Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+base_model: Qwen/Qwen3-4B-Instruct-2507
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- griffith-bigdata/sft_text2sql
+model-index:
+- name: Qwen3-4B-SQL-Writer
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen3-4B-SQL-Writer
+
+This model is a fine-tuned version of [/export/home/s2986280/Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co//export/home/s2986280/Qwen/Qwen3-4B-Instruct-2507) on the /export/home/s2986280/sft_text2sql_v2 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 128
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.2.2
+- Datasets 4.1.1
+- Tokenizers 0.22.1

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
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 3.4672082649056543e+18,
+    "train_loss": 0.4149530680001188,
+    "train_runtime": 38080.8907,
+    "train_samples": 37603,
+    "train_samples_per_second": 1.975,
+    "train_steps_per_second": 0.015
+}

chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "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": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8499d6707246997452aea4e70b9423807228e42a7f50f349e73973ebe75400f
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1479ee37433264a52ed6c085c7fd3243a5e26c7eca69b112cd277c86a282d407
+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 sha256:1e8514169a312b061bd0214ac4c684df479f0fd66a58f8e37b662298dd0c8f3b
+size 11422753

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 3.4672082649056543e+18,
+    "train_loss": 0.4149530680001188,
+    "train_runtime": 38080.8907,
+    "train_samples": 37603,
+    "train_samples_per_second": 1.975,
+    "train_steps_per_second": 0.015
+}

trainer_state.json

@@ -0,0 +1,869 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 588,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0034038932028507603,
+      "grad_norm": 14.875,
+      "learning_rate": 2e-05,
+      "loss": 1.0797,
+      "step": 1
+    },
+    {
+      "epoch": 0.017019466014253803,
+      "grad_norm": 1.5234375,
+      "learning_rate": 1.999771640780308e-05,
+      "loss": 0.6999,
+      "step": 5
+    },
+    {
+      "epoch": 0.03403893202850761,
+      "grad_norm": 1.109375,
+      "learning_rate": 1.9988441101966807e-05,
+      "loss": 0.5892,
+      "step": 10
+    },
+    {
+      "epoch": 0.05105839804276141,
+      "grad_norm": 1.109375,
+      "learning_rate": 1.9972037971811802e-05,
+      "loss": 0.5472,
+      "step": 15
+    },
+    {
+      "epoch": 0.06807786405701521,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.9948518722731208e-05,
+      "loss": 0.5298,
+      "step": 20
+    },
+    {
+      "epoch": 0.08509733007126902,
+      "grad_norm": 1.0,
+      "learning_rate": 1.991790013823246e-05,
+      "loss": 0.5166,
+      "step": 25
+    },
+    {
+      "epoch": 0.10211679608552282,
+      "grad_norm": 1.046875,
+      "learning_rate": 1.9880204067960473e-05,
+      "loss": 0.4988,
+      "step": 30
+    },
+    {
+      "epoch": 0.11913626209977662,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.983545741210553e-05,
+      "loss": 0.4867,
+      "step": 35
+    },
+    {
+      "epoch": 0.13615572811403043,
+      "grad_norm": 0.921875,
+      "learning_rate": 1.9783692102207156e-05,
+      "loss": 0.4763,
+      "step": 40
+    },
+    {
+      "epoch": 0.15317519412828423,
+      "grad_norm": 0.859375,
+      "learning_rate": 1.9724945078367513e-05,
+      "loss": 0.4625,
+      "step": 45
+    },
+    {
+      "epoch": 0.17019466014253803,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 0.4578,
+      "step": 50
+    },
+    {
+      "epoch": 0.18721412615679184,
