初始化项目，由ModelHub XC社区提供模型

Model: jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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 +1,69 @@
+---
+library_name: transformers
+base_model: Qwen/Qwen3-8B-Base
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrachat_200k
+model-index:
+- name: qwen3-8b-base-sft-ultrachat-4xh200-batch-128-20260420-124036
+  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. -->
+
+# qwen3-8b-base-sft-ultrachat-4xh200-batch-128-20260420-124036
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B-Base](https://huggingface.co/Qwen/Qwen3-8B-Base) on the HuggingFaceH4/ultrachat_200k dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0849
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0891        | 0.2111 | 200  | 1.1102          |
+| 1.095         | 0.4222 | 400  | 1.0990          |
+| 1.0886        | 0.6332 | 600  | 1.0901          |
+| 1.0856        | 0.8443 | 800  | 1.0849          |
+
+
+### Framework versions
+
+- Transformers 4.51.0
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.21.4

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 +1,14 @@
+{
+    "epoch": 0.9994722955145119,
+    "eval_loss": 1.084205985069275,
+    "eval_runtime": 268.589,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 49.954,
+    "eval_steps_per_second": 0.782,
+    "total_flos": 2.8182891025525637e+18,
+    "train_loss": 1.100929617000608,
+    "train_runtime": 11309.6924,
+    "train_samples": 207864,
+    "train_samples_per_second": 10.721,
+    "train_steps_per_second": 0.084
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9994722955145119,
+    "eval_loss": 1.084205985069275,
+    "eval_runtime": 268.589,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 49.954,
+    "eval_steps_per_second": 0.782
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76f1c54c6608a0d3eb2bef8c307d841b0093af4b4c363c89da6e4f2193294e4
+size 4972454376

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078e0d33058f2fe12fb85dce665c13a2b896fc00ceac85cea125071ce1cc27b1
+size 4832048608

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b8ec82a609f105d28a2e1976dc83c44f7a8051b72a472535504aa90593912d
+size 4832048656

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a6edf78f5855d228458b922dd9bbbeff16aa51ece2bbd8f5bf594bce012f3d
+size 4999855528

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4625d2a7af6cd6da567f4d5646a9b87001aaa788e880aaec0019f6d9ccc41f83
+size 4832048672

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:196329d5490cdaf6e3c80078b802e8f301f69ad18f2fd4f05a04c3a5c2f1a658
+size 4832048672

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac641adcef45a28ede965972faabd970cbddc698e9b5617149fd6a2588cc6d3
+size 3462482728

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9994722955145119,
+    "total_flos": 2.8182891025525637e+18,
+    "train_loss": 1.100929617000608,
+    "train_runtime": 11309.6924,
+    "train_samples": 207864,
+    "train_samples_per_second": 10.721,
+    "train_steps_per_second": 0.084
+}

