Upload folder using huggingface_hub

added_tokens.json

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

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.2"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9b01feff6928da730d72033888fdd733face20ce5ef2fa1f7b80284601eec0
+size 4972454376

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a223b7cee445b96bf92a77caa62e6312f7711237d534010669ca83b0b746c4
+size 4832048608

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7989dcc2b2f143da6ba1f3cd46b038c8f0094a0a3aaa22c36c16e370d5ec03b7
+size 4832048656

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f91effc8c0e16240e1b532a4718fc5bb00e3e61126e247df8c20111c565e4d
+size 4999855528

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a02d73e2d402d5ddbd5d3886635a760c4108e8fe21e941409e33daa41862dd8
+size 4832048672

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3af8fc1f48c8da50937f388484804491e27426c58eeffb0e86b05eb1693d213
+size 4832048672

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b806a3ef4b19f919f7dba454efe6b90b2016852bbc4c9b89cb90c6fff61912
+size 3462482728

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 32762941440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,1811 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 62,
+  "global_step": 248,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008064516129032258,
+      "grad_norm": 0.5517980456352234,
+      "learning_rate": 0.0,
+      "loss": 0.6082,
+      "step": 1
+    },
+    {
+      "epoch": 0.016129032258064516,
+      "grad_norm": 0.6390311121940613,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 0.6493,
+      "step": 2
+    },
+    {
+      "epoch": 0.024193548387096774,
+      "grad_norm": 0.5991142392158508,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 0.632,
+      "step": 3
+    },
+    {
+      "epoch": 0.03225806451612903,
+      "grad_norm": 0.8278654217720032,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 0.6719,
+      "step": 4
+    },
+    {
+      "epoch": 0.04032258064516129,
+      "grad_norm": 0.6159102916717529,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.6637,
+      "step": 5
+    },
+    {
+      "epoch": 0.04838709677419355,
+      "grad_norm": 0.6641815304756165,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.662,
+      "step": 6
+    },
+    {
+      "epoch": 0.056451612903225805,
+      "grad_norm": 0.5588157773017883,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.6753,
+      "step": 7
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 0.57755446434021,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 0.659,
+      "step": 8
+    },
+    {
+      "epoch": 0.07258064516129033,
+      "grad_norm": 0.6825008392333984,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.6533,
+      "step": 9
+    },
+    {
+      "epoch": 0.08064516129032258,
+      "grad_norm": 0.7022811770439148,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 0.6344,
+      "step": 10
+    },
+    {
+      "epoch": 0.08870967741935484,
+      "grad_norm": 0.7072175741195679,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.6597,
+      "step": 11
+    },
+    {
+      "epoch": 0.0967741935483871,
+      "grad_norm": 0.7066731452941895,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 0.6266,
+      "step": 12
+    },
+    {
+      "epoch": 0.10483870967741936,
+      "grad_norm": 0.6061089038848877,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.6296,
+      "step": 13
+    },
+    {
+      "epoch": 0.11290322580645161,
+      "grad_norm": 0.6052113175392151,
+      "learning_rate": 1e-05,
+      "loss": 0.6517,
+      "step": 14
+    },
+    {
+      "epoch": 0.12096774193548387,
+      "grad_norm": 0.6143882274627686,
+      "learning_rate": 9.999553216051892e-06,
+      "loss": 0.6206,
+      "step": 15
+    },
+    {
+      "epoch": 0.12903225806451613,
+      "grad_norm": 0.6051825284957886,
+      "learning_rate": 9.99821294405392e-06,
+      "loss": 0.6079,
+      "step": 16
+    },
+    {
+      "epoch": 0.13709677419354838,
+      "grad_norm": 0.6209076642990112,
+      "learning_rate": 9.995979423530893e-06,
+      "loss": 0.61,
+      "step": 17
+    },
+    {
+      "epoch": 0.14516129032258066,
+      "grad_norm": 0.5994704365730286,
+      "learning_rate": 9.992853053643257e-06,
+      "loss": 0.6067,
+      "step": 18
+    },
+    {
+      "epoch": 0.1532258064516129,
+      "grad_norm": 0.6294693350791931,
+      "learning_rate": 9.988834393115768e-06,
+      "loss": 0.6015,
+      "step": 19
+    },
+    {
+      "epoch": 0.16129032258064516,
+      "grad_norm": 0.6730523109436035,
+      "learning_rate": 9.983924160137627e-06,
+      "loss": 0.6268,
+      "step": 20
+    },
+    {
+      "epoch": 0.1693548387096774,
+      "grad_norm": 0.8425688147544861,
+      "learning_rate": 9.978123232234147e-06,
+      "loss": 0.6132,
+      "step": 21
+    },
+    {
+      "epoch": 0.1774193548387097,
+      "grad_norm": 0.6424095034599304,
+      "learning_rate": 9.971432646109919e-06,
+      "loss": 0.5772,
+      "step": 22
+    },
+    {
+      "epoch": 0.18548387096774194,
+      "grad_norm": 0.6459460854530334,
+      "learning_rate": 9.963853597463533e-06,
+      "loss": 0.6112,
+      "step": 23
+    },
+    {
+      "epoch": 0.1935483870967742,
+      "grad_norm": 0.6047711968421936,
+      "learning_rate": 9.955387440773902e-06,
+      "loss": 0.6247,
+      "step": 24
+    },
+    {
+      "epoch": 0.20161290322580644,
+      "grad_norm": 0.620063304901123,
+      "learning_rate": 9.946035689058189e-06,
+      "loss": 0.6092,
+      "step": 25
+    },
+    {
+      "epoch": 0.20967741935483872,
+      "grad_norm": 0.6238256096839905,
+      "learning_rate": 9.935800013601415e-06,
+      "loss": 0.6189,
