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 +1,60 @@
+---
+library_name: transformers
+base_model: Qwen/Qwen2.5-Coder-3B-Instruct
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- griffith-bigdata/sft_text2sql
+model-index:
+- name: Qwen-2.5-Coder-3B-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. -->
+
+# Qwen-2.5-Coder-3B-SQL-Writer
+
+This model is a fine-tuned version of [/home/datht/huggingface/Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co//home/datht/huggingface/Qwen/Qwen2.5-Coder-3B-Instruct) on the /home/datht/mats/data/sft/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: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 128
+- total_eval_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.2.2+cu121
+- Datasets 4.1.1
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9946814168705456,
+    "total_flos": 2.1138563148357304e+18,
+    "train_loss": 0.4405478376373903,
+    "train_runtime": 25027.7179,
+    "train_samples": 37603,
+    "train_samples_per_second": 3.005,
+    "train_steps_per_second": 0.023
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/home/datht/huggingface/Qwen/Qwen2.5-Coder-3B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.45.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ca11f48e4b94713268508e27d399ef6e344770313bc0aa333e29658a81038d
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e7d63a7e780eb2f18b87642be883ddc8a392fb6e2c8dc81439ad308ec460d2b
+size 1214366696

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 6171877376
+  },
+  "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-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_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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"
+  }
+}

runs/Oct11_07-10-34_a6000/events.out.tfevents.1760166694.a6000.2127441.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a7170b92870a22708e525c3d33e3dc3e2151855131af1a74aa04d7aa12e8e9
+size 30286

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 sha256:690a58f7f9f9b3288faff3efe69defcb16891902894699bb920c605e180432c9
+size 11421995

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9946814168705456,
+    "total_flos": 2.1138563148357304e+18,
+    "train_loss": 0.4405478376373903,
+    "train_runtime": 25027.7179,
+    "train_samples": 37603,
+    "train_samples_per_second": 3.005,
+    "train_steps_per_second": 0.023
+}

trainer_state.json

@@ -0,0 +1,868 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9946814168705456,
+  "eval_steps": 500,
+  "global_step": 586,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0034038932028507603,
+      "grad_norm": 7.0625,
+      "learning_rate": 1.9999856294471073e-05,
+      "loss": 1.1956,
+      "step": 1
+    },
+    {
+      "epoch": 0.017019466014253803,
+      "grad_norm": 1.453125,
+      "learning_rate": 1.9996407568285402e-05,
+      "loss": 0.8575,
+      "step": 5
+    },
+    {
+      "epoch": 0.03403893202850761,
+      "grad_norm": 1.046875,
+      "learning_rate": 1.9985632854254735e-05,
+      "loss": 0.7124,
+      "step": 10
+    },
+    {
+      "epoch": 0.05105839804276141,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.996768359939288e-05,
+      "loss": 0.6181,
+      "step": 15
+    },
+    {
+      "epoch": 0.06807786405701521,
+      "grad_norm": 1.0078125,
+      "learning_rate": 1.994257269999431e-05,
+      "loss": 0.613,
+      "step": 20
+    },
+    {
+      "epoch": 0.08509733007126902,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.991031819789732e-05,
+      "loss": 0.5848,
+      "step": 25
+    },
+    {
+      "epoch": 0.10211679608552282,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.9870943267521144e-05,
+      "loss": 0.5576,
+      "step": 30
+    },
+    {
+      "epoch": 0.11913626209977662,
+      "grad_norm": 0.875,