trainer_state.json

@@ -0,0 +1,740 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9994722955145119,
+  "eval_steps": 200,
+  "global_step": 947,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0010554089709762533,
+      "grad_norm": 4.428989887237549,
+      "learning_rate": 0.0,
+      "loss": 1.4444,
+      "step": 1
+    },
+    {
+      "epoch": 0.010554089709762533,
+      "grad_norm": 3.5337846279144287,
+      "learning_rate": 1.8947368421052634e-06,
+      "loss": 1.4272,
+      "step": 10
+    },
+    {
+      "epoch": 0.021108179419525065,
+      "grad_norm": 1.0835645198822021,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.3383,
+      "step": 20
+    },
+    {
+      "epoch": 0.0316622691292876,
+      "grad_norm": 1.217992901802063,
+      "learning_rate": 6.105263157894738e-06,
+      "loss": 1.2714,
+      "step": 30
+    },
+    {
+      "epoch": 0.04221635883905013,
+      "grad_norm": 1.7282902002334595,
+      "learning_rate": 8.210526315789475e-06,
+      "loss": 1.2262,
+      "step": 40
+    },
+    {
+      "epoch": 0.052770448548812667,
+      "grad_norm": 1.640160322189331,
+      "learning_rate": 1.0315789473684213e-05,
+      "loss": 1.1945,
+      "step": 50
+    },
+    {
+      "epoch": 0.0633245382585752,
+      "grad_norm": 1.4558825492858887,
+      "learning_rate": 1.2421052631578949e-05,
+      "loss": 1.1686,
+      "step": 60
+    },
+    {
+      "epoch": 0.07387862796833773,
+      "grad_norm": 1.016249656677246,
+      "learning_rate": 1.4526315789473687e-05,
+      "loss": 1.1422,
+      "step": 70
+    },
+    {
+      "epoch": 0.08443271767810026,
+      "grad_norm": 0.7121432423591614,
+      "learning_rate": 1.6631578947368423e-05,
+      "loss": 1.1314,
+      "step": 80
+    },
+    {
+      "epoch": 0.09498680738786279,
+      "grad_norm": 0.7841984033584595,
+      "learning_rate": 1.873684210526316e-05,
+      "loss": 1.1275,
+      "step": 90
+    },
+    {
+      "epoch": 0.10554089709762533,
+      "grad_norm": 0.6388397216796875,
+      "learning_rate": 1.999891231617599e-05,
+      "loss": 1.1178,
+      "step": 100
+    },
+    {
+      "epoch": 0.11609498680738786,
+      "grad_norm": 0.5346229076385498,
+      "learning_rate": 1.9986678590325273e-05,
+      "loss": 1.1205,
+      "step": 110
+    },
+    {
+      "epoch": 0.1266490765171504,
+      "grad_norm": 0.6061886548995972,
+      "learning_rate": 1.996086822074945e-05,
+      "loss": 1.1135,
+      "step": 120
+    },
+    {
+      "epoch": 0.13720316622691292,
+      "grad_norm": 0.5429868698120117,
+      "learning_rate": 1.9921516296010645e-05,
+      "loss": 1.1072,
+      "step": 130
+    },
+    {
+      "epoch": 0.14775725593667546,
+      "grad_norm": 0.5146633386611938,
+      "learning_rate": 1.9868676314081907e-05,
+      "loss": 1.0997,
+      "step": 140
+    },
+    {
+      "epoch": 0.158311345646438,
+      "grad_norm": 0.5138978362083435,
+      "learning_rate": 1.980242010961803e-05,
+      "loss": 1.0973,
+      "step": 150
+    },
+    {
+      "epoch": 0.16886543535620052,
+      "grad_norm": 0.48871827125549316,
+      "learning_rate": 1.9722837756298112e-05,
+      "loss": 1.1089,
+      "step": 160
+    },
+    {
+      "epoch": 0.17941952506596306,
+      "grad_norm": 0.5564476251602173,
+      "learning_rate": 1.96300374443726e-05,
+      "loss": 1.0914,
+      "step": 170
+    },
+    {
+      "epoch": 0.18997361477572558,
+      "grad_norm": 0.48119252920150757,
+      "learning_rate": 1.9524145333581315e-05,
+      "loss": 1.1018,
+      "step": 180
+    },
+    {
+      "epoch": 0.20052770448548812,
+      "grad_norm": 0.45517972111701965,
+      "learning_rate": 1.9405305381642376e-05,
+      "loss": 1.0982,
