Training in progress, step 272, checkpoint

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-136/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-272/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-272/added_tokens.json

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

checkpoint-272/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-272/generation_config.json

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

checkpoint-272/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec4ca625a35e84d3503101386e6c8f8674eab84bc64dda7758e7345d63c0c02
+size 4902257696

checkpoint-272/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571c1ee44f1247ece2f7cda9048ed869222722ff5024eb5a0b33ff7d60b5e2fb
+size 4915960368

checkpoint-272/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c48388f898f318b56263cbbf31485cf7e16df9832f043b467604b64d086c307
+size 4983068496

checkpoint-272/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e98acbab238fdb3c80917cef2ec677a9ae2c2e62aca9e4d6ae286e57044ca9b
+size 1580230264

checkpoint-272/model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-272/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03a1829d4946065c5b67c9b6c8046108a7eaa659d6780663fbc091d18400be8
+size 16637925676

checkpoint-272/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a02d728a763af949adfec4bf1d121e1daf1ef655fd3b17a42c2399e0221768dd
+size 15024

checkpoint-272/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60087aa7d44f5751e6a709354a90b705404a21a9437680f20377cf12743341b
+size 15024

checkpoint-272/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c962bfcedafeb4fe574f63e648405b9b28a01333d49c391529b2c7a4fead463
+size 15024

checkpoint-272/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478ec022631f64178ab44a8355b560b75c942f4cf348cc636a8cb37ec3bec6cc
+size 15024

checkpoint-272/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846b6bb7ea8557d5f0c16d1ab2e2b5d3e020e5888f4779d7eb8505ca3a9dc6ef
+size 1064

checkpoint-272/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-272/tokenizer.json

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

checkpoint-272/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-272/trainer_state.json

