,
+      "step": 405
+    },
+    {
+      "epoch": 2.5161290322580645,
+      "grad_norm": 0.3556855618953705,
+      "learning_rate": 9.858518550184154e-06,
+      "loss": 0.4784,
+      "step": 410
+    },
+    {
+      "epoch": 2.546850998463902,
+      "grad_norm": 0.350763201713562,
+      "learning_rate": 9.849910750108718e-06,
+      "loss": 0.4796,
+      "step": 415
+    },
+    {
+      "epoch": 2.5775729646697387,
+      "grad_norm": 0.40554359555244446,
+      "learning_rate": 9.841052757659525e-06,
+      "loss": 0.4795,
+      "step": 420
+    },
+    {
+      "epoch": 2.608294930875576,
+      "grad_norm": 0.38155123591423035,
+      "learning_rate": 9.831945029793884e-06,
+      "loss": 0.4824,
+      "step": 425
+    },
+    {
+      "epoch": 2.6390168970814134,
+      "grad_norm": 0.34588319063186646,
+      "learning_rate": 9.822588036352201e-06,
+      "loss": 0.4812,
+      "step": 430
+    },
+    {
+      "epoch": 2.6697388632872503,
+      "grad_norm": 0.3738536536693573,
+      "learning_rate": 9.812982260033753e-06,
+      "loss": 0.4776,
+      "step": 435
+    },
+    {
+      "epoch": 2.7004608294930876,
+      "grad_norm": 0.34988853335380554,
+      "learning_rate": 9.803128196371778e-06,
+      "loss": 0.4827,
+      "step": 440
+    },
+    {
+      "epoch": 2.731182795698925,
+      "grad_norm": 0.3567947447299957,
+      "learning_rate": 9.793026353707915e-06,
+      "loss": 0.4824,
+      "step": 445
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.3680736720561981,
+      "learning_rate": 9.782677253165979e-06,
+      "loss": 0.4817,
+      "step": 450
+    },
+    {
+      "epoch": 2.792626728110599,
+      "grad_norm": 0.3302510380744934,
+      "learning_rate": 9.77208142862508e-06,
+      "loss": 0.4799,
+      "step": 455
+    },
+    {
+      "epoch": 2.823348694316436,
+      "grad_norm": 0.3362921178340912,
+      "learning_rate": 9.761239426692077e-06,
+      "loss": 0.4792,
+      "step": 460
+    },
+    {
+      "epoch": 2.8540706605222734,
+      "grad_norm": 0.3084135949611664,
+      "learning_rate": 9.750151806673389e-06,
+      "loss": 0.4798,
+      "step": 465
+    },
+    {
+      "epoch": 2.8847926267281108,
+      "grad_norm": 0.3991258442401886,
+      "learning_rate": 9.738819140546135e-06,
+      "loss": 0.4776,
+      "step": 470
+    },
+    {
+      "epoch": 2.9155145929339477,
+      "grad_norm": 0.3840397298336029,
+      "learning_rate": 9.727242012928622e-06,
+      "loss": 0.4827,
+      "step": 475
+    },
+    {
+      "epoch": 2.946236559139785,
+      "grad_norm": 0.3366018235683441,
+      "learning_rate": 9.715421021050205e-06,
+      "loss": 0.478,
+      "step": 480
+    },
+    {
+      "epoch": 2.976958525345622,
+      "grad_norm": 0.3289054036140442,
+      "learning_rate": 9.703356774720454e-06,
+      "loss": 0.4806,
+      "step": 485
+    },
+    {
+      "epoch": 3.0061443932411676,
+      "grad_norm": 0.41949138045310974,
+      "learning_rate": 9.69104989629772e-06,
+      "loss": 0.474,
+      "step": 490
+    },
+    {
+      "epoch": 3.0368663594470044,
+      "grad_norm": 0.3739219605922699,
+      "learning_rate": 9.678501020657008e-06,
+      "loss": 0.4555,
+      "step": 495
+    },
+    {
+      "epoch": 3.067588325652842,
+      "grad_norm": 0.3918289244174957,
+      "learning_rate": 9.665710795157236e-06,
+      "loss": 0.4559,
+      "step": 500
+    },
+    {
+      "epoch": 3.098310291858679,
+      "grad_norm": 0.37078753113746643,
+      "learning_rate": 9.652679879607843e-06,
+      "loss": 0.4523,
+      "step": 505
+    },
+    {
+      "epoch": 3.129032258064516,
+      "grad_norm": 0.39428192377090454,
+      "learning_rate": 9.639408946234745e-06,
+      "loss": 0.455,
+      "step": 510
+    },
+    {
+      "epoch": 3.1597542242703534,
+      "grad_norm": 0.36103686690330505,
+      "learning_rate": 9.625898679645656e-06,
+      "loss": 0.4539,
+      "step": 515
+    },
+    {
+      "epoch": 3.1904761904761907,
+      "grad_norm": 0.3871241807937622,
+      "learning_rate": 9.612149776794776e-06,
+      "loss": 0.4585,
+      "step": 520
+    },
+    {
+      "epoch": 3.2211981566820276,
+      "grad_norm": 0.3608538508415222,
+      "learning_rate": 9.59816294694684e-06,
+      "loss": 0.4545,
+      "step": 525
+    },
+    {
+      "epoch": 3.251920122887865,
+      "grad_norm": 0.33820873498916626,
+      "learning_rate": 9.583938911640513e-06,
+      "loss": 0.4581,
+      "step": 530
+    },
+    {
+      "epoch": 3.282642089093702,
+      "grad_norm": 0.3311152160167694,
+      "learning_rate": 9.569478404651192e-06,
+      "loss": 0.4572,
+      "step": 535
+    },
+    {
+      "epoch": 3.313364055299539,
+      "grad_norm": 0.3974754512310028,
+      "learning_rate": 9.55478217195313e-06,
+      "loss": 0.4579,
+      "step": 540
+    },
+    {
+      "epoch": 3.3440860215053765,
+      "grad_norm": 0.36764049530029297,
+      "learning_rate": 9.53985097168097e-06,
+      "loss": 0.4548,
+      "step": 545
+    },
+    {
+      "epoch": 3.3748079877112134,
+      "grad_norm": 0.3310830295085907,
+      "learning_rate": 9.524685574090627e-06,
+      "loss": 0.4596,
+      "step": 550
+    },
+    {
+      "epoch": 3.4055299539170507,
+      "grad_norm": 0.35807356238365173,
+      "learning_rate": 9.50928676151955e-06,
+      "loss": 0.4561,
+      "step": 555
+    },
