Upload embedding model newatomic37

.gitattributes

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

added_tokens.json

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

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d97ea5d30b87e889964b83c723b321e6930038897c76734c0b97998dd26257
+size 4965826464

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35503d5bff4fb978bbba48c81e2ce6d0244d7a4f2b3a835b7b7db7c9dbf0c35d
+size 3077765624

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8043548672
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1488be6077b34b8add52f471a1f6d8628b5f26ae4b3c1782bd43de31367e8f1
+size 11423046

tokenizer_config.json

@@ -0,0 +1,213 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 1536,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 37,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0547945205479452,
+      "grad_norm": 180.05765669383916,
+      "learning_rate": 2.242438242175754e-06,
+      "loss": 13.125,
+      "step": 2
+    },
+    {
+      "epoch": 0.1095890410958904,
+      "grad_norm": 194.9212123528507,
+      "learning_rate": 4.484876484351508e-06,
+      "loss": 13.6562,
+      "step": 4
+    },
+    {
+      "epoch": 0.1643835616438356,
+      "grad_norm": 183.5584675658948,
+      "learning_rate": 5.796618766207391e-06,
+      "loss": 13.4375,
+      "step": 6
+    },
+    {
+      "epoch": 0.2191780821917808,
+      "grad_norm": 172.5618529609364,
+      "learning_rate": 6.727314726527262e-06,
+      "loss": 12.9531,
+      "step": 8
+    },
+    {
+      "epoch": 0.273972602739726,
+      "grad_norm": 157.57820334060722,
+      "learning_rate": 7.44921859773347e-06,
+      "loss": 11.875,
+      "step": 10
+    },
+    {
+      "epoch": 0.3287671232876712,
+      "grad_norm": 137.3144971772426,
+      "learning_rate": 8.039057008383146e-06,
+      "loss": 11.5469,
+      "step": 12
+    },
+    {
+      "epoch": 0.3835616438356164,
+      "grad_norm": 133.22523175168658,
+      "learning_rate": 8.53775827875806e-06,
+      "loss": 11.5156,
+      "step": 14
+    },
+    {
+      "epoch": 0.4383561643835616,
+      "grad_norm": 144.46175801179288,
+      "learning_rate": 8.969752968703017e-06,
+      "loss": 11.375,
+      "step": 16
+    },
+    {
+      "epoch": 0.4931506849315068,
+      "grad_norm": 112.70851635623477,
+      "learning_rate": 9.350799290239027e-06,
+      "loss": 11.4688,
+      "step": 18
+    },
+    {
+      "epoch": 0.547945205479452,
+      "grad_norm": 96.66131548816342,
+      "learning_rate": 9.691656839909223e-06,
+      "loss": 11.2188,
+      "step": 20
+    },
+    {
+      "epoch": 0.6027397260273972,
+      "grad_norm": 89.74411287825117,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 11.375,
+      "step": 22
+    },
+    {
+      "epoch": 0.6575342465753424,
+      "grad_norm": 81.71078858231157,
+      "learning_rate": 9.948453608247423e-06,
+      "loss": 11.1719,
+      "step": 24
+    },
+    {
+      "epoch": 0.7123287671232876,
+      "grad_norm": 77.70779884032373,
+      "learning_rate": 9.84536082474227e-06,
+      "loss": 11.2031,
+      "step": 26
+    },
+    {
+      "epoch": 0.7671232876712328,
+      "grad_norm": 75.4640906408115,
+      "learning_rate": 9.742268041237114e-06,
+      "loss": 11.0781,
+      "step": 28
+    },
+    {
+      "epoch": 0.821917808219178,
+      "grad_norm": 70.56872029649819,
+      "learning_rate": 9.63917525773196e-06,
+      "loss": 10.6562,
+      "step": 30
+    },
+    {
+      "epoch": 0.8767123287671232,
+      "grad_norm": 69.4620760741923,
+      "learning_rate": 9.536082474226806e-06,
+      "loss": 10.8906,
+      "step": 32
+    },
+    {
+      "epoch": 0.9315068493150684,
+      "grad_norm": 70.70229240835477,
+      "learning_rate": 9.43298969072165e-06,
+      "loss": 10.6562,
+      "step": 34
+    },
+    {
+      "epoch": 0.9863013698630136,
+      "grad_norm": 67.07330699280296,
+      "learning_rate": 9.329896907216496e-06,
+      "loss": 10.4219,
+      "step": 36
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f0933396899b1a4a5b9874eccd365f731a5c4f775c3d81bbe3d34b22adf611
+size 7928