Upload full fine-tuned Qwen3-4B-Instruct-2507 model (auto-generated README)

.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

README.md

@@ -0,0 +1,67 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- u-10bei/sft_alfworld_trajectory_dataset_v5
+- u-10bei/sft_alfworld_trajectory_dataset_v4
+- u-10bei/sft_alfworld_trajectory_dataset_v3
+- u-10bei/dbbench_sft_dataset_react_v4
+language:
+- en
+license: apache-2.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- agent
+- tool-use
+- alfworld
+- dbbench
+---
+
+# qwen3-4b-agent-v6-900
+
+This repository provides a **LoRA adapter** fine-tuned from
+**Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
+
+This repository contains **LoRA adapter weights only**.
+The base model must be loaded separately.
+
+## Training Objective
+
+This adapter is trained to improve **multi-turn agent task performance**
+on ALFWorld (household tasks) and DBBench (database operations).
+
+Loss is applied to **all assistant turns** in the multi-turn trajectory,
+enabling the model to learn environment observation, action selection,
+tool use, and recovery from errors.
+
+## Training Configuration
+
+- Base model: Qwen/Qwen3-4B-Instruct-2507
+- Method: full
+- Max sequence length: 4096
+- Epochs: 2
+- Learning rate: 2e-06
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+base = "Qwen/Qwen3-4B-Instruct-2507"
+adapter = "your_id/your-repo"
+
+tokenizer = AutoTokenizer.from_pretrained(base)
+model = AutoModelForCausalLM.from_pretrained(
+    base,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+```
+
+## Sources & Terms (IMPORTANT)
+
+Training data: u-10bei/sft_alfworld_trajectory_dataset_v5, SELEE/sft_alfworld_trajectory_dataset_v4_labeled, , SELEE/sft_alfworld_trajectory_dataset_v3_labeled, u-10bei/dbbench_sft_dataset_react_v4
+
+Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
+Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.

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
+}

chat_template.jinja

@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message.role == 'system' %}{{ '<|im_start|>system
+' + message.content + '<|im_end|>
+' }}{% elif message.role == 'user' %}{{ '<|im_start|>user
+' + message.content + '<|im_end|>
+' }}{% elif message.role == 'assistant' %}{{ '<|im_start|>assistant
+' + message.content + '<|im_end|>
+' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.2",
+  "unsloth_version": "2025.12.7",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 262144,
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.56.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:581ffed1068b1f622f62b0d6bb5655ac7c25bc89898530af3adc8784fe878e22
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2896a0e89e5327bcdc8e6e1da010aa6996585831276332542f0b99799c35ae24
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_parameters": 4022468096,
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1070 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013527223537368955,
+      "grad_norm": 110.5,
+      "learning_rate": 1.2162162162162163e-07,
+      "loss": 2.9783,
+      "step": 10
+    },
+    {
+      "epoch": 0.02705444707473791,
+      "grad_norm": 113.0,
+      "learning_rate": 2.567567567567567e-07,
+      "loss": 3.0679,
+      "step": 20
+    },
+    {
+      "epoch": 0.040581670612106865,
+      "grad_norm": 106.0,
+      "learning_rate": 3.918918918918919e-07,
+      "loss": 3.0966,
+      "step": 30
+    },
+    {
+      "epoch": 0.05410889414947582,