+      "grad_norm": 0.87109375,
+      "learning_rate": 1.9586678530366607e-05,
+      "loss": 0.4492,
+      "step": 55
+    },
+    {
+      "epoch": 0.20423359217104564,
+      "grad_norm": 1.0078125,
+      "learning_rate": 1.950725767422103e-05,
+      "loss": 0.4445,
+      "step": 60
+    },
+    {
+      "epoch": 0.22125305818529944,
+      "grad_norm": 1.03125,
+      "learning_rate": 1.9421052369755335e-05,
+      "loss": 0.4502,
+      "step": 65
+    },
+    {
+      "epoch": 0.23827252419955325,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.932812413370265e-05,
+      "loss": 0.4432,
+      "step": 70
+    },
+    {
+      "epoch": 0.25529199021380705,
+      "grad_norm": 0.9296875,
+      "learning_rate": 1.922853928032904e-05,
+      "loss": 0.4402,
+      "step": 75
+    },
+    {
+      "epoch": 0.27231145622806086,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.9122368874111172e-05,
+      "loss": 0.4406,
+      "step": 80
+    },
+    {
+      "epoch": 0.28933092224231466,
+      "grad_norm": 0.859375,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.4454,
+      "step": 85
+    },
+    {
+      "epoch": 0.30635038825656846,
+      "grad_norm": 0.95703125,
+      "learning_rate": 1.8890579104475996e-05,
+      "loss": 0.4357,
+      "step": 90
+    },
+    {
+      "epoch": 0.32336985427082227,
+      "grad_norm": 0.87890625,
+      "learning_rate": 1.8765125147926477e-05,
+      "loss": 0.4334,
+      "step": 95
+    },
+    {
+      "epoch": 0.34038932028507607,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.8633416334232754e-05,
+      "loss": 0.4453,
+      "step": 100
+    },
+    {
+      "epoch": 0.3574087862993299,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.849554665176354e-05,
+      "loss": 0.4359,
+      "step": 105
+    },
+    {
+      "epoch": 0.3744282523135837,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.835161448532839e-05,
+      "loss": 0.4443,
+      "step": 110
+    },
+    {
+      "epoch": 0.3914477183278375,
+      "grad_norm": 0.953125,
+      "learning_rate": 1.820172254596956e-05,
+      "loss": 0.4256,
+      "step": 115
+    },
+    {
+      "epoch": 0.4084671843420913,
+      "grad_norm": 0.9296875,
+      "learning_rate": 1.8045977797666685e-05,
+      "loss": 0.4268,
+      "step": 120
+    },
+    {
+      "epoch": 0.4254866503563451,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.788449138100648e-05,
+      "loss": 0.4408,
+      "step": 125
+    },
+    {
+      "epoch": 0.4425061163705989,
+      "grad_norm": 0.95703125,
+      "learning_rate": 1.771737853387202e-05,
+      "loss": 0.4348,
+      "step": 130
+    },
+    {
+      "epoch": 0.4595255823848527,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.7544758509208148e-05,
+      "loss": 0.4332,
+      "step": 135
+    },
+    {
+      "epoch": 0.4765450483991065,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.7366754489921694e-05,
+      "loss": 0.4266,
+      "step": 140
+    },
+    {
+      "epoch": 0.4935645144133603,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.7183493500977277e-05,
+      "loss": 0.4207,
+      "step": 145
+    },
+    {
+      "epoch": 0.5105839804276141,
+      "grad_norm": 0.93359375,
+      "learning_rate": 1.699510631875134e-05,
+      "loss": 0.4211,
+      "step": 150
+    },
+    {
+      "epoch": 0.5276034464418679,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.6801727377709195e-05,
+      "loss": 0.4363,
+      "step": 155
+    },
+    {
+      "epoch": 0.5446229124561217,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.6603494674471595e-05,
+      "loss": 0.4223,
+      "step": 160
+    },
+    {
+      "epoch": 0.5616423784703755,