+      "learning_rate": 1.9824476199215526e-05,
+      "loss": 0.5539,
+      "step": 35
+    },
+    {
+      "epoch": 0.13615572811403043,
+      "grad_norm": 0.8828125,
+      "learning_rate": 1.9770950378934433e-05,
+      "loss": 0.5261,
+      "step": 40
+    },
+    {
+      "epoch": 0.15317519412828423,
+      "grad_norm": 0.83984375,
+      "learning_rate": 1.9710404264248734e-05,
+      "loss": 0.5085,
+      "step": 45
+    },
+    {
+      "epoch": 0.17019466014253803,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.964288135671494e-05,
+      "loss": 0.5053,
+      "step": 50
+    },
+    {
+      "epoch": 0.18721412615679184,
+      "grad_norm": 0.84765625,
+      "learning_rate": 1.9568430170619953e-05,
+      "loss": 0.4847,
+      "step": 55
+    },
+    {
+      "epoch": 0.20423359217104564,
+      "grad_norm": 0.98828125,
+      "learning_rate": 1.94871041981242e-05,
+      "loss": 0.4862,
+      "step": 60
+    },
+    {
+      "epoch": 0.22125305818529944,
+      "grad_norm": 0.9375,
+      "learning_rate": 1.939896187082824e-05,
+      "loss": 0.4877,
+      "step": 65
+    },
+    {
+      "epoch": 0.23827252419955325,
+      "grad_norm": 0.92578125,
+      "learning_rate": 1.9304066517790465e-05,
+      "loss": 0.481,
+      "step": 70
+    },
+    {
+      "epoch": 0.25529199021380705,
+      "grad_norm": 0.953125,
+      "learning_rate": 1.9202486320026045e-05,
+      "loss": 0.4754,
+      "step": 75
+    },
+    {
+      "epoch": 0.27231145622806086,
+      "grad_norm": 0.96875,
+      "learning_rate": 1.9094294261519787e-05,
+      "loss": 0.4881,
+      "step": 80
+    },
+    {
+      "epoch": 0.28933092224231466,
+      "grad_norm": 0.8203125,
+      "learning_rate": 1.897956807678813e-05,
+      "loss": 0.4884,
+      "step": 85
+    },
+    {
+      "epoch": 0.30635038825656846,
+      "grad_norm": 0.87890625,
+      "learning_rate": 1.8858390195027986e-05,
+      "loss": 0.4759,
+      "step": 90
+    },
+    {
+      "epoch": 0.32336985427082227,
+      "grad_norm": 0.93359375,
+      "learning_rate": 1.873084768089246e-05,
+      "loss": 0.4678,
+      "step": 95
+    },
+    {
+      "epoch": 0.34038932028507607,
+      "grad_norm": 0.87890625,
+      "learning_rate": 1.8597032171936103e-05,
+      "loss": 0.4744,
+      "step": 100
+    },
+    {
+      "epoch": 0.3574087862993299,
+      "grad_norm": 0.8359375,
+      "learning_rate": 1.8457039812774574e-05,
+      "loss": 0.4693,
+      "step": 105
+    },
+    {
+      "epoch": 0.3744282523135837,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.831097118600604e-05,
+      "loss": 0.4697,
+      "step": 110
+    },
+    {
+      "epoch": 0.3914477183278375,
+      "grad_norm": 0.89453125,
+      "learning_rate": 1.8158931239943957e-05,
+      "loss": 0.4524,
+      "step": 115
+    },
+    {
+      "epoch": 0.4084671843420913,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.800102921321316e-05,
+      "loss": 0.4487,
+      "step": 120
+    },
+    {
+      "epoch": 0.4254866503563451,
+      "grad_norm": 0.9296875,
+      "learning_rate": 1.7837378556263368e-05,
+      "loss": 0.4683,
+      "step": 125
+    },
+    {
+      "epoch": 0.4425061163705989,
+      "grad_norm": 0.98828125,
+      "learning_rate": 1.766809684985661e-05,
+      "loss": 0.4567,
+      "step": 130
+    },
+    {
+      "epoch": 0.4595255823848527,
+      "grad_norm": 0.90625,
+      "learning_rate": 1.7493305720587047e-05,
+      "loss": 0.4682,
+      "step": 135
+    },
+    {
+      "epoch": 0.4765450483991065,
+      "grad_norm": 0.9609375,
+      "learning_rate": 1.7313130753493917e-05,
+      "loss": 0.4649,
+      "step": 140
+    },
+    {
+      "epoch": 0.4935645144133603,
+      "grad_norm": 0.92578125,
+      "learning_rate": 1.7127701401830422e-05,
+      "loss": 0.4412,
+      "step": 145
+    },
+    {