@@ -0,0 +1,2074 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 17,
+  "global_step": 272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007352941176470588,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.0,
+      "loss": 1.6433,
+      "step": 1
+    },
+    {
+      "epoch": 0.007352941176470588,
+      "eval_loss": 2.023996114730835,
+      "eval_runtime": 29.0075,
+      "eval_samples_per_second": 1.517,
+      "eval_steps_per_second": 0.379,
+      "step": 1
+    },
+    {
+      "epoch": 0.014705882352941176,
+      "grad_norm": 1.9921875,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.8443,
+      "step": 2
+    },
+    {
+      "epoch": 0.022058823529411766,
+      "grad_norm": 2.015625,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 1.7175,
+      "step": 3
+    },
+    {
+      "epoch": 0.029411764705882353,
+      "grad_norm": 1.5625,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.5511,
+      "step": 4
+    },
+    {
+      "epoch": 0.03676470588235294,
+      "grad_norm": 1.4375,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 1.3348,
+      "step": 5
+    },
+    {
+      "epoch": 0.04411764705882353,
+      "grad_norm": 1.8671875,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 1.6403,
+      "step": 6
+    },
+    {
+      "epoch": 0.051470588235294115,
+      "grad_norm": 1.9375,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 2.4032,
+      "step": 7
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 1.734375,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 1.6092,
+      "step": 8
+    },
+    {
+      "epoch": 0.0661764705882353,
+      "grad_norm": 1.6484375,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 1.5771,
+      "step": 9
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 1.3515625,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 1.5274,
+      "step": 10
+    },
+    {
+      "epoch": 0.08088235294117647,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 1.8263,
+      "step": 11
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 1.59375,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 1.9586,
+      "step": 12
+    },
+    {
+      "epoch": 0.09558823529411764,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 1.9486,
+      "step": 13
+    },
+    {
+      "epoch": 0.10294117647058823,
+      "grad_norm": 1.2578125,
+      "learning_rate": 1e-05,
+      "loss": 2.0083,
+      "step": 14
+    },
+    {
+      "epoch": 0.11029411764705882,
+      "grad_norm": 1.3359375,
+      "learning_rate": 9.999632180371776e-06,
+      "loss": 1.3495,
+      "step": 15
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 1.3828125,
+      "learning_rate": 9.998528775603612e-06,
+      "loss": 1.45,
+      "step": 16
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.996689948037081e-06,
+      "loss": 1.5696,
+      "step": 17
+    },
+    {
+      "epoch": 0.125,
+      "eval_loss": 2.0076510906219482,
+      "eval_runtime": 29.101,
+      "eval_samples_per_second": 1.512,
+      "eval_steps_per_second": 0.378,
+      "step": 17
+    },
+    {
+      "epoch": 0.1323529411764706,
+      "grad_norm": 1.296875,
+      "learning_rate": 9.994115968214933e-06,
+      "loss": 1.9919,
+      "step": 18
+    },
+    {
+      "epoch": 0.13970588235294118,
+      "grad_norm": 1.265625,
+      "learning_rate": 9.990807214841288e-06,
+      "loss": 1.1574,
+      "step": 19
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.98676417472592e-06,
+      "loss": 1.7192,
+      "step": 20
+    },
+    {
+      "epoch": 0.15441176470588236,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.981987442712634e-06,
+      "loss": 1.42,
+      "step": 21
+    },
+    {
+      "epoch": 0.16176470588235295,
+      "grad_norm": 1.265625,
+      "learning_rate": 9.976477721591746e-06,
+      "loss": 1.903,
+      "step": 22
+    },
+    {
+      "epoch": 0.16911764705882354,
+      "grad_norm": 1.375,
+      "learning_rate": 9.97023582199669e-06,
+      "loss": 1.6847,
+      "step": 23
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.963262662284735e-06,
+      "loss": 1.9539,
+      "step": 24
+    },
+    {
+      "epoch": 0.18382352941176472,
+      "grad_norm": 1.40625,
+      "learning_rate": 9.955559268401893e-06,
+      "loss": 1.8249,
+      "step": 25
+    },
+    {
+      "epoch": 0.19117647058823528,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.947126773731949e-06,
+      "loss": 1.5185,
+      "step": 26
+    },
+    {
+      "epoch": 0.19852941176470587,
+      "grad_norm": 1.3125,
+      "learning_rate": 9.937966418929725e-06,
+      "loss": 1.9394,
+      "step": 27
+    },
+    {
+      "epoch": 0.20588235294117646,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.928079551738542e-06,
+      "loss": 1.5664,
+      "step": 28
+    },
+    {
+      "epoch": 0.21323529411764705,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.917467626791925e-06,
+      "loss": 1.5556,
+      "step": 29
+    },
+    {
+      "epoch": 0.22058823529411764,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.90613220539959e-06,
+      "loss": 1.4611,
+      "step": 30
+    },
+    {
+      "epoch": 0.22794117647058823,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.89407495531773e-06,
+      "loss": 1.0783,
+      "step": 31
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 1.21875,
+      "learning_rate": 9.881297650503641e-06,
+      "loss": 1.8567,
+      "step": 32
+    },
+    {
+      "epoch": 0.2426470588235294,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.867802170854724e-06,
+      "loss": 1.8233,
+      "step": 33
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.875,
+      "learning_rate": 9.853590501931905e-06,
+      "loss": 2.5862,
+      "step": 34
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.9994938373565674,
+      "eval_runtime": 28.2547,
+      "eval_samples_per_second": 1.557,
+      "eval_steps_per_second": 0.389,
+      "step": 34
+    },
+    {
+      "epoch": 0.25735294117647056,
+      "grad_norm": 1.296875,
+      "learning_rate": 9.838664734667496e-06,
+      "loss": 1.8706,
+      "step": 35
+    },
+    {
+      "epoch": 0.2647058823529412,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.82302706505756e-06,
+      "loss": 1.783,
+      "step": 36
+    },
+    {
+      "epoch": 0.27205882352941174,
+      "grad_norm": 1.3125,
+      "learning_rate": 9.806679793838829e-06,
+      "loss": 1.6925,
+      "step": 37
+    },
+    {
+      "epoch": 0.27941176470588236,
+      "grad_norm": 1.2109375,
+      "learning_rate": 9.78962532615019e-06,
+      "loss": 1.4931,
+      "step": 38
+    },
+    {
+      "epoch": 0.2867647058823529,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.771866171178832e-06,
+      "loss": 1.7531,
+      "step": 39
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 1.140625,
+      "learning_rate": 9.753404941791063e-06,
+      "loss": 1.7975,
