Upload ./train_results.json with huggingface_hub
This commit is contained in:
ai-modelscope
36
.gitattributes
vendored
36
.gitattributes
vendored
@@ -1,47 +1,39 @@
|
|||||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.bz2 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
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
*.lfs.* 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
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
*.msgpack 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
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pb 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
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
*.rar 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
|
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
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tgz 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
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
|
||||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|||||||
183
README.md
183
README.md
@@ -1,47 +1,146 @@
|
|||||||
---
|
---
|
||||||
license: Apache License 2.0
|
license: cc-by-4.0
|
||||||
|
tags:
|
||||||
#model-type:
|
- alignment
|
||||||
##如 gpt、phi、llama、chatglm、baichuan 等
|
- value alignment
|
||||||
#- gpt
|
- AI safety
|
||||||
|
- safety
|
||||||
#domain:
|
- LLM
|
||||||
##如 nlp、cv、audio、multi-modal
|
- history
|
||||||
#- nlp
|
datasets:
|
||||||
|
- PKU-Alignment/ProgressGym-HistText
|
||||||
#language:
|
- PKU-Alignment/ProgressGym-TimelessQA
|
||||||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
base_model:
|
||||||
#- cn
|
- PKU-Alignment/ProgressGym-HistLlama3-8B-C019-pretrain
|
||||||
|
- meta-llama/Meta-Llama-3-8B
|
||||||
#metrics:
|
|
||||||
##如 CIDEr、Blue、ROUGE 等
|
|
||||||
#- CIDEr
|
|
||||||
|
|
||||||
#tags:
|
|
||||||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
|
||||||
#- pretrained
|
|
||||||
|
|
||||||
#tools:
|
|
||||||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
|
||||||
#- vllm
|
|
||||||
---
|
---
|
||||||
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
|
|
||||||
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
|
||||||
|
|
||||||
SDK下载
|
# ProgressGym-HistLlama3-8B-C019-instruct
|
||||||
```bash
|
|
||||||
#安装ModelScope
|
## Overview
|
||||||
pip install modelscope
|
|
||||||
```
|
#### The ProgressGym Framework
|
||||||
```python
|
|
||||||
#SDK模型下载
|
|
||||||
from modelscope import snapshot_download
|
|
||||||
model_dir = snapshot_download('PKU-Alignment/ProgressGym-HistLlama3-8B-C019-instruct-v0.2')
|
**ProgressGym-HistLlama3-8B-C019-instruct** is part of the **ProgressGym** framework for research and experimentation on *progress alignment* - the emulation of moral progress in AI alignment algorithms, as a measure to prevent risks of societal value lock-in.
|
||||||
```
|
|
||||||
Git下载
|
To quote the paper [*ProgressGym: Alignment with a Millennium of Moral Progress*](https://arxiv.org/abs/2406.20087):
|
||||||
```
|
|
||||||
#Git模型下载
|
> Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral beliefs and, consequently, the perpetuation of problematic moral practices on a broad scale.
|
||||||
git clone https://www.modelscope.cn/PKU-Alignment/ProgressGym-HistLlama3-8B-C019-instruct-v0.2.git
|
>
|
||||||
|
> We introduce *progress alignment* as a technical solution to mitigate this imminent risk. Progress alignment algorithms learn to emulate the mechanics of human moral progress, thereby addressing the susceptibility of existing alignment methods to contemporary moral blindspots.
|
||||||
|
|
||||||
|
#### ProgressGym-HistLlama3-8B-C019-instruct
|
||||||
|
|
||||||
|
ProgressGym-HistLlama3-8B-C019-instruct is one of the **36 historical language models** in the ProgressGym framework.
|
||||||
|
|
||||||
|
**ProgressGym-HistLlama3-8B-C019-instruct is under continual iteration.** Improving upon the current version, new versions of the model are currently being trained to reflect historical moral tendencies in ever more comprehensive ways.