+      "grad_norm": 102.5,
+      "learning_rate": 5.270270270270269e-07,
+      "loss": 2.9748,
+      "step": 40
+    },
+    {
+      "epoch": 0.06763611768684477,
+      "grad_norm": 95.5,
+      "learning_rate": 6.621621621621622e-07,
+      "loss": 2.9264,
+      "step": 50
+    },
+    {
+      "epoch": 0.08116334122421373,
+      "grad_norm": 85.5,
+      "learning_rate": 7.972972972972972e-07,
+      "loss": 2.7277,
+      "step": 60
+    },
+    {
+      "epoch": 0.09469056476158269,
+      "grad_norm": 85.5,
+      "learning_rate": 9.324324324324324e-07,
+      "loss": 2.6271,
+      "step": 70
+    },
+    {
+      "epoch": 0.10821778829895164,
+      "grad_norm": 96.0,
+      "learning_rate": 1.0675675675675675e-06,
+      "loss": 2.4285,
+      "step": 80
+    },
+    {
+      "epoch": 0.1217450118363206,
+      "grad_norm": 70.0,
+      "learning_rate": 1.2027027027027026e-06,
+      "loss": 2.0623,
+      "step": 90
+    },
+    {
+      "epoch": 0.13527223537368954,
+      "grad_norm": 54.5,
+      "learning_rate": 1.3378378378378378e-06,
+      "loss": 1.7022,
+      "step": 100
+    },
+    {
+      "epoch": 0.1487994589110585,
+      "grad_norm": 31.5,
+      "learning_rate": 1.472972972972973e-06,
+      "loss": 1.4259,
+      "step": 110
+    },
+    {
+      "epoch": 0.16232668244842746,
+      "grad_norm": 19.375,
+      "learning_rate": 1.608108108108108e-06,
+      "loss": 1.1437,
+      "step": 120
+    },
+    {
+      "epoch": 0.17585390598579642,
+      "grad_norm": 13.0,
+      "learning_rate": 1.743243243243243e-06,
+      "loss": 0.9886,
+      "step": 130
+    },
+    {
+      "epoch": 0.18938112952316538,
+      "grad_norm": 9.625,
+      "learning_rate": 1.8783783783783783e-06,
+      "loss": 0.8594,
+      "step": 140
+    },
+    {
+      "epoch": 0.2029083530605343,
+      "grad_norm": 8.5,
+      "learning_rate": 1.9999972186150605e-06,
+      "loss": 0.7673,
+      "step": 150
+    },
+    {
+      "epoch": 0.21643557659790327,
+      "grad_norm": 5.78125,
+      "learning_rate": 1.9996634711432784e-06,
+      "loss": 0.7322,
+      "step": 160
+    },
+    {
+      "epoch": 0.22996280013527223,
+      "grad_norm": 6.09375,
+      "learning_rate": 1.9987736594069414e-06,
+      "loss": 0.6586,
+      "step": 170
+    },
+    {
+      "epoch": 0.2434900236726412,
+      "grad_norm": 5.40625,
+      "learning_rate": 1.997328278365126e-06,
+      "loss": 0.6214,
+      "step": 180
+    },
+    {
+      "epoch": 0.2570172472100101,
+      "grad_norm": 7.15625,
+      "learning_rate": 1.9953281320131465e-06,
+      "loss": 0.5825,
+      "step": 190
+    },
+    {
+      "epoch": 0.2705444707473791,
+      "grad_norm": 5.1875,
+      "learning_rate": 1.992774332935329e-06,
+      "loss": 0.5826,
+      "step": 200
+    },
+    {
+      "epoch": 0.28407169428474804,
+      "grad_norm": 4.875,
+      "learning_rate": 1.989668301686138e-06,
+      "loss": 0.5562,
+      "step": 210
+    },
+    {
+      "epoch": 0.297598917822117,
+      "grad_norm": 6.0625,
+      "learning_rate": 1.9860117659999875e-06,
+      "loss": 0.5323,
+      "step": 220
+    },
+    {
+      "epoch": 0.31112614135948596,
+      "grad_norm": 5.40625,
+      "learning_rate": 1.981806759830189e-06,
+      "loss": 0.5352,
+      "step": 230
+    },
+    {
+      "epoch": 0.3246533648968549,
+      "grad_norm": 5.3125,
+      "learning_rate": 1.9770556222175607e-06,
+      "loss": 0.5354,
+      "step": 240
+    },
+    {