+      "step": 40
+    },
+    {
+      "epoch": 0.3014705882352941,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.734244354147897e-06,
+      "loss": 1.7083,
+      "step": 41
+    },
+    {
+      "epoch": 0.3088235294117647,
+      "grad_norm": 1.359375,
+      "learning_rate": 9.714387227305422e-06,
+      "loss": 1.6907,
+      "step": 42
+    },
+    {
+      "epoch": 0.3161764705882353,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.693836482800044e-06,
+      "loss": 1.9384,
+      "step": 43
+    },
+    {
+      "epoch": 0.3235294117647059,
+      "grad_norm": 1.3515625,
+      "learning_rate": 9.672595144218646e-06,
+      "loss": 1.8993,
+      "step": 44
+    },
+    {
+      "epoch": 0.33088235294117646,
+      "grad_norm": 1.1875,
+      "learning_rate": 9.65066633675373e-06,
+      "loss": 1.6913,
+      "step": 45
+    },
+    {
+      "epoch": 0.3382352941176471,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.628053286743619e-06,
+      "loss": 1.4722,
+      "step": 46
+    },
+    {
+      "epoch": 0.34558823529411764,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.604759321197775e-06,
+      "loss": 1.7211,
+      "step": 47
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 1.375,
+      "learning_rate": 9.580787867307293e-06,
+      "loss": 1.9391,
+      "step": 48
+    },
+    {
+      "epoch": 0.3602941176470588,
+      "grad_norm": 1.3125,
+      "learning_rate": 9.55614245194068e-06,
+      "loss": 1.6147,
+      "step": 49
+    },
+    {
+      "epoch": 0.36764705882352944,
+      "grad_norm": 1.1484375,
+      "learning_rate": 9.53082670112494e-06,
+      "loss": 1.5916,
+      "step": 50
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 1.375,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 1.9231,
+      "step": 51
+    },
+    {
+      "epoch": 0.375,
+      "eval_loss": 1.9944037199020386,
+      "eval_runtime": 28.9271,
+      "eval_samples_per_second": 1.521,
+      "eval_steps_per_second": 0.38,
+      "step": 51
+    },
+    {
+      "epoch": 0.38235294117647056,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.478199189831184e-06,
+      "loss": 1.6755,
+      "step": 52
+    },
+    {
+      "epoch": 0.3897058823529412,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.450895172325822e-06,
+      "loss": 1.6623,
+      "step": 53
+    },
+    {
+      "epoch": 0.39705882352941174,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.422936304177439e-06,
+      "loss": 1.2844,
+      "step": 54
+    },
+    {
+      "epoch": 0.40441176470588236,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.394326698914229e-06,
+      "loss": 1.779,
+      "step": 55
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 1.21875,
+      "learning_rate": 9.365070565805941e-06,
+      "loss": 1.2299,
+      "step": 56
+    },
+    {
+      "epoch": 0.41911764705882354,
+      "grad_norm": 1.21875,
+      "learning_rate": 9.335172209244577e-06,
+      "loss": 1.9589,
+      "step": 57
+    },
+    {
+      "epoch": 0.4264705882352941,
+      "grad_norm": 1.78125,
+      "learning_rate": 9.304636028111093e-06,
+      "loss": 1.7626,
+      "step": 58
+    },
+    {
+      "epoch": 0.4338235294117647,
+      "grad_norm": 1.1875,
+      "learning_rate": 9.273466515128209e-06,
+      "loss": 1.4811,
+      "step": 59
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "grad_norm": 0.90625,
+      "learning_rate": 9.241668256199392e-06,
+      "loss": 1.3207,
+      "step": 60
+    },
+    {
+      "epoch": 0.4485294117647059,
+      "grad_norm": 0.875,
+      "learning_rate": 9.209245929734156e-06,
+      "loss": 1.0984,
+      "step": 61
+    },
+    {
+      "epoch": 0.45588235294117646,
+      "grad_norm": 1.25,
+      "learning_rate": 9.176204305959727e-06,
+      "loss": 1.7514,
+      "step": 62
+    },
+    {
+      "epoch": 0.4632352941176471,
+      "grad_norm": 1.40625,
+      "learning_rate": 9.142548246219212e-06,
+      "loss": 2.0432,
+      "step": 63
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 3.09375,
+      "learning_rate": 9.108282702256366e-06,
+      "loss": 3.1275,
+      "step": 64
+    },
+    {
+      "epoch": 0.47794117647058826,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.073412715487045e-06,
+      "loss": 2.0289,
+      "step": 65
+    },
+    {
+      "epoch": 0.4852941176470588,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.037943416257475e-06,
+      "loss": 1.8555,
+      "step": 66
+    },
+    {
+      "epoch": 0.49264705882352944,
+      "grad_norm": 1.1953125,
+      "learning_rate": 9.001880023089442e-06,
+      "loss": 1.8256,
+      "step": 67
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.34375,
+      "learning_rate": 8.96522784191249e-06,
+      "loss": 1.9655,
+      "step": 68
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.9907618761062622,
+      "eval_runtime": 29.101,
+      "eval_samples_per_second": 1.512,
+      "eval_steps_per_second": 0.378,
+      "step": 68
+    },
+    {
+      "epoch": 0.5073529411764706,
+      "grad_norm": 0.8515625,
+      "learning_rate": 8.927992265283282e-06,
+      "loss": 1.2591,
+      "step": 69
+    },
+    {
+      "epoch": 0.5147058823529411,
+      "grad_norm": 1.046875,
+      "learning_rate": 8.890178771592198e-06,
+      "loss": 1.644,
+      "step": 70
+    },
+    {
+      "epoch": 0.5220588235294118,
+      "grad_norm": 2.03125,
+      "learning_rate": 8.851792924257316e-06,
+      "loss": 1.6287,
+      "step": 71
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 1.125,
+      "learning_rate": 8.812840370905872e-06,
+      "loss": 1.5483,
+      "step": 72
+    },
+    {
+      "epoch": 0.5367647058823529,
+      "grad_norm": 1.125,
+      "learning_rate": 8.773326842543348e-06,
+      "loss": 1.664,
+      "step": 73
+    },
+    {
+      "epoch": 0.5441176470588235,
+      "grad_norm": 1.3046875,
+      "learning_rate": 8.733258152710262e-06,
+      "loss": 1.9707,
+      "step": 74
+    },
+    {
+      "epoch": 0.5514705882352942,
+      "grad_norm": 1.046875,
+      "learning_rate": 8.692640196626859e-06,
+      "loss": 1.6404,
+      "step": 75
+    },
+    {
+      "epoch": 0.5588235294117647,
+      "grad_norm": 1.1171875,
+      "learning_rate": 8.651478950325739e-06,
+      "loss": 1.5971,
+      "step": 76
+    },
+    {
+      "epoch": 0.5661764705882353,
+      "grad_norm": 1.21875,
+      "learning_rate": 8.609780469772623e-06,
+      "loss": 1.7441,
+      "step": 77
+    },
+    {
+      "epoch": 0.5735294117647058,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.567550889975362e-06,
+      "loss": 1.7133,
+      "step": 78
+    },
+    {
+      "epoch": 0.5808823529411765,
+      "grad_norm": 1.078125,
+      "learning_rate": 8.524796424081291e-06,
+      "loss": 1.3789,
+      "step": 79
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 1.0078125,
+      "learning_rate": 8.481523362463111e-06,