+      "step": 190
+    },
+    {
+      "epoch": 0.21108179419525067,
+      "grad_norm": 0.47854238748550415,
+      "learning_rate": 1.9273679148545246e-05,
+      "loss": 1.0891,
+      "step": 200
+    },
+    {
+      "epoch": 0.21108179419525067,
+      "eval_loss": 1.11018705368042,
+      "eval_runtime": 269.0491,
+      "eval_samples_per_second": 49.868,
+      "eval_steps_per_second": 0.781,
+      "step": 200
+    },
+    {
+      "epoch": 0.22163588390501318,
+      "grad_norm": 0.43568843603134155,
+      "learning_rate": 1.9129445576913886e-05,
+      "loss": 1.0998,
+      "step": 210
+    },
+    {
+      "epoch": 0.23218997361477572,
+      "grad_norm": 0.4271477162837982,
+      "learning_rate": 1.897280074873868e-05,
+      "loss": 1.1231,
+      "step": 220
+    },
+    {
+      "epoch": 0.24274406332453827,
+      "grad_norm": 0.44812774658203125,
+      "learning_rate": 1.8803957618807764e-05,
+      "loss": 1.1038,
+      "step": 230
+    },
+    {
+      "epoch": 0.2532981530343008,
+      "grad_norm": 0.4037184417247772,
+      "learning_rate": 1.862314572520028e-05,
+      "loss": 1.1104,
+      "step": 240
+    },
+    {
+      "epoch": 0.2638522427440633,
+      "grad_norm": 0.44267192482948303,
+      "learning_rate": 1.843061087723496e-05,
+      "loss": 1.0939,
+      "step": 250
+    },
+    {
+      "epoch": 0.27440633245382584,
+      "grad_norm": 0.44187697768211365,
+      "learning_rate": 1.8226614821298444e-05,
+      "loss": 1.1081,
+      "step": 260
+    },
+    {
+      "epoch": 0.2849604221635884,
+      "grad_norm": 0.41764840483665466,
+      "learning_rate": 1.8011434885007482e-05,
+      "loss": 1.0985,
+      "step": 270
+    },
+    {
+      "epoch": 0.2955145118733509,
+      "grad_norm": 0.3874802589416504,
+      "learning_rate": 1.7785363600188894e-05,
+      "loss": 1.1005,
+      "step": 280
+    },
+    {
+      "epoch": 0.30606860158311344,
+      "grad_norm": 0.3772076666355133,
+      "learning_rate": 1.7548708305189724e-05,
+      "loss": 1.09,
+      "step": 290
+    },
+    {
+      "epoch": 0.316622691292876,
+      "grad_norm": 0.4143645167350769,
+      "learning_rate": 1.7301790727058344e-05,
+      "loss": 1.0849,
+      "step": 300
+    },
+    {
+      "epoch": 0.32717678100263853,
+      "grad_norm": 0.43071797490119934,
+      "learning_rate": 1.7044946544164434e-05,
+      "loss": 1.0956,
+      "step": 310
+    },
+    {
+      "epoch": 0.33773087071240104,
+      "grad_norm": 0.3988950252532959,
+      "learning_rate": 1.6778524929852513e-05,
+      "loss": 1.1042,
+      "step": 320
+    },
+    {
+      "epoch": 0.3482849604221636,
+      "grad_norm": 0.40434718132019043,
+      "learning_rate": 1.650288807774937e-05,
+      "loss": 1.0978,
+      "step": 330
+    },
+    {
+      "epoch": 0.35883905013192613,
+      "grad_norm": 0.41674408316612244,
+      "learning_rate": 1.6218410709370735e-05,
+      "loss": 1.0914,
+      "step": 340
+    },
+    {
+      "epoch": 0.36939313984168864,
+      "grad_norm": 0.395465224981308,
+      "learning_rate": 1.592547956469662e-05,
+      "loss": 1.1126,
+      "step": 350
+    },
+    {
+      "epoch": 0.37994722955145116,
+      "grad_norm": 0.3750782608985901,
+      "learning_rate": 1.562449287640781e-05,
+      "loss": 1.099,
+      "step": 360
+    },
+    {
+      "epoch": 0.39050131926121373,
+      "grad_norm": 0.3862684369087219,
+      "learning_rate": 1.5315859828498353e-05,
+      "loss": 1.0933,
+      "step": 370
+    },
+    {
+      "epoch": 0.40105540897097625,
+      "grad_norm": 0.40379074215888977,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.0905,
+      "step": 380
+    },
+    {
+      "epoch": 0.41160949868073876,