+      "epoch": 0.3381805884342239,
+      "grad_norm": 4.125,
+      "learning_rate": 1.9717609959893315e-06,
+      "loss": 0.4923,
+      "step": 250
+    },
+    {
+      "epoch": 0.35170781197159284,
+      "grad_norm": 4.6875,
+      "learning_rate": 1.965925826289068e-06,
+      "loss": 0.4907,
+      "step": 260
+    },
+    {
+      "epoch": 0.3652350355089618,
+      "grad_norm": 5.34375,
+      "learning_rate": 1.9595533589384306e-06,
+      "loss": 0.4875,
+      "step": 270
+    },
+    {
+      "epoch": 0.37876225904633076,
+      "grad_norm": 5.09375,
+      "learning_rate": 1.952647138631682e-06,
+      "loss": 0.4771,
+      "step": 280
+    },
+    {
+      "epoch": 0.3922894825836997,
+      "grad_norm": 6.1875,
+      "learning_rate": 1.945211006963945e-06,
+      "loss": 0.4683,
+      "step": 290
+    },
+    {
+      "epoch": 0.4058167061210686,
+      "grad_norm": 4.96875,
+      "learning_rate": 1.937249100294311e-06,
+      "loss": 0.4597,
+      "step": 300
+    },
+    {
+      "epoch": 0.4193439296584376,
+      "grad_norm": 5.6875,
+      "learning_rate": 1.9287658474449836e-06,
+      "loss": 0.4553,
+      "step": 310
+    },
+    {
+      "epoch": 0.43287115319580655,
+      "grad_norm": 4.46875,
+      "learning_rate": 1.9197659672377386e-06,
+      "loss": 0.4499,
+      "step": 320
+    },
+    {
+      "epoch": 0.4463983767331755,
+      "grad_norm": 5.25,
+      "learning_rate": 1.9102544658690745e-06,
+      "loss": 0.4559,
+      "step": 330
+    },
+    {
+      "epoch": 0.45992560027054447,
+      "grad_norm": 4.625,
+      "learning_rate": 1.9002366341255067e-06,
+      "loss": 0.4354,
+      "step": 340
+    },
+    {
+      "epoch": 0.4734528238079134,
+      "grad_norm": 5.8125,
+      "learning_rate": 1.8897180444405612e-06,
+      "loss": 0.4524,
+      "step": 350
+    },
+    {
+      "epoch": 0.4869800473452824,
+      "grad_norm": 6.28125,
+      "learning_rate": 1.8787045477950988e-06,
+      "loss": 0.4259,
+      "step": 360
+    },
+    {
+      "epoch": 0.5005072708826513,
+      "grad_norm": 5.1875,
+      "learning_rate": 1.8672022704627e-06,
+      "loss": 0.4254,
+      "step": 370
+    },
+    {
+      "epoch": 0.5140344944200202,
+      "grad_norm": 5.875,
+      "learning_rate": 1.8552176106019153e-06,
+      "loss": 0.43,
+      "step": 380
+    },
+    {
+      "epoch": 0.5275617179573893,
+      "grad_norm": 6.65625,
+      "learning_rate": 1.8427572346972803e-06,
+      "loss": 0.415,
+      "step": 390
+    },
+    {
+      "epoch": 0.5410889414947582,
+      "grad_norm": 5.4375,
+      "learning_rate": 1.829828073851075e-06,
+      "loss": 0.4145,
+      "step": 400
+    },
+    {
+      "epoch": 0.5546161650321272,
+      "grad_norm": 6.90625,
+      "learning_rate": 1.8164373199278855e-06,
+      "loss": 0.4049,
+      "step": 410
+    },
+    {
+      "epoch": 0.5681433885694961,
+      "grad_norm": 4.90625,
+      "learning_rate": 1.8025924215541229e-06,
+      "loss": 0.4087,
+      "step": 420
+    },
+    {
+      "epoch": 0.5816706121068651,
+      "grad_norm": 5.8125,
+      "learning_rate": 1.7883010799747095e-06,
+      "loss": 0.4131,
+      "step": 430
+    },
+    {
+      "epoch": 0.595197835644234,
+      "grad_norm": 8.0,
+      "learning_rate": 1.7735712447692536e-06,
+      "loss": 0.4282,
+      "step": 440
+    },
+    {
+      "epoch": 0.608725059181603,
+      "grad_norm": 4.46875,
+      "learning_rate": 1.7584111094300824e-06,
+      "loss": 0.4094,