+      "loss": 1.3651,
+      "step": 80
+    },
+    {
+      "epoch": 0.5955882352941176,
+      "grad_norm": 1.1015625,
+      "learning_rate": 8.437738071793394e-06,
+      "loss": 2.0325,
+      "step": 81
+    },
+    {
+      "epoch": 0.6029411764705882,
+      "grad_norm": 1.125,
+      "learning_rate": 8.393446994107876e-06,
+      "loss": 1.6342,
+      "step": 82
+    },
+    {
+      "epoch": 0.6102941176470589,
+      "grad_norm": 1.3046875,
+      "learning_rate": 8.348656645857648e-06,
+      "loss": 1.9204,
+      "step": 83
+    },
+    {
+      "epoch": 0.6176470588235294,
+      "grad_norm": 2.0625,
+      "learning_rate": 8.303373616950408e-06,
+      "loss": 2.6573,
+      "step": 84
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.0859375,
+      "learning_rate": 8.257604569780898e-06,
+      "loss": 1.6909,
+      "step": 85
+    },
+    {
+      "epoch": 0.625,
+      "eval_loss": 1.9879568815231323,
+      "eval_runtime": 28.4352,
+      "eval_samples_per_second": 1.547,
+      "eval_steps_per_second": 0.387,
+      "step": 85
+    },
+    {
+      "epoch": 0.6323529411764706,
+      "grad_norm": 1.03125,
+      "learning_rate": 8.21135623825068e-06,
+      "loss": 1.6941,
+      "step": 86
+    },
+    {
+      "epoch": 0.6397058823529411,
+      "grad_norm": 1.3046875,
+      "learning_rate": 8.164635426777404e-06,
+      "loss": 1.2534,
+      "step": 87
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 1.125,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 1.5544,
+      "step": 88
+    },
+    {
+      "epoch": 0.6544117647058824,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.069803928235689e-06,
+      "loss": 1.2404,
+      "step": 89
+    },
+    {
+      "epoch": 0.6617647058823529,
+      "grad_norm": 1.015625,
+      "learning_rate": 8.021707193521865e-06,
+      "loss": 1.3714,
+      "step": 90
+    },
+    {
+      "epoch": 0.6691176470588235,
+      "grad_norm": 1.078125,
+      "learning_rate": 7.973165881521435e-06,
+      "loss": 1.5804,
+      "step": 91
+    },
+    {
+      "epoch": 0.6764705882352942,
+      "grad_norm": 1.3359375,
+      "learning_rate": 7.924187134013323e-06,
+      "loss": 1.627,
+      "step": 92
+    },
+    {
+      "epoch": 0.6838235294117647,
+      "grad_norm": 1.046875,
+      "learning_rate": 7.874778157135416e-06,
+      "loss": 1.3964,
+      "step": 93
+    },
+    {
+      "epoch": 0.6911764705882353,
+      "grad_norm": 1.1328125,
+      "learning_rate": 7.824946220324313e-06,
+      "loss": 1.5446,
+      "step": 94
+    },
+    {
+      "epoch": 0.6985294117647058,
+      "grad_norm": 1.4609375,
+      "learning_rate": 7.774698655245802e-06,
+      "loss": 1.7198,
+      "step": 95
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.98046875,
+      "learning_rate": 7.724042854716169e-06,
+      "loss": 1.594,
+      "step": 96
+    },
+    {
+      "epoch": 0.7132352941176471,
+      "grad_norm": 1.109375,
+      "learning_rate": 7.6729862716145e-06,
+      "loss": 1.7797,
+      "step": 97
+    },
+    {
+      "epoch": 0.7205882352941176,
+      "grad_norm": 1.3828125,
+      "learning_rate": 7.621536417786159e-06,
+      "loss": 2.3605,
+      "step": 98
+    },
+    {
+      "epoch": 0.7279411764705882,
+      "grad_norm": 0.9765625,
+      "learning_rate": 7.56970086293759e-06,
+      "loss": 1.5639,
+      "step": 99
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "grad_norm": 1.3203125,
+      "learning_rate": 7.5174872335226e-06,
+      "loss": 1.9192,
+      "step": 100
+    },
+    {
+      "epoch": 0.7426470588235294,
+      "grad_norm": 0.9765625,
+      "learning_rate": 7.464903211620291e-06,
+      "loss": 1.7064,
+      "step": 101
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.265625,
+      "learning_rate": 7.4119565338048195e-06,
+      "loss": 1.8634,
+      "step": 102
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.9857271909713745,
+      "eval_runtime": 28.8833,
+      "eval_samples_per_second": 1.523,
+      "eval_steps_per_second": 0.381,
+      "step": 102
+    },
+    {
+      "epoch": 0.7573529411764706,
+      "grad_norm": 1.0703125,
+      "learning_rate": 7.358654990007123e-06,
+      "loss": 1.6888,
+      "step": 103
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 1.1640625,
+      "learning_rate": 7.305006422368811e-06,
+      "loss": 1.5068,
+      "step": 104
+    },
+    {
+      "epoch": 0.7720588235294118,
+      "grad_norm": 0.8984375,
+      "learning_rate": 7.251018724088367e-06,
+      "loss": 1.2948,
+      "step": 105
+    },
+    {
+      "epoch": 0.7794117647058824,
+      "grad_norm": 1.46875,
+      "learning_rate": 7.196699838259834e-06,
+      "loss": 1.7578,
+      "step": 106
+    },
+    {
+      "epoch": 0.7867647058823529,
+      "grad_norm": 1.171875,
+      "learning_rate": 7.142057756704168e-06,
+      "loss": 1.8871,
+      "step": 107
+    },
+    {
+      "epoch": 0.7941176470588235,
+      "grad_norm": 1.046875,
+      "learning_rate": 7.087100518793421e-06,
+      "loss": 1.6245,
+      "step": 108
+    },
+    {
+      "epoch": 0.8014705882352942,
+      "grad_norm": 1.09375,
+      "learning_rate": 7.031836210267915e-06,
+      "loss": 1.9928,
+      "step": 109
+    },
+    {
+      "epoch": 0.8088235294117647,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.976272962046619e-06,
+      "loss": 1.6471,
+      "step": 110
+    },
+    {
+      "epoch": 0.8161764705882353,
+      "grad_norm": 1.171875,
+      "learning_rate": 6.920418949030856e-06,
+      "loss": 2.0028,
+      "step": 111
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.864282388901544e-06,
+      "loss": 1.3726,
+      "step": 112
+    },
+    {
+      "epoch": 0.8308823529411765,
+      "grad_norm": 1.015625,
+      "learning_rate": 6.807871540910155e-06,
+      "loss": 1.7367,
+      "step": 113
+    },
+    {
+      "epoch": 0.8382352941176471,
+      "grad_norm": 1.0703125,
+      "learning_rate": 6.751194704663544e-06,
+      "loss": 1.6541,
+      "step": 114
+    },
+    {
+      "epoch": 0.8455882352941176,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.694260218902845e-06,
+      "loss": 1.8604,
+      "step": 115
+    },
+    {
+      "epoch": 0.8529411764705882,
+      "grad_norm": 1.21875,
+      "learning_rate": 6.637076460276612e-06,
+      "loss": 1.8829,
+      "step": 116
+    },
+    {
+      "epoch": 0.8602941176470589,
+      "grad_norm": 1.0390625,
+      "learning_rate": 6.579651842108381e-06,
+      "loss": 1.692,
+      "step": 117
+    },
+    {
+      "epoch": 0.8676470588235294,
+      "grad_norm": 1.2734375,
+      "learning_rate": 6.521994813158834e-06,
+      "loss": 2.1307,
+      "step": 118
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 1.140625,
+      "learning_rate": 6.464113856382752e-06,
+      "loss": 1.6684,
+      "step": 119
+    },
+    {
+      "epoch": 0.875,
+      "eval_loss": 1.9832121133804321,