+      "epoch": 0.5105839804276141,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.6937150894053306e-05,
+      "loss": 0.4505,
+      "step": 150
+    },
+    {
+      "epoch": 0.5276034464418679,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.674161613810003e-05,
+      "loss": 0.4655,
+      "step": 155
+    },
+    {
+      "epoch": 0.5446229124561217,
+      "grad_norm": 0.96484375,
+      "learning_rate": 1.6541237623022333e-05,
+      "loss": 0.4536,
+      "step": 160
+    },
+    {
+      "epoch": 0.5616423784703755,
+      "grad_norm": 0.84765625,
+      "learning_rate": 1.6336159318046698e-05,
+      "loss": 0.4398,
+      "step": 165
+    },
+    {
+      "epoch": 0.5786618444846293,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.612652856913449e-05,
+      "loss": 0.4548,
+      "step": 170
+    },
+    {
+      "epoch": 0.5956813104988831,
+      "grad_norm": 0.9453125,
+      "learning_rate": 1.5912495993115848e-05,
+      "loss": 0.4456,
+      "step": 175
+    },
+    {
+      "epoch": 0.6127007765131369,
+      "grad_norm": 0.953125,
+      "learning_rate": 1.5694215369473584e-05,
+      "loss": 0.4466,
+      "step": 180
+    },
+    {
+      "epoch": 0.6297202425273907,
+      "grad_norm": 0.93359375,
+      "learning_rate": 1.547184352985472e-05,
+      "loss": 0.4353,
+      "step": 185
+    },
+    {
+      "epoch": 0.6467397085416445,
+      "grad_norm": 0.9296875,
+      "learning_rate": 1.5245540245389053e-05,
+      "loss": 0.426,
+      "step": 190
+    },
+    {
+      "epoch": 0.6637591745558983,
+      "grad_norm": 0.93359375,
+      "learning_rate": 1.501546811189584e-05,
+      "loss": 0.4273,
+      "step": 195
+    },
+    {
+      "epoch": 0.6807786405701521,
+      "grad_norm": 0.875,
+      "learning_rate": 1.4781792433060884e-05,
+      "loss": 0.4401,
+      "step": 200
+    },
+    {
+      "epoch": 0.6977981065844059,
+      "grad_norm": 0.96875,
+      "learning_rate": 1.4544681101668099e-05,
+      "loss": 0.423,
+      "step": 205
+    },
+    {
+      "epoch": 0.7148175725986597,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.4304304478970839e-05,
+      "loss": 0.4402,
+      "step": 210
+    },
+    {
+      "epoch": 0.7318370386129135,
+      "grad_norm": 0.90625,
+      "learning_rate": 1.4060835272289673e-05,
+      "loss": 0.4352,
+      "step": 215
+    },
+    {
+      "epoch": 0.7488565046271674,
+      "grad_norm": 0.9375,
+      "learning_rate": 1.381444841092452e-05,
+      "loss": 0.434,
+      "step": 220
+    },
+    {
+      "epoch": 0.7658759706414211,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.3565320920470348e-05,
+      "loss": 0.4287,
+      "step": 225
+    },
+    {
+      "epoch": 0.782895436655675,
+      "grad_norm": 0.87890625,
+      "learning_rate": 1.3313631795626691e-05,
+      "loss": 0.431,
+      "step": 230
+    },
+    {
+      "epoch": 0.7999149026699287,
+      "grad_norm": 0.875,
+      "learning_rate": 1.3059561871592413e-05,
+      "loss": 0.4329,
+      "step": 235
+    },
+    {
+      "epoch": 0.8169343686841826,
+      "grad_norm": 0.90625,
+      "learning_rate": 1.2803293694138077e-05,
+      "loss": 0.4258,
+      "step": 240
+    },
+    {
+      "epoch": 0.8339538346984363,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.254501138844931e-05,
+      "loss": 0.4118,
+      "step": 245
+    },
+    {
+      "epoch": 0.8509733007126902,
+      "grad_norm": 0.89453125,
+      "learning_rate": 1.228490052683537e-05,
+      "loss": 0.4249,
+      "step": 250
+    },
+    {
+      "epoch": 0.8679927667269439,
+      "grad_norm": 0.84765625,
+      "learning_rate": 1.202314799539797e-05,
+      "loss": 0.4339,
+      "step": 255
+    },
+    {
+      "epoch": 0.8850122327411978,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.1759941859756173e-05,
+      "loss": 0.4336,