+    {
+      "epoch": 3.436251920122888,
+      "grad_norm": 0.3509482741355896,
+      "learning_rate": 9.493655328346378e-06,
+      "loss": 0.4601,
+      "step": 560
+    },
+    {
+      "epoch": 3.466973886328725,
+      "grad_norm": 0.32899123430252075,
+      "learning_rate": 9.477792080949938e-06,
+      "loss": 0.458,
+      "step": 565
+    },
+    {
+      "epoch": 3.4976958525345623,
+      "grad_norm": 0.3493783473968506,
+      "learning_rate": 9.461697837667668e-06,
+      "loss": 0.4578,
+      "step": 570
+    },
+    {
+      "epoch": 3.528417818740399,
+      "grad_norm": 0.42410966753959656,
+      "learning_rate": 9.445373428753386e-06,
+      "loss": 0.457,
+      "step": 575
+    },
+    {
+      "epoch": 3.5591397849462365,
+      "grad_norm": 0.39236894249916077,
+      "learning_rate": 9.42881969633447e-06,
+      "loss": 0.4621,
+      "step": 580
+    },
+    {
+      "epoch": 3.589861751152074,
+      "grad_norm": 0.3428690433502197,
+      "learning_rate": 9.412037494368412e-06,
+      "loss": 0.4613,
+      "step": 585
+    },
+    {
+      "epoch": 3.6205837173579107,
+      "grad_norm": 0.3500923216342926,
+      "learning_rate": 9.395027688598756e-06,
+      "loss": 0.4553,
+      "step": 590
+    },
+    {
+      "epoch": 3.651305683563748,
+      "grad_norm": 0.3521360456943512,
+      "learning_rate": 9.377791156510456e-06,
+      "loss": 0.4609,
+      "step": 595
+    },
+    {
+      "epoch": 3.6820276497695854,
+      "grad_norm": 0.3520371615886688,
+      "learning_rate": 9.360328787284587e-06,
+      "loss": 0.4561,
+      "step": 600
+    },
+    {
+      "epoch": 3.7127496159754223,
+      "grad_norm": 0.37317851185798645,
+      "learning_rate": 9.342641481752492e-06,
+      "loss": 0.4543,
+      "step": 605
+    },
+    {
+      "epoch": 3.7434715821812596,
+      "grad_norm": 0.3881990313529968,
+      "learning_rate": 9.324730152349305e-06,
+      "loss": 0.4573,
+      "step": 610
+    },
+    {
+      "epoch": 3.774193548387097,
+      "grad_norm": 0.34541720151901245,
+      "learning_rate": 9.306595723066878e-06,
+      "loss": 0.4588,
+      "step": 615
+    },
+    {
+      "epoch": 3.804915514592934,
+      "grad_norm": 0.6174806356430054,
+      "learning_rate": 9.28823912940612e-06,
+      "loss": 0.4615,
+      "step": 620
+    },
+    {
+      "epoch": 3.835637480798771,
+      "grad_norm": 0.37580618262290955,
+      "learning_rate": 9.26966131832873e-06,
+      "loss": 0.4603,
+      "step": 625
+    },
+    {
+      "epoch": 3.8663594470046085,
+      "grad_norm": 0.3373568058013916,
+      "learning_rate": 9.250863248208357e-06,
+      "loss": 0.4575,
+      "step": 630
+    },
+    {
+      "epoch": 3.8970814132104454,
+      "grad_norm": 0.3492389917373657,
+      "learning_rate": 9.231845888781153e-06,
+      "loss": 0.457,
+      "step": 635
+    },
+    {
+      "epoch": 3.9278033794162828,
+      "grad_norm": 0.353481262922287,
+      "learning_rate": 9.212610221095748e-06,
+      "loss": 0.4593,
+      "step": 640
+    },
+    {
+      "epoch": 3.9585253456221197,
+      "grad_norm": 0.339603066444397,
+      "learning_rate": 9.193157237462642e-06,
+      "loss": 0.4583,
+      "step": 645
+    },
+    {
+      "epoch": 3.989247311827957,
+      "grad_norm": 0.35986068844795227,
+      "learning_rate": 9.173487941403011e-06,
+      "loss": 0.4575,
+      "step": 650
+    },
+    {
+      "epoch": 4.018433179723503,
+      "grad_norm": 0.39629873633384705,
+      "learning_rate": 9.153603347596946e-06,
+      "loss": 0.4437,
+      "step": 655
+    },
+    {
+      "epoch": 4.04915514592934,
+      "grad_norm": 0.38085299730300903,
+      "learning_rate": 9.133504481831103e-06,
+      "loss": 0.4315,
+      "step": 660
+    },
+    {
+      "epoch": 4.0798771121351765,
+      "grad_norm": 0.375144898891449,
+      "learning_rate": 9.113192380945783e-06,
+      "loss": 0.4332,
+      "step": 665
+    },
+    {
+      "epoch": 4.110599078341014,
+      "grad_norm": 0.3690689206123352,
+      "learning_rate": 9.092668092781454e-06,
+      "loss": 0.4286,
+      "step": 670
+    },
+    {
+      "epoch": 4.141321044546851,
+      "grad_norm": 0.3713686764240265,
+      "learning_rate": 9.071932676124686e-06,
+      "loss": 0.4321,
+      "step": 675
+    },
+    {
+      "epoch": 4.172043010752688,
+      "grad_norm": 0.37255361676216125,
+      "learning_rate": 9.050987200653538e-06,
+      "loss": 0.4308,
+      "step": 680
+    },
+    {
+      "epoch": 4.202764976958525,
+      "grad_norm": 0.4153440296649933,
+      "learning_rate": 9.029832746882372e-06,
+      "loss": 0.434,
+      "step": 685
+    },
+    {
+      "epoch": 4.233486943164363,
+      "grad_norm": 0.3848015367984772,
+      "learning_rate": 9.008470406106118e-06,
+      "loss": 0.4321,
+      "step": 690
+    },
+    {
+      "epoch": 4.2642089093702,
+      "grad_norm": 0.38491949439048767,
+      "learning_rate": 8.986901280343973e-06,
+      "loss": 0.437,
+      "step": 695
+    },
+    {
+      "epoch": 4.2949308755760365,
+      "grad_norm": 0.40272125601768494,
+      "learning_rate": 8.96512648228255e-06,
+      "loss": 0.4327,
+      "step": 700
+    },
+    {
+      "epoch": 4.325652841781874,
+      "grad_norm": 0.40901532769203186,
+      "learning_rate": 8.943147135218482e-06,
+      "loss": 0.4355,
+      "step": 705
+    },
+    {