+      "grad_norm": 0.953125,
+      "learning_rate": 1.640054966933935e-05,
+      "loss": 0.4122,
+      "step": 165
+    },
+    {
+      "epoch": 0.5786618444846293,
+      "grad_norm": 0.80078125,
+      "learning_rate": 1.6193037185346225e-05,
+      "loss": 0.4276,
+      "step": 170
+    },
+    {
+      "epoch": 0.5956813104988831,
+      "grad_norm": 1.0,
+      "learning_rate": 1.598110530491216e-05,
+      "loss": 0.4221,
+      "step": 175
+    },
+    {
+      "epoch": 0.6127007765131369,
+      "grad_norm": 0.9375,
+      "learning_rate": 1.576490526417059e-05,
+      "loss": 0.4189,
+      "step": 180
+    },
+    {
+      "epoch": 0.6297202425273907,
+      "grad_norm": 0.93359375,
+      "learning_rate": 1.554459134504523e-05,
+      "loss": 0.4126,
+      "step": 185
+    },
+    {
+      "epoch": 0.6467397085416445,
+      "grad_norm": 0.98828125,
+      "learning_rate": 1.5320320765153367e-05,
+      "loss": 0.4146,
+      "step": 190
+    },
+    {
+      "epoch": 0.6637591745558983,
+      "grad_norm": 0.9921875,
+      "learning_rate": 1.5092253565614234e-05,
+      "loss": 0.4166,
+      "step": 195
+    },
+    {
+      "epoch": 0.6807786405701521,
+      "grad_norm": 0.828125,
+      "learning_rate": 1.4860552496842493e-05,
+      "loss": 0.4169,
+      "step": 200
+    },
+    {
+      "epoch": 0.6977981065844059,
+      "grad_norm": 0.9375,
+      "learning_rate": 1.4625382902408356e-05,
+      "loss": 0.4066,
+      "step": 205
+    },
+    {
+      "epoch": 0.7148175725986597,
+      "grad_norm": 0.84765625,
+      "learning_rate": 1.4386912601047214e-05,
+      "loss": 0.414,
+      "step": 210
+    },
+    {
+      "epoch": 0.7318370386129135,
+      "grad_norm": 0.7734375,
+      "learning_rate": 1.4145311766902956e-05,
+      "loss": 0.4098,
+      "step": 215
+    },
+    {
+      "epoch": 0.7488565046271674,
+      "grad_norm": 0.8203125,
+      "learning_rate": 1.390075280809047e-05,
+      "loss": 0.4155,
+      "step": 220
+    },
+    {
+      "epoch": 0.7658759706414211,
+      "grad_norm": 0.921875,
+      "learning_rate": 1.3653410243663953e-05,
+      "loss": 0.416,
+      "step": 225
+    },
+    {
+      "epoch": 0.782895436655675,
+      "grad_norm": 0.84765625,
+      "learning_rate": 1.3403460579078833e-05,
+      "loss": 0.4145,
+      "step": 230
+    },
+    {
+      "epoch": 0.7999149026699287,
+      "grad_norm": 0.859375,
+      "learning_rate": 1.315108218023621e-05,
+      "loss": 0.4167,
+      "step": 235
+    },
+    {
+      "epoch": 0.8169343686841826,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.289645514619963e-05,
+      "loss": 0.4097,
+      "step": 240
+    },
+    {
+      "epoch": 0.8339538346984363,
+      "grad_norm": 0.8359375,
+      "learning_rate": 1.2639761180675098e-05,
+      "loss": 0.4031,
+      "step": 245
+    },
+    {
+      "epoch": 0.8509733007126902,
+      "grad_norm": 0.875,
+      "learning_rate": 1.2381183462345983e-05,
+      "loss": 0.4001,
+      "step": 250
+    },
+    {
+      "epoch": 0.8679927667269439,
+      "grad_norm": 0.78125,
+      "learning_rate": 1.2120906514155371e-05,
+      "loss": 0.4107,
+      "step": 255
+    },
+    {
+      "epoch": 0.8850122327411978,
+      "grad_norm": 0.79296875,
+      "learning_rate": 1.1859116071629148e-05,
+      "loss": 0.416,
+      "step": 260
+    },
+    {
+      "epoch": 0.9020316987554515,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.1595998950333794e-05,
+      "loss": 0.4115,
+      "step": 265
+    },
+    {
+      "epoch": 0.9190511647697054,
+      "grad_norm": 0.828125,
+      "learning_rate": 1.1331742912563413e-05,
+      "loss": 0.4074,
+      "step": 270
+    },
+    {