+      "step": 260
+    },
+    {
+      "epoch": 0.9020316987554515,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.1495471229923805e-05,
+      "loss": 0.435,
+      "step": 265
+    },
+    {
+      "epoch": 0.9190511647697054,
+      "grad_norm": 0.875,
+      "learning_rate": 1.1229926124436506e-05,
+      "loss": 0.4182,
+      "step": 270
+    },
+    {
+      "epoch": 0.9360706307839591,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.0963497333826002e-05,
+      "loss": 0.4221,
+      "step": 275
+    },
+    {
+      "epoch": 0.953090096798213,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.0696376283539704e-05,
+      "loss": 0.4157,
+      "step": 280
+    },
+    {
+      "epoch": 0.9701095628124667,
+      "grad_norm": 0.89453125,
+      "learning_rate": 1.042875489640415e-05,
+      "loss": 0.4402,
+      "step": 285
+    },
+    {
+      "epoch": 0.9871290288267206,
+      "grad_norm": 0.9375,
+      "learning_rate": 1.0160825454731072e-05,
+      "loss": 0.425,
+      "step": 290
+    },
+    {
+      "epoch": 1.0041484948409745,
+      "grad_norm": 0.8515625,
+      "learning_rate": 9.892780462165172e-06,
+      "loss": 0.4046,
+      "step": 295
+    },
+    {
+      "epoch": 1.0211679608552282,
+      "grad_norm": 0.890625,
+      "learning_rate": 9.624812505372907e-06,
+      "loss": 0.4138,
+      "step": 300
+    },
+    {
+      "epoch": 1.038187426869482,
+      "grad_norm": 0.84765625,
+      "learning_rate": 9.35711411567156e-06,
+      "loss": 0.3996,
+      "step": 305
+    },
+    {
+      "epoch": 1.0552068928837357,
+      "grad_norm": 0.88671875,
+      "learning_rate": 9.089877630698159e-06,
+      "loss": 0.4033,
+      "step": 310
+    },
+    {
+      "epoch": 1.0722263588979897,
+      "grad_norm": 0.828125,
+      "learning_rate": 8.823295056217487e-06,
+      "loss": 0.4152,
+      "step": 315
+    },
+    {
+      "epoch": 1.0892458249122434,
+      "grad_norm": 0.859375,
+      "learning_rate": 8.557557928168568e-06,
+      "loss": 0.3985,
+      "step": 320
+    },
+    {
+      "epoch": 1.1062652909264972,
+      "grad_norm": 0.9140625,
+      "learning_rate": 8.292857175048715e-06,
+      "loss": 0.3984,
+      "step": 325
+    },
+    {
+      "epoch": 1.123284756940751,
+      "grad_norm": 0.8828125,
+      "learning_rate": 8.029382980734e-06,
+      "loss": 0.4165,
+      "step": 330
+    },
+    {
+      "epoch": 1.1403042229550047,
+      "grad_norm": 0.8828125,
+      "learning_rate": 7.767324647834759e-06,
+      "loss": 0.3934,
+      "step": 335
+    },
+    {
+      "epoch": 1.1573236889692586,
+      "grad_norm": 0.82421875,
+      "learning_rate": 7.506870461684215e-06,
+      "loss": 0.4083,
+      "step": 340
+    },
+    {
+      "epoch": 1.1743431549835124,
+      "grad_norm": 0.84765625,
+      "learning_rate": 7.24820755505808e-06,
+      "loss": 0.4071,
+      "step": 345
+    },
+    {
+      "epoch": 1.1913626209977661,
+      "grad_norm": 0.85546875,
+      "learning_rate": 6.991521773722186e-06,
+      "loss": 0.4187,
+      "step": 350
+    },
+    {
+      "epoch": 1.20838208701202,
+      "grad_norm": 0.95703125,
+      "learning_rate": 6.736997542904844e-06,
+      "loss": 0.4026,
+      "step": 355
+    },
+    {
+      "epoch": 1.2254015530262738,
+      "grad_norm": 0.8671875,
+      "learning_rate": 6.484817734789839e-06,
+      "loss": 0.4099,
+      "step": 360
+    },
+    {
+      "epoch": 1.2424210190405276,
+      "grad_norm": 0.8125,
+      "learning_rate": 6.235163537125257e-06,
+      "loss": 0.3996,
+      "step": 365
+    },
+    {
+      "epoch": 1.2594404850547813,
+      "grad_norm": 0.95703125,
+      "learning_rate": 5.988214323042581e-06,
+      "loss": 0.397,
+      "step": 370
+    },
+    {
+      "epoch": 1.276459951069035,
+      "grad_norm": 0.8828125,
+      "learning_rate": 5.744147522179515e-06,