+      "epoch": 4.356374807987711,
+      "grad_norm": 0.37816864252090454,
+      "learning_rate": 8.920964373000474e-06,
+      "loss": 0.4309,
+      "step": 710
+    },
+    {
+      "epoch": 4.387096774193548,
+      "grad_norm": 0.3686360716819763,
+      "learning_rate": 8.898579339970806e-06,
+      "loss": 0.4333,
+      "step": 715
+    },
+    {
+      "epoch": 4.417818740399386,
+      "grad_norm": 0.3904341161251068,
+      "learning_rate": 8.875993190906309e-06,
+      "loss": 0.436,
+      "step": 720
+    },
+    {
+      "epoch": 4.448540706605223,
+      "grad_norm": 0.369642049074173,
+      "learning_rate": 8.85320709095878e-06,
+      "loss": 0.4393,
+      "step": 725
+    },
+    {
+      "epoch": 4.47926267281106,
+      "grad_norm": 0.39105841517448425,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.4335,
+      "step": 730
+    },
+    {
+      "epoch": 4.509984639016897,
+      "grad_norm": 0.35647451877593994,
+      "learning_rate": 8.80703975053554e-06,
+      "loss": 0.4365,
+      "step": 735
+    },
+    {
+      "epoch": 4.540706605222734,
+      "grad_norm": 0.37886905670166016,
+      "learning_rate": 8.783660891694683e-06,
+      "loss": 0.4358,
+      "step": 740
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.33613675832748413,
+      "learning_rate": 8.760086845117648e-06,
+      "loss": 0.4339,
+      "step": 745
+    },
+    {
+      "epoch": 4.602150537634409,
+      "grad_norm": 0.3609409034252167,
+      "learning_rate": 8.736318826918909e-06,
+      "loss": 0.4367,
+      "step": 750
+    },
+    {
+      "epoch": 4.632872503840246,
+      "grad_norm": 0.3324005603790283,
+      "learning_rate": 8.71235806321936e-06,
+      "loss": 0.4368,
+      "step": 755
+    },
+    {
+      "epoch": 4.663594470046083,
+      "grad_norm": 0.34170496463775635,
+      "learning_rate": 8.688205790083053e-06,
+      "loss": 0.4364,
+      "step": 760
+    },
+    {
+      "epoch": 4.6943164362519205,
+      "grad_norm": 0.3765306770801544,
+      "learning_rate": 8.663863253453444e-06,
+      "loss": 0.4381,
+      "step": 765
+    },
+    {
+      "epoch": 4.725038402457757,
+      "grad_norm": 0.3638916611671448,
+      "learning_rate": 8.639331709089107e-06,
+      "loss": 0.438,
+      "step": 770
+    },
+    {
+      "epoch": 4.755760368663594,
+      "grad_norm": 0.3378274738788605,
+      "learning_rate": 8.614612422498965e-06,
+      "loss": 0.4396,
+      "step": 775
+    },
+    {
+      "epoch": 4.786482334869431,
+      "grad_norm": 0.3760294020175934,
+      "learning_rate": 8.589706668876995e-06,
+      "loss": 0.4387,
+      "step": 780
+    },
+    {
+      "epoch": 4.817204301075269,
+      "grad_norm": 0.3364088535308838,
+      "learning_rate": 8.564615733036457e-06,
+      "loss": 0.4388,
+      "step": 785
+    },
+    {
+      "epoch": 4.847926267281106,
+      "grad_norm": 0.3584051728248596,
+      "learning_rate": 8.539340909343597e-06,
+      "loss": 0.4355,
+      "step": 790
+    },
+    {
+      "epoch": 4.878648233486944,
+      "grad_norm": 0.3589382469654083,
+      "learning_rate": 8.513883501650892e-06,
+      "loss": 0.4393,
+      "step": 795
+    },
+    {
+      "epoch": 4.9093701996927805,
+      "grad_norm": 0.362913578748703,
+      "learning_rate": 8.488244823229781e-06,
+      "loss": 0.4391,
+      "step": 800
+    },
+    {
+      "epoch": 4.940092165898617,
+      "grad_norm": 0.38569971919059753,
+      "learning_rate": 8.462426196702912e-06,
+      "loss": 0.44,
+      "step": 805
+    },
+    {
+      "epoch": 4.970814132104454,
+      "grad_norm": 0.7799672484397888,
+      "learning_rate": 8.436428953975921e-06,
+      "loss": 0.4402,
+      "step": 810
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.35950392484664917,
+      "learning_rate": 8.41025443616872e-06,
+      "loss": 0.4385,
+      "step": 815
+    },
+    {
+      "epoch": 5.030721966205837,
+      "grad_norm": 0.434950053691864,
+      "learning_rate": 8.38390399354631e-06,
+      "loss": 0.4124,
+      "step": 820
+    },
+    {
+      "epoch": 5.061443932411675,
+      "grad_norm": 0.38890355825424194,
+      "learning_rate": 8.357378985449124e-06,
+      "loss": 0.4077,
+      "step": 825
+    },
+    {
+      "epoch": 5.092165898617512,
+      "grad_norm": 0.3747502267360687,
+      "learning_rate": 8.330680780222907e-06,
+      "loss": 0.4116,
+      "step": 830
+    },
+    {
+      "epoch": 5.1228878648233485,
+      "grad_norm": 0.4041999578475952,
+      "learning_rate": 8.303810755148127e-06,
+      "loss": 0.4125,
+      "step": 835
+    },
+    {
+      "epoch": 5.153609831029186,
+      "grad_norm": 0.8506478667259216,
+      "learning_rate": 8.276770296368922e-06,
+      "loss": 0.4086,
+      "step": 840
+    },
+    {
+      "epoch": 5.184331797235023,
+      "grad_norm": 0.43535116314888,
+      "learning_rate": 8.249560798821592e-06,
+      "loss": 0.4118,
+      "step": 845
+    },
+    {
+      "epoch": 5.21505376344086,
+      "grad_norm": 0.4166457951068878,
+      "learning_rate": 8.222183666162647e-06,
+      "loss": 0.41,
+      "step": 850
+    },
+    {
+      "epoch": 5.245775729646698,
+      "grad_norm": 0.3790026009082794,
+      "learning_rate": 8.194640310696383e-06,
+      "loss": 0.4131,
+      "step": 855
+    },
+    {
+      "epoch": 5.276497695852535,
+      "grad_norm": 0.4068205654621124,
