初始化项目，由ModelHub XC社区提供模型
Model: TheFinAI/Fin-o1-8B Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -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
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- TheFinAI/FinCoT
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- Qwen/Qwen3-8B
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- finance
|
||||
---
|
||||
# 🦙 Fino1-8B
|
||||
|
||||
**Fin-o1-8B** is a fine-tuned version of **Qwen3-8B**, designed to improve performance on **[financial reasoning tasks]**. This model has been trained using **SFT** and **RF** on **TheFinAI/Fino1_Reasoning_Path_FinQA**, enhancing its capabilities in **financial reasoning tasks**.
|
||||
Check our paper arxiv.org/abs/2502.08127 for more details.
|
||||
|
||||
## 📌 Model Details
|
||||
- **Model Name**: `Fin-o1-8B`
|
||||
- **Base Model**: `Qwen3-8B`
|
||||
- **Fine-Tuned On**: `TheFinAI/FinCoT` Derived from FinQA, TATQA, DocMath-Eval, Econ-Logic, BizBench-QA, DocFinQA dataset.
|
||||
- **Training Method**: SFT and GRPO
|
||||
- **Objective**: `[Enhance performance on specific tasks such as financial mathemtical reasoning]`
|
||||
- **Tokenizer**: Inherited from `Qwen3-8B`
|
||||
|
||||
|
||||
## 📊 Training Configuration
|
||||
- **Training Hardware**: `GPU: [e.g., 8xA100]`
|
||||
- **Batch Size**: `[e.g., 16]`
|
||||
- **Learning Rate**: `[e.g., 2e-5]`
|
||||
- **Epochs**: `[e.g., 3]`
|
||||
- **Optimizer**: `[e.g., AdamW, LAMB]`
|
||||
|
||||
## 🔧 Usage
|
||||
To use `Fin-o1-8B` with Hugging Face's `transformers` library:
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "TheFinAI/Fin-o1-8B"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name)
|
||||
|
||||
input_text = "What is the results of 3-5?"
|
||||
inputs = tokenizer(input_text, return_tensors="pt")
|
||||
|
||||
output = model.generate(**inputs, max_new_tokens=200)
|
||||
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
## 💡 Citation
|
||||
|
||||
If you use this model in your research, please cite:
|
||||
```python
|
||||
@article{qian2025fino1,
|
||||
title={Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance},
|
||||
author={Qian, Lingfei and Zhou, Weipeng and Wang, Yan and Peng, Xueqing and Huang, Jimin and Xie, Qianqian},
|
||||
journal={arXiv preprint arXiv:2502.08127},
|
||||
year={2025}
|
||||
}
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -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
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.0013743292051367462,
|
||||
"train_runtime": 7960.7406,
|
||||
"train_samples": 1525,
|
||||
"train_samples_per_second": 0.754,
|
||||
"train_steps_per_second": 0.063
|
||||
}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.2",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.51.2"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c4c3eaf4e935e1526cd49cd3bc3219d783ec8e29581fe4296a7e2670ab72a7ab
|
||||
size 4902257696
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:330839f22c0cf6d5b537ed2afce9f71ca5486b2b776a22b3d23094070db7bd1d
|
||||
size 4915960368
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ad531484162a71e791f17b5203e731586dad43571dd6fc59559debe0d1861f8e
|
||||
size 4983068496
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fab31c76825dbb628e1596e58c6412987dd7d818cefd0d8d37eafe4c5cb93c15
|
||||
size 1580230264
|
||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16381470720