+      "step": 26
+    },
+    {
+      "epoch": 0.21774193548387097,
+      "grad_norm": 0.6274495720863342,
+      "learning_rate": 9.92468224365778e-06,
+      "loss": 0.6163,
+      "step": 27
+    },
+    {
+      "epoch": 0.22580645161290322,
+      "grad_norm": 0.626072108745575,
+      "learning_rate": 9.91268436612374e-06,
+      "loss": 0.6279,
+      "step": 28
+    },
+    {
+      "epoch": 0.23387096774193547,
+      "grad_norm": 0.6366428136825562,
+      "learning_rate": 9.899808525182935e-06,
+      "loss": 0.5975,
+      "step": 29
+    },
+    {
+      "epoch": 0.24193548387096775,
+      "grad_norm": 0.6221742033958435,
+      "learning_rate": 9.886057021922984e-06,
+      "loss": 0.6157,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.6204385757446289,
+      "learning_rate": 9.871432313924255e-06,
+      "loss": 0.5863,
+      "step": 31
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.6196408271789551,
+      "learning_rate": 9.85593701482066e-06,
+      "loss": 0.6448,
+      "step": 32
+    },
+    {
+      "epoch": 0.2661290322580645,
+      "grad_norm": 0.6383486986160278,
+      "learning_rate": 9.839573893832564e-06,
+      "loss": 0.6007,
+      "step": 33
+    },
+    {
+      "epoch": 0.27419354838709675,
+      "grad_norm": 0.7581177949905396,
+      "learning_rate": 9.822345875271884e-06,
+      "loss": 0.6094,
+      "step": 34
+    },
+    {
+      "epoch": 0.28225806451612906,
+      "grad_norm": 0.6488061547279358,
+      "learning_rate": 9.804256038019482e-06,
+      "loss": 0.6151,
+      "step": 35
+    },
+    {
+      "epoch": 0.2903225806451613,
+      "grad_norm": 0.7306289672851562,
+      "learning_rate": 9.785307614974922e-06,
+      "loss": 0.6023,
+      "step": 36
+    },
+    {
+      "epoch": 0.29838709677419356,
+      "grad_norm": 0.638602077960968,
+      "learning_rate": 9.765503992478704e-06,
+      "loss": 0.6147,
+      "step": 37
+    },
+    {
+      "epoch": 0.3064516129032258,
+      "grad_norm": 0.6609564423561096,
+      "learning_rate": 9.74484870970709e-06,
+      "loss": 0.5955,
+      "step": 38
+    },
+    {
+      "epoch": 0.31451612903225806,
+      "grad_norm": 0.5976406931877136,
+      "learning_rate": 9.723345458039595e-06,
+      "loss": 0.6386,
+      "step": 39
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.6053065061569214,
+      "learning_rate": 9.700998080399287e-06,
+      "loss": 0.6287,
+      "step": 40
+    },
+    {
+      "epoch": 0.33064516129032256,
+      "grad_norm": 0.6144651174545288,
+      "learning_rate": 9.677810570566011e-06,
+      "loss": 0.6216,
+      "step": 41
+    },
+    {
+      "epoch": 0.3387096774193548,
+      "grad_norm": 0.6920744180679321,
+      "learning_rate": 9.653787072462644e-06,
+      "loss": 0.6105,
+      "step": 42
+    },
+    {
+      "epoch": 0.3467741935483871,
+      "grad_norm": 0.6383086442947388,
+      "learning_rate": 9.628931879414519e-06,
+      "loss": 0.5992,
+      "step": 43
+    },
+    {
+      "epoch": 0.3548387096774194,
+      "grad_norm": 0.6331540942192078,
+      "learning_rate": 9.603249433382145e-06,
+      "loss": 0.6204,
+      "step": 44
+    },
+    {
+      "epoch": 0.3629032258064516,
+      "grad_norm": 0.5912304520606995,
+      "learning_rate": 9.57674432416738e-06,
+      "loss": 0.6228,
+      "step": 45
+    },
+    {
+      "epoch": 0.3709677419354839,
+      "grad_norm": 0.6208971738815308,
+      "learning_rate": 9.549421288593157e-06,
+      "loss": 0.6186,
+      "step": 46
+    },
+    {
+      "epoch": 0.3790322580645161,
+      "grad_norm": 0.6380787491798401,
+      "learning_rate": 9.521285209656964e-06,
+      "loss": 0.6102,
+      "step": 47
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 0.6055821180343628,
+      "learning_rate": 9.492341115658167e-06,
+      "loss": 0.635,
+      "step": 48
+    },
+    {
+      "epoch": 0.3951612903225806,
+      "grad_norm": 0.6085134148597717,
+      "learning_rate": 9.462594179299408e-06,
+      "loss": 0.5884,
+      "step": 49
+    },
+    {
+      "epoch": 0.4032258064516129,
+      "grad_norm": 0.6542190909385681,
+      "learning_rate": 9.432049716762151e-06,
+      "loss": 0.596,
+      "step": 50
+    },
+    {
+      "epoch": 0.4112903225806452,
+      "grad_norm": 0.6214224100112915,
+      "learning_rate": 9.400713186756625e-06,
+      "loss": 0.607,
+      "step": 51
+    },
+    {
+      "epoch": 0.41935483870967744,
+      "grad_norm": 0.6380740404129028,
+      "learning_rate": 9.368590189546268e-06,
+      "loss": 0.6075,
+      "step": 52
+    },
+    {
+      "epoch": 0.4274193548387097,
+      "grad_norm": 0.6142477989196777,
+      "learning_rate": 9.335686465946888e-06,
+      "loss": 0.6312,
+      "step": 53
+    },
+    {
+      "epoch": 0.43548387096774194,
+      "grad_norm": 0.5984505414962769,
+      "learning_rate": 9.302007896300697e-06,
+      "loss": 0.5824,
+      "step": 54
+    },
+    {
+      "epoch": 0.4435483870967742,
+      "grad_norm": 0.582324743270874,
+      "learning_rate": 9.267560499425425e-06,
+      "loss": 0.6131,
+      "step": 55
+    },
+    {
+      "epoch": 0.45161290322580644,
+      "grad_norm": 0.6623991131782532,
+      "learning_rate": 9.232350431538656e-06,
+      "loss": 0.603,
+      "step": 56
+    },
+    {
+      "epoch": 0.4596774193548387,
+      "grad_norm": 0.6425934433937073,
+      "learning_rate": 9.196383985157657e-06,
+      "loss": 0.5863,
+      "step": 57
+    },
+    {
+      "epoch": 0.46774193548387094,
+      "grad_norm": 0.5947446823120117,
+      "learning_rate": 9.159667587974786e-06,
+      "loss": 0.6035,
+      "step": 58
+    },
+    {
+      "epoch": 0.47580645161290325,
+      "grad_norm": 0.6562256813049316,
+      "learning_rate": 9.122207801708802e-06,