+      "step": 450
+    },
+    {
+      "epoch": 0.6222522827189719,
+      "grad_norm": 4.84375,
+      "learning_rate": 1.7428291068045998e-06,
+      "loss": 0.3987,
+      "step": 460
+    },
+    {
+      "epoch": 0.6357795062563408,
+      "grad_norm": 5.125,
+      "learning_rate": 1.726833904404504e-06,
+      "loss": 0.3932,
+      "step": 470
+    },
+    {
+      "epoch": 0.6493067297937098,
+      "grad_norm": 6.25,
+      "learning_rate": 1.7104343995844715e-06,
+      "loss": 0.4026,
+      "step": 480
+    },
+    {
+      "epoch": 0.6628339533310788,
+      "grad_norm": 5.25,
+      "learning_rate": 1.6936397145929877e-06,
+      "loss": 0.4307,
+      "step": 490
+    },
+    {
+      "epoch": 0.6763611768684478,
+      "grad_norm": 5.53125,
+      "learning_rate": 1.676459191498087e-06,
+      "loss": 0.3874,
+      "step": 500
+    },
+    {
+      "epoch": 0.6898884004058167,
+      "grad_norm": 6.03125,
+      "learning_rate": 1.6589023869908107e-06,
+      "loss": 0.3754,
+      "step": 510
+    },
+    {
+      "epoch": 0.7034156239431857,
+      "grad_norm": 7.21875,
+      "learning_rate": 1.6409790670692858e-06,
+      "loss": 0.3837,
+      "step": 520
+    },
+    {
+      "epoch": 0.7169428474805546,
+      "grad_norm": 6.3125,
+      "learning_rate": 1.6226992016063724e-06,
+      "loss": 0.3889,
+      "step": 530
+    },
+    {
+      "epoch": 0.7304700710179236,
+      "grad_norm": 6.125,
+      "learning_rate": 1.6040729588039088e-06,
+      "loss": 0.3778,
+      "step": 540
+    },
+    {
+      "epoch": 0.7439972945552925,
+      "grad_norm": 7.5,
+      "learning_rate": 1.5851106995366337e-06,
+      "loss": 0.3654,
+      "step": 550
+    },
+    {
+      "epoch": 0.7575245180926615,
+      "grad_norm": 7.125,
+      "learning_rate": 1.5658229715889345e-06,
+      "loss": 0.3725,
+      "step": 560
+    },
+    {
+      "epoch": 0.7710517416300304,
+      "grad_norm": 5.84375,
+      "learning_rate": 1.5462205037876272e-06,
+      "loss": 0.3743,
+      "step": 570
+    },
+    {
+      "epoch": 0.7845789651673994,
+      "grad_norm": 7.03125,
+      "learning_rate": 1.526314200034031e-06,
+      "loss": 0.39,
+      "step": 580
+    },
+    {
+      "epoch": 0.7981061887047683,
+      "grad_norm": 8.1875,
+      "learning_rate": 1.5061151332386564e-06,
+      "loss": 0.3562,
+      "step": 590
+    },
+    {
+      "epoch": 0.8116334122421373,
+      "grad_norm": 6.625,
+      "learning_rate": 1.4856345391618827e-06,
+      "loss": 0.3658,
+      "step": 600
+    },
+    {
+      "epoch": 0.8251606357795063,
+      "grad_norm": 6.4375,
+      "learning_rate": 1.4648838101640517e-06,
+      "loss": 0.3547,
+      "step": 610
+    },
+    {
+      "epoch": 0.8386878593168752,
+      "grad_norm": 5.75,
+      "learning_rate": 1.443874488868448e-06,
+      "loss": 0.3692,
+      "step": 620
+    },
+    {
+      "epoch": 0.8522150828542442,
+      "grad_norm": 7.03125,
+      "learning_rate": 1.4226182617406994e-06,
+      "loss": 0.3878,
+      "step": 630
+    },
+    {
+      "epoch": 0.8657423063916131,
+      "grad_norm": 6.875,
+      "learning_rate": 1.4011269525881635e-06,
+      "loss": 0.371,
+      "step": 640
+    },
+    {
+      "epoch": 0.8792695299289821,
+      "grad_norm": 7.03125,
+      "learning_rate": 1.379412515982917e-06,
+      "loss": 0.3665,
+      "step": 650
+    },
+    {
+      "epoch": 0.892796753466351,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.3574870306120077e-06,