+      "eval_runtime": 28.1006,
+      "eval_samples_per_second": 1.566,
+      "eval_steps_per_second": 0.391,
+      "step": 119
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 1.1015625,
+      "learning_rate": 6.406017487680938e-06,
+      "loss": 1.8429,
+      "step": 120
+    },
+    {
+      "epoch": 0.8897058823529411,
+      "grad_norm": 1.015625,
+      "learning_rate": 6.3477142546472836e-06,
+      "loss": 1.748,
+      "step": 121
+    },
+    {
+      "epoch": 0.8970588235294118,
+      "grad_norm": 1.1875,
+      "learning_rate": 6.28921273531119e-06,
+      "loss": 1.4421,
+      "step": 122
+    },
+    {
+      "epoch": 0.9044117647058824,
+      "grad_norm": 1.5234375,
+      "learning_rate": 6.230521536875494e-06,
+      "loss": 1.8182,
+      "step": 123
+    },
+    {
+      "epoch": 0.9117647058823529,
+      "grad_norm": 1.2734375,
+      "learning_rate": 6.171649294450113e-06,
+      "loss": 1.9269,
+      "step": 124
+    },
+    {
+      "epoch": 0.9191176470588235,
+      "grad_norm": 1.234375,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 1.6172,
+      "step": 125
+    },
+    {
+      "epoch": 0.9264705882352942,
+      "grad_norm": 1.3046875,
+      "learning_rate": 6.053396349978632e-06,
+      "loss": 1.7184,
+      "step": 126
+    },
+    {
+      "epoch": 0.9338235294117647,
+      "grad_norm": 1.0234375,
+      "learning_rate": 5.994033046234163e-06,
+      "loss": 1.3447,
+      "step": 127
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.890625,
+      "learning_rate": 5.934523492543489e-06,
+      "loss": 1.158,
+      "step": 128
+    },
+    {
+      "epoch": 0.9485294117647058,
+      "grad_norm": 1.21875,
+      "learning_rate": 5.874876444419377e-06,
+      "loss": 2.0378,
+      "step": 129
+    },
+    {
+      "epoch": 0.9558823529411765,
+      "grad_norm": 1.0703125,
+      "learning_rate": 5.815100677603854e-06,
+      "loss": 1.7901,
+      "step": 130
+    },
+    {
+      "epoch": 0.9632352941176471,
+      "grad_norm": 1.15625,
+      "learning_rate": 5.75520498677705e-06,
+      "loss": 1.6435,
+      "step": 131
+    },
+    {
+      "epoch": 0.9705882352941176,
+      "grad_norm": 1.1484375,
+      "learning_rate": 5.695198184263259e-06,
+      "loss": 1.8977,
+      "step": 132
+    },
+    {
+      "epoch": 0.9779411764705882,
+      "grad_norm": 1.046875,
+      "learning_rate": 5.635089098734394e-06,
+      "loss": 1.4106,
+      "step": 133
+    },
+    {
+      "epoch": 0.9852941176470589,
+      "grad_norm": 1.234375,
+      "learning_rate": 5.574886573911056e-06,
+      "loss": 1.8682,
+      "step": 134
+    },
+    {
+      "epoch": 0.9926470588235294,
+      "grad_norm": 0.90234375,
+      "learning_rate": 5.514599467261363e-06,
+      "loss": 0.9243,
+      "step": 135
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.578125,
+      "learning_rate": 5.454236648697776e-06,
+      "loss": 1.8727,
+      "step": 136
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.981597661972046,
+      "eval_runtime": 29.087,
+      "eval_samples_per_second": 1.513,
+      "eval_steps_per_second": 0.378,
+      "step": 136
+    },
+    {
+      "epoch": 1.0073529411764706,
+      "grad_norm": 0.99609375,
+      "learning_rate": 5.3938069992720894e-06,
+      "loss": 1.6062,
+      "step": 137
+    },
+    {
+      "epoch": 1.0147058823529411,
+      "grad_norm": 1.1171875,
+      "learning_rate": 5.333319409868777e-06,
+      "loss": 1.8066,
+      "step": 138
+    },
+    {
+      "epoch": 1.0220588235294117,
+      "grad_norm": 1.1953125,
+      "learning_rate": 5.272782779896898e-06,
+      "loss": 1.6509,
+      "step": 139
+    },
+    {
+      "epoch": 1.0294117647058822,
+      "grad_norm": 0.98046875,
+      "learning_rate": 5.212206015980742e-06,
+      "loss": 1.5008,
+      "step": 140
+    },
+    {
+      "epoch": 1.036764705882353,
+      "grad_norm": 0.98828125,
+      "learning_rate": 5.151598030649425e-06,
+      "loss": 1.3041,
+      "step": 141
+    },
+    {
+      "epoch": 1.0441176470588236,
+      "grad_norm": 1.2109375,
+      "learning_rate": 5.090967741025599e-06,
+      "loss": 1.5998,
+      "step": 142
+    },
+    {
+      "epoch": 1.0514705882352942,
+      "grad_norm": 1.9375,
+      "learning_rate": 5.030324067513499e-06,
+      "loss": 2.3704,
+      "step": 143
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 1.0234375,
+      "learning_rate": 4.969675932486503e-06,
+      "loss": 1.5675,
+      "step": 144
+    },
+    {
+      "epoch": 1.0661764705882353,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4.909032258974403e-06,
+      "loss": 1.5082,
+      "step": 145
+    },
+    {
+      "epoch": 1.0735294117647058,
+      "grad_norm": 0.9765625,
+      "learning_rate": 4.848401969350577e-06,
+      "loss": 1.4901,
+      "step": 146
+    },
+    {
+      "epoch": 1.0808823529411764,
+      "grad_norm": 1.0234375,
+      "learning_rate": 4.78779398401926e-06,
+      "loss": 1.7717,
+      "step": 147
+    },
+    {
+      "epoch": 1.088235294117647,
+      "grad_norm": 1.0234375,
+      "learning_rate": 4.7272172201031055e-06,
+      "loss": 1.8931,
+      "step": 148
+    },
+    {
+      "epoch": 1.0955882352941178,
+      "grad_norm": 1.125,
+      "learning_rate": 4.666680590131225e-06,
+      "loss": 1.916,
+      "step": 149
+    },
+    {
+      "epoch": 1.1029411764705883,
+      "grad_norm": 1.03125,
+      "learning_rate": 4.606193000727913e-06,
+      "loss": 1.9528,
+      "step": 150
+    },
+    {
+      "epoch": 1.1102941176470589,
+      "grad_norm": 1.0,
+      "learning_rate": 4.545763351302224e-06,
+      "loss": 1.3164,
+      "step": 151
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 1.4453125,
+      "learning_rate": 4.485400532738638e-06,
+      "loss": 1.4166,
+      "step": 152
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 1.1328125,
+      "learning_rate": 4.425113426088945e-06,
+      "loss": 1.542,
+      "step": 153
+    },
+    {
+      "epoch": 1.125,
+      "eval_loss": 1.9806106090545654,
+      "eval_runtime": 28.4601,
+      "eval_samples_per_second": 1.546,
+      "eval_steps_per_second": 0.387,
+      "step": 153
+    },
+    {
+      "epoch": 1.1323529411764706,
+      "grad_norm": 1.046875,
+      "learning_rate": 4.364910901265607e-06,
+      "loss": 1.9457,
+      "step": 154
+    },
+    {
+      "epoch": 1.1397058823529411,
+      "grad_norm": 0.91015625,
+      "learning_rate": 4.3048018157367435e-06,
+      "loss": 1.1295,
+      "step": 155
+    },
+    {
+      "epoch": 1.1470588235294117,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4.244795013222951e-06,
+      "loss": 1.6723,
+      "step": 156
+    },
+    {
+      "epoch": 1.1544117647058822,
+      "grad_norm": 1.0546875,
+      "learning_rate": 4.184899322396147e-06,
+      "loss": 1.3933,
+      "step": 157
+    },
+    {
+      "epoch": 1.161764705882353,
+      "grad_norm": 1.0234375,