+      "loss": 0.6313,
+      "step": 59
+    },
+    {
+      "epoch": 0.4838709677419355,
+      "grad_norm": 0.6266179084777832,
+      "learning_rate": 9.08401132093219e-06,
+      "loss": 0.5946,
+      "step": 60
+    },
+    {
+      "epoch": 0.49193548387096775,
+      "grad_norm": 0.6250705122947693,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.6302,
+      "step": 61
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.6279906034469604,
+      "learning_rate": 9.005435711203619e-06,
+      "loss": 0.6082,
+      "step": 62
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.7696727514266968,
+      "eval_runtime": 9.3663,
+      "eval_samples_per_second": 24.983,
+      "eval_steps_per_second": 1.068,
+      "step": 62
+    },
+    {
+      "checkpoint_runtime": 64.4057
+    },
+    {
+      "epoch": 0.5080645161290323,
+      "grad_norm": 0.7122681736946106,
+      "learning_rate": 8.965070624780117e-06,
+      "loss": 0.6037,
+      "step": 63
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.5835853219032288,
+      "learning_rate": 8.923996926393306e-06,
+      "loss": 0.6168,
+      "step": 64
+    },
+    {
+      "epoch": 0.5241935483870968,
+      "grad_norm": 0.6679734587669373,
+      "learning_rate": 8.882221956470838e-06,
+      "loss": 0.6323,
+      "step": 65
+    },
+    {
+      "epoch": 0.532258064516129,
+      "grad_norm": 0.6001929044723511,
+      "learning_rate": 8.839753180767108e-06,
+      "loss": 0.597,
+      "step": 66
+    },
+    {
+      "epoch": 0.5403225806451613,
+      "grad_norm": 0.5785935521125793,
+      "learning_rate": 8.79659818902903e-06,
+      "loss": 0.5914,
+      "step": 67
+    },
+    {
+      "epoch": 0.5483870967741935,
+      "grad_norm": 0.6068294644355774,
+      "learning_rate": 8.75276469363964e-06,
+      "loss": 0.6113,
+      "step": 68
+    },
+    {
+      "epoch": 0.5564516129032258,
+      "grad_norm": 0.6160874962806702,
+      "learning_rate": 8.708260528239788e-06,
+      "loss": 0.5993,
+      "step": 69
+    },
+    {
+      "epoch": 0.5645161290322581,
+      "grad_norm": 0.6260392665863037,
+      "learning_rate": 8.663093646328166e-06,
+      "loss": 0.6012,
+      "step": 70
+    },
+    {
+      "epoch": 0.5725806451612904,
+      "grad_norm": 0.5908513069152832,
+      "learning_rate": 8.617272119839903e-06,
+      "loss": 0.623,
+      "step": 71
+    },
+    {
+      "epoch": 0.5806451612903226,
+      "grad_norm": 0.6037243604660034,
+      "learning_rate": 8.570804137704005e-06,
+      "loss": 0.5978,
+      "step": 72
+    },
+    {
+      "epoch": 0.5887096774193549,
+      "grad_norm": 0.6131466627120972,
+      "learning_rate": 8.523698004379878e-06,
+      "loss": 0.6068,
+      "step": 73
+    },
+    {
+      "epoch": 0.5967741935483871,
+      "grad_norm": 0.5952907800674438,
+      "learning_rate": 8.475962138373212e-06,
+      "loss": 0.6054,
+      "step": 74
+    },
+    {
+      "epoch": 0.6048387096774194,
+      "grad_norm": 0.5911087393760681,
+      "learning_rate": 8.427605070731482e-06,
+      "loss": 0.6141,
+      "step": 75
+    },
+    {
+      "epoch": 0.6129032258064516,
+      "grad_norm": 0.6031507849693298,
+      "learning_rate": 8.378635443519327e-06,
+      "loss": 0.6077,
+      "step": 76
+    },
+    {
+      "epoch": 0.6209677419354839,
+      "grad_norm": 0.5819121599197388,
+      "learning_rate": 8.3290620082741e-06,
+      "loss": 0.5874,
+      "step": 77
+    },
+    {
+      "epoch": 0.6290322580645161,
+      "grad_norm": 0.6011428833007812,
+      "learning_rate": 8.278893624441849e-06,
+      "loss": 0.6011,
+      "step": 78
+    },
+    {
+      "epoch": 0.6370967741935484,
+      "grad_norm": 0.6003097295761108,
+      "learning_rate": 8.228139257794012e-06,
+      "loss": 0.6033,
+      "step": 79
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.6365466713905334,
+      "learning_rate": 8.17680797882512e-06,
+      "loss": 0.6218,
+      "step": 80
+    },
+    {
+      "epoch": 0.6532258064516129,
+      "grad_norm": 0.614172637462616,
+      "learning_rate": 8.124908961131759e-06,
+      "loss": 0.6243,
+      "step": 81
+    },
+    {
+      "epoch": 0.6612903225806451,
+      "grad_norm": 0.6372578144073486,
+      "learning_rate": 8.072451479773143e-06,
+      "loss": 0.6113,
+      "step": 82
+    },
+    {
+      "epoch": 0.6693548387096774,
+      "grad_norm": 0.675305962562561,
+      "learning_rate": 8.019444909613524e-06,
+      "loss": 0.6241,
+      "step": 83
+    },
+    {
+      "epoch": 0.6774193548387096,
+      "grad_norm": 0.6111373901367188,
+      "learning_rate": 7.965898723646777e-06,
+      "loss": 0.6217,
+      "step": 84
+    },
+    {
+      "epoch": 0.6854838709677419,
+      "grad_norm": 0.6612839102745056,
+      "learning_rate": 7.911822491303453e-06,
+      "loss": 0.6068,
+      "step": 85
+    },
+    {
+      "epoch": 0.6935483870967742,
+      "grad_norm": 0.6315973401069641,
+      "learning_rate": 7.857225876740585e-06,
+      "loss": 0.612,
+      "step": 86
+    },
+    {
+      "epoch": 0.7016129032258065,
+      "grad_norm": 0.6035977602005005,
+      "learning_rate": 7.802118637114575e-06,
+      "loss": 0.6125,
+      "step": 87
+    },
+    {
+      "epoch": 0.7096774193548387,
+      "grad_norm": 0.6258041858673096,
+      "learning_rate": 7.74651062083746e-06,
+      "loss": 0.6161,
+      "step": 88
+    },
+    {
+      "epoch": 0.717741935483871,
+      "grad_norm": 0.60235595703125,
+      "learning_rate": 7.690411765816864e-06,
+      "loss": 0.6262,
+      "step": 89
+    },
+    {
+      "epoch": 0.7258064516129032,
+      "grad_norm": 0.6624128818511963,
+      "learning_rate": 7.633832097679959e-06,
+      "loss": 0.5987,
+      "step": 90
+    },
+    {