+      "epoch": 0.9360706307839591,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.1066536533351202e-05,
+      "loss": 0.4027,
+      "step": 275
+    },
+    {
+      "epoch": 0.953090096798213,
+      "grad_norm": 0.875,
+      "learning_rate": 1.0800569065900935e-05,
+      "loss": 0.3988,
+      "step": 280
+    },
+    {
+      "epoch": 0.9701095628124667,
+      "grad_norm": 0.79296875,
+      "learning_rate": 1.0534030306534491e-05,
+      "loss": 0.4047,
+      "step": 285
+    },
+    {
+      "epoch": 0.9871290288267206,
+      "grad_norm": 0.85546875,
+      "learning_rate": 1.0267110459251824e-05,
+      "loss": 0.4081,
+      "step": 290
+    },
+    {
+      "epoch": 1.0034038932028508,
+      "grad_norm": 0.8359375,
+      "learning_rate": 1e-05,
+      "loss": 0.3962,
+      "step": 295
+    },
+    {
+      "epoch": 1.0204233592171046,
+      "grad_norm": 1.0,
+      "learning_rate": 9.732889540748181e-06,
+      "loss": 0.3991,
+      "step": 300
+    },
+    {
+      "epoch": 1.0374428252313583,
+      "grad_norm": 0.89453125,
+      "learning_rate": 9.46596969346551e-06,
+      "loss": 0.3899,
+      "step": 305
+    },
+    {
+      "epoch": 1.054462291245612,
+      "grad_norm": 0.8828125,
+      "learning_rate": 9.199430934099068e-06,
+      "loss": 0.3907,
+      "step": 310
+    },
+    {
+      "epoch": 1.071481757259866,
+      "grad_norm": 0.86328125,
+      "learning_rate": 8.933463466648798e-06,
+      "loss": 0.3885,
+      "step": 315
+    },
+    {
+      "epoch": 1.0885012232741198,
+      "grad_norm": 0.7578125,
+      "learning_rate": 8.66825708743659e-06,
+      "loss": 0.3883,
+      "step": 320
+    },
+    {
+      "epoch": 1.1055206892883735,
+      "grad_norm": 0.93359375,
+      "learning_rate": 8.404001049666211e-06,
+      "loss": 0.388,
+      "step": 325
+    },
+    {
+      "epoch": 1.1225401553026273,
+      "grad_norm": 0.79296875,
+      "learning_rate": 8.140883928370855e-06,
+      "loss": 0.3888,
+      "step": 330
+    },
+    {
+      "epoch": 1.1395596213168813,
+      "grad_norm": 1.0,
+      "learning_rate": 7.879093485844635e-06,
+      "loss": 0.384,
+      "step": 335
+    },
+    {
+      "epoch": 1.156579087331135,
+      "grad_norm": 0.890625,
+      "learning_rate": 7.618816537654018e-06,
+      "loss": 0.3886,
+      "step": 340
+    },
+    {
+      "epoch": 1.1735985533453888,
+      "grad_norm": 0.80859375,
+      "learning_rate": 7.360238819324903e-06,
+      "loss": 0.3875,
+      "step": 345
+    },
+    {
+      "epoch": 1.1906180193596425,
+      "grad_norm": 0.84375,
+      "learning_rate": 7.1035448538003706e-06,
+      "loss": 0.3922,
+      "step": 350
+    },
+    {
+      "epoch": 1.2076374853738965,
+      "grad_norm": 1.0390625,
+      "learning_rate": 6.848917819763794e-06,
+      "loss": 0.3881,
+      "step": 355
+    },
+    {
+      "epoch": 1.2246569513881502,
+      "grad_norm": 0.74609375,
+      "learning_rate": 6.596539420921171e-06,
+      "loss": 0.3943,
+      "step": 360
+    },
+    {
+      "epoch": 1.241676417402404,
+      "grad_norm": 0.89453125,
+      "learning_rate": 6.34658975633605e-06,
+      "loss": 0.3899,
+      "step": 365
+    },
+    {
+      "epoch": 1.2586958834166577,
+      "grad_norm": 0.859375,
+      "learning_rate": 6.099247191909532e-06,
+      "loss": 0.3782,
+      "step": 370
+    },
+    {
+      "epoch": 1.2757153494309117,
+      "grad_norm": 0.953125,
+      "learning_rate": 5.8546882330970454e-06,
+      "loss": 0.3873,
+      "step": 375
+    },
+    {
+      "epoch": 1.2927348154451654,
+      "grad_norm": 0.81640625,
+      "learning_rate": 5.6130873989527925e-06,
+      "loss": 0.3908,
+      "step": 380
+    },
+    {