+      "learning_rate": 8.16693215330204e-06,
+      "loss": 0.4149,
+      "step": 860
+    },
+    {
+      "epoch": 5.307219662058372,
+      "grad_norm": 0.40233853459358215,
+      "learning_rate": 8.139060623360494e-06,
+      "loss": 0.414,
+      "step": 865
+    },
+    {
+      "epoch": 5.337941628264209,
+      "grad_norm": 0.4058436155319214,
+      "learning_rate": 8.111027158680516e-06,
+      "loss": 0.4128,
+      "step": 870
+    },
+    {
+      "epoch": 5.368663594470046,
+      "grad_norm": 0.35581091046333313,
+      "learning_rate": 8.082833205424614e-06,
+      "loss": 0.412,
+      "step": 875
+    },
+    {
+      "epoch": 5.399385560675883,
+      "grad_norm": 0.39174729585647583,
+      "learning_rate": 8.054480218034415e-06,
+      "loss": 0.4127,
+      "step": 880
+    },
+    {
+      "epoch": 5.43010752688172,
+      "grad_norm": 0.4122447371482849,
+      "learning_rate": 8.02596965915564e-06,
+      "loss": 0.4143,
+      "step": 885
+    },
+    {
+      "epoch": 5.460829493087558,
+      "grad_norm": 0.37394076585769653,
+      "learning_rate": 7.997302999562657e-06,
+      "loss": 0.4165,
+      "step": 890
+    },
+    {
+      "epoch": 5.491551459293395,
+      "grad_norm": 0.38974493741989136,
+      "learning_rate": 7.968481718082601e-06,
+      "loss": 0.4158,
+      "step": 895
+    },
+    {
+      "epoch": 5.522273425499232,
+      "grad_norm": 0.3667392134666443,
+      "learning_rate": 7.93950730151908e-06,
+      "loss": 0.4186,
+      "step": 900
+    },
+    {
+      "epoch": 5.552995391705069,
+      "grad_norm": 0.3641802668571472,
+      "learning_rate": 7.910381244575491e-06,
+      "loss": 0.4146,
+      "step": 905
+    },
+    {
+      "epoch": 5.583717357910906,
+      "grad_norm": 0.37418097257614136,
+      "learning_rate": 7.881105049777902e-06,
+      "loss": 0.4146,
+      "step": 910
+    },
+    {
+      "epoch": 5.614439324116743,
+      "grad_norm": 0.3662942051887512,
+      "learning_rate": 7.851680227397541e-06,
+      "loss": 0.4181,
+      "step": 915
+    },
+    {
+      "epoch": 5.645161290322581,
+      "grad_norm": 0.3564474284648895,
+      "learning_rate": 7.82210829537289e-06,
+      "loss": 0.4122,
+      "step": 920
+    },
+    {
+      "epoch": 5.675883256528418,
+      "grad_norm": 0.3735935091972351,
+      "learning_rate": 7.792390779231374e-06,
+      "loss": 0.4152,
+      "step": 925
+    },
+    {
+      "epoch": 5.706605222734255,
+      "grad_norm": 0.3896511197090149,
+      "learning_rate": 7.762529212010675e-06,
+      "loss": 0.4125,
+      "step": 930
+    },
+    {
+      "epoch": 5.7373271889400925,
+      "grad_norm": 0.42632153630256653,
+      "learning_rate": 7.732525134179625e-06,
+      "loss": 0.4138,
+      "step": 935
+    },
+    {
+      "epoch": 5.768049155145929,
+      "grad_norm": 0.3700067698955536,
+      "learning_rate": 7.702380093558766e-06,
+      "loss": 0.4128,
+      "step": 940
+    },
+    {
+      "epoch": 5.798771121351766,
+      "grad_norm": 0.3713553547859192,
+      "learning_rate": 7.672095645240479e-06,
+      "loss": 0.4153,
+      "step": 945
+    },
+    {
+      "epoch": 5.829493087557603,
+      "grad_norm": 0.49530503153800964,
+      "learning_rate": 7.641673351508774e-06,
+      "loss": 0.4159,
+      "step": 950
+    },
+    {
+      "epoch": 5.860215053763441,
+      "grad_norm": 0.3351239562034607,
+      "learning_rate": 7.6111147817586925e-06,
+      "loss": 0.4181,
+      "step": 955
+    },
+    {
+      "epoch": 5.890937019969278,
+      "grad_norm": 0.3583086133003235,
+      "learning_rate": 7.580421512415349e-06,
+      "loss": 0.4148,
+      "step": 960
+    },
+    {
+      "epoch": 5.921658986175116,
+      "grad_norm": 0.3566780388355255,
+      "learning_rate": 7.549595126852605e-06,
+      "loss": 0.4133,
+      "step": 965
+    },
+    {
+      "epoch": 5.9523809523809526,
+      "grad_norm": 0.3630661964416504,
+      "learning_rate": 7.518637215311388e-06,
+      "loss": 0.4151,
+      "step": 970
+    },
+    {
+      "epoch": 5.983102918586789,
+      "grad_norm": 0.35128363966941833,
+      "learning_rate": 7.487549374817662e-06,
+      "loss": 0.4159,
+      "step": 975
+    },
+    {
+      "epoch": 6.012288786482335,
+      "grad_norm": 0.442436158657074,
+      "learning_rate": 7.456333209100032e-06,
+      "loss": 0.4034,
+      "step": 980
+    },
+    {
+      "epoch": 6.043010752688172,
+      "grad_norm": 0.41370487213134766,
+      "learning_rate": 7.424990328507017e-06,
+      "loss": 0.3851,
+      "step": 985
+    },
+    {
+      "epoch": 6.073732718894009,
+      "grad_norm": 0.4333699941635132,
+      "learning_rate": 7.393522349923981e-06,
+      "loss": 0.3869,
+      "step": 990
+    },
+    {
+      "epoch": 6.104454685099847,
+      "grad_norm": 0.4446549415588379,
+      "learning_rate": 7.361930896689713e-06,
+      "loss": 0.3836,
+      "step": 995
+    },
+    {
+      "epoch": 6.135176651305684,
+      "grad_norm": 0.40873849391937256,
+      "learning_rate": 7.330217598512696e-06,
+      "loss": 0.3857,
+      "step": 1000
+    },
+    {
+      "epoch": 6.1658986175115205,
+      "grad_norm": 0.4244365990161896,
+      "learning_rate": 7.2983840913870215e-06,
+      "loss": 0.3863,
+      "step": 1005
+    },
+    {
+      "epoch": 6.196620583717358,
+      "grad_norm": 0.3845650851726532,
+      "learning_rate": 7.266432017508008e-06,