+      "epoch": 0.7338709677419355,
+      "grad_norm": 0.6165940761566162,
+      "learning_rate": 7.5767817279817505e-06,
+      "loss": 0.6244,
+      "step": 91
+    },
+    {
+      "epoch": 0.7419354838709677,
+      "grad_norm": 0.6158416867256165,
+      "learning_rate": 7.519270852398002e-06,
+      "loss": 0.6203,
+      "step": 92
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.7253459692001343,
+      "learning_rate": 7.461309748903138e-06,
+      "loss": 0.6093,
+      "step": 93
+    },
+    {
+      "epoch": 0.7580645161290323,
+      "grad_norm": 0.6656257510185242,
+      "learning_rate": 7.402908775933419e-06,
+      "loss": 0.6055,
+      "step": 94
+    },
+    {
+      "epoch": 0.7661290322580645,
+      "grad_norm": 0.6135536432266235,
+      "learning_rate": 7.344078370535757e-06,
+      "loss": 0.5945,
+      "step": 95
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.6283413767814636,
+      "learning_rate": 7.284829046502467e-06,
+      "loss": 0.6121,
+      "step": 96
+    },
+    {
+      "epoch": 0.782258064516129,
+      "grad_norm": 0.6993898153305054,
+      "learning_rate": 7.225171392492316e-06,
+      "loss": 0.5969,
+      "step": 97
+    },
+    {
+      "epoch": 0.7903225806451613,
+      "grad_norm": 0.5875230431556702,
+      "learning_rate": 7.165116070138183e-06,
+      "loss": 0.5811,
+      "step": 98
+    },
+    {
+      "epoch": 0.7983870967741935,
+      "grad_norm": 0.5970051884651184,
+      "learning_rate": 7.104673812141676e-06,
+      "loss": 0.612,
+      "step": 99
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 0.6021542549133301,
+      "learning_rate": 7.04385542035506e-06,
+      "loss": 0.6125,
+      "step": 100
+    },
+    {
+      "epoch": 0.8145161290322581,
+      "grad_norm": 0.7024378180503845,
+      "learning_rate": 6.982671763850814e-06,
+      "loss": 0.6232,
+      "step": 101
+    },
+    {
+      "epoch": 0.8225806451612904,
+      "grad_norm": 0.6071297526359558,
+      "learning_rate": 6.921133776979186e-06,
+      "loss": 0.6085,
+      "step": 102
+    },
+    {
+      "epoch": 0.8306451612903226,
+      "grad_norm": 0.5934585332870483,
+      "learning_rate": 6.859252457414067e-06,
+      "loss": 0.6064,
+      "step": 103
+    },
+    {
+      "epoch": 0.8387096774193549,
+      "grad_norm": 0.5972087383270264,
+      "learning_rate": 6.797038864187564e-06,
+      "loss": 0.6153,
+      "step": 104
+    },
+    {
+      "epoch": 0.8467741935483871,
+      "grad_norm": 0.5931298136711121,
+      "learning_rate": 6.7345041157136035e-06,
+      "loss": 0.6394,
+      "step": 105
+    },
+    {
+      "epoch": 0.8548387096774194,
+      "grad_norm": 0.6027710437774658,
+      "learning_rate": 6.67165938780091e-06,
+      "loss": 0.6287,
+      "step": 106
+    },
+    {
+      "epoch": 0.8629032258064516,
+      "grad_norm": 0.616108238697052,
+      "learning_rate": 6.608515911655744e-06,
+      "loss": 0.5961,
+      "step": 107
+    },
+    {
+      "epoch": 0.8709677419354839,
+      "grad_norm": 0.5857760310173035,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.5986,
+      "step": 108
+    },
+    {
+      "epoch": 0.8790322580645161,
+      "grad_norm": 0.5985046029090881,
+      "learning_rate": 6.481377904428171e-06,
+      "loss": 0.6192,
+      "step": 109
+    },
+    {
+      "epoch": 0.8870967741935484,
+      "grad_norm": 0.6490822434425354,
+      "learning_rate": 6.41740609463409e-06,
+      "loss": 0.5938,
+      "step": 110
+    },
+    {
+      "epoch": 0.8951612903225806,
+      "grad_norm": 0.5827641487121582,
+      "learning_rate": 6.353180975123595e-06,
+      "loss": 0.6006,
+      "step": 111
+    },
+    {
+      "epoch": 0.9032258064516129,
+      "grad_norm": 0.6040430665016174,
+      "learning_rate": 6.2887140237976714e-06,
+      "loss": 0.6576,
+      "step": 112
+    },
+    {
+      "epoch": 0.9112903225806451,
+      "grad_norm": 0.6271264553070068,
+      "learning_rate": 6.224016761775933e-06,
+      "loss": 0.6286,
+      "step": 113
+    },
+    {
+      "epoch": 0.9193548387096774,
+      "grad_norm": 0.7163254618644714,
+      "learning_rate": 6.1591007513376425e-06,
+      "loss": 0.625,
+      "step": 114
+    },
+    {
+      "epoch": 0.9274193548387096,
+      "grad_norm": 0.6243981719017029,
+      "learning_rate": 6.093977593855376e-06,
+      "loss": 0.6291,
+      "step": 115
+    },
+    {
+      "epoch": 0.9354838709677419,
+      "grad_norm": 0.6018924117088318,
+      "learning_rate": 6.028658927721698e-06,
+      "loss": 0.6112,
+      "step": 116
+    },
+    {
+      "epoch": 0.9435483870967742,
+      "grad_norm": 0.6228638291358948,
+      "learning_rate": 5.963156426269228e-06,
+      "loss": 0.6086,
+      "step": 117
+    },
+    {
+      "epoch": 0.9516129032258065,
+      "grad_norm": 0.6100144982337952,
+      "learning_rate": 5.897481795684447e-06,
+      "loss": 0.6395,
+      "step": 118
+    },
+    {
+      "epoch": 0.9596774193548387,
+      "grad_norm": 0.5865968465805054,
+      "learning_rate": 5.831646772915651e-06,
+      "loss": 0.6323,
+      "step": 119
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.6958960890769958,
+      "learning_rate": 5.765663123575401e-06,
+      "loss": 0.6163,
+      "step": 120
+    },
+    {
+      "epoch": 0.9758064516129032,
+      "grad_norm": 0.5920268297195435,
+      "learning_rate": 5.699542639837844e-06,
+      "loss": 0.6121,
+      "step": 121
+    },
+    {
+      "epoch": 0.9838709677419355,
+      "grad_norm": 0.6195198893547058,
+      "learning_rate": 5.633297138331285e-06,
+      "loss": 0.6239,
+      "step": 122
+    },
+    {
+      "epoch": 0.9919354838709677,
+      "grad_norm": 0.6433055400848389,
+      "learning_rate": 5.566938458026411e-06,
+      "loss": 0.6243,