+      "grad_norm": 0.3791244328022003,
+      "learning_rate": 1.4677342794574819e-05,
+      "loss": 1.0835,
+      "step": 390
+    },
+    {
+      "epoch": 0.42216358839050133,
+      "grad_norm": 0.36901775002479553,
+      "learning_rate": 1.4348326856751496e-05,
+      "loss": 1.095,
+      "step": 400
+    },
+    {
+      "epoch": 0.42216358839050133,
+      "eval_loss": 1.0990158319473267,
+      "eval_runtime": 269.2071,
+      "eval_samples_per_second": 49.839,
+      "eval_steps_per_second": 0.78,
+      "step": 400
+    },
+    {
+      "epoch": 0.43271767810026385,
+      "grad_norm": 0.38086214661598206,
+      "learning_rate": 1.401339947559889e-05,
+      "loss": 1.1001,
+      "step": 410
+    },
+    {
+      "epoch": 0.44327176781002636,
+      "grad_norm": 0.42641252279281616,
+      "learning_rate": 1.367301597664757e-05,
+      "loss": 1.085,
+      "step": 420
+    },
+    {
+      "epoch": 0.45382585751978893,
+      "grad_norm": 0.37229016423225403,
+      "learning_rate": 1.3327639102885939e-05,
+      "loss": 1.0852,
+      "step": 430
+    },
+    {
+      "epoch": 0.46437994722955145,
+      "grad_norm": 0.38543465733528137,
+      "learning_rate": 1.2977738385672558e-05,
+      "loss": 1.0982,
+      "step": 440
+    },
+    {
+      "epoch": 0.47493403693931396,
+      "grad_norm": 0.36999842524528503,
+      "learning_rate": 1.2623789506419792e-05,
+      "loss": 1.0844,
+      "step": 450
+    },
+    {
+      "epoch": 0.48548812664907653,
+      "grad_norm": 0.3730550706386566,
+      "learning_rate": 1.2266273649916669e-05,
+      "loss": 1.0838,
+      "step": 460
+    },
+    {
+      "epoch": 0.49604221635883905,
+      "grad_norm": 0.35631632804870605,
+      "learning_rate": 1.190567685016998e-05,
+      "loss": 1.076,
+      "step": 470
+    },
+    {
+      "epoch": 0.5065963060686016,
+      "grad_norm": 0.3838544487953186,
+      "learning_rate": 1.1542489329653024e-05,
+      "loss": 1.0831,
+      "step": 480
+    },
+    {
+      "epoch": 0.5171503957783641,
+      "grad_norm": 0.40018004179000854,
+      "learning_rate": 1.1177204832860214e-05,
+      "loss": 1.0813,
+      "step": 490
+    },
+    {
+      "epoch": 0.5277044854881267,
+      "grad_norm": 0.3892735540866852,
+      "learning_rate": 1.08103199550736e-05,
+      "loss": 1.0909,
+      "step": 500
+    },
+    {
+      "epoch": 0.5382585751978892,
+      "grad_norm": 0.42785775661468506,
+      "learning_rate": 1.044233346725379e-05,
+      "loss": 1.0827,
+      "step": 510
+    },
+    {
+      "epoch": 0.5488126649076517,
+      "grad_norm": 0.37400808930397034,
+      "learning_rate": 1.0073745637973125e-05,
+      "loss": 1.0896,
+      "step": 520
+    },
+    {
+      "epoch": 0.5593667546174143,
+      "grad_norm": 0.38293296098709106,
+      "learning_rate": 9.705057553312857e-06,
+      "loss": 1.0847,
+      "step": 530
+    },
+    {
+      "epoch": 0.5699208443271768,
+      "grad_norm": 0.39219433069229126,
+      "learning_rate": 9.336770435648963e-06,
+      "loss": 1.0833,
+      "step": 540
+    },
+    {
+      "epoch": 0.5804749340369393,
+      "grad_norm": 0.3722192645072937,
+      "learning_rate": 8.969384962252646e-06,
+      "loss": 1.0823,
+      "step": 550
+    },
+    {
+      "epoch": 0.5910290237467019,
+      "grad_norm": 0.4041948914527893,
+      "learning_rate": 8.60340058463194e-06,
+      "loss": 1.0733,
+      "step": 560
+    },
+    {
+      "epoch": 0.6015831134564644,
+      "grad_norm": 0.36892595887184143,
+      "learning_rate": 8.239314849539639e-06,
+      "loss": 1.0618,
+      "step": 570
+    },
+    {
+      "epoch": 0.6121372031662269,
+      "grad_norm": 0.3803699314594269,