+      "loss": 0.3901,
+      "step": 1010
+    },
+    {
+      "epoch": 6.227342549923195,
+      "grad_norm": 0.39868220686912537,
+      "learning_rate": 7.234363025187474e-06,
+      "loss": 0.3855,
+      "step": 1015
+    },
+    {
+      "epoch": 6.258064516129032,
+      "grad_norm": 0.37892380356788635,
+      "learning_rate": 7.202178768768711e-06,
+      "loss": 0.3928,
+      "step": 1020
+    },
+    {
+      "epoch": 6.28878648233487,
+      "grad_norm": 0.3923156261444092,
+      "learning_rate": 7.169880908541136e-06,
+      "loss": 0.3921,
+      "step": 1025
+    },
+    {
+      "epoch": 6.319508448540707,
+      "grad_norm": 0.39880916476249695,
+      "learning_rate": 7.137471110654656e-06,
+      "loss": 0.3938,
+      "step": 1030
+    },
+    {
+      "epoch": 6.350230414746544,
+      "grad_norm": 0.4066980481147766,
+      "learning_rate": 7.104951047033697e-06,
+      "loss": 0.3906,
+      "step": 1035
+    },
+    {
+      "epoch": 6.380952380952381,
+      "grad_norm": 0.3751300573348999,
+      "learning_rate": 7.0723223952909694e-06,
+      "loss": 0.3909,
+      "step": 1040
+    },
+    {
+      "epoch": 6.411674347158218,
+      "grad_norm": 0.3525156080722809,
+      "learning_rate": 7.039586838640918e-06,
+      "loss": 0.3894,
+      "step": 1045
+    },
+    {
+      "epoch": 6.442396313364055,
+      "grad_norm": 0.36944258213043213,
+      "learning_rate": 7.006746065812895e-06,
+      "loss": 0.3909,
+      "step": 1050
+    },
+    {
+      "epoch": 6.473118279569892,
+      "grad_norm": 0.3836762011051178,
+      "learning_rate": 6.973801770964031e-06,
+      "loss": 0.3896,
+      "step": 1055
+    },
+    {
+      "epoch": 6.50384024577573,
+      "grad_norm": 0.41395968198776245,
+      "learning_rate": 6.940755653591859e-06,
+      "loss": 0.3889,
+      "step": 1060
+    },
+    {
+      "epoch": 6.534562211981567,
+      "grad_norm": 0.42266151309013367,
+      "learning_rate": 6.907609418446623e-06,
+      "loss": 0.3924,
+      "step": 1065
+    },
+    {
+      "epoch": 6.565284178187404,
+      "grad_norm": 0.38352274894714355,
+      "learning_rate": 6.8743647754433485e-06,
+      "loss": 0.3934,
+      "step": 1070
+    },
+    {
+      "epoch": 6.596006144393241,
+      "grad_norm": 0.3761062026023865,
+      "learning_rate": 6.841023439573623e-06,
+      "loss": 0.3915,
+      "step": 1075
+    },
+    {
+      "epoch": 6.626728110599078,
+      "grad_norm": 0.38670945167541504,
+      "learning_rate": 6.807587130817134e-06,
+      "loss": 0.3925,
+      "step": 1080
+    },
+    {
+      "epoch": 6.657450076804915,
+      "grad_norm": 0.36626312136650085,
+      "learning_rate": 6.774057574052932e-06,
+      "loss": 0.3944,
+      "step": 1085
+    },
+    {
+      "epoch": 6.688172043010753,
+      "grad_norm": 0.4045194685459137,
+      "learning_rate": 6.740436498970453e-06,
+      "loss": 0.3955,
+      "step": 1090
+    },
+    {
+      "epoch": 6.71889400921659,
+      "grad_norm": 0.4138599932193756,
+      "learning_rate": 6.706725639980294e-06,
+      "loss": 0.3929,
+      "step": 1095
+    },
+    {
+      "epoch": 6.749615975422427,
+      "grad_norm": 0.39506402611732483,
+      "learning_rate": 6.6729267361247295e-06,
+      "loss": 0.3883,
+      "step": 1100
+    },
+    {
+      "epoch": 6.7803379416282645,
+      "grad_norm": 0.3903568387031555,
+      "learning_rate": 6.639041530988009e-06,
+      "loss": 0.3939,
+      "step": 1105
+    },
+    {
+      "epoch": 6.811059907834101,
+      "grad_norm": 0.3678980767726898,
+      "learning_rate": 6.605071772606404e-06,
+      "loss": 0.394,
+      "step": 1110
+    },
+    {
+      "epoch": 6.841781874039938,
+      "grad_norm": 0.35300132632255554,
+      "learning_rate": 6.571019213378034e-06,
+      "loss": 0.391,
+      "step": 1115
+    },
+    {
+      "epoch": 6.872503840245776,
+      "grad_norm": 0.3788436949253082,
+      "learning_rate": 6.536885609972467e-06,
+      "loss": 0.397,
+      "step": 1120
+    },
+    {
+      "epoch": 6.903225806451613,
+      "grad_norm": 0.38878560066223145,
+      "learning_rate": 6.502672723240103e-06,
+      "loss": 0.3969,
+      "step": 1125
+    },
+    {
+      "epoch": 6.93394777265745,
+      "grad_norm": 0.4072780907154083,
+      "learning_rate": 6.4683823181213224e-06,
+      "loss": 0.3969,
+      "step": 1130
+    },
+    {
+      "epoch": 6.964669738863288,
+      "grad_norm": 0.40496107935905457,
+      "learning_rate": 6.434016163555452e-06,
+      "loss": 0.3957,
+      "step": 1135
+    },
+    {
+      "epoch": 6.9953917050691246,
+      "grad_norm": 0.3747064173221588,
+      "learning_rate": 6.399576032389505e-06,
+      "loss": 0.3984,
+      "step": 1140
+    },
+    {
+      "epoch": 7.024577572964669,
+      "grad_norm": 0.5090351104736328,
+      "learning_rate": 6.365063701286728e-06,
+      "loss": 0.3714,
+      "step": 1145
+    },
+    {
+      "epoch": 7.055299539170507,
+      "grad_norm": 0.42551228404045105,
+      "learning_rate": 6.330480950634942e-06,
+      "loss": 0.3673,
+      "step": 1150
+    },
+    {
+      "epoch": 7.086021505376344,
+      "grad_norm": 0.4707318842411041,
+      "learning_rate": 6.2958295644547026e-06,
+      "loss": 0.3641,
+      "step": 1155
+    },
+    {
+      "epoch": 7.116743471582181,
+      "grad_norm": 0.40848663449287415,