+      "step": 123
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9132500290870667,
+      "learning_rate": 5.500478458120493e-06,
+      "loss": 0.5416,
+      "step": 124
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7586155533790588,
+      "eval_runtime": 9.3994,
+      "eval_samples_per_second": 24.895,
+      "eval_steps_per_second": 1.064,
+      "step": 124
+    },
+    {
+      "checkpoint_runtime": 62.6926
+    },
+    {
+      "epoch": 1.0080645161290323,
+      "grad_norm": 1.2273164987564087,
+      "learning_rate": 5.433929015917988e-06,
+      "loss": 0.4912,
+      "step": 125
+    },
+    {
+      "epoch": 1.0161290322580645,
+      "grad_norm": 0.8512174487113953,
+      "learning_rate": 5.367302024707911e-06,
+      "loss": 0.5181,
+      "step": 126
+    },
+    {
+      "epoch": 1.0241935483870968,
+      "grad_norm": 0.7072561383247375,
+      "learning_rate": 5.300609391638336e-06,
+      "loss": 0.4996,
+      "step": 127
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 0.6743839383125305,
+      "learning_rate": 5.233863035588427e-06,
+      "loss": 0.5049,
+      "step": 128
+    },
+    {
+      "epoch": 1.0403225806451613,
+      "grad_norm": 0.6355977654457092,
+      "learning_rate": 5.1670748850383734e-06,
+      "loss": 0.4736,
+      "step": 129
+    },
+    {
+      "epoch": 1.0483870967741935,
+      "grad_norm": 0.7739989161491394,
+      "learning_rate": 5.1002568759376134e-06,
+      "loss": 0.5077,
+      "step": 130
+    },
+    {
+      "epoch": 1.0564516129032258,
+      "grad_norm": 0.9043926000595093,
+      "learning_rate": 5.033420949571712e-06,
+      "loss": 0.5143,
+      "step": 131
+    },
+    {
+      "epoch": 1.064516129032258,
+      "grad_norm": 0.9883599877357483,
+      "learning_rate": 4.96657905042829e-06,
+      "loss": 0.4991,
+      "step": 132
+    },
+    {
+      "epoch": 1.0725806451612903,
+      "grad_norm": 0.8478935956954956,
+      "learning_rate": 4.899743124062387e-06,
+      "loss": 0.5036,
+      "step": 133
+    },
+    {
+      "epoch": 1.0806451612903225,
+      "grad_norm": 0.7680084109306335,
+      "learning_rate": 4.832925114961629e-06,
+      "loss": 0.493,
+      "step": 134
+    },
+    {
+      "epoch": 1.0887096774193548,
+      "grad_norm": 0.7357969284057617,
+      "learning_rate": 4.766136964411576e-06,
+      "loss": 0.4906,
+      "step": 135
+    },
+    {
+      "epoch": 1.096774193548387,
+      "grad_norm": 0.6527146100997925,
+      "learning_rate": 4.699390608361665e-06,
+      "loss": 0.4976,
+      "step": 136
+    },
+    {
+      "epoch": 1.1048387096774193,
+      "grad_norm": 0.7036378383636475,
+      "learning_rate": 4.6326979752920905e-06,
+      "loss": 0.4821,
+      "step": 137
+    },
+    {
+      "epoch": 1.1129032258064515,
+      "grad_norm": 0.7150796055793762,
+      "learning_rate": 4.566070984082013e-06,
+      "loss": 0.5033,
+      "step": 138
+    },
+    {
+      "epoch": 1.120967741935484,
+      "grad_norm": 1.9774234294891357,
+      "learning_rate": 4.499521541879508e-06,
+      "loss": 0.4855,
+      "step": 139
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 0.7293978929519653,
+      "learning_rate": 4.433061541973591e-06,
+      "loss": 0.4821,
+      "step": 140
+    },
+    {
+      "epoch": 1.1370967741935485,
+      "grad_norm": 0.7031348943710327,
+      "learning_rate": 4.366702861668717e-06,
+      "loss": 0.4914,
+      "step": 141
+    },
+    {
+      "epoch": 1.1451612903225807,
+      "grad_norm": 0.9272693991661072,
+      "learning_rate": 4.300457360162158e-06,
+      "loss": 0.4937,
+      "step": 142
+    },
+    {
+      "epoch": 1.153225806451613,
+      "grad_norm": 0.6710570454597473,
+      "learning_rate": 4.2343368764246005e-06,
+      "loss": 0.4857,
+      "step": 143
+    },
+    {
+      "epoch": 1.1612903225806452,
+      "grad_norm": 0.6494666934013367,
+      "learning_rate": 4.1683532270843505e-06,
+      "loss": 0.4897,
+      "step": 144
+    },
+    {
+      "epoch": 1.1693548387096775,
+      "grad_norm": 0.6740890741348267,
+      "learning_rate": 4.102518204315555e-06,
+      "loss": 0.5068,
+      "step": 145
+    },
+    {
+      "epoch": 1.1774193548387097,
+      "grad_norm": 0.6629785895347595,
+      "learning_rate": 4.036843573730774e-06,
+      "loss": 0.4992,
+      "step": 146
+    },
+    {
+      "epoch": 1.185483870967742,
+      "grad_norm": 1.0301792621612549,
+      "learning_rate": 3.971341072278302e-06,
+      "loss": 0.5187,
+      "step": 147
+    },
+    {
+      "epoch": 1.1935483870967742,
+      "grad_norm": 0.6788991689682007,
+      "learning_rate": 3.906022406144625e-06,
+      "loss": 0.4991,
+      "step": 148
+    },
+    {
+      "epoch": 1.2016129032258065,
+      "grad_norm": 0.7261366248130798,
+      "learning_rate": 3.840899248662358e-06,
+      "loss": 0.5155,
+      "step": 149
+    },
+    {
+      "epoch": 1.2096774193548387,
+      "grad_norm": 0.6745786666870117,
+      "learning_rate": 3.77598323822407e-06,
+      "loss": 0.4979,
+      "step": 150
+    },
+    {
+      "epoch": 1.217741935483871,
+      "grad_norm": 0.643515944480896,
+      "learning_rate": 3.711285976202331e-06,
+      "loss": 0.5064,
+      "step": 151
+    },
+    {
+      "epoch": 1.2258064516129032,
+      "grad_norm": 0.6859997510910034,
+      "learning_rate": 3.6468190248764063e-06,
+      "loss": 0.5076,
+      "step": 152
+    },
+    {
+      "epoch": 1.2338709677419355,
+      "grad_norm": 0.6736048460006714,
+      "learning_rate": 3.582593905365912e-06,
+      "loss": 0.4812,
+      "step": 153
+    },
+    {
+      "epoch": 1.2419354838709677,
+      "grad_norm": 0.6538953185081482,
+      "learning_rate": 3.518622095571831e-06,
+      "loss": 0.5014,
+      "step": 154