+      "learning_rate": 7.877622722570772e-06,
+      "loss": 1.0896,
+      "step": 580
+    },
+    {
+      "epoch": 0.6226912928759895,
+      "grad_norm": 0.3644523620605469,
+      "learning_rate": 7.518815915269025e-06,
+      "loss": 1.0819,
+      "step": 590
+    },
+    {
+      "epoch": 0.633245382585752,
+      "grad_norm": 0.3542793095111847,
+      "learning_rate": 7.163382216657033e-06,
+      "loss": 1.0886,
+      "step": 600
+    },
+    {
+      "epoch": 0.633245382585752,
+      "eval_loss": 1.090126872062683,
+      "eval_runtime": 268.9072,
+      "eval_samples_per_second": 49.895,
+      "eval_steps_per_second": 0.781,
+      "step": 600
+    },
+    {
+      "epoch": 0.6437994722955145,
+      "grad_norm": 0.3555884063243866,
+      "learning_rate": 6.811804830099186e-06,
+      "loss": 1.0655,
+      "step": 610
+    },
+    {
+      "epoch": 0.6543535620052771,
+      "grad_norm": 0.3567143380641937,
+      "learning_rate": 6.464561716398565e-06,
+      "loss": 1.078,
+      "step": 620
+    },
+    {
+      "epoch": 0.6649076517150396,
+      "grad_norm": 0.3770051598548889,
+      "learning_rate": 6.122124944020978e-06,
+      "loss": 1.0836,
+      "step": 630
+    },
+    {
+      "epoch": 0.6754617414248021,
+      "grad_norm": 0.352397084236145,
+      "learning_rate": 5.78496004732952e-06,
+      "loss": 1.0719,
+      "step": 640
+    },
+    {
+      "epoch": 0.6860158311345647,
+      "grad_norm": 0.3588451147079468,
+      "learning_rate": 5.453525393702053e-06,
+      "loss": 1.0849,
+      "step": 650
+    },
+    {
+      "epoch": 0.6965699208443272,
+      "grad_norm": 0.40011218190193176,
+      "learning_rate": 5.128271560392037e-06,
+      "loss": 1.082,
+      "step": 660
+    },
+    {
+      "epoch": 0.7071240105540897,
+      "grad_norm": 0.34496238827705383,
+      "learning_rate": 4.809640721979856e-06,
+      "loss": 1.077,
+      "step": 670
+    },
+    {
+      "epoch": 0.7176781002638523,
+      "grad_norm": 0.38083967566490173,
+      "learning_rate": 4.498066049247344e-06,
+      "loss": 1.0639,
+      "step": 680
+    },
+    {
+      "epoch": 0.7282321899736148,
+      "grad_norm": 0.3846307098865509,
+      "learning_rate": 4.193971120292793e-06,
+      "loss": 1.0778,
+      "step": 690
+    },
+    {
+      "epoch": 0.7387862796833773,
+      "grad_norm": 0.33913660049438477,
+      "learning_rate": 3.897769344686929e-06,
+      "loss": 1.0952,
+      "step": 700
+    },
+    {
+      "epoch": 0.7493403693931399,
+      "grad_norm": 0.3537193536758423,
+      "learning_rate": 3.6098634014527866e-06,
+      "loss": 1.0853,
+      "step": 710
+    },
+    {
+      "epoch": 0.7598944591029023,
+      "grad_norm": 0.3514321446418762,
+      "learning_rate": 3.330644691633492e-06,
+      "loss": 1.0786,
+      "step": 720
+    },
+    {
+      "epoch": 0.7704485488126649,
+      "grad_norm": 0.34657713770866394,
+      "learning_rate": 3.0604928061921847e-06,
+      "loss": 1.0609,
+      "step": 730
+    },
+    {
+      "epoch": 0.7810026385224275,
+      "grad_norm": 0.34931546449661255,
+      "learning_rate": 2.7997750099674282e-06,
+      "loss": 1.0845,
+      "step": 740
+    },
+    {
+      "epoch": 0.7915567282321899,
+      "grad_norm": 0.3565938174724579,
+      "learning_rate": 2.548845742385717e-06,
+      "loss": 1.0762,
+      "step": 750
+    },
+    {
+      "epoch": 0.8021108179419525,
+      "grad_norm": 0.36780357360839844,
+      "learning_rate": 2.3080461356097938e-06,
+      "loss": 1.0719,
+      "step": 760
+    },
+    {
+      "epoch": 0.8126649076517151,
+      "grad_norm": 0.3430708348751068,
+      "learning_rate": 2.077703550777882e-06,
+      "loss": 1.0945,
+      "step": 770
+    },
+    {