+      "learning_rate": 6.261111330307272e-06,
+      "loss": 0.3628,
+      "step": 1160
+    },
+    {
+      "epoch": 7.147465437788019,
+      "grad_norm": 0.4382622539997101,
+      "learning_rate": 6.22632803920239e-06,
+      "loss": 0.3691,
+      "step": 1165
+    },
+    {
+      "epoch": 7.178187403993856,
+      "grad_norm": 0.3866026699542999,
+      "learning_rate": 6.191481485505898e-06,
+      "loss": 0.3639,
+      "step": 1170
+    },
+    {
+      "epoch": 7.2089093701996925,
+      "grad_norm": 0.4263141453266144,
+      "learning_rate": 6.1565734668471614e-06,
+      "loss": 0.3634,
+      "step": 1175
+    },
+    {
+      "epoch": 7.23963133640553,
+      "grad_norm": 0.4050372242927551,
+      "learning_rate": 6.121605784026339e-06,
+      "loss": 0.3648,
+      "step": 1180
+    },
+    {
+      "epoch": 7.270353302611367,
+      "grad_norm": 0.3879098892211914,
+      "learning_rate": 6.086580240921486e-06,
+      "loss": 0.3667,
+      "step": 1185
+    },
+    {
+      "epoch": 7.301075268817204,
+      "grad_norm": 0.4055810868740082,
+      "learning_rate": 6.051498644395496e-06,
+      "loss": 0.3656,
+      "step": 1190
+    },
+    {
+      "epoch": 7.331797235023042,
+      "grad_norm": 0.42201170325279236,
+      "learning_rate": 6.01636280420289e-06,
+      "loss": 0.3679,
+      "step": 1195
+    },
+    {
+      "epoch": 7.362519201228879,
+      "grad_norm": 0.4164835214614868,
+      "learning_rate": 5.981174532896459e-06,
+      "loss": 0.367,
+      "step": 1200
+    },
+    {
+      "epoch": 7.393241167434716,
+      "grad_norm": 0.39605438709259033,
+      "learning_rate": 5.9459356457337556e-06,
+      "loss": 0.3647,
+      "step": 1205
+    },
+    {
+      "epoch": 7.423963133640553,
+      "grad_norm": 0.4393250644207001,
+      "learning_rate": 5.910647960583458e-06,
+      "loss": 0.3733,
+      "step": 1210
+    },
+    {
+      "epoch": 7.45468509984639,
+      "grad_norm": 0.37553438544273376,
+      "learning_rate": 5.875313297831579e-06,
+      "loss": 0.37,
+      "step": 1215
+    },
+    {
+      "epoch": 7.485407066052227,
+      "grad_norm": 0.3898600935935974,
+      "learning_rate": 5.839933480287572e-06,
+      "loss": 0.3678,
+      "step": 1220
+    },
+    {
+      "epoch": 7.516129032258064,
+      "grad_norm": 0.4083476662635803,
+      "learning_rate": 5.804510333090287e-06,
+      "loss": 0.3665,
+      "step": 1225
+    },
+    {
+      "epoch": 7.546850998463902,
+      "grad_norm": 0.40433645248413086,
+      "learning_rate": 5.769045683613822e-06,
+      "loss": 0.3715,
+      "step": 1230
+    },
+    {
+      "epoch": 7.577572964669739,
+      "grad_norm": 0.4303235709667206,
+      "learning_rate": 5.733541361373253e-06,
+      "loss": 0.3711,
+      "step": 1235
+    },
+    {
+      "epoch": 7.6082949308755765,
+      "grad_norm": 0.40306177735328674,
+      "learning_rate": 5.697999197930259e-06,
+      "loss": 0.3659,
+      "step": 1240
+    },
+    {
+      "epoch": 7.639016897081413,
+      "grad_norm": 0.39787065982818604,
+      "learning_rate": 5.662421026798624e-06,
+      "loss": 0.3722,
+      "step": 1245
+    },
+    {
+      "epoch": 7.66973886328725,
+      "grad_norm": 0.401962012052536,
+      "learning_rate": 5.626808683349672e-06,
+      "loss": 0.3691,
+      "step": 1250
+    },
+    {
+      "epoch": 7.700460829493087,
+      "grad_norm": 0.38256722688674927,
+      "learning_rate": 5.591164004717567e-06,
+      "loss": 0.3694,
+      "step": 1255
+    },
+    {
+      "epoch": 7.731182795698925,
+      "grad_norm": 0.4020300507545471,
+      "learning_rate": 5.55548882970455e-06,
+      "loss": 0.3728,
+      "step": 1260
+    },
+    {
+      "epoch": 7.761904761904762,
+      "grad_norm": 0.41450026631355286,
+      "learning_rate": 5.519784998686081e-06,
+      "loss": 0.3673,
+      "step": 1265
+    },
+    {
+      "epoch": 7.792626728110599,
+      "grad_norm": 0.36544522643089294,
+      "learning_rate": 5.484054353515896e-06,
+      "loss": 0.3729,
+      "step": 1270
+    },
+    {
+      "epoch": 7.8233486943164365,
+      "grad_norm": 0.38962146639823914,
+      "learning_rate": 5.448298737430992e-06,
+      "loss": 0.3697,
+      "step": 1275
+    },
+    {
+      "epoch": 7.854070660522273,
+      "grad_norm": 0.425886869430542,
+      "learning_rate": 5.412519994956543e-06,
+      "loss": 0.3733,
+      "step": 1280
+    },
+    {
+      "epoch": 7.88479262672811,
+      "grad_norm": 0.3979520797729492,
+      "learning_rate": 5.376719971810741e-06,
+      "loss": 0.3734,
+      "step": 1285
+    },
+    {
+      "epoch": 7.915514592933948,
+      "grad_norm": 0.38723668456077576,
+      "learning_rate": 5.340900514809587e-06,
+      "loss": 0.3726,
+      "step": 1290
+    },
+    {
+      "epoch": 7.946236559139785,
+      "grad_norm": 0.37770572304725647,
+      "learning_rate": 5.305063471771614e-06,
+      "loss": 0.3699,
+      "step": 1295
+    },
+    {
+      "epoch": 7.976958525345622,
+      "grad_norm": 0.398049533367157,
+      "learning_rate": 5.26921069142257e-06,
+      "loss": 0.3717,
+      "step": 1300
+    },
+    {
+      "epoch": 8.006144393241167,
+      "grad_norm": 0.5838120579719543,
+      "learning_rate": 5.233344023300037e-06,
+      "loss": 0.3649,
+      "step": 1305
+    },
+    {
+      "epoch": 8.036866359447005,
+      "grad_norm": 0.4888751208782196,