+      "loss": 0.3801,
+      "step": 660
+    },
+    {
+      "epoch": 0.90632397700372,
+      "grad_norm": 9.5,
+      "learning_rate": 1.335362692558667e-06,
+      "loss": 0.3746,
+      "step": 670
+    },
+    {
+      "epoch": 0.9198512005410889,
+      "grad_norm": 6.4375,
+      "learning_rate": 1.3130518085182222e-06,
+      "loss": 0.3675,
+      "step": 680
+    },
+    {
+      "epoch": 0.933378424078458,
+      "grad_norm": 7.21875,
+      "learning_rate": 1.2905667889524769e-06,
+      "loss": 0.3494,
+      "step": 690
+    },
+    {
+      "epoch": 0.9469056476158269,
+      "grad_norm": 7.09375,
+      "learning_rate": 1.2679201411863749e-06,
+      "loss": 0.3706,
+      "step": 700
+    },
+    {
+      "epoch": 0.9604328711531958,
+      "grad_norm": 6.0,
+      "learning_rate": 1.245124462450783e-06,
+      "loss": 0.3664,
+      "step": 710
+    },
+    {
+      "epoch": 0.9739600946905648,
+      "grad_norm": 5.8125,
+      "learning_rate": 1.2221924328752616e-06,
+      "loss": 0.3694,
+      "step": 720
+    },
+    {
+      "epoch": 0.9874873182279337,
+      "grad_norm": 7.65625,
+      "learning_rate": 1.199136808434725e-06,
+      "loss": 0.3601,
+      "step": 730
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 13.0625,
+      "learning_rate": 1.1759704138539119e-06,
+      "loss": 0.3654,
+      "step": 740
+    },
+    {
+      "epoch": 1.013527223537369,
+      "grad_norm": 8.0625,
+      "learning_rate": 1.1527061354736127e-06,
+      "loss": 0.3354,
+      "step": 750
+    },
+    {
+      "epoch": 1.0270544470747378,
+      "grad_norm": 6.21875,
+      "learning_rate": 1.1293569140826237e-06,
+      "loss": 0.3584,
+      "step": 760
+    },
+    {
+      "epoch": 1.040581670612107,
+      "grad_norm": 7.625,
+      "learning_rate": 1.105935737719416e-06,
+      "loss": 0.3522,
+      "step": 770
+    },
+    {
+      "epoch": 1.0541088941494758,
+      "grad_norm": 8.125,
+      "learning_rate": 1.082455634447518e-06,
+      "loss": 0.3658,
+      "step": 780
+    },
+    {
+      "epoch": 1.0676361176868447,
+      "grad_norm": 6.46875,
+      "learning_rate": 1.0589296651086376e-06,
+      "loss": 0.3669,
+      "step": 790
+    },
+    {
+      "epoch": 1.0811633412242136,
+      "grad_norm": 6.0,
+      "learning_rate": 1.0353709160575487e-06,
+      "loss": 0.3513,
+      "step": 800
+    },
+    {
+      "epoch": 1.0946905647615828,
+      "grad_norm": 5.59375,
+      "learning_rate": 1.011792491882789e-06,
+      "loss": 0.3563,
+      "step": 810
+    },
+    {
+      "epoch": 1.1082177882989517,
+      "grad_norm": 6.3125,
+      "learning_rate": 9.882075081172112e-07,
+      "loss": 0.3527,
+      "step": 820
+    },
+    {
+      "epoch": 1.1217450118363206,
+      "grad_norm": 6.09375,
+      "learning_rate": 9.646290839424514e-07,
+      "loss": 0.351,
+      "step": 830
+    },
+    {
+      "epoch": 1.1352722353736895,
+      "grad_norm": 7.40625,
+      "learning_rate": 9.410703348913626e-07,
+      "loss": 0.363,
+      "step": 840
+    },
+    {
+      "epoch": 1.1487994589110584,
+      "grad_norm": 6.21875,
+      "learning_rate": 9.17544365552482e-07,
+      "loss": 0.3461,
+      "step": 850
+    },
+    {
+      "epoch": 1.1623266824484275,
+      "grad_norm": 9.1875,
+      "learning_rate": 8.94064262280584e-07,
+      "loss": 0.341,
+      "step": 860
+    },
+    {
+      "epoch": 1.1758539059857964,
+      "grad_norm": 6.75,