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.6264058351516724,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.4934,
+      "step": 155
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "grad_norm": 0.6770332455635071,
+      "learning_rate": 3.391484088344257e-06,
+      "loss": 0.4973,
+      "step": 156
+    },
+    {
+      "epoch": 1.2661290322580645,
+      "grad_norm": 0.7549557089805603,
+      "learning_rate": 3.328340612199091e-06,
+      "loss": 0.5133,
+      "step": 157
+    },
+    {
+      "epoch": 1.2741935483870968,
+      "grad_norm": 0.6272417902946472,
+      "learning_rate": 3.265495884286397e-06,
+      "loss": 0.4789,
+      "step": 158
+    },
+    {
+      "epoch": 1.282258064516129,
+      "grad_norm": 0.9803722500801086,
+      "learning_rate": 3.202961135812437e-06,
+      "loss": 0.4906,
+      "step": 159
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.6124163866043091,
+      "learning_rate": 3.1407475425859348e-06,
+      "loss": 0.5033,
+      "step": 160
+    },
+    {
+      "epoch": 1.2983870967741935,
+      "grad_norm": 0.7405635714530945,
+      "learning_rate": 3.078866223020815e-06,
+      "loss": 0.5072,
+      "step": 161
+    },
+    {
+      "epoch": 1.3064516129032258,
+      "grad_norm": 0.689418613910675,
+      "learning_rate": 3.017328236149187e-06,
+      "loss": 0.467,
+      "step": 162
+    },
+    {
+      "epoch": 1.314516129032258,
+      "grad_norm": 0.6370119452476501,
+      "learning_rate": 2.956144579644942e-06,
+      "loss": 0.5046,
+      "step": 163
+    },
+    {
+      "epoch": 1.3225806451612903,
+      "grad_norm": 0.6629266142845154,
+      "learning_rate": 2.8953261878583263e-06,
+      "loss": 0.5168,
+      "step": 164
+    },
+    {
+      "epoch": 1.3306451612903225,
+      "grad_norm": 0.6177526712417603,
+      "learning_rate": 2.834883929861818e-06,
+      "loss": 0.4943,
+      "step": 165
+    },
+    {
+      "epoch": 1.3387096774193548,
+      "grad_norm": 0.6319835186004639,
+      "learning_rate": 2.7748286075076834e-06,
+      "loss": 0.5137,
+      "step": 166
+    },
+    {
+      "epoch": 1.346774193548387,
+      "grad_norm": 0.6541087031364441,
+      "learning_rate": 2.715170953497532e-06,
+      "loss": 0.4956,
+      "step": 167
+    },
+    {
+      "epoch": 1.3548387096774195,
+      "grad_norm": 0.6293665170669556,
+      "learning_rate": 2.6559216294642446e-06,
+      "loss": 0.5165,
+      "step": 168
+    },
+    {
+      "epoch": 1.3629032258064515,
+      "grad_norm": 0.8250333666801453,
+      "learning_rate": 2.5970912240665815e-06,
+      "loss": 0.5087,
+      "step": 169
+    },
+    {
+      "epoch": 1.370967741935484,
+      "grad_norm": 0.7579450011253357,
+      "learning_rate": 2.5386902510968627e-06,
+      "loss": 0.4912,
+      "step": 170
+    },
+    {
+      "epoch": 1.379032258064516,
+      "grad_norm": 0.6229978203773499,
+      "learning_rate": 2.4807291476019996e-06,
+      "loss": 0.514,
+      "step": 171
+    },
+    {
+      "epoch": 1.3870967741935485,
+      "grad_norm": 0.6009650826454163,
+      "learning_rate": 2.4232182720182524e-06,
+      "loss": 0.5059,
+      "step": 172
+    },
+    {
+      "epoch": 1.3951612903225805,
+      "grad_norm": 0.6187584400177002,
+      "learning_rate": 2.3661679023200422e-06,
+      "loss": 0.5219,
+      "step": 173
+    },
+    {
+      "epoch": 1.403225806451613,
+      "grad_norm": 0.6182239651679993,
+      "learning_rate": 2.309588234183137e-06,
+      "loss": 0.5258,
+      "step": 174
+    },
+    {
+      "epoch": 1.4112903225806452,
+      "grad_norm": 0.642212986946106,
+      "learning_rate": 2.2534893791625408e-06,
+      "loss": 0.5062,
+      "step": 175
+    },
+    {
+      "epoch": 1.4193548387096775,
+      "grad_norm": 0.6238389015197754,
+      "learning_rate": 2.197881362885426e-06,
+      "loss": 0.5217,
+      "step": 176
+    },
+    {
+      "epoch": 1.4274193548387097,
+      "grad_norm": 0.6173287034034729,
+      "learning_rate": 2.1427741232594185e-06,
+      "loss": 0.502,
+      "step": 177
+    },
+    {
+      "epoch": 1.435483870967742,
+      "grad_norm": 0.6221210956573486,
+      "learning_rate": 2.0881775086965494e-06,
+      "loss": 0.5185,
+      "step": 178
+    },
+    {
+      "epoch": 1.4435483870967742,
+      "grad_norm": 0.6135408878326416,
+      "learning_rate": 2.0341012763532243e-06,
+      "loss": 0.5287,
+      "step": 179
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.6056985259056091,
+      "learning_rate": 1.9805550903864775e-06,
+      "loss": 0.5061,
+      "step": 180
+    },
+    {
+      "epoch": 1.4596774193548387,
+      "grad_norm": 0.6103174686431885,
+      "learning_rate": 1.9275485202268574e-06,
+      "loss": 0.5287,
+      "step": 181
+    },
+    {
+      "epoch": 1.467741935483871,
+      "grad_norm": 0.6178581714630127,
+      "learning_rate": 1.875091038868243e-06,
+      "loss": 0.5009,
+      "step": 182
+    },
+    {
+      "epoch": 1.4758064516129032,
+      "grad_norm": 0.6111758947372437,
+      "learning_rate": 1.8231920211748822e-06,
+      "loss": 0.4809,
+      "step": 183
+    },
+    {
+      "epoch": 1.4838709677419355,
+      "grad_norm": 0.6187841892242432,
+      "learning_rate": 1.771860742205988e-06,
+      "loss": 0.5102,
+      "step": 184
+    },
+    {
+      "epoch": 1.4919354838709677,
+      "grad_norm": 0.6165513396263123,
+      "learning_rate": 1.7211063755581524e-06,
+      "loss": 0.4961,
+      "step": 185
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.6021883487701416,
+      "learning_rate": 1.6709379917259028e-06,
+      "loss": 0.515,
+      "step": 186
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.7888004183769226,
+      "eval_runtime": 9.3786,
+      "eval_samples_per_second": 24.95,