+      "learning_rate": 5.197465317658036e-06,
+      "loss": 0.3417,
+      "step": 1310
+    },
+    {
+      "epoch": 8.067588325652842,
+      "grad_norm": 0.4426686465740204,
+      "learning_rate": 5.161576425371554e-06,
+      "loss": 0.3448,
+      "step": 1315
+    },
+    {
+      "epoch": 8.09831029185868,
+      "grad_norm": 0.4328514635562897,
+      "learning_rate": 5.125679197841088e-06,
+      "loss": 0.3427,
+      "step": 1320
+    },
+    {
+      "epoch": 8.129032258064516,
+      "grad_norm": 0.461224764585495,
+      "learning_rate": 5.089775486897121e-06,
+      "loss": 0.3411,
+      "step": 1325
+    },
+    {
+      "epoch": 8.159754224270353,
+      "grad_norm": 0.41059058904647827,
+      "learning_rate": 5.053867144704594e-06,
+      "loss": 0.3432,
+      "step": 1330
+    },
+    {
+      "epoch": 8.19047619047619,
+      "grad_norm": 0.4233262538909912,
+      "learning_rate": 5.017956023667363e-06,
+      "loss": 0.3428,
+      "step": 1335
+    },
+    {
+      "epoch": 8.221198156682028,
+      "grad_norm": 0.44398781657218933,
+      "learning_rate": 4.982043976332638e-06,
+      "loss": 0.3396,
+      "step": 1340
+    },
+    {
+      "epoch": 8.251920122887865,
+      "grad_norm": 0.43628108501434326,
+      "learning_rate": 4.946132855295407e-06,
+      "loss": 0.3432,
+      "step": 1345
+    },
+    {
+      "epoch": 8.282642089093702,
+      "grad_norm": 0.45262426137924194,
+      "learning_rate": 4.910224513102881e-06,
+      "loss": 0.34,
+      "step": 1350
+    },
+    {
+      "epoch": 8.31336405529954,
+      "grad_norm": 0.46370255947113037,
+      "learning_rate": 4.8743208021589135e-06,
+      "loss": 0.3404,
+      "step": 1355
+    },
+    {
+      "epoch": 8.344086021505376,
+      "grad_norm": 0.40948814153671265,
+      "learning_rate": 4.838423574628447e-06,
+      "loss": 0.3431,
+      "step": 1360
+    },
+    {
+      "epoch": 8.374807987711213,
+      "grad_norm": 0.4436282813549042,
+      "learning_rate": 4.802534682341966e-06,
+      "loss": 0.3446,
+      "step": 1365
+    },
+    {
+      "epoch": 8.40552995391705,
+      "grad_norm": 0.4203520119190216,
+      "learning_rate": 4.7666559766999635e-06,
+      "loss": 0.3478,
+      "step": 1370
+    },
+    {
+      "epoch": 8.436251920122888,
+      "grad_norm": 0.4091641306877136,
+      "learning_rate": 4.730789308577432e-06,
+      "loss": 0.3461,
+      "step": 1375
+    },
+    {
+      "epoch": 8.466973886328725,
+      "grad_norm": 0.4320433735847473,
+      "learning_rate": 4.694936528228387e-06,
+      "loss": 0.3504,
+      "step": 1380
+    },
+    {
+      "epoch": 8.497695852534562,
+      "grad_norm": 0.4243397116661072,
+      "learning_rate": 4.659099485190414e-06,
+      "loss": 0.3444,
+      "step": 1385
+    },
+    {
+      "epoch": 8.5284178187404,
+      "grad_norm": 0.42783576250076294,
+      "learning_rate": 4.6232800281892604e-06,
+      "loss": 0.3398,
+      "step": 1390
+    },
+    {
+      "epoch": 8.559139784946236,
+      "grad_norm": 0.395312637090683,
+      "learning_rate": 4.587480005043458e-06,
+      "loss": 0.3472,
+      "step": 1395
+    },
+    {
+      "epoch": 8.589861751152073,
+      "grad_norm": 0.41875869035720825,
+      "learning_rate": 4.551701262569009e-06,
+      "loss": 0.3475,
+      "step": 1400
+    },
+    {
+      "epoch": 8.620583717357912,
+      "grad_norm": 0.4307910203933716,
+      "learning_rate": 4.515945646484105e-06,
+      "loss": 0.3465,
+      "step": 1405
+    },
+    {
+      "epoch": 8.651305683563749,
+      "grad_norm": 0.40852200984954834,
+      "learning_rate": 4.480215001313919e-06,
+      "loss": 0.3497,
+      "step": 1410
+    },
+    {
+      "epoch": 8.682027649769585,
+      "grad_norm": 0.4345207214355469,
+      "learning_rate": 4.444511170295451e-06,
+      "loss": 0.3474,
+      "step": 1415
+    },
+    {
+      "epoch": 8.712749615975422,
+      "grad_norm": 0.4096705913543701,
+      "learning_rate": 4.408835995282434e-06,
+      "loss": 0.3472,
+      "step": 1420
+    },
+    {
+      "epoch": 8.74347158218126,
+      "grad_norm": 0.4314156770706177,
+      "learning_rate": 4.373191316650328e-06,
+      "loss": 0.3518,
+      "step": 1425
+    },
+    {
+      "epoch": 8.774193548387096,
+      "grad_norm": 0.41832414269447327,
+      "learning_rate": 4.3375789732013775e-06,
+      "loss": 0.3498,
+      "step": 1430
+    },
+    {
+      "epoch": 8.804915514592935,
+      "grad_norm": 0.42618289589881897,
+      "learning_rate": 4.302000802069744e-06,
+      "loss": 0.3486,
+      "step": 1435
+    },
+    {
+      "epoch": 8.835637480798772,
+      "grad_norm": 0.43849977850914,
+      "learning_rate": 4.2664586386267474e-06,
+      "loss": 0.346,
+      "step": 1440
+    },
+    {
+      "epoch": 8.866359447004609,
+      "grad_norm": 0.42157772183418274,
+      "learning_rate": 4.230954316386179e-06,
+      "loss": 0.3475,
+      "step": 1445
+    },
+    {
+      "epoch": 8.897081413210445,
+      "grad_norm": 0.39600861072540283,
+      "learning_rate": 4.195489666909714e-06,
+      "loss": 0.3455,
+      "step": 1450
+    },
+    {
+      "epoch": 8.927803379416282,
+      "grad_norm": 0.3980286419391632,
+      "learning_rate": 4.160066519712428e-06,
+      "loss": 0.3488,
+      "step": 1455
+    },
+    {
+      "epoch": 8.95852534562212,
+      "grad_norm": 0.41449347138404846,