+      "epoch": 0.8232189973614775,
+      "grad_norm": 0.361824631690979,
+      "learning_rate": 1.8581311329642592e-06,
+      "loss": 1.0916,
+      "step": 780
+    },
+    {
+      "epoch": 0.8337730870712401,
+      "grad_norm": 0.3385472893714905,
+      "learning_rate": 1.6496273854662482e-06,
+      "loss": 1.084,
+      "step": 790
+    },
+    {
+      "epoch": 0.8443271767810027,
+      "grad_norm": 0.3720723092556,
+      "learning_rate": 1.452475763996326e-06,
+      "loss": 1.0856,
+      "step": 800
+    },
+    {
+      "epoch": 0.8443271767810027,
+      "eval_loss": 1.0849097967147827,
+      "eval_runtime": 268.3585,
+      "eval_samples_per_second": 49.997,
+      "eval_steps_per_second": 0.783,
+      "step": 800
+    },
+    {
+      "epoch": 0.8548812664907651,
+      "grad_norm": 0.3724263906478882,
+      "learning_rate": 1.2669442913310725e-06,
+      "loss": 1.0773,
+      "step": 810
+    },
+    {
+      "epoch": 0.8654353562005277,
+      "grad_norm": 0.38541847467422485,
+      "learning_rate": 1.0932851929407828e-06,
+      "loss": 1.0793,
+      "step": 820
+    },
+    {
+      "epoch": 0.8759894459102903,
+      "grad_norm": 0.3606375753879547,
+      "learning_rate": 9.31734554095165e-07,
+      "loss": 1.0976,
+      "step": 830
+    },
+    {
+      "epoch": 0.8865435356200527,
+      "grad_norm": 0.34657078981399536,
+      "learning_rate": 7.825119989112173e-07,
+      "loss": 1.0815,
+      "step": 840
+    },
+    {
+      "epoch": 0.8970976253298153,
+      "grad_norm": 0.34550759196281433,
+      "learning_rate": 6.458203917796546e-07,
+      "loss": 1.0883,
+      "step": 850
+    },
+    {
+      "epoch": 0.9076517150395779,
+      "grad_norm": 0.34100624918937683,
+      "learning_rate": 5.218455615757601e-07,
+      "loss": 1.0781,
+      "step": 860
+    },
+    {
+      "epoch": 0.9182058047493403,
+      "grad_norm": 0.336028516292572,
+      "learning_rate": 4.107560490295992e-07,
+      "loss": 1.0716,
+      "step": 870
+    },
+    {
+      "epoch": 0.9287598944591029,
+      "grad_norm": 0.35316023230552673,
+      "learning_rate": 3.127028775990515e-07,
+      "loss": 1.0755,
+      "step": 880
+    },
+    {
+      "epoch": 0.9393139841688655,
+      "grad_norm": 0.3301040232181549,
+      "learning_rate": 2.2781934815713224e-07,
+      "loss": 1.0718,
+      "step": 890
+    },
+    {
+      "epoch": 0.9498680738786279,
+      "grad_norm": 0.3545936048030853,
+      "learning_rate": 1.562208577727442e-07,
+      "loss": 1.0812,
+      "step": 900
+    },
+    {
+      "epoch": 0.9604221635883905,
+      "grad_norm": 0.3564644455909729,
+      "learning_rate": 9.800474283119143e-08,
+      "loss": 1.0775,
+      "step": 910
+    },
+    {
+      "epoch": 0.9709762532981531,
+      "grad_norm": 0.34894269704818726,
+      "learning_rate": 5.325014670776951e-08,
+      "loss": 1.0694,
+      "step": 920
+    },
+    {
+      "epoch": 0.9815303430079155,
+      "grad_norm": 0.3846621811389923,
+      "learning_rate": 2.201791217428917e-08,
+      "loss": 1.0691,
+      "step": 930
+    },
+    {
+      "epoch": 0.9920844327176781,
+      "grad_norm": 0.3404500186443329,
+      "learning_rate": 4.3504986848297295e-09,
+      "loss": 1.0701,
+      "step": 940
+    },
+    {
+      "epoch": 0.9994722955145119,
+      "step": 947,
+      "total_flos": 2.8182891025525637e+18,
+      "train_loss": 1.100929617000608,
+      "train_runtime": 11309.6924,
+      "train_samples_per_second": 10.721,
+      "train_steps_per_second": 0.084
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 947,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8182891025525637e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}