+      "learning_rate": 8.706430859173763e-07,
+      "loss": 0.3629,
+      "step": 870
+    },
+    {
+      "epoch": 1.1893811295231653,
+      "grad_norm": 5.84375,
+      "learning_rate": 8.472938645263874e-07,
+      "loss": 0.3517,
+      "step": 880
+    },
+    {
+      "epoch": 1.2029083530605342,
+      "grad_norm": 6.5625,
+      "learning_rate": 8.24029586146088e-07,
+      "loss": 0.3583,
+      "step": 890
+    },
+    {
+      "epoch": 1.2164355765979034,
+      "grad_norm": 6.28125,
+      "learning_rate": 8.00863191565275e-07,
+      "loss": 0.3587,
+      "step": 900
+    },
+    {
+      "epoch": 1.2299628001352723,
+      "grad_norm": 5.625,
+      "learning_rate": 7.778075671247385e-07,
+      "loss": 0.3413,
+      "step": 910
+    },
+    {
+      "epoch": 1.2434900236726412,
+      "grad_norm": 6.5625,
+      "learning_rate": 7.548755375492172e-07,
+      "loss": 0.3496,
+      "step": 920
+    },
+    {
+      "epoch": 1.25701724721001,
+      "grad_norm": 5.9375,
+      "learning_rate": 7.320798588136253e-07,
+      "loss": 0.346,
+      "step": 930
+    },
+    {
+      "epoch": 1.270544470747379,
+      "grad_norm": 6.0625,
+      "learning_rate": 7.094332110475234e-07,
+      "loss": 0.3389,
+      "step": 940
+    },
+    {
+      "epoch": 1.284071694284748,
+      "grad_norm": 7.34375,
+      "learning_rate": 6.869481914817779e-07,
+      "loss": 0.3491,
+      "step": 950
+    },
+    {
+      "epoch": 1.297598917822117,
+      "grad_norm": 7.21875,
+      "learning_rate": 6.646373074413329e-07,
+      "loss": 0.3394,
+      "step": 960
+    },
+    {
+      "epoch": 1.311126141359486,
+      "grad_norm": 9.5,
+      "learning_rate": 6.425129693879925e-07,
+      "loss": 0.3489,
+      "step": 970
+    },
+    {
+      "epoch": 1.324653364896855,
+      "grad_norm": 6.375,
+      "learning_rate": 6.205874840170832e-07,
+      "loss": 0.3424,
+      "step": 980
+    },
+    {
+      "epoch": 1.338180588434224,
+      "grad_norm": 6.96875,
+      "learning_rate": 5.988730474118367e-07,
+      "loss": 0.3559,
+      "step": 990
+    },
+    {
+      "epoch": 1.3517078119715928,
+      "grad_norm": 5.5625,
+      "learning_rate": 5.773817382593007e-07,
+      "loss": 0.3402,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3652350355089617,
+      "grad_norm": 8.25,
+      "learning_rate": 5.561255111315523e-07,
+      "loss": 0.3494,
+      "step": 1010
+    },
+    {
+      "epoch": 1.3787622590463307,
+      "grad_norm": 6.40625,
+      "learning_rate": 5.351161898359484e-07,
+      "loss": 0.3321,
+      "step": 1020
+    },
+    {
+      "epoch": 1.3922894825836998,
+      "grad_norm": 9.5625,
+      "learning_rate": 5.143654608381171e-07,
+      "loss": 0.3432,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4058167061210687,
+      "grad_norm": 6.90625,
+      "learning_rate": 4.938848667613436e-07,
+      "loss": 0.3378,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4193439296584376,
+      "grad_norm": 7.6875,
+      "learning_rate": 4.7368579996596903e-07,
+      "loss": 0.3529,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4328711531958065,
+      "grad_norm": 6.3125,
+      "learning_rate": 4.5377949621237255e-07,
+      "loss": 0.3541,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4463983767331756,
+      "grad_norm": 6.0,
+      "learning_rate": 4.341770284110655e-07,
+      "loss": 0.3264,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4599256002705445,
+      "grad_norm": 6.3125,