+      "loss": 0.3983,
+      "step": 375
+    },
+    {
+      "epoch": 1.293479417083289,
+      "grad_norm": 0.87109375,
+      "learning_rate": 5.503138493199247e-06,
+      "loss": 0.4045,
+      "step": 380
+    },
+    {
+      "epoch": 1.3104988830975428,
+      "grad_norm": 0.8125,
+      "learning_rate": 5.26536039779761e-06,
+      "loss": 0.4186,
+      "step": 385
+    },
+    {
+      "epoch": 1.3275183491117966,
+      "grad_norm": 0.88671875,
+      "learning_rate": 5.030984076288805e-06,
+      "loss": 0.4073,
+      "step": 390
+    },
+    {
+      "epoch": 1.3445378151260505,
+      "grad_norm": 0.90234375,
+      "learning_rate": 4.800177924858933e-06,
+      "loss": 0.4093,
+      "step": 395
+    },
+    {
+      "epoch": 1.3615572811403043,
+      "grad_norm": 0.8828125,
+      "learning_rate": 4.573107774575665e-06,
+      "loss": 0.4009,
+      "step": 400
+    },
+    {
+      "epoch": 1.378576747154558,
+      "grad_norm": 0.88671875,
+      "learning_rate": 4.34993677224086e-06,
+      "loss": 0.3877,
+      "step": 405
+    },
+    {
+      "epoch": 1.3955962131688118,
+      "grad_norm": 0.890625,
+      "learning_rate": 4.130825263171833e-06,
+      "loss": 0.4145,
+      "step": 410
+    },
+    {
+      "epoch": 1.4126156791830655,
+      "grad_norm": 0.8359375,
+      "learning_rate": 3.915930675995424e-06,
+      "loss": 0.409,
+      "step": 415
+    },
+    {
+      "epoch": 1.4296351451973195,
+      "grad_norm": 0.9296875,
+      "learning_rate": 3.7054074095376845e-06,
+      "loss": 0.412,
+      "step": 420
+    },
+    {
+      "epoch": 1.4466546112115732,
+      "grad_norm": 0.88671875,
+      "learning_rate": 3.4994067218904383e-06,
+      "loss": 0.4094,
+      "step": 425
+    },
+    {
+      "epoch": 1.463674077225827,
+      "grad_norm": 0.96875,
+      "learning_rate": 3.2980766217343852e-06,
+      "loss": 0.4011,
+      "step": 430
+    },
+    {
+      "epoch": 1.480693543240081,
+      "grad_norm": 0.85546875,
+      "learning_rate": 3.101561761996912e-06,
+      "loss": 0.4041,
+      "step": 435
+    },
+    {
+      "epoch": 1.4977130092543347,
+      "grad_norm": 0.8515625,
+      "learning_rate": 2.910003335920918e-06,
+      "loss": 0.4129,
+      "step": 440
+    },
+    {
+      "epoch": 1.5147324752685885,
+      "grad_norm": 0.87890625,
+      "learning_rate": 2.7235389756194097e-06,
+      "loss": 0.4021,
+      "step": 445
+    },
+    {
+      "epoch": 1.5317519412828422,
+      "grad_norm": 0.875,
+      "learning_rate": 2.542302653188704e-06,
+      "loss": 0.409,
+      "step": 450
+    },
+    {
+      "epoch": 1.548771407297096,
+      "grad_norm": 0.921875,
+      "learning_rate": 2.3664245844513078e-06,
+      "loss": 0.3986,
+      "step": 455
+    },
+    {
+      "epoch": 1.5657908733113497,
+      "grad_norm": 0.8828125,
+      "learning_rate": 2.1960311353976318e-06,
+      "loss": 0.4126,
+      "step": 460
+    },
+    {
+      "epoch": 1.5828103393256037,
+      "grad_norm": 0.87890625,
+      "learning_rate": 2.031244731393739e-06,
+      "loss": 0.4007,
+      "step": 465
+    },
+    {
+      "epoch": 1.5998298053398574,
+      "grad_norm": 0.8359375,
+      "learning_rate": 1.8721837692204115e-06,
+      "loss": 0.3942,
+      "step": 470
+    },
+    {
+      "epoch": 1.6168492713541114,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.7189625320066573e-06,
+      "loss": 0.3918,
+      "step": 475
+    },
+    {
+      "epoch": 1.6338687373683651,
+      "grad_norm": 0.8515625,
+      "learning_rate": 1.5716911071188611e-06,
+      "loss": 0.4207,
+      "step": 480
+    },
+    {
+      "epoch": 1.6508882033826189,
+      "grad_norm": 0.83203125,
+      "learning_rate": 1.4304753070645083e-06,
+      "loss": 0.3924,
+      "step": 485
+    },
+    {
+      "epoch": 1.6679076693968726,