|
||||||
|
|
||||||
|
**ProgressGym-HistLlama3-8B-C019-instruct is a 19th-century historical language model.** Based on [Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B), It is continued-pretrained on the 19th-century text data from [ProgressGym-HistText](https://huggingface.co/datasets/PKU-Alignment/ProgressGym-HistText), using the following hyperparameters:
|
||||||
|
|
||||||
|
- learning_rate: 1.5e-05
|
||||||
|
- train_batch_size: 8
|
||||||
|
- eval_batch_size: 16
|
||||||
|
- seed: 42
|
||||||
|
- distributed_type: multi-GPU
|
||||||
|
- num_devices: 8
|
||||||
|
- total_train_batch_size: 64
|
||||||
|
- total_eval_batch_size: 128
|
||||||
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||||
|
- lr_scheduler_type: polynomial
|
||||||
|
- lr_scheduler_warmup_steps: 20
|
||||||
|
- num_epochs: 4.0
|
||||||
|
- mixed_precision_training: Native AMP
|
||||||
|
|
||||||
|
... with the following training results:
|
||||||
|
|
||||||
|
| Training Loss | Epoch | Step | Validation Loss |
|
||||||
|
|:-------------:|:------:|:----:|:---------------:|
|
||||||
|
| 2.3809 | 0.1923 | 200 | 2.4207 |
|
||||||
|
| 2.3057 | 0.3846 | 400 | 2.3750 |
|
||||||
|
| 2.35 | 0.5769 | 600 | 2.3477 |
|
||||||
|
| 2.3291 | 0.7692 | 800 | 2.3324 |
|
||||||
|
| 2.2998 | 0.9615 | 1000 | 2.3237 |
|
||||||
|
| 2.1248 | 1.1538 | 1200 | 2.3361 |
|
||||||
|
| 2.1239 | 1.3462 | 1400 | 2.3344 |
|
||||||
|
| 2.1521 | 1.5385 | 1600 | 2.3338 |
|
||||||
|
| 2.1359 | 1.7308 | 1800 | 2.3336 |
|
||||||
|
| 2.0531 | 1.9231 | 2000 | 2.3332 |
|
||||||
|
| 2.0783 | 2.1154 | 2200 | 2.3357 |
|
||||||
|
| 2.0952 | 2.3077 | 2400 | 2.3360 |
|
||||||
|
| 2.1009 | 2.5 | 2600 | 2.3361 |
|
||||||
|
| 2.125 | 2.6923 | 2800 | 2.3360 |
|
||||||
|
| 2.1206 | 2.8846 | 3000 | 2.3360 |
|
||||||
|
| 2.0593 | 3.0769 | 3200 | 2.3363 |
|
||||||
|
| 2.0927 | 3.2692 | 3400 | 2.3365 |
|
||||||
|
| 2.093 | 3.4615 | 3600 | 2.3368 |
|
||||||
|
| 2.066 | 3.6538 | 3800 | 2.3363 |
|
||||||
|
| 2.1086 | 3.8462 | 4000 | 2.3362 |
|
||||||
|
|
||||||
|
Note that the training data volume for the continued pretraining stage is capped at 3GB. When the corresponding century's corpus exceeds this volume, the training data is randomly sampled to fit the volume.
|
||||||
|
|
||||||
|
**ProgressGym-HistLlama3-8B-C019-instruct is an instruction-tuned language model.** It is tuned on [ProgressGym-TimelessQA](https://huggingface.co/datasets/PKU-Alignment/ProgressGym-TimelessQA), using the following hyperparameters. Note, however, that the snapshot at training step 10 is used for the final model, to minimize erosion of the value tendencies learned during continued pretraining; we qualitatively observe that this snapshot still possesses strong instruction-following capabilities.