+      "learning_rate": 4.1488930046336623e-07,
+      "loss": 0.3408,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4734528238079134,
+      "grad_norm": 8.25,
+      "learning_rate": 3.9592704119609124e-07,
+      "loss": 0.363,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4869800473452823,
+      "grad_norm": 6.59375,
+      "learning_rate": 3.773007983936275e-07,
+      "loss": 0.3512,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5005072708826512,
+      "grad_norm": 9.3125,
+      "learning_rate": 3.5902093293071423e-07,
+      "loss": 0.335,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5140344944200201,
+      "grad_norm": 6.3125,
+      "learning_rate": 3.4109761300918917e-07,
+      "loss": 0.3461,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5275617179573893,
+      "grad_norm": 6.53125,
+      "learning_rate": 3.2354080850191325e-07,
+      "loss": 0.3425,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5410889414947582,
+      "grad_norm": 6.625,
+      "learning_rate": 3.0636028540701233e-07,
+      "loss": 0.34,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5546161650321273,
+      "grad_norm": 6.75,
+      "learning_rate": 2.895656004155288e-07,
+      "loss": 0.3464,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5681433885694962,
+      "grad_norm": 5.875,
+      "learning_rate": 2.7316609559549563e-07,
+      "loss": 0.341,
+      "step": 1160
+    },
+    {
+      "epoch": 1.581670612106865,
+      "grad_norm": 8.1875,
+      "learning_rate": 2.571708931954e-07,
+      "loss": 0.3426,
+      "step": 1170
+    },
+    {
+      "epoch": 1.595197835644234,
+      "grad_norm": 6.375,
+      "learning_rate": 2.4158889056991773e-07,
+      "loss": 0.3494,
+      "step": 1180
+    },
+    {
+      "epoch": 1.608725059181603,
+      "grad_norm": 6.625,
+      "learning_rate": 2.2642875523074613e-07,
+      "loss": 0.3509,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6222522827189718,
+      "grad_norm": 5.9375,
+      "learning_rate": 2.1169892002529044e-07,
+      "loss": 0.3508,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6357795062563407,
+      "grad_norm": 7.75,
+      "learning_rate": 1.9740757844587708e-07,
+      "loss": 0.3542,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6493067297937098,
+      "grad_norm": 5.875,
+      "learning_rate": 1.835626800721144e-07,
+      "loss": 0.3559,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6628339533310788,
+      "grad_norm": 5.75,
+      "learning_rate": 1.7017192614892506e-07,
+      "loss": 0.33,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6763611768684479,
+      "grad_norm": 6.8125,
+      "learning_rate": 1.5724276530271962e-07,
+      "loss": 0.3553,
+      "step": 1240
+    },
+    {
+      "epoch": 1.6898884004058168,
+      "grad_norm": 6.625,
+      "learning_rate": 1.447823893980845e-07,
+      "loss": 0.3394,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7034156239431857,
+      "grad_norm": 6.75,
+      "learning_rate": 1.3279772953729983e-07,
+      "loss": 0.3379,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7169428474805546,
+      "grad_norm": 8.25,
+      "learning_rate": 1.21295452204901e-07,
+      "loss": 0.3532,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7304700710179235,
+      "grad_norm": 6.5625,
+      "learning_rate": 1.1028195555943876e-07,
+      "loss": 0.3352,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7439972945552924,