+      "grad_norm": 0.84765625,
+      "learning_rate": 1.295416593467338e-06,
+      "loss": 0.3986,
+      "step": 490
+    },
+    {
+      "epoch": 1.6849271354111264,
+      "grad_norm": 0.859375,
+      "learning_rate": 1.166612004168568e-06,
+      "loss": 0.4055,
+      "step": 495
+    },
+    {
+      "epoch": 1.7019466014253801,
+      "grad_norm": 0.98046875,
+      "learning_rate": 1.0441540835065101e-06,
+      "loss": 0.3996,
+      "step": 500
+    },
+    {
+      "epoch": 1.718966067439634,
+      "grad_norm": 0.8359375,
+      "learning_rate": 9.28130815824746e-07,
+      "loss": 0.411,
+      "step": 505
+    },
+    {
+      "epoch": 1.7359855334538878,
+      "grad_norm": 0.8359375,
+      "learning_rate": 8.186255622565642e-07,
+      "loss": 0.4101,
+      "step": 510
+    },
+    {
+      "epoch": 1.7530049994681418,
+      "grad_norm": 0.89453125,
+      "learning_rate": 7.15717000831132e-07,
+      "loss": 0.4132,
+      "step": 515
+    },
+    {
+      "epoch": 1.7700244654823956,
+      "grad_norm": 0.875,
+      "learning_rate": 6.19479069944402e-07,
+      "loss": 0.4109,
+      "step": 520
+    },
+    {
+      "epoch": 1.7870439314966493,
+      "grad_norm": 0.8828125,
+      "learning_rate": 5.299809152353863e-07,
+      "loss": 0.4106,
+      "step": 525
+    },
+    {
+      "epoch": 1.804063397510903,
+      "grad_norm": 0.8671875,
+      "learning_rate": 4.4728683990596267e-07,
+      "loss": 0.3986,
+      "step": 530
+    },
+    {
+      "epoch": 1.8210828635251568,
+      "grad_norm": 0.8671875,
+      "learning_rate": 3.714562585198922e-07,
+      "loss": 0.4101,
+      "step": 535
+    },
+    {
+      "epoch": 1.8381023295394106,
+      "grad_norm": 0.9296875,
+      "learning_rate": 3.025436543142801e-07,
+      "loss": 0.3974,
+      "step": 540
+    },
+    {
+      "epoch": 1.8551217955536645,
+      "grad_norm": 0.93359375,
+      "learning_rate": 2.4059854005410224e-07,
+      "loss": 0.4048,
+      "step": 545
+    },
+    {
+      "epoch": 1.8721412615679183,
+      "grad_norm": 0.90625,
+      "learning_rate": 1.856654224579635e-07,
+      "loss": 0.4075,
+      "step": 550
+    },
+    {
+      "epoch": 1.8891607275821722,
+      "grad_norm": 0.9375,
+      "learning_rate": 1.3778377022063083e-07,
+      "loss": 0.4045,
+      "step": 555
+    },
+    {
+      "epoch": 1.906180193596426,
+      "grad_norm": 0.9140625,
+      "learning_rate": 9.698798565531464e-08,
+      "loss": 0.4043,
+      "step": 560
+    },
+    {
+      "epoch": 1.9231996596106797,
+      "grad_norm": 0.86328125,
+      "learning_rate": 6.330737997607194e-08,
+      "loss": 0.3944,
+      "step": 565
+    },
+    {
+      "epoch": 1.9402191256249335,
+      "grad_norm": 0.84375,
+      "learning_rate": 3.6766152238106866e-08,
+      "loss": 0.4082,
+      "step": 570
+    },
+    {
+      "epoch": 1.9572385916391872,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.738337195107187e-08,
+      "loss": 0.404,
+      "step": 575
+    },
+    {
+      "epoch": 1.974258057653441,
+      "grad_norm": 0.88671875,
+      "learning_rate": 5.172965377890915e-09,
+      "loss": 0.4013,
+      "step": 580
+    },
+    {
+      "epoch": 1.991277523667695,
+      "grad_norm": 0.87890625,
+      "learning_rate": 1.4370552892883916e-10,
+      "loss": 0.4101,
+      "step": 585
+    },
+    {
+      "epoch": 1.9946814168705456,
+      "step": 586,
+      "total_flos": 2.1138563148357304e+18,
+      "train_loss": 0.4405478376373903,
+      "train_runtime": 25027.7179,
+      "train_samples_per_second": 3.005,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 586,
+  "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": 2.1138563148357304e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1308ddaa7512a3fe9582495d267ec1f98bca04d479ccea4a5576aee63e23de81
+size 5304