+      "learning_rate": 4.125123555580624e-06,
+      "loss": 1.8577,
+      "step": 158
+    },
+    {
+      "epoch": 1.1691176470588236,
+      "grad_norm": 1.0703125,
+      "learning_rate": 4.0654765074565125e-06,
+      "loss": 1.6555,
+      "step": 159
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 1.5390625,
+      "learning_rate": 4.00596695376584e-06,
+      "loss": 1.9155,
+      "step": 160
+    },
+    {
+      "epoch": 1.1838235294117647,
+      "grad_norm": 1.2109375,
+      "learning_rate": 3.94660365002137e-06,
+      "loss": 1.7921,
+      "step": 161
+    },
+    {
+      "epoch": 1.1911764705882353,
+      "grad_norm": 1.03125,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 1.492,
+      "step": 162
+    },
+    {
+      "epoch": 1.1985294117647058,
+      "grad_norm": 1.1875,
+      "learning_rate": 3.8283507055498886e-06,
+      "loss": 1.9106,
+      "step": 163
+    },
+    {
+      "epoch": 1.2058823529411764,
+      "grad_norm": 1.0859375,
+      "learning_rate": 3.7694784631245066e-06,
+      "loss": 1.539,
+      "step": 164
+    },
+    {
+      "epoch": 1.213235294117647,
+      "grad_norm": 1.0390625,
+      "learning_rate": 3.7107872646888115e-06,
+      "loss": 1.5264,
+      "step": 165
+    },
+    {
+      "epoch": 1.2205882352941178,
+      "grad_norm": 1.0703125,
+      "learning_rate": 3.6522857453527172e-06,
+      "loss": 1.4314,
+      "step": 166
+    },
+    {
+      "epoch": 1.2279411764705883,
+      "grad_norm": 0.88671875,
+      "learning_rate": 3.5939825123190637e-06,
+      "loss": 1.0555,
+      "step": 167
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 1.0546875,
+      "learning_rate": 3.5358861436172487e-06,
+      "loss": 1.8202,
+      "step": 168
+    },
+    {
+      "epoch": 1.2426470588235294,
+      "grad_norm": 1.453125,
+      "learning_rate": 3.478005186841167e-06,
+      "loss": 1.777,
+      "step": 169
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.953125,
+      "learning_rate": 3.4203481578916197e-06,
+      "loss": 2.5733,
+      "step": 170
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 1.9800699949264526,
+      "eval_runtime": 28.6845,
+      "eval_samples_per_second": 1.534,
+      "eval_steps_per_second": 0.383,
+      "step": 170
+    },
+    {
+      "epoch": 1.2573529411764706,
+      "grad_norm": 1.0859375,
+      "learning_rate": 3.3629235397233894e-06,
+      "loss": 1.8338,
+      "step": 171
+    },
+    {
+      "epoch": 1.2647058823529411,
+      "grad_norm": 1.1796875,
+      "learning_rate": 3.305739781097157e-06,
+      "loss": 1.7603,
+      "step": 172
+    },
+    {
+      "epoch": 1.2720588235294117,
+      "grad_norm": 1.0859375,
+      "learning_rate": 3.248805295336458e-06,
+      "loss": 1.6503,
+      "step": 173
+    },
+    {
+      "epoch": 1.2794117647058822,
+      "grad_norm": 1.0390625,
+      "learning_rate": 3.192128459089846e-06,
+      "loss": 1.4681,
+      "step": 174
+    },
+    {
+      "epoch": 1.2867647058823528,
+      "grad_norm": 1.1640625,
+      "learning_rate": 3.1357176110984578e-06,
+      "loss": 1.7137,
+      "step": 175
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 1.0078125,
+      "learning_rate": 3.079581050969146e-06,
+      "loss": 1.7776,
+      "step": 176
+    },
+    {
+      "epoch": 1.3014705882352942,
+      "grad_norm": 0.96484375,
+      "learning_rate": 3.0237270379533823e-06,
+      "loss": 1.6797,
+      "step": 177
+    },
+    {
+      "epoch": 1.3088235294117647,
+      "grad_norm": 1.1015625,
+      "learning_rate": 2.968163789732087e-06,
+      "loss": 1.6639,
+      "step": 178
+    },
+    {
+      "epoch": 1.3161764705882353,
+      "grad_norm": 1.1796875,
+      "learning_rate": 2.912899481206582e-06,
+      "loss": 1.9166,
+      "step": 179
+    },
+    {
+      "epoch": 1.3235294117647058,
+      "grad_norm": 1.3203125,
+      "learning_rate": 2.8579422432958316e-06,
+      "loss": 1.8786,
+      "step": 180
+    },
+    {
+      "epoch": 1.3308823529411764,
+      "grad_norm": 1.09375,
+      "learning_rate": 2.803300161740166e-06,
+      "loss": 1.6681,
+      "step": 181
+    },
+    {
+      "epoch": 1.3382352941176472,
+      "grad_norm": 0.93359375,
+      "learning_rate": 2.748981275911633e-06,
+      "loss": 1.4445,
+      "step": 182
+    },
+    {
+      "epoch": 1.3455882352941178,
+      "grad_norm": 1.34375,
+      "learning_rate": 2.69499357763119e-06,
+      "loss": 1.6979,
+      "step": 183
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 1.2890625,
+      "learning_rate": 2.641345009992878e-06,
+      "loss": 1.9119,
+      "step": 184
+    },
+    {
+      "epoch": 1.3602941176470589,
+      "grad_norm": 1.09375,
+      "learning_rate": 2.5880434661951826e-06,
+      "loss": 1.5965,
+      "step": 185
+    },
+    {
+      "epoch": 1.3676470588235294,
+      "grad_norm": 0.9765625,
+      "learning_rate": 2.5350967883797095e-06,
+      "loss": 1.5683,
+      "step": 186
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 1.1015625,
+      "learning_rate": 2.4825127664774008e-06,
+      "loss": 1.8934,
+      "step": 187
+    },
+    {
+      "epoch": 1.375,
+      "eval_loss": 1.9797371625900269,
+      "eval_runtime": 29.165,
+      "eval_samples_per_second": 1.509,
+      "eval_steps_per_second": 0.377,
+      "step": 187
+    },
+    {
+      "epoch": 1.3823529411764706,
+      "grad_norm": 1.0546875,
+      "learning_rate": 2.4302991370624106e-06,
+      "loss": 1.6543,
+      "step": 188
+    },
+    {
+      "epoch": 1.3897058823529411,
+      "grad_norm": 0.9921875,
+      "learning_rate": 2.3784635822138424e-06,
+      "loss": 1.6389,
+      "step": 189
+    },
+    {
+      "epoch": 1.3970588235294117,
+      "grad_norm": 1.03125,
+      "learning_rate": 2.3270137283855022e-06,
+      "loss": 1.2686,
+      "step": 190
+    },
+    {
+      "epoch": 1.4044117647058822,
+      "grad_norm": 1.1015625,
+      "learning_rate": 2.2759571452838325e-06,
+      "loss": 1.7589,
+      "step": 191
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.99609375,
+      "learning_rate": 2.2253013447541993e-06,
+      "loss": 1.2093,
+      "step": 192
+    },
+    {
+      "epoch": 1.4191176470588236,
+      "grad_norm": 1.0703125,
+      "learning_rate": 2.17505377967569e-06,
+      "loss": 1.9398,
+      "step": 193
+    },
+    {
+      "epoch": 1.4264705882352942,
+      "grad_norm": 1.3671875,
+      "learning_rate": 2.125221842864585e-06,
+      "loss": 1.7399,
+      "step": 194
+    },
+    {
+      "epoch": 1.4338235294117647,
+      "grad_norm": 1.03125,
+      "learning_rate": 2.075812865986677e-06,
+      "loss": 1.4623,
+      "step": 195
+    },
+    {
+      "epoch": 1.4411764705882353,
+      "grad_norm": 0.87109375,
+      "learning_rate": 2.0268341184785674e-06,
+      "loss": 1.303,
+      "step": 196
+    },
+    {
+      "epoch": 1.4485294117647058,
+      "grad_norm": 0.76953125,