+      "grad_norm": 5.5,
+      "learning_rate": 9.976336587449307e-08,
+      "loss": 0.3532,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7575245180926615,
+      "grad_norm": 8.75,
+      "learning_rate": 8.974553413092556e-08,
+      "loss": 0.3405,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7710517416300304,
+      "grad_norm": 6.4375,
+      "learning_rate": 8.023403276226127e-08,
+      "loss": 0.3612,
+      "step": 1310
+    },
+    {
+      "epoch": 1.7845789651673996,
+      "grad_norm": 6.46875,
+      "learning_rate": 7.123415255501652e-08,
+      "loss": 0.3513,
+      "step": 1320
+    },
+    {
+      "epoch": 1.7981061887047685,
+      "grad_norm": 7.625,
+      "learning_rate": 6.27508997056888e-08,
+      "loss": 0.3525,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8116334122421374,
+      "grad_norm": 6.78125,
+      "learning_rate": 5.478899303605511e-08,
+      "loss": 0.3466,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8251606357795063,
+      "grad_norm": 6.15625,
+      "learning_rate": 4.735286136831806e-08,
+      "loss": 0.3486,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8386878593168752,
+      "grad_norm": 6.65625,
+      "learning_rate": 4.0446641061569144e-08,
+      "loss": 0.3363,
+      "step": 1360
+    },
+    {
+      "epoch": 1.852215082854244,
+      "grad_norm": 7.84375,
+      "learning_rate": 3.4074173710931796e-08,
+      "loss": 0.3437,
+      "step": 1370
+    },
+    {
+      "epoch": 1.865742306391613,
+      "grad_norm": 8.0625,
+      "learning_rate": 2.8239004010668367e-08,
+      "loss": 0.3358,
+      "step": 1380
+    },
+    {
+      "epoch": 1.879269529928982,
+      "grad_norm": 7.09375,
+      "learning_rate": 2.294437778243963e-08,
+      "loss": 0.3632,
+      "step": 1390
+    },
+    {
+      "epoch": 1.892796753466351,
+      "grad_norm": 6.375,
+      "learning_rate": 1.8193240169810942e-08,
+      "loss": 0.381,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9063239770037201,
+      "grad_norm": 6.3125,
+      "learning_rate": 1.3988234000012367e-08,
+      "loss": 0.3476,
+      "step": 1410
+    },
+    {
+      "epoch": 1.919851200541089,
+      "grad_norm": 6.71875,
+      "learning_rate": 1.0331698313861937e-08,
+      "loss": 0.3403,
+      "step": 1420
+    },
+    {
+      "epoch": 1.933378424078458,
+      "grad_norm": 6.1875,
+      "learning_rate": 7.22566706467076e-09,
+      "loss": 0.345,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9469056476158269,
+      "grad_norm": 6.5625,
+      "learning_rate": 4.6718679868533725e-09,
+      "loss": 0.3618,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9604328711531958,
+      "grad_norm": 7.78125,
+      "learning_rate": 2.671721634873725e-09,
+      "loss": 0.3297,
+      "step": 1450
+    },
+    {
+      "epoch": 1.9739600946905647,
+      "grad_norm": 7.46875,
+      "learning_rate": 1.2263405930585947e-09,
+      "loss": 0.3393,
+      "step": 1460
+    },
+    {
+      "epoch": 1.9874873182279336,
+      "grad_norm": 7.125,
+      "learning_rate": 3.365288567216407e-10,
+      "loss": 0.362,
+      "step": 1470
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 11.3125,
+      "learning_rate": 2.7813849394764386e-12,
+      "loss": 0.3342,
+      "step": 1480
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.144769262871982e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29584707bab19d8948d0c8547d5a03b0bb6f97f8784a95562316035226abd387
+size 5777