+      "epoch": 1.3097542814594192,
+      "grad_norm": 0.86328125,
+      "learning_rate": 5.37461709759165e-06,
+      "loss": 0.3933,
+      "step": 385
+    },
+    {
+      "epoch": 1.326773747473673,
+      "grad_norm": 0.87890625,
+      "learning_rate": 5.139447503157513e-06,
+      "loss": 0.3879,
+      "step": 390
+    },
+    {
+      "epoch": 1.3437932134879267,
+      "grad_norm": 0.98828125,
+      "learning_rate": 4.9077464343857694e-06,
+      "loss": 0.3956,
+      "step": 395
+    },
+    {
+      "epoch": 1.3608126795021807,
+      "grad_norm": 0.8125,
+      "learning_rate": 4.679679234846636e-06,
+      "loss": 0.3827,
+      "step": 400
+    },
+    {
+      "epoch": 1.3778321455164344,
+      "grad_norm": 0.88671875,
+      "learning_rate": 4.455408654954771e-06,
+      "loss": 0.3851,
+      "step": 405
+    },
+    {
+      "epoch": 1.3948516115306882,
+      "grad_norm": 0.796875,
+      "learning_rate": 4.23509473582941e-06,
+      "loss": 0.3891,
+      "step": 410
+    },
+    {
+      "epoch": 1.4118710775449421,
+      "grad_norm": 0.90234375,
+      "learning_rate": 4.01889469508784e-06,
+      "loss": 0.3824,
+      "step": 415
+    },
+    {
+      "epoch": 1.4288905435591959,
+      "grad_norm": 0.8203125,
+      "learning_rate": 3.8069628146537796e-06,
+      "loss": 0.3948,
+      "step": 420
+    },
+    {
+      "epoch": 1.4459100095734496,
+      "grad_norm": 0.73046875,
+      "learning_rate": 3.5994503306606497e-06,
+      "loss": 0.3848,
+      "step": 425
+    },
+    {
+      "epoch": 1.4629294755877034,
+      "grad_norm": 0.84375,
+      "learning_rate": 3.3965053255284085e-06,
+      "loss": 0.3839,
+      "step": 430
+    },
+    {
+      "epoch": 1.4799489416019571,
+      "grad_norm": 0.9296875,
+      "learning_rate": 3.1982726222908046e-06,
+      "loss": 0.387,
+      "step": 435
+    },
+    {
+      "epoch": 1.496968407616211,
+      "grad_norm": 0.89453125,
+      "learning_rate": 3.004893681248662e-06,
+      "loss": 0.3905,
+      "step": 440
+    },
+    {
+      "epoch": 1.5139878736304648,
+      "grad_norm": 0.83984375,
+      "learning_rate": 2.8165064990227255e-06,
+      "loss": 0.385,
+      "step": 445
+    },
+    {
+      "epoch": 1.5310073396447188,
+      "grad_norm": 0.81640625,
+      "learning_rate": 2.6332455100783084e-06,
+      "loss": 0.3902,
+      "step": 450
+    },
+    {
+      "epoch": 1.5480268056589725,
+      "grad_norm": 0.8515625,
+      "learning_rate": 2.4552414907918565e-06,
+      "loss": 0.384,
+      "step": 455
+    },
+    {
+      "epoch": 1.5650462716732263,
+      "grad_norm": 0.82421875,
+      "learning_rate": 2.282621466127982e-06,
+      "loss": 0.3854,
+      "step": 460
+    },
+    {
+      "epoch": 1.58206573768748,
+      "grad_norm": 0.7734375,
+      "learning_rate": 2.1155086189935227e-06,
+      "loss": 0.3911,
+      "step": 465
+    },
+    {
+      "epoch": 1.5990852037017338,
+      "grad_norm": 0.83203125,
+      "learning_rate": 1.9540222023333165e-06,
+      "loss": 0.3855,
+      "step": 470
+    },
+    {
+      "epoch": 1.6161046697159875,
+      "grad_norm": 0.78515625,
+      "learning_rate": 1.7982774540304404e-06,
+      "loss": 0.3861,
+      "step": 475
+    },
+    {
+      "epoch": 1.6331241357302415,
+      "grad_norm": 0.77734375,
+      "learning_rate": 1.6483855146716155e-06,
+      "loss": 0.3919,
+      "step": 480
+    },
+    {
+      "epoch": 1.6501436017444953,
+      "grad_norm": 0.94140625,
+      "learning_rate": 1.504453348236461e-06,
+      "loss": 0.3797,
+      "step": 485
+    },
+    {
+      "epoch": 1.6671630677587492,
+      "grad_norm": 0.8515625,
+      "learning_rate": 1.3665836657672493e-06,
+      "loss": 0.3855,