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -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
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
|
||||
size 11422821
|
||||
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -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": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.0013743292051367462,
|
||||
"train_runtime": 7960.7406,
|
||||
"train_samples": 1525,
|
||||
"train_samples_per_second": 0.754,
|
||||
"train_steps_per_second": 0.063
|
||||
}
|
||||
641
trainer_state.json
Normal file
641
trainer_state.json
Normal file
@@ -0,0 +1,641 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.9666011787819253,
|
||||
"eval_steps": 500,
|
||||
"global_step": 500,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 579.5,
|
||||
"completions/max_terminated_length": 579.5,
|
||||
"completions/mean_length": 445.5,
|
||||
"completions/mean_terminated_length": 445.5,
|
||||
"completions/min_length": 358.5,
|
||||
"completions/min_terminated_length": 358.5,
|
||||
"epoch": 0.003929273084479371,
|
||||
"grad_norm": 0.46015690099076406,
|
||||
"kl": 0.0,
|
||||
"learning_rate": 0.0,
|
||||
"loss": -0.0157,
|
||||
"num_tokens": 18992.0,
|
||||
"reward": 9.166666984558105,
|
||||
"reward_std": 1.178511381149292,
|
||||
"rewards/accuracy_reward/mean": 1.8333333134651184,
|
||||
"rewards/accuracy_reward/std": 0.40824830532073975,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 554.4736842105264,
|
||||
"completions/max_terminated_length": 554.4736842105264,
|
||||
"completions/mean_length": 427.37282040244656,
|
||||
"completions/mean_terminated_length": 427.37282040244656,
|
||||
"completions/min_length": 322.5,
|
||||
"completions/min_terminated_length": 322.5,
|
||||
"epoch": 0.07858546168958742,
|
||||
"grad_norm": 0.37367734361954813,
|
||||
"kl": 0.0002414552788985403,
|
||||
"learning_rate": 1.14e-06,
|
||||
"loss": 0.0021,
|
||||
"num_tokens": 366755.0,
|
||||
"reward": 9.62719312467073,
|
||||
"reward_std": 0.5272287757773149,
|
||||
"rewards/accuracy_reward/mean": 1.9254385891713595,
|
||||
"rewards/accuracy_reward/std": 0.18263739974875198,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 543.875,
|
||||
"completions/max_terminated_length": 543.875,
|
||||
"completions/mean_length": 423.0708427429199,
|
||||
"completions/mean_terminated_length": 423.0708427429199,
|
||||
"completions/min_length": 319.9,
|
||||
"completions/min_terminated_length": 319.9,
|
||||
"epoch": 0.15717092337917485,
|
||||
"grad_norm": 0.5322056075322863,
|
||||
"kl": 0.0003676414489746094,
|
||||
"learning_rate": 2.34e-06,
|
||||
"loss": 0.0042,
|
||||
"num_tokens": 745300.0,
|
||||
"reward": 9.479166793823243,
|
||||
"reward_std": 0.5008673369884491,
|
||||
"rewards/accuracy_reward/mean": 1.8958333283662796,
|
||||
"rewards/accuracy_reward/std": 0.20629913210868836,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 571.275,
|
||||
"completions/max_terminated_length": 571.275,
|
||||
"completions/mean_length": 416.7875122070312,
|
||||
"completions/mean_terminated_length": 416.7875122070312,
|
||||
"completions/min_length": 318.6,
|
||||
"completions/min_terminated_length": 318.6,
|
||||
"epoch": 0.2357563850687623,
|
||||
"grad_norm": 0.46502934681984226,
|
||||
"kl": 0.0017244338989257813,
|
||||
"learning_rate": 2.9970400926424076e-06,
|
||||
"loss": 0.0059,
|
||||
"num_tokens": 1102433.0,
|
||||
"reward": 9.479166793823243,
|
||||