+      "learning_rate": 4.1246867021684206e-06,
+      "loss": 0.345,
+      "step": 1460
+    },
+    {
+      "epoch": 8.989247311827956,
+      "grad_norm": 0.43595919013023376,
+      "learning_rate": 4.089352039416543e-06,
+      "loss": 0.3476,
+      "step": 1465
+    },
+    {
+      "epoch": 9.018433179723502,
+      "grad_norm": 0.5251989364624023,
+      "learning_rate": 4.054064354266244e-06,
+      "loss": 0.3327,
+      "step": 1470
+    },
+    {
+      "epoch": 9.049155145929339,
+      "grad_norm": 0.4793786108493805,
+      "learning_rate": 4.018825467103542e-06,
+      "loss": 0.318,
+      "step": 1475
+    },
+    {
+      "epoch": 9.079877112135177,
+      "grad_norm": 0.4722115993499756,
+      "learning_rate": 3.983637195797111e-06,
+      "loss": 0.3217,
+      "step": 1480
+    },
+    {
+      "epoch": 9.110599078341014,
+      "grad_norm": 0.4697054326534271,
+      "learning_rate": 3.948501355604507e-06,
+      "loss": 0.3184,
+      "step": 1485
+    },
+    {
+      "epoch": 9.141321044546851,
+      "grad_norm": 0.4698534607887268,
+      "learning_rate": 3.9134197590785164e-06,
+      "loss": 0.3193,
+      "step": 1490
+    },
+    {
+      "epoch": 9.172043010752688,
+      "grad_norm": 0.4833962917327881,
+      "learning_rate": 3.878394215973663e-06,
+      "loss": 0.3243,
+      "step": 1495
+    },
+    {
+      "epoch": 9.202764976958525,
+      "grad_norm": 0.47097915410995483,
+      "learning_rate": 3.843426533152841e-06,
+      "loss": 0.3218,
+      "step": 1500
+    },
+    {
+      "epoch": 9.233486943164362,
+      "grad_norm": 0.4613553285598755,
+      "learning_rate": 3.808518514494105e-06,
+      "loss": 0.3191,
+      "step": 1505
+    },
+    {
+      "epoch": 9.2642089093702,
+      "grad_norm": 0.4618718922138214,
+      "learning_rate": 3.773671960797613e-06,
+      "loss": 0.3219,
+      "step": 1510
+    },
+    {
+      "epoch": 9.294930875576037,
+      "grad_norm": 0.45279550552368164,
+      "learning_rate": 3.7388886696927317e-06,
+      "loss": 0.3235,
+      "step": 1515
+    },
+    {
+      "epoch": 9.325652841781874,
+      "grad_norm": 0.4596066176891327,
+      "learning_rate": 3.704170435545299e-06,
+      "loss": 0.3183,
+      "step": 1520
+    },
+    {
+      "epoch": 9.356374807987711,
+      "grad_norm": 0.4353365898132324,
+      "learning_rate": 3.6695190493650608e-06,
+      "loss": 0.3204,
+      "step": 1525
+    },
+    {
+      "epoch": 9.387096774193548,
+      "grad_norm": 0.444594144821167,
+      "learning_rate": 3.634936298713274e-06,
+      "loss": 0.3225,
+      "step": 1530
+    },
+    {
+      "epoch": 9.417818740399385,
+      "grad_norm": 0.43966248631477356,
+      "learning_rate": 3.6004239676104957e-06,
+      "loss": 0.3236,
+      "step": 1535
+    },
+    {
+      "epoch": 9.448540706605222,
+      "grad_norm": 0.4758555591106415,
+      "learning_rate": 3.5659838364445505e-06,
+      "loss": 0.3219,
+      "step": 1540
+    },
+    {
+      "epoch": 9.47926267281106,
+      "grad_norm": 0.4469148814678192,
+      "learning_rate": 3.5316176818786797e-06,
+      "loss": 0.324,
+      "step": 1545
+    },
+    {
+      "epoch": 9.509984639016897,
+      "grad_norm": 0.4485386908054352,
+      "learning_rate": 3.497327276759899e-06,
+      "loss": 0.3238,
+      "step": 1550
+    },
+    {
+      "epoch": 9.540706605222734,
+      "grad_norm": 0.44222620129585266,
+      "learning_rate": 3.463114390027533e-06,
+      "loss": 0.3205,
+      "step": 1555
+    },
+    {
+      "epoch": 9.571428571428571,
+      "grad_norm": 0.45242762565612793,
+      "learning_rate": 3.4289807866219683e-06,
+      "loss": 0.3222,
+      "step": 1560
+    },
+    {
+      "epoch": 9.602150537634408,
+      "grad_norm": 0.44047296047210693,
+      "learning_rate": 3.394928227393598e-06,
+      "loss": 0.3277,
+      "step": 1565
+    },
+    {
+      "epoch": 9.632872503840245,
+      "grad_norm": 0.44352057576179504,
+      "learning_rate": 3.3609584690119924e-06,
+      "loss": 0.3231,
+      "step": 1570
+    },
+    {
+      "epoch": 9.663594470046084,
+      "grad_norm": 0.44703468680381775,
+      "learning_rate": 3.3270732638752713e-06,
+      "loss": 0.3242,
+      "step": 1575
+    },
+    {
+      "epoch": 9.69431643625192,
+      "grad_norm": 0.46220463514328003,
+      "learning_rate": 3.293274360019707e-06,
+      "loss": 0.3256,
+      "step": 1580
+    },
+    {
+      "epoch": 9.725038402457757,
+      "grad_norm": 0.4843495786190033,
+      "learning_rate": 3.259563501029548e-06,
+      "loss": 0.3279,
+      "step": 1585
+    },
+    {
+      "epoch": 9.755760368663594,
+      "grad_norm": 0.4653911292552948,
+      "learning_rate": 3.2259424259470705e-06,
+      "loss": 0.3233,
+      "step": 1590
+    },
+    {
+      "epoch": 9.786482334869431,
+      "grad_norm": 0.45650723576545715,
+      "learning_rate": 3.1924128691828678e-06,
+      "loss": 0.324,
+      "step": 1595
+    },
+    {
+      "epoch": 9.817204301075268,
+      "grad_norm": 0.5246464014053345,
+      "learning_rate": 3.158976560426379e-06,
+      "loss": 0.3286,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2430,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.4548687991848042e+19,
+  "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 sha256:7fc3a06490eacaa5c07f40008683352e150e12cb8622c53832fde4d1fc850a5c
+size 7544