+      "eval_steps_per_second": 1.066,
+      "step": 186
+    },
+    {
+      "checkpoint_runtime": 61.0063
+    },
+    {
+      "epoch": 1.5080645161290323,
+      "grad_norm": 0.6081679463386536,
+      "learning_rate": 1.6213645564806751e-06,
+      "loss": 0.4932,
+      "step": 187
+    },
+    {
+      "epoch": 1.5161290322580645,
+      "grad_norm": 0.6672825813293457,
+      "learning_rate": 1.5723949292685193e-06,
+      "loss": 0.5009,
+      "step": 188
+    },
+    {
+      "epoch": 1.5241935483870968,
+      "grad_norm": 0.6208696961402893,
+      "learning_rate": 1.5240378616267887e-06,
+      "loss": 0.5103,
+      "step": 189
+    },
+    {
+      "epoch": 1.532258064516129,
+      "grad_norm": 0.6016614437103271,
+      "learning_rate": 1.4763019956201252e-06,
+      "loss": 0.5132,
+      "step": 190
+    },
+    {
+      "epoch": 1.5403225806451613,
+      "grad_norm": 0.6239025592803955,
+      "learning_rate": 1.4291958622959972e-06,
+      "loss": 0.5196,
+      "step": 191
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 0.5971823930740356,
+      "learning_rate": 1.382727880160098e-06,
+      "loss": 0.4877,
+      "step": 192
+    },
+    {
+      "epoch": 1.5564516129032258,
+      "grad_norm": 0.6277076005935669,
+      "learning_rate": 1.3369063536718347e-06,
+      "loss": 0.5139,
+      "step": 193
+    },
+    {
+      "epoch": 1.564516129032258,
+      "grad_norm": 0.6051625609397888,
+      "learning_rate": 1.2917394717602123e-06,
+      "loss": 0.5035,
+      "step": 194
+    },
+    {
+      "epoch": 1.5725806451612905,
+      "grad_norm": 0.6475934386253357,
+      "learning_rate": 1.2472353063603626e-06,
+      "loss": 0.4832,
+      "step": 195
+    },
+    {
+      "epoch": 1.5806451612903225,
+      "grad_norm": 0.6042674779891968,
+      "learning_rate": 1.2034018109709716e-06,
+      "loss": 0.5039,
+      "step": 196
+    },
+    {
+      "epoch": 1.588709677419355,
+      "grad_norm": 0.6283749341964722,
+      "learning_rate": 1.1602468192328936e-06,
+      "loss": 0.4993,
+      "step": 197
+    },
+    {
+      "epoch": 1.596774193548387,
+      "grad_norm": 0.6274955868721008,
+      "learning_rate": 1.1177780435291641e-06,
+      "loss": 0.5431,
+      "step": 198
+    },
+    {
+      "epoch": 1.6048387096774195,
+      "grad_norm": 0.6180588603019714,
+      "learning_rate": 1.0760030736066952e-06,
+      "loss": 0.4847,
+      "step": 199
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.6047401428222656,
+      "learning_rate": 1.0349293752198842e-06,
+      "loss": 0.5274,
+      "step": 200
+    },
+    {
+      "epoch": 1.620967741935484,
+      "grad_norm": 0.6300760507583618,
+      "learning_rate": 9.945642887963842e-07,
+      "loss": 0.509,
+      "step": 201
+    },
+    {
+      "epoch": 1.629032258064516,
+      "grad_norm": 0.6328046917915344,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.4818,
+      "step": 202
+    },
+    {
+      "epoch": 1.6370967741935485,
+      "grad_norm": 0.6061556935310364,
+      "learning_rate": 9.159886790678124e-07,
+      "loss": 0.5238,
+      "step": 203
+    },
+    {
+      "epoch": 1.6451612903225805,
+      "grad_norm": 0.6284255385398865,
+      "learning_rate": 8.777921982911996e-07,
+      "loss": 0.5151,
+      "step": 204
+    },
+    {
+      "epoch": 1.653225806451613,
+      "grad_norm": 0.7236056327819824,
+      "learning_rate": 8.40332412025216e-07,
+      "loss": 0.5038,
+      "step": 205
+    },
+    {
+      "epoch": 1.661290322580645,
+      "grad_norm": 0.6204567551612854,
+      "learning_rate": 8.036160148423449e-07,
+      "loss": 0.5249,
+      "step": 206
+    },
+    {
+      "epoch": 1.6693548387096775,
+      "grad_norm": 0.597579836845398,
+      "learning_rate": 7.676495684613433e-07,
+      "loss": 0.494,
+      "step": 207
+    },
+    {
+      "epoch": 1.6774193548387095,
+      "grad_norm": 0.6009876132011414,
+      "learning_rate": 7.324395005745772e-07,
+      "loss": 0.5084,
+      "step": 208
+    },
+    {
+      "epoch": 1.685483870967742,
+      "grad_norm": 0.5991401672363281,
+      "learning_rate": 6.979921036993042e-07,
+      "loss": 0.4954,
+      "step": 209
+    },
+    {
+      "epoch": 1.6935483870967742,
+      "grad_norm": 0.6033263802528381,
+      "learning_rate": 6.643135340531137e-07,
+      "loss": 0.5162,
+      "step": 210
+    },
+    {
+      "epoch": 1.7016129032258065,
+      "grad_norm": 0.6148812174797058,
+      "learning_rate": 6.314098104537325e-07,
+      "loss": 0.5156,
+      "step": 211
+    },
+    {
+      "epoch": 1.7096774193548387,
+      "grad_norm": 0.6587268710136414,
+      "learning_rate": 5.992868132433755e-07,
+      "loss": 0.5075,
+      "step": 212
+    },
+    {
+      "epoch": 1.717741935483871,
+      "grad_norm": 0.6037371754646301,
+      "learning_rate": 5.679502832378497e-07,
+      "loss": 0.5371,
+      "step": 213
+    },
+    {
+      "epoch": 1.7258064516129032,
+      "grad_norm": 0.5974512100219727,
+      "learning_rate": 5.374058207005945e-07,
+      "loss": 0.5101,
+      "step": 214
+    },
+    {
+      "epoch": 1.7338709677419355,
+      "grad_norm": 0.6330116391181946,
+      "learning_rate": 5.076588843418345e-07,
+      "loss": 0.5309,
+      "step": 215
+    },
+    {
+      "epoch": 1.7419354838709677,
+      "grad_norm": 0.6081858277320862,
+      "learning_rate": 4.787147903430383e-07,
+      "loss": 0.4972,
+      "step": 216
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.6095616221427917,
+      "learning_rate": 4.505787114068433e-07,
+      "loss": 0.5308,
+      "step": 217
+    },
+    {
+      "epoch": 1.7580645161290323,
+      "grad_norm": 0.6092073321342468,
+      "learning_rate": 4.232556758326212e-07,
+      "loss": 0.5083,