"reward_std": 0.5597929060459137,
|
||||
"rewards/accuracy_reward/mean": 1.8958333283662796,
|
||||
"rewards/accuracy_reward/std": 0.2154431849718094,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 529.75,
|
||||
"completions/max_terminated_length": 529.75,
|
||||
"completions/mean_length": 416.1666778564453,
|
||||
"completions/mean_terminated_length": 416.1666778564453,
|
||||
"completions/min_length": 324.725,
|
||||
"completions/min_terminated_length": 324.725,
|
||||
"epoch": 0.3143418467583497,
|
||||
"grad_norm": 0.03393033103037874,
|
||||
"kl": 0.005292510986328125,
|
||||
"learning_rate": 2.969362874399016e-06,
|
||||
"loss": -0.0009,
|
||||
"num_tokens": 1476975.0,
|
||||
"reward": 9.583333444595336,
|
||||
"reward_std": 0.3535534143447876,
|
||||
"rewards/accuracy_reward/mean": 1.9166666626930238,
|
||||
"rewards/accuracy_reward/std": 0.17411426901817323,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 527.25,
|
||||
"completions/max_terminated_length": 527.25,
|
||||
"completions/mean_length": 416.6166793823242,
|
||||
"completions/mean_terminated_length": 416.6166793823242,
|
||||
"completions/min_length": 323.575,
|
||||
"completions/min_terminated_length": 323.575,
|
||||
"epoch": 0.3929273084479371,
|
||||
"grad_norm": 0.030903746658924047,
|
||||
"kl": 0.008585357666015625,
|
||||
"learning_rate": 2.913086179180945e-06,
|
||||
"loss": 0.0066,
|
||||
"num_tokens": 1840061.0,
|
||||
"reward": 9.604166769981385,
|
||||
"reward_std": 0.5597929060459137,
|
||||
"rewards/accuracy_reward/mean": 1.920833334326744,
|
||||
"rewards/accuracy_reward/std": 0.16390806138515474,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 541.625,
|
||||
"completions/max_terminated_length": 541.625,
|
||||
"completions/mean_length": 409.9083450317383,
|
||||
"completions/mean_terminated_length": 409.9083450317383,
|
||||
"completions/min_length": 306.25,
|
||||
"completions/min_terminated_length": 306.25,
|
||||
"epoch": 0.4715127701375246,
|
||||
"grad_norm": 0.45989535358245415,
|
||||
"kl": 0.012615966796875,
|
||||
"learning_rate": 2.829305368846822e-06,
|
||||
"loss": -0.0081,
|
||||
"num_tokens": 2205137.0,
|
||||
"reward": 9.583333444595336,
|
||||
"reward_std": 0.5303301155567169,
|
||||
"rewards/accuracy_reward/mean": 1.9166666597127915,
|
||||
"rewards/accuracy_reward/std": 0.18471990823745726,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 566.95,
|
||||
"completions/max_terminated_length": 566.95,
|
||||
"completions/mean_length": 433.34167709350584,
|
||||
"completions/mean_terminated_length": 433.34167709350584,
|
||||
"completions/min_length": 330.4,
|
||||
"completions/min_terminated_length": 330.4,
|
||||
"epoch": 0.550098231827112,
|
||||
"grad_norm": 0.037923463367969736,
|
||||
"kl": 0.0144561767578125,
|
||||
"learning_rate": 2.7196511415705416e-06,
|
||||
"loss": 0.0048,
|
||||
"num_tokens": 2588775.0,
|
||||
"reward": 9.416666793823243,
|
||||
"reward_std": 0.4714045524597168,
|
||||
"rewards/accuracy_reward/mean": 1.883333331346512,
|
||||
"rewards/accuracy_reward/std": 0.2257540464401245,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 567.8,
|
||||
"completions/max_terminated_length": 567.8,
|
||||
"completions/mean_length": 438.3958457946777,
|
||||
"completions/mean_terminated_length": 438.3958457946777,
|
||||
"completions/min_length": 330.85,
|
||||
"completions/min_terminated_length": 330.85,
|
||||
"epoch": 0.6286836935166994,