|
||||||
|
- learning_rate: 1.5e-05
|
||||||
|
- train_batch_size: 8
|
||||||
|
- eval_batch_size: 16
|
||||||
|
- seed: 42
|
||||||
|
- distributed_type: multi-GPU
|
||||||
|
- num_devices: 8
|
||||||
|
- total_train_batch_size: 64
|
||||||
|
- total_eval_batch_size: 128
|
||||||
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||||
|
- lr_scheduler_type: polynomial
|
||||||
|
- lr_scheduler_warmup_steps: 20
|
||||||
|
- num_epochs: 4.0
|
||||||
|
- mixed_precision_training: Native AMP
|
||||||
|
|
||||||
|
... with the following training results:
|
||||||
|
|
||||||
|
| Training Loss | Epoch | Step | Validation Loss |
|
||||||
|
|:-------------:|:------:|:----:|:---------------:|
|
||||||
|
| 0.8164 | 0.4167 | 20 | 0.8431 |
|
||||||
|
| 0.7962 | 0.8333 | 40 | 0.8462 |
|
||||||
|
| 0.4335 | 1.25 | 60 | 0.8650 |
|
||||||
|
| 0.4578 | 1.6667 | 80 | 0.8533 |
|
||||||
|
| 0.3944 | 2.0833 | 100 | 0.8484 |
|
||||||
|
| 0.3997 | 2.5 | 120 | 0.8528 |
|
||||||
|
| 0.3752 | 2.9167 | 140 | 0.8573 |
|
||||||
|
| 0.3697 | 3.3333 | 160 | 0.8608 |
|
||||||
|
| 0.3636 | 3.75 | 180 | 0.8634 |
|
||||||
|
|
||||||
|
|
||||||
|
## Links
|
||||||
|
|
||||||
|
- **[Paper Preprint]** [ProgressGym: Alignment with a Millennium of Moral Progress](https://arxiv.org/abs/2406.20087)
|
||||||
|
- **[Leaderboard & Interactive Playground]** [PKU-Alignment/ProgressGym-LeaderBoard](https://huggingface.co/spaces/PKU-Alignment/ProgressGym-LeaderBoard)
|
||||||
|
- **[Huggingface Data & Model Collection]** [PKU-Alignment/ProgressGym](https://huggingface.co/collections/PKU-Alignment/progressgym-666735fcf3e4efa276226eaa)
|
||||||
|
- **[Github Codebase]** [PKU-Alignment/ProgressGym](https://github.com/PKU-Alignment/ProgressGym)
|
||||||
|
- **[Documentation]** [ProgressGym Documentation](https://pku-alignment.github.io/ProgressGym/)
|
||||||
|
- **[PyPI Package]** *(coming soon - [stay tuned](https://forms.gle/1TWFLL4ZCLeYTD5N6)!)*
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
|
||||||
|
If the datasets, models, or framework of ProgressGym help you in your project, please cite ProgressGym using the bibtex entry below.
|
||||||
|
|
||||||
|
```text
|
||||||
|
@article{progressgym,
|
||||||
|
title={ProgressGym: Alignment with a Millennium of Moral Progress},
|
||||||
|
author={Tianyi Qiu and Yang Zhang and Xuchuan Huang and Jasmine Xinze Li and Jiaming Ji and Yaodong Yang},
|
||||||
|
journal={arXiv preprint arXiv:2406.20087},
|
||||||
|
eprint={2406.20087},
|
||||||
|
eprinttype = {arXiv},
|
||||||
|
year={2024}
|
||||||
|
}
|
||||||
```
|
```
|
||||||
|
|
||||||
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|
## Ethics Statement
|
||||||
|
|
||||||
|
- **Copyright information of historical text data sources**:
|
||||||
|
- Project Gutenberg, one among our four source of our historical text data, consists only of texts in the public domain.
|
||||||
|
- For the text that we draw from Internet Archive, we only include those that uploaded by *Library of Congress*, which are texts freely released online by the U.S. Library of Congress for research and public use.
|
||||||
|
- The text data from Early English Books Online are, according to their publisher, "freely available to the public" and "available for access, distribution, use, or reuse by anyone".
|
||||||
|
- The last remaining source of our historical text data, the Pile of Law dataset, is released under a Creative Commons license, which we adhere to in our use.
|
||||||
|
- **Reproducibility**: To ensure reproducibility, we open-source all the code involved in the production of our main results (including the entire pipeline starting from data collection and model training), as well as the supporting infrastructure (the ProgressGym framework), making replication as easy as running a few simple script files.