+      "learning_rate": 1.978292806478134e-06,
+      "loss": 1.0736,
+      "step": 197
+    },
+    {
+      "epoch": 1.4558823529411764,
+      "grad_norm": 1.140625,
+      "learning_rate": 1.930196071764312e-06,
+      "loss": 1.7327,
+      "step": 198
+    },
+    {
+      "epoch": 1.4632352941176472,
+      "grad_norm": 1.296875,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 2.01,
+      "step": 199
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.8353645732225977e-06,
+      "loss": 3.1163,
+      "step": 200
+    },
+    {
+      "epoch": 1.4779411764705883,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.7886437617493206e-06,
+      "loss": 1.9975,
+      "step": 201
+    },
+    {
+      "epoch": 1.4852941176470589,
+      "grad_norm": 1.0390625,
+      "learning_rate": 1.7423954302191047e-06,
+      "loss": 1.8281,
+      "step": 202
+    },
+    {
+      "epoch": 1.4926470588235294,
+      "grad_norm": 0.98828125,
+      "learning_rate": 1.6966263830495939e-06,
+      "loss": 1.8038,
+      "step": 203
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.125,
+      "learning_rate": 1.6513433541423529e-06,
+      "loss": 1.9386,
+      "step": 204
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.9795974493026733,
+      "eval_runtime": 27.8777,
+      "eval_samples_per_second": 1.578,
+      "eval_steps_per_second": 0.395,
+      "step": 204
+    },
+    {
+      "epoch": 1.5073529411764706,
+      "grad_norm": 0.78515625,
+      "learning_rate": 1.6065530058921253e-06,
+      "loss": 1.2361,
+      "step": 205
+    },
+    {
+      "epoch": 1.5147058823529411,
+      "grad_norm": 1.0546875,
+      "learning_rate": 1.562261928206608e-06,
+      "loss": 1.6261,
+      "step": 206
+    },
+    {
+      "epoch": 1.5220588235294117,
+      "grad_norm": 1.078125,
+      "learning_rate": 1.5184766375368914e-06,
+      "loss": 1.6148,
+      "step": 207
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 1.0859375,
+      "learning_rate": 1.4752035759187106e-06,
+      "loss": 1.5313,
+      "step": 208
+    },
+    {
+      "epoch": 1.5367647058823528,
+      "grad_norm": 1.078125,
+      "learning_rate": 1.4324491100246386e-06,
+      "loss": 1.6464,
+      "step": 209
+    },
+    {
+      "epoch": 1.5441176470588234,
+      "grad_norm": 1.234375,
+      "learning_rate": 1.390219530227378e-06,
+      "loss": 1.9547,
+      "step": 210
+    },
+    {
+      "epoch": 1.5514705882352942,
+      "grad_norm": 0.95703125,
+      "learning_rate": 1.348521049674264e-06,
+      "loss": 1.6224,
+      "step": 211
+    },
+    {
+      "epoch": 1.5588235294117647,
+      "grad_norm": 1.015625,
+      "learning_rate": 1.3073598033731427e-06,
+      "loss": 1.5813,
+      "step": 212
+    },
+    {
+      "epoch": 1.5661764705882353,
+      "grad_norm": 1.09375,
+      "learning_rate": 1.2667418472897386e-06,
+      "loss": 1.7288,
+      "step": 213
+    },
+    {
+      "epoch": 1.5735294117647058,
+      "grad_norm": 1.2578125,
+      "learning_rate": 1.2266731574566536e-06,
+      "loss": 1.6956,
+      "step": 214
+    },
+    {
+      "epoch": 1.5808823529411766,
+      "grad_norm": 0.921875,
+      "learning_rate": 1.1871596290941278e-06,
+      "loss": 1.3637,
+      "step": 215
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 0.96484375,
+      "learning_rate": 1.1482070757426855e-06,
+      "loss": 1.3508,
+      "step": 216
+    },
+    {
+      "epoch": 1.5955882352941178,
+      "grad_norm": 0.98828125,
+      "learning_rate": 1.1098212284078037e-06,
+      "loss": 2.0166,
+      "step": 217
+    },
+    {
+      "epoch": 1.6029411764705883,
+      "grad_norm": 1.0390625,
+      "learning_rate": 1.07200773471672e-06,
+      "loss": 1.6187,
+      "step": 218
+    },
+    {
+      "epoch": 1.6102941176470589,
+      "grad_norm": 1.2109375,
+      "learning_rate": 1.0347721580875125e-06,
+      "loss": 1.9056,
+      "step": 219
+    },
+    {
+      "epoch": 1.6176470588235294,
+      "grad_norm": 1.75,
+      "learning_rate": 9.981199769105605e-07,
+      "loss": 2.6408,
+      "step": 220
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 1.0546875,
+      "learning_rate": 9.62056583742527e-07,
+      "loss": 1.6764,
+      "step": 221
+    },
+    {
+      "epoch": 1.625,
+      "eval_loss": 1.9795591831207275,
+      "eval_runtime": 29.1758,
+      "eval_samples_per_second": 1.508,
+      "eval_steps_per_second": 0.377,
+      "step": 221
+    },
+    {
+      "epoch": 1.6323529411764706,
+      "grad_norm": 1.2734375,
+      "learning_rate": 9.26587284512957e-07,
+      "loss": 1.6724,
+      "step": 222
+    },
+    {
+      "epoch": 1.6397058823529411,
+      "grad_norm": 1.1328125,
+      "learning_rate": 8.917172977436356e-07,
+      "loss": 1.2422,
+      "step": 223
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 1.1953125,
+      "learning_rate": 8.574517537807897e-07,
+      "loss": 1.543,
+      "step": 224
+    },
+    {
+      "epoch": 1.6544117647058822,
+      "grad_norm": 1.0703125,
+      "learning_rate": 8.237956940402758e-07,
+      "loss": 1.2271,
+      "step": 225
+    },
+    {
+      "epoch": 1.6617647058823528,
+      "grad_norm": 0.94921875,
+      "learning_rate": 7.907540702658456e-07,
+      "loss": 1.3496,
+      "step": 226
+    },
+    {
+      "epoch": 1.6691176470588234,
+      "grad_norm": 1.0234375,
+      "learning_rate": 7.583317438006094e-07,
+      "loss": 1.565,
+      "step": 227
+    },
+    {
+      "epoch": 1.6764705882352942,
+      "grad_norm": 1.40625,
+      "learning_rate": 7.265334848717931e-07,
+      "loss": 1.6159,
+      "step": 228
+    },
+    {
+      "epoch": 1.6838235294117647,
+      "grad_norm": 0.89453125,
+      "learning_rate": 6.953639718889077e-07,
+      "loss": 1.3744,
+      "step": 229
+    },
+    {
+      "epoch": 1.6911764705882353,
+      "grad_norm": 1.0625,
+      "learning_rate": 6.648277907554235e-07,
+      "loss": 1.5341,
+      "step": 230
+    },
+    {
+      "epoch": 1.6985294117647058,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.349294341940593e-07,
+      "loss": 1.7079,
+      "step": 231
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.9375,
+      "learning_rate": 6.056733010857713e-07,
+      "loss": 1.5848,
+      "step": 232
+    },
+    {
+      "epoch": 1.7132352941176472,
+      "grad_norm": 1.0859375,
+      "learning_rate": 5.770636958225617e-07,
+      "loss": 1.7697,
+      "step": 233
+    },
+    {
+      "epoch": 1.7205882352941178,
+      "grad_norm": 1.4765625,
+      "learning_rate": 5.491048276741784e-07,
+      "loss": 2.3449,
+      "step": 234
+    },
+    {
+      "epoch": 1.7279411764705883,
+      "grad_norm": 0.95703125,
+      "learning_rate": 5.218008101688172e-07,
+      "loss": 1.5532,
+      "step": 235
+    },
+    {
+      "epoch": 1.7352941176470589,
+      "grad_norm": 1.2265625,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 1.9012,