|
||||
"grad_norm": 0.03890017799267318,
|
||||
"kl": 0.0144439697265625,
|
||||
"learning_rate": 2.5862577921562017e-06,
|
||||
"loss": 0.0022,
|
||||
"num_tokens": 2969880.0,
|
||||
"reward": 9.70833342075348,
|
||||
"reward_std": 0.294627845287323,
|
||||
"rewards/accuracy_reward/mean": 1.941666665673256,
|
||||
"rewards/accuracy_reward/std": 0.1278819650411606,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 542.925,
|
||||
"completions/max_terminated_length": 542.925,
|
||||
"completions/mean_length": 432.9458457946777,
|
||||
"completions/mean_terminated_length": 432.9458457946777,
|
||||
"completions/min_length": 343.425,
|
||||
"completions/min_terminated_length": 343.425,
|
||||
"epoch": 0.7072691552062869,
|
||||
"grad_norm": 0.029836981989722188,
|
||||
"kl": 0.01332855224609375,
|
||||
"learning_rate": 2.4317216704174657e-06,
|
||||
"loss": 0.0032,
|
||||
"num_tokens": 3344559.0,
|
||||
"reward": 9.666666722297668,
|
||||
"reward_std": 0.3535534143447876,
|
||||
"rewards/accuracy_reward/mean": 1.933333334326744,
|
||||
"rewards/accuracy_reward/std": 0.11828449666500092,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 553.825,
|
||||
"completions/max_terminated_length": 553.825,
|
||||
"completions/mean_length": 432.8000114440918,
|
||||
"completions/mean_terminated_length": 432.8000114440918,
|
||||
"completions/min_length": 329.975,
|
||||
"completions/min_terminated_length": 329.975,
|
||||
"epoch": 0.7858546168958742,
|
||||
"grad_norm": 0.028665697797427125,
|
||||
"kl": 0.01359100341796875,
|
||||
"learning_rate": 2.2590506461817453e-06,
|
||||
"loss": 0.0011,
|
||||
"num_tokens": 3723883.0,
|
||||
"reward": 9.666666769981385,
|
||||
"reward_std": 0.4714045524597168,
|
||||
"rewards/accuracy_reward/mean": 1.9333333283662797,
|
||||
"rewards/accuracy_reward/std": 0.14829438030719758,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 565.9,
|
||||
"completions/max_terminated_length": 565.9,
|
||||
"completions/mean_length": 442.46251068115237,
|
||||
"completions/mean_terminated_length": 442.46251068115237,
|
||||
"completions/min_length": 349.45,
|
||||
"completions/min_terminated_length": 349.45,
|
||||
"epoch": 0.8644400785854617,
|
||||
"grad_norm": 0.03081820386262942,
|
||||
"kl": 0.01476898193359375,
|
||||
"learning_rate": 2.0716055645254116e-06,
|
||||
"loss": -0.0006,
|
||||
"num_tokens": 4106760.0,
|
||||
"reward": 9.812500023841858,
|
||||
"reward_std": 0.2062394917011261,
|
||||
"rewards/accuracy_reward/mean": 1.9625000029802322,
|
||||
"rewards/accuracy_reward/std": 0.06714880466461182,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 570.925,
|
||||
"completions/max_terminated_length": 570.925,
|
||||
"completions/mean_length": 430.3500122070312,
|
||||
"completions/mean_terminated_length": 430.3500122070312,
|
||||
"completions/min_length": 335.975,
|
||||
"completions/min_terminated_length": 335.975,
|
||||
"epoch": 0.9430255402750491,
|
||||
"grad_norm": 0.0325454508362931,
|
||||
"kl": 0.01363067626953125,
|
||||
"learning_rate": 1.8730348307472826e-06,
|
||||
"loss": -0.0006,
|
||||
"num_tokens": 4498062.0,
|
||||
"reward": 9.70833342075348,
|
||||
"reward_std": 0.4124789834022522,
|
||||
"rewards/accuracy_reward/mean": 1.9416666626930237,
|
||||
"rewards/accuracy_reward/std": 0.1278819650411606,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 546.625,
|
||||
"completions/max_terminated_length": 546.625,
|