|
||||||
|
- **Misuse Prevention**: In order to prevent potential misuse of progress alignment algorithms, we have carefully formulated progress alignment as strictly value-neutral, without *a priori* assumptions on the direction of progress. In the event of potential misuse of our dataset, we condemn any misuse attempt to the strongest degree possible, and will work with the research community on whistleblowing for such attempts.
|
||||||
|
- **Open-Sourcing**: We confirm that our code, data, and models are to be open-sourced under a CC-BY 4.0 license. We will continue to maintain and update our open-source repositories and models.
|
||||||
12
all_results.json
Normal file
12
all_results.json
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"eval_loss": 0.7724230289459229,
|
||||||
|
"eval_runtime": 0.9494,
|
||||||
|
"eval_samples_per_second": 358.103,
|
||||||
|
"eval_steps_per_second": 3.16,
|
||||||
|
"total_flos": 1286744309760.0,
|
||||||
|
"train_loss": 0.8072919050852457,
|
||||||
|
"train_runtime": 252.4103,
|
||||||
|
"train_samples_per_second": 12.099,
|
||||||
|
"train_steps_per_second": 0.19
|
||||||
|
}
|
||||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "./output/training_results/C019_random_sample_Meta-Llama-3-8B_pretrain_20240726_033210",
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 128000,
|
||||||
|
"eos_token_id": 128001,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 14336,
|
||||||
|
"max_position_embeddings": 8192,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 32,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 500000.0,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.40.1",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 128256
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
7
eval_results.json
Normal file
7
eval_results.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"eval_loss": 0.7724230289459229,
|
||||||
|
"eval_runtime": 0.9494,
|
||||||
|
"eval_samples_per_second": 358.103,
|
||||||
|
"eval_steps_per_second": 3.16
|
||||||
|
}
|
||||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 128000,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": 128001,
|
||||||
|
"max_length": 4096,
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_p": 0.9,
|
||||||
|
"transformers_version": "4.40.1"
|
||||||
|
}
|
||||||
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:de2222ca7dfbb9afb1cb55d34ac5540b2a52e7d9a4c5bf6d1b96cf56bbd38c30
|
||||||
|
size 4976698592
|
||||||
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:ba79b30a855d719948e0b0fb2c475d1168797043fb21fee0b67284823612d60b
|
||||||
|
size 4999802616
|
||||||
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:c6857c8cdd20c1422c6e7ec80702bf8bab5583c12757c8c7311b2e5e62d73253
|
||||||
|
size 4915916080
|
||||||
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:a7c885a9471e455105a4d521ee6a7e003abac6e10870ca7b084e56a568f0f012
|
||||||
|
size 1168138808
|
||||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 16060522496
|
||||||
|
},
|
||||||
|
"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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-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_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-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-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_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00004-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-00004-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_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.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_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_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_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_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_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_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_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_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_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_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-00002-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_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
readme-assets/data-sources.png
Normal file
BIN
readme-assets/data-sources.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 85 KiB |
BIN
readme-assets/data-stats.png
Normal file
BIN
readme-assets/data-stats.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 210 KiB |
BIN
readme-assets/main-diagram.png
Normal file
BIN
readme-assets/main-diagram.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 178 KiB |