+      "step": 490
+    },
+    {
+      "epoch": 1.684182533773003,
+      "grad_norm": 0.72265625,
+      "learning_rate": 1.2348748520735221e-06,
+      "loss": 0.3845,
+      "step": 495
+    },
+    {
+      "epoch": 1.7012019997872567,
+      "grad_norm": 0.98828125,
+      "learning_rate": 1.1094208955240083e-06,
+      "loss": 0.3848,
+      "step": 500
+    },
+    {
+      "epoch": 1.7182214658015105,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.3907,
+      "step": 505
+    },
+    {
+      "epoch": 1.7352409318157642,
+      "grad_norm": 0.78125,
+      "learning_rate": 8.776311258888303e-07,
+      "loss": 0.3839,
+      "step": 510
+    },
+    {
+      "epoch": 1.752260397830018,
+      "grad_norm": 0.8203125,
+      "learning_rate": 7.714607196709633e-07,
+      "loss": 0.3916,
+      "step": 515
+    },
+    {
+      "epoch": 1.769279863844272,
+      "grad_norm": 0.81640625,
+      "learning_rate": 6.718758662973524e-07,
+      "loss": 0.3918,
+      "step": 520
+    },
+    {
+      "epoch": 1.7862993298585257,
+      "grad_norm": 0.91015625,
+      "learning_rate": 5.789476302446662e-07,
+      "loss": 0.3952,
+      "step": 525
+    },
+    {
+      "epoch": 1.8033187958727797,
+      "grad_norm": 0.8203125,
+      "learning_rate": 4.927423257789721e-07,
+      "loss": 0.3874,
+      "step": 530
+    },
+    {
+      "epoch": 1.8203382618870334,
+      "grad_norm": 0.8125,
+      "learning_rate": 4.133214696333943e-07,
+      "loss": 0.396,
+      "step": 535
+    },
+    {
+      "epoch": 1.8373577279012872,
+      "grad_norm": 0.875,
+      "learning_rate": 3.4074173710931804e-07,
+      "loss": 0.3822,
+      "step": 540
+    },
+    {
+      "epoch": 1.854377193915541,
+      "grad_norm": 0.87890625,
+      "learning_rate": 2.750549216324894e-07,
+      "loss": 0.3823,
+      "step": 545
+    },
+    {
+      "epoch": 1.8713966599297946,
+      "grad_norm": 0.83984375,
+      "learning_rate": 2.1630789779284677e-07,
+      "loss": 0.3943,
+      "step": 550
+    },
+    {
+      "epoch": 1.8884161259440484,
+      "grad_norm": 0.90625,
+      "learning_rate": 1.6454258789447286e-07,
+      "loss": 0.3882,
+      "step": 555
+    },
+    {
+      "epoch": 1.9054355919583021,
+      "grad_norm": 1.296875,
+      "learning_rate": 1.1979593203953033e-07,
+      "loss": 0.39,
+      "step": 560
+    },
+    {
+      "epoch": 1.9224550579725561,
+      "grad_norm": 0.765625,
+      "learning_rate": 8.209986176753947e-08,
+      "loss": 0.3884,
+      "step": 565
+    },
+    {
+      "epoch": 1.9394745239868099,
+      "grad_norm": 0.7265625,
+      "learning_rate": 5.1481277268794486e-08,
+      "loss": 0.3931,
+      "step": 570
+    },
+    {
+      "epoch": 1.9564939900010638,
+      "grad_norm": 0.8671875,
+      "learning_rate": 2.796202818819871e-08,
+      "loss": 0.389,
+      "step": 575
+    },
+    {
+      "epoch": 1.9735134560153176,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.1558898033191545e-08,
+      "loss": 0.3864,
+      "step": 580
+    },
+    {
+      "epoch": 1.9905329220295713,
+      "grad_norm": 0.8515625,
+      "learning_rate": 2.2835921969210917e-09,
+      "loss": 0.3921,
+      "step": 585
+    },
+    {
+      "epoch": 2.0,
+      "step": 588,
+      "total_flos": 3.4672082649056543e+18,
+      "train_loss": 0.4149530680001188,
+      "train_runtime": 38080.8907,
+      "train_samples_per_second": 1.975,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 588,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.4672082649056543e+18,
+  "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 sha256:8dc4306c08577f4175c6f1fe64e919c450820c309f86e5ad620e8ef910dcf021
+size 5432