+      "step": 218
+    },
+    {
+      "epoch": 1.7661290322580645,
+      "grad_norm": 0.6203122138977051,
+      "learning_rate": 3.9675056661785563e-07,
+      "loss": 0.4993,
+      "step": 219
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 0.6208032965660095,
+      "learning_rate": 3.710681205854838e-07,
+      "loss": 0.527,
+      "step": 220
+    },
+    {
+      "epoch": 1.782258064516129,
+      "grad_norm": 0.5900985598564148,
+      "learning_rate": 3.462129275373577e-07,
+      "loss": 0.5327,
+      "step": 221
+    },
+    {
+      "epoch": 1.7903225806451613,
+      "grad_norm": 0.6186009049415588,
+      "learning_rate": 3.2218942943399114e-07,
+      "loss": 0.5428,
+      "step": 222
+    },
+    {
+      "epoch": 1.7983870967741935,
+      "grad_norm": 0.6499991416931152,
+      "learning_rate": 2.9900191960071544e-07,
+      "loss": 0.5133,
+      "step": 223
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 0.619238018989563,
+      "learning_rate": 2.7665454196040665e-07,
+      "loss": 0.5467,
+      "step": 224
+    },
+    {
+      "epoch": 1.814516129032258,
+      "grad_norm": 0.5999795198440552,
+      "learning_rate": 2.5515129029290984e-07,
+      "loss": 0.5093,
+      "step": 225
+    },
+    {
+      "epoch": 1.8225806451612905,
+      "grad_norm": 0.6380183696746826,
+      "learning_rate": 2.3449600752129598e-07,
+      "loss": 0.5387,
+      "step": 226
+    },
+    {
+      "epoch": 1.8306451612903225,
+      "grad_norm": 0.5732983946800232,
+      "learning_rate": 2.1469238502507926e-07,
+      "loss": 0.5138,
+      "step": 227
+    },
+    {
+      "epoch": 1.838709677419355,
+      "grad_norm": 0.622412919998169,
+      "learning_rate": 1.957439619805196e-07,
+      "loss": 0.5229,
+      "step": 228
+    },
+    {
+      "epoch": 1.846774193548387,
+      "grad_norm": 0.6154828667640686,
+      "learning_rate": 1.776541247281177e-07,
+      "loss": 0.5372,
+      "step": 229
+    },
+    {
+      "epoch": 1.8548387096774195,
+      "grad_norm": 0.7694344520568848,
+      "learning_rate": 1.6042610616743782e-07,
+      "loss": 0.5274,
+      "step": 230
+    },
+    {
+      "epoch": 1.8629032258064515,
+      "grad_norm": 0.5814746022224426,
+      "learning_rate": 1.440629851793407e-07,
+      "loss": 0.5043,
+      "step": 231
+    },
+    {
+      "epoch": 1.870967741935484,
+      "grad_norm": 0.6514173150062561,
+      "learning_rate": 1.2856768607574565e-07,
+      "loss": 0.5299,
+      "step": 232
+    },
+    {
+      "epoch": 1.879032258064516,
+      "grad_norm": 0.606774628162384,
+      "learning_rate": 1.1394297807701737e-07,
+      "loss": 0.5359,
+      "step": 233
+    },
+    {
+      "epoch": 1.8870967741935485,
+      "grad_norm": 0.6160103678703308,
+      "learning_rate": 1.0019147481706626e-07,
+      "loss": 0.5221,
+      "step": 234
+    },
+    {
+      "epoch": 1.8951612903225805,
+      "grad_norm": 0.5801188945770264,
+      "learning_rate": 8.731563387626096e-08,
+      "loss": 0.5225,
+      "step": 235
+    },
+    {
+      "epoch": 1.903225806451613,
+      "grad_norm": 0.6326424479484558,
+      "learning_rate": 7.531775634222138e-08,
+      "loss": 0.5184,
+      "step": 236
+    },
+    {
+      "epoch": 1.911290322580645,
+      "grad_norm": 0.6097948551177979,
+      "learning_rate": 6.419998639858538e-08,
+      "loss": 0.5057,
+      "step": 237
+    },
+    {
+      "epoch": 1.9193548387096775,
+      "grad_norm": 0.5916938185691833,
+      "learning_rate": 5.396431094181198e-08,
+      "loss": 0.5234,
+      "step": 238
+    },
+    {
+      "epoch": 1.9274193548387095,
+      "grad_norm": 0.6183552145957947,
+      "learning_rate": 4.461255922609986e-08,
+      "loss": 0.5053,
+      "step": 239
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 0.5926957726478577,
+      "learning_rate": 3.6146402536468285e-08,
+      "loss": 0.5075,
+      "step": 240
+    },
+    {
+      "epoch": 1.9435483870967742,
+      "grad_norm": 0.6980299949645996,
+      "learning_rate": 2.8567353890082696e-08,
+      "loss": 0.5185,
+      "step": 241
+    },
+    {
+      "epoch": 1.9516129032258065,
+      "grad_norm": 1.8381667137145996,
+      "learning_rate": 2.1876767765853237e-08,
+      "loss": 0.5262,
+      "step": 242
+    },
+    {
+      "epoch": 1.9596774193548387,
+      "grad_norm": 0.6078267097473145,
+      "learning_rate": 1.6075839862374487e-08,
+      "loss": 0.5576,
+      "step": 243
+    },
+    {
+      "epoch": 1.967741935483871,
+      "grad_norm": 0.6254344582557678,
+      "learning_rate": 1.1165606884234182e-08,
+      "loss": 0.5408,
+      "step": 244
+    },
+    {
+      "epoch": 1.9758064516129032,
+      "grad_norm": 0.6521915197372437,
+      "learning_rate": 7.146946356743068e-09,
+      "loss": 0.5135,
+      "step": 245
+    },
+    {
+      "epoch": 1.9838709677419355,
+      "grad_norm": 0.6430618762969971,
+      "learning_rate": 4.020576469108139e-09,
+      "loss": 0.5046,
+      "step": 246
+    },
+    {
+      "epoch": 1.9919354838709677,
+      "grad_norm": 0.6160573363304138,
+      "learning_rate": 1.7870559460814173e-09,
+      "loss": 0.5487,
+      "step": 247
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8116743564605713,
+      "learning_rate": 4.4678394810981904e-10,
+      "loss": 0.4323,
+      "step": 248
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7841667532920837,
+      "eval_runtime": 9.3777,
+      "eval_samples_per_second": 24.953,
+      "eval_steps_per_second": 1.066,
+      "step": 248
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 248,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 62,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.458133172542505e+17,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}