BIN
readme-assets/moral-evals.png
Normal file
BIN
readme-assets/moral-evals.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 218 KiB |
3
scheduler.pt
Normal file
3
scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:66fb89fbf07fdcc0f97b9253d717055ec03edba28e10a6afd1b52d275ba66248
|
||||||
|
size 1064
|
||||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<|begin_of_text|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|end_of_text|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|end_of_text|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
410563
tokenizer.json
Normal file
410563
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2065
tokenizer_config.json
Normal file
2065
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"total_flos": 1286744309760.0,
|
||||||
|
"train_loss": 0.8072919050852457,
|
||||||
|
"train_runtime": 252.4103,
|
||||||
|
"train_samples_per_second": 12.099,
|
||||||
|
"train_steps_per_second": 0.19
|
||||||
|
}
|
||||||
28
trainer_log.jsonl
Normal file
28
trainer_log.jsonl
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{"current_steps": 1, "total_steps": 48, "loss": 1.0289, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.020833333333333332, "percentage": 2.08, "elapsed_time": "0:00:06", "remaining_time": "0:04:54"}
|
||||||
|
{"current_steps": 3, "total_steps": 48, "loss": 0.9475, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.5e-07, "epoch": 0.0625, "percentage": 6.25, "elapsed_time": "0:00:07", "remaining_time": "0:01:58"}
|
||||||
|
{"current_steps": 5, "total_steps": 48, "loss": null, "eval_loss": 0.9170231819152832, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.10416666666666667, "percentage": 10.42, "elapsed_time": "0:00:09", "remaining_time": "0:01:20"}
|
||||||
|
{"current_steps": 6, "total_steps": 48, "loss": 1.032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-06, "epoch": 0.125, "percentage": 12.5, "elapsed_time": "0:00:10", "remaining_time": "0:01:16"}
|
||||||
|
{"current_steps": 9, "total_steps": 48, "loss": 0.8569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7988636363636366e-06, "epoch": 0.1875, "percentage": 18.75, "elapsed_time": "0:00:13", "remaining_time": "0:00:56"}
|
||||||
|
{"current_steps": 10, "total_steps": 48, "loss": null, "eval_loss": 0.8191882967948914, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.20833333333333334, "percentage": 20.83, "elapsed_time": "0:00:13", "remaining_time": "0:00:51"}
|
||||||
|
{"current_steps": 12, "total_steps": 48, "loss": 0.7857, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6647727272727274e-06, "epoch": 0.25, "percentage": 25.0, "elapsed_time": "0:01:02", "remaining_time": "0:03:08"}
|
||||||
|
{"current_steps": 15, "total_steps": 48, "loss": 0.8358, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4636363636363635e-06, "epoch": 0.3125, "percentage": 31.25, "elapsed_time": "0:01:05", "remaining_time": "0:02:23"}
|
||||||
|
{"current_steps": 15, "total_steps": 48, "loss": null, "eval_loss": 0.8035795092582703, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.3125, "percentage": 31.25, "elapsed_time": "0:01:05", "remaining_time": "0:02:23"}
|
||||||
|
{"current_steps": 18, "total_steps": 48, "loss": 0.7692, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2625e-06, "epoch": 0.375, "percentage": 37.5, "elapsed_time": "0:01:08", "remaining_time": "0:01:53"}
|
||||||
|
{"current_steps": 20, "total_steps": 48, "loss": null, "eval_loss": 0.7883596420288086, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.4166666666666667, "percentage": 41.67, "elapsed_time": "0:01:09", "remaining_time": "0:01:37"}
|
||||||
|
{"current_steps": 21, "total_steps": 48, "loss": 0.8029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0613636363636364e-06, "epoch": 0.4375, "percentage": 43.75, "elapsed_time": "0:01:59", "remaining_time": "0:02:33"}
|
||||||
|
{"current_steps": 24, "total_steps": 48, "loss": 0.7192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8602272727272725e-06, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:02:01", "remaining_time": "0:02:01"}
|
||||||
|
{"current_steps": 25, "total_steps": 48, "loss": null, "eval_loss": 0.7828572392463684, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5208333333333334, "percentage": 52.08, "elapsed_time": "0:02:02", "remaining_time": "0:01:52"}
|
||||||
|
{"current_steps": 27, "total_steps": 48, "loss": 0.7906, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.659090909090909e-06, "epoch": 0.5625, "percentage": 56.25, "elapsed_time": "0:02:04", "remaining_time": "0:01:36"}
|
||||||
|