||||
"completions/mean_length": 429.0875114440918,
|
||||
"completions/mean_terminated_length": 429.0875114440918,
|
||||
"completions/min_length": 333.85,
|
||||
"completions/min_terminated_length": 333.85,
|
||||
"epoch": 1.0235756385068762,
|
||||
"grad_norm": 0.0281329807884298,
|
||||
"kl": 0.01484832763671875,
|
||||
"learning_rate": 1.667203398309488e-06,
|
||||
"loss": -0.0006,
|
||||
"num_tokens": 4844839.0,
|
||||
"reward": 9.666666746139526,
|
||||
"reward_std": 0.47140454649925234,
|
||||
"rewards/accuracy_reward/mean": 1.9333333313465118,
|
||||
"rewards/accuracy_reward/std": 0.13859225809574127,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 530.05,
|
||||
"completions/max_terminated_length": 530.05,
|
||||
"completions/mean_length": 412.9875099182129,
|
||||
"completions/mean_terminated_length": 412.9875099182129,
|
||||
"completions/min_length": 319.675,
|
||||
"completions/min_terminated_length": 319.675,
|
||||
"epoch": 1.1021611001964637,
|
||||
"grad_norm": 0.03324322790874101,
|
||||
"kl": 0.0139068603515625,
|
||||
"learning_rate": 1.458117541914647e-06,
|
||||
"loss": 0.0015,
|
||||
"num_tokens": 5222808.0,
|
||||
"reward": 9.791666746139526,
|
||||
"reward_std": 0.294627845287323,
|
||||
"rewards/accuracy_reward/mean": 1.9583333313465119,
|
||||
"rewards/accuracy_reward/std": 0.10206207633018494,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 524.825,
|
||||
"completions/max_terminated_length": 524.825,
|
||||
"completions/mean_length": 404.3958435058594,
|
||||
"completions/mean_terminated_length": 404.3958435058594,
|
||||
"completions/min_length": 308.875,
|
||||
"completions/min_terminated_length": 308.875,
|
||||
"epoch": 1.180746561886051,
|
||||
"grad_norm": 0.03412086623724304,
|
||||
"kl": 0.0137176513671875,
|
||||
"learning_rate": 1.2498468799258468e-06,
|
||||
"loss": 0.0031,
|
||||
"num_tokens": 5583225.0,
|
||||
"reward": 9.791666746139526,
|
||||
"reward_std": 0.294627845287323,
|
||||
"rewards/accuracy_reward/mean": 1.9583333283662796,
|
||||
"rewards/accuracy_reward/std": 0.10206207633018494,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 516.05,
|
||||
"completions/max_terminated_length": 516.05,
|
||||
"completions/mean_length": 395.33334197998045,
|
||||
"completions/mean_terminated_length": 395.33334197998045,
|
||||
"completions/min_length": 304.5,
|
||||
"completions/min_terminated_length": 304.5,
|
||||
"epoch": 1.2593320235756384,
|
||||
"grad_norm": 0.03048435461570321,
|
||||
"kl": 0.01298065185546875,
|
||||
"learning_rate": 1.0464451638743333e-06,
|
||||
"loss": 0.0031,
|
||||
"num_tokens": 5944449.0,
|
||||
"reward": 9.770833396911621,
|
||||
"reward_std": 0.2062394917011261,
|
||||
"rewards/accuracy_reward/mean": 1.9541666686534882,
|
||||
"rewards/accuracy_reward/std": 0.09726334214210511,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 553.4,
|
||||
"completions/max_terminated_length": 553.4,
|
||||
"completions/mean_length": 425.20000915527345,
|
||||
"completions/mean_terminated_length": 425.20000915527345,
|
||||
"completions/min_length": 323.3,
|
||||
"completions/min_terminated_length": 323.3,
|
||||
"epoch": 1.3379174852652258,
|
||||
"grad_norm": 0.7144758682156833,
|
||||
"kl": 0.01336822509765625,
|
||||
"learning_rate": 8.518713767970263e-07,
|
||||
"loss": 0.0009,
|
||||
"num_tokens": 6321679.0,
|
||||
"reward": 9.604166793823243,
|
||||
"reward_std": 0.4419417679309845,
|
||||