+      "step": 236
+    },
+    {
+      "epoch": 1.7426470588235294,
+      "grad_norm": 0.91796875,
+      "learning_rate": 4.6917329887506133e-07,
+      "loss": 1.6908,
+      "step": 237
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.1640625,
+      "learning_rate": 4.43857548059321e-07,
+      "loss": 1.8524,
+      "step": 238
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 1.9795602560043335,
+      "eval_runtime": 28.9797,
+      "eval_samples_per_second": 1.518,
+      "eval_steps_per_second": 0.38,
+      "step": 238
+    },
+    {
+      "epoch": 1.7573529411764706,
+      "grad_norm": 1.0234375,
+      "learning_rate": 4.192121326927073e-07,
+      "loss": 1.681,
+      "step": 239
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 1.09375,
+      "learning_rate": 3.952406788022267e-07,
+      "loss": 1.4955,
+      "step": 240
+    },
+    {
+      "epoch": 1.7720588235294117,
+      "grad_norm": 0.87109375,
+      "learning_rate": 3.71946713256382e-07,
+      "loss": 1.2862,
+      "step": 241
+    },
+    {
+      "epoch": 1.7794117647058822,
+      "grad_norm": 1.1796875,
+      "learning_rate": 3.4933366324627183e-07,
+      "loss": 1.7497,
+      "step": 242
+    },
+    {
+      "epoch": 1.7867647058823528,
+      "grad_norm": 1.078125,
+      "learning_rate": 3.274048557813553e-07,
+      "loss": 1.8767,
+      "step": 243
+    },
+    {
+      "epoch": 1.7941176470588234,
+      "grad_norm": 1.015625,
+      "learning_rate": 3.061635171999566e-07,
+      "loss": 1.6158,
+      "step": 244
+    },
+    {
+      "epoch": 1.8014705882352942,
+      "grad_norm": 1.03125,
+      "learning_rate": 2.85612772694579e-07,
+      "loss": 1.9836,
+      "step": 245
+    },
+    {
+      "epoch": 1.8088235294117647,
+      "grad_norm": 0.953125,
+      "learning_rate": 2.6575564585210487e-07,
+      "loss": 1.6339,
+      "step": 246
+    },
+    {
+      "epoch": 1.8161764705882353,
+      "grad_norm": 1.1640625,
+      "learning_rate": 2.4659505820893827e-07,
+      "loss": 1.9937,
+      "step": 247
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 0.9609375,
+      "learning_rate": 2.2813382882116986e-07,
+      "loss": 1.3654,
+      "step": 248
+    },
+    {
+      "epoch": 1.8308823529411766,
+      "grad_norm": 0.99609375,
+      "learning_rate": 2.1037467384981024e-07,
+      "loss": 1.7286,
+      "step": 249
+    },
+    {
+      "epoch": 1.8382352941176472,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.933202061611722e-07,
+      "loss": 1.6418,
+      "step": 250
+    },
+    {
+      "epoch": 1.8455882352941178,
+      "grad_norm": 0.94921875,
+      "learning_rate": 1.769729349424415e-07,
+      "loss": 1.8501,
+      "step": 251
+    },
+    {
+      "epoch": 1.8529411764705883,
+      "grad_norm": 1.15625,
+      "learning_rate": 1.6133526533250566e-07,
+      "loss": 1.876,
+      "step": 252
+    },
+    {
+      "epoch": 1.8602941176470589,
+      "grad_norm": 0.9921875,
+      "learning_rate": 1.4640949806809523e-07,
+      "loss": 1.6815,
+      "step": 253
+    },
+    {
+      "epoch": 1.8676470588235294,
+      "grad_norm": 1.1953125,
+      "learning_rate": 1.3219782914527633e-07,
+      "loss": 2.1211,
+      "step": 254
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.1171875,
+      "learning_rate": 1.1870234949636072e-07,
+      "loss": 1.661,
+      "step": 255
+    },
+    {
+      "epoch": 1.875,
+      "eval_loss": 1.979546308517456,
+      "eval_runtime": 28.9374,
+      "eval_samples_per_second": 1.521,
+      "eval_steps_per_second": 0.38,
+      "step": 255
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.0592504468227127e-07,
+      "loss": 1.8337,
+      "step": 256
+    },
+    {
+      "epoch": 1.8897058823529411,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.386779460041018e-08,
+      "loss": 1.7393,
+      "step": 257
+    },
+    {
+      "epoch": 1.8970588235294117,
+      "grad_norm": 1.1015625,
+      "learning_rate": 8.253237320807461e-08,
+      "loss": 1.4356,
+      "step": 258
+    },
+    {
+      "epoch": 1.9044117647058822,
+      "grad_norm": 1.328125,
+      "learning_rate": 7.192044826145772e-08,
+      "loss": 1.8109,
+      "step": 259
+    },
+    {
+      "epoch": 1.9117647058823528,
+      "grad_norm": 1.234375,
+      "learning_rate": 6.203358107027491e-08,
+      "loss": 1.9221,
+      "step": 260
+    },
+    {
+      "epoch": 1.9191176470588234,
+      "grad_norm": 1.1796875,
+      "learning_rate": 5.2873226268052026e-08,
+      "loss": 1.611,
+      "step": 261
+    },
+    {
+      "epoch": 1.9264705882352942,
+      "grad_norm": 1.2421875,
+      "learning_rate": 4.444073159810769e-08,
+      "loss": 1.7129,
+      "step": 262
+    },
+    {
+      "epoch": 1.9338235294117647,
+      "grad_norm": 1.046875,
+      "learning_rate": 3.673733771526466e-08,
+      "loss": 1.3399,
+      "step": 263
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.88671875,
+      "learning_rate": 2.976417800331144e-08,
+      "loss": 1.1532,
+      "step": 264
+    },
+    {
+      "epoch": 1.9485294117647058,
+      "grad_norm": 1.2265625,
+      "learning_rate": 2.352227840825394e-08,
+      "loss": 2.0323,
+      "step": 265
+    },
+    {
+      "epoch": 1.9558823529411766,
+      "grad_norm": 1.0234375,
+      "learning_rate": 1.8012557287367394e-08,
+      "loss": 1.7834,
+      "step": 266
+    },
+    {
+      "epoch": 1.9632352941176472,
+      "grad_norm": 1.0859375,
+      "learning_rate": 1.3235825274081626e-08,
+      "loss": 1.6388,
+      "step": 267
+    },
+    {
+      "epoch": 1.9705882352941178,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.192785158713691e-09,
+      "loss": 1.8893,
+      "step": 268
+    },
+    {
+      "epoch": 1.9779411764705883,
+      "grad_norm": 1.0234375,
+      "learning_rate": 5.884031785068356e-09,
+      "loss": 1.4061,
+      "step": 269
+    },
+    {
+      "epoch": 1.9852941176470589,
+      "grad_norm": 1.2578125,
+      "learning_rate": 3.3100519629203353e-09,
+      "loss": 1.8636,
+      "step": 270
+    },
+    {
+      "epoch": 1.9926470588235294,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.471224396389359e-09,
+      "loss": 0.9198,
+      "step": 271
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3359375,
+      "learning_rate": 3.678196282252966e-10,
+      "loss": 1.8697,
+      "step": 272
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.979569435119629,
+      "eval_runtime": 27.7469,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.396,
+      "step": 272
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 272,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 136,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.618953940445954e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-272/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982309b232617b9bfc0df4d297ea42402a906069dd07d503a1b422c96356e1aa
+size 10872