"rewards/accuracy_reward/mean": 1.9208333313465118,
|
||||
"rewards/accuracy_reward/std": 0.17891300320625306,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 574.225,
|
||||
"completions/max_terminated_length": 574.225,
|
||||
"completions/mean_length": 443.48334350585935,
|
||||
"completions/mean_terminated_length": 443.48334350585935,
|
||||
"completions/min_length": 340.075,
|
||||
"completions/min_terminated_length": 340.075,
|
||||
"epoch": 1.4165029469548134,
|
||||
"grad_norm": 0.03770084296737852,
|
||||
"kl": 0.01368255615234375,
|
||||
"learning_rate": 6.69912676134984e-07,
|
||||
"loss": 0.0042,
|
||||
"num_tokens": 6707325.0,
|
||||
"reward": 9.666666746139526,
|
||||
"reward_std": 0.35355340838432314,
|
||||
"rewards/accuracy_reward/mean": 1.9333333313465118,
|
||||
"rewards/accuracy_reward/std": 0.13859225809574127,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 562.675,
|
||||
"completions/max_terminated_length": 562.675,
|
||||
"completions/mean_length": 438.5416793823242,
|
||||
"completions/mean_terminated_length": 438.5416793823242,
|
||||
"completions/min_length": 346.0,
|
||||
"completions/min_terminated_length": 346.0,
|
||||
"epoch": 1.4950884086444007,
|
||||
"grad_norm": 0.02727792542475105,
|
||||
"kl": 0.0121246337890625,
|
||||
"learning_rate": 5.041106810216376e-07,
|
||||
"loss": 0.0017,
|
||||
"num_tokens": 7081575.0,
|
||||
"reward": 9.604166769981385,
|
||||
"reward_std": 0.4419417679309845,
|
||||
"rewards/accuracy_reward/mean": 1.9208333283662795,
|
||||
"rewards/accuracy_reward/std": 0.16006682813167572,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 549.7,
|
||||
"completions/max_terminated_length": 549.7,
|
||||
"completions/mean_length": 434.0916748046875,
|
||||
"completions/mean_terminated_length": 434.0916748046875,
|
||||
"completions/min_length": 341.4,
|
||||
"completions/min_terminated_length": 341.4,
|
||||
"epoch": 1.5736738703339883,
|
||||
"grad_norm": 0.030573782966379155,
|
||||
"kl": 0.012384033203125,
|
||||
"learning_rate": 3.5769253869489515e-07,
|
||||
"loss": -0.0017,
|
||||
"num_tokens": 7465665.0,
|
||||
"reward": 9.77083342075348,
|
||||
"reward_std": 0.3240906298160553,
|
||||
"rewards/accuracy_reward/mean": 1.9541666626930236,
|
||||
"rewards/accuracy_reward/std": 0.11226828396320343,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 529.95,
|
||||
"completions/max_terminated_length": 529.95,
|
||||
"completions/mean_length": 423.4125099182129,
|
||||
"completions/mean_terminated_length": 423.4125099182129,
|
||||
"completions/min_length": 337.4,
|
||||
"completions/min_terminated_length": 337.4,
|
||||
"epoch": 1.6522593320235757,
|
||||
"grad_norm": 0.026892810354609234,
|
||||
"kl": 0.011712646484375,
|
||||
"learning_rate": 2.3350811174697772e-07,
|
||||
"loss": 0.0009,
|
||||
"num_tokens": 7851292.0,
|
||||
"reward": 9.895833349227905,
|
||||
"reward_std": 0.1473139226436615,
|
||||
"rewards/accuracy_reward/mean": 1.9791666686534881,
|
||||
"rewards/accuracy_reward/std": 0.03602609634399414,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 548.65,
|
||||
"completions/max_terminated_length": 548.65,
|
||||
"completions/mean_length": 438.77084121704104,
|
||||
"completions/mean_terminated_length": 438.77084121704104,
|
||||
"completions/min_length": 344.9,
|
||||
"completions/min_terminated_length": 344.9,
|
||||
"epoch": 1.730844793713163,
|
||||
"grad_norm": 0.7530350302626055,
|
||||
"kl": 0.012438201904296875,
|
||||
"learning_rate": 1.3397450879073447e-07,
|
||||
"loss": 0.0001,
|
||||
"num_tokens": 8224807.0,
|
||||
"reward": 9.68750011920929,
|
||||
"reward_std": 0.4419417679309845,
|
||||
"rewards/accuracy_reward/mean": 1.9374999940395354,
|
||||
"rewards/accuracy_reward/std": 0.1530931144952774,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 531.9,
|
||||
"completions/max_terminated_length": 531.9,
|
||||
"completions/mean_length": 419.85418167114256,
|
||||
"completions/mean_terminated_length": 419.85418167114256,
|
||||
"completions/min_length": 322.85,
|
||||
"completions/min_terminated_length": 322.85,
|
||||
"epoch": 1.8094302554027504,
|
||||
"grad_norm": 0.3868391159083008,
|
||||
"kl": 0.011206817626953126,
|
||||
"learning_rate": 6.102903818991374e-08,
|
||||
"loss": 0.0016,
|
||||
"num_tokens": 8589626.0,
|
||||
"reward": 9.55208342075348,
|
||||
"reward_std": 0.5155987203121185,
|
||||
"rewards/accuracy_reward/mean": 1.910416665673256,
|
||||
"rewards/accuracy_reward/std": 0.1655041679739952,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 554.8,
|
||||
"completions/max_terminated_length": 554.8,
|
||||
"completions/mean_length": 438.46667556762696,
|
||||
"completions/mean_terminated_length": 438.46667556762696,
|
||||
"completions/min_length": 341.875,
|
||||
"completions/min_terminated_length": 341.875,
|
||||
"epoch": 1.888015717092338,
|
||||
"grad_norm": 0.05259089172915785,
|
||||
"kl": 0.011602783203125,
|
||||
"learning_rate": 1.60915005555175e-08,
|
||||
"loss": -0.0007,
|
||||
"num_tokens": 8961090.0,
|
||||
"reward": 9.562500095367431,
|
||||
"reward_std": 0.3830161988735199,
|
||||
"rewards/accuracy_reward/mean": 1.9125,
|
||||
"rewards/accuracy_reward/std": 0.16931553483009337,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"clip_ratio": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 544.9,
|
||||
"completions/max_terminated_length": 544.9,
|
||||
"completions/mean_length": 435.1583450317383,
|
||||
"completions/mean_terminated_length": 435.1583450317383,
|
||||
"completions/min_length": 346.2,
|
||||
"completions/min_terminated_length": 346.2,
|
||||
"epoch": 1.9666011787819253,
|
||||
"grad_norm": 0.02646975626285412,
|
||||
"kl": 0.01181793212890625,
|
||||
"learning_rate": 3.655394190787975e-11,
|
||||
"loss": 0.0015,
|
||||
"num_tokens": 9338954.0,
|
||||
"reward": 9.750000047683717,
|
||||
"reward_std": 0.2357022762298584,
|
||||
"rewards/accuracy_reward/mean": 1.9499999970197677,
|
||||
"rewards/accuracy_reward/std": 0.08862337470054626,
|
||||
"rewards/format_reward/mean": 0.0,
|
||||
"rewards/format_reward/std": 0.0,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 1.9666011787819253,
|
||||
"step": 500,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.0013743292051367462,
|
||||
"train_runtime": 7960.7406,
|
||||
"train_samples_per_second": 0.754,
|
||||
"train_steps_per_second": 0.063
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 500,
|
||||
"num_input_tokens_seen": 9338954,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 500,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": false,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 0.0,
|
||||
"train_batch_size": 2,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:09182feceeb6e2499f0d2611b1d1349926d7b36c79f0961a3c22db11ab66707a
|
||||
size 8568
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user