{"current_steps": 30, "total_steps": 48, "loss": 0.8181, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4579545454545454e-06, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:02:06", "remaining_time": "0:01:15"}
|
||||||
|
{"current_steps": 30, "total_steps": 48, "loss": null, "eval_loss": 0.7780725955963135, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:02:06", "remaining_time": "0:01:15"}
|
||||||
|
{"current_steps": 33, "total_steps": 48, "loss": 0.6879, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2568181818181817e-06, "epoch": 0.6875, "percentage": 68.75, "elapsed_time": "0:02:57", "remaining_time": "0:01:20"}
|
||||||
|
{"current_steps": 35, "total_steps": 48, "loss": null, "eval_loss": 0.7747842669487, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7291666666666666, "percentage": 72.92, "elapsed_time": "0:02:58", "remaining_time": "0:01:06"}
|
||||||
|
{"current_steps": 36, "total_steps": 48, "loss": 0.7508, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0556818181818182e-06, "epoch": 0.75, "percentage": 75.0, "elapsed_time": "0:03:00", "remaining_time": "0:01:00"}
|
||||||
|
{"current_steps": 39, "total_steps": 48, "loss": 0.7032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.545454545454544e-07, "epoch": 0.8125, "percentage": 81.25, "elapsed_time": "0:03:02", "remaining_time": "0:00:42"}
|
||||||
|
{"current_steps": 40, "total_steps": 48, "loss": null, "eval_loss": 0.7724230289459229, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8333333333333334, "percentage": 83.33, "elapsed_time": "0:03:03", "remaining_time": "0:00:36"}
|
||||||
|
{"current_steps": 42, "total_steps": 48, "loss": 0.7755, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.534090909090911e-07, "epoch": 0.875, "percentage": 87.5, "elapsed_time": "0:03:54", "remaining_time": "0:00:33"}
|
||||||
|
{"current_steps": 45, "total_steps": 48, "loss": 0.8136, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.522727272727273e-07, "epoch": 0.9375, "percentage": 93.75, "elapsed_time": "0:03:56", "remaining_time": "0:00:15"}
|
||||||
|
{"current_steps": 45, "total_steps": 48, "loss": null, "eval_loss": 0.7702701091766357, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9375, "percentage": 93.75, "elapsed_time": "0:03:56", "remaining_time": "0:00:15"}
|
||||||
|
{"current_steps": 48, "total_steps": 48, "loss": 0.8008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.511363636363638e-07, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:59", "remaining_time": "0:00:00"}
|
||||||
|
{"current_steps": 48, "total_steps": 48, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:59", "remaining_time": "0:00:00"}
|
||||||
|
{"current_steps": 3, "total_steps": 3, "loss": null, "eval_loss": 0.7724230289459229, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:04:37", "remaining_time": "0:00:00"}
|
||||||
65
trainer_state.json
Normal file
65
trainer_state.json
Normal file
@@ -0,0 +1,65 @@
|
|||||||
|
{
|
||||||
|
"best_metric": 0.8191882967948914,
|
||||||
|
"best_model_checkpoint": "./output/training_results/C019_random_sample_Meta-Llama-3-8B_instruct_20240729_013421/checkpoint-10",
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"eval_steps": 5,
|
||||||
|
"global_step": 10,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.020833333333333332,
|
||||||
|
"grad_norm": 0.0,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"loss": 1.0289,
|
||||||
|
"step": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.0625,
|
||||||
|
"grad_norm": 12.807647290251596,
|
||||||
|
"learning_rate": 7.5e-07,
|
||||||
|
"loss": 0.9475,
|
||||||
|
"step": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"eval_loss": 0.9170231819152832,
|
||||||
|
"eval_runtime": 0.9021,
|
||||||
|
"eval_samples_per_second": 376.881,
|
||||||
|
"eval_steps_per_second": 3.325,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.125,
|
||||||
|
"grad_norm": 7.514247491325009,
|
||||||
|
"learning_rate": 3e-06,
|
||||||
|
"loss": 1.032,
|
||||||
|
"step": 6
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1875,
|
||||||
|
"grad_norm": 5.115521699952678,
|
||||||
|
"learning_rate": 2.7988636363636366e-06,
|
||||||
|
"loss": 0.8569,
|
||||||
|
"step": 9
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"eval_loss": 0.8191882967948914,
|
||||||
|
"eval_runtime": 0.8786,
|
||||||
|
"eval_samples_per_second": 386.993,
|
||||||
|
"eval_steps_per_second": 3.415,
|
||||||
|
"step": 10
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 3,
|
||||||
|
"max_steps": 48,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 1,
|
||||||
|
"save_steps": 10,
|
||||||
|
"total_flos": 210197544960.0,
|
||||||
|
"train_batch_size": 8,
|
||||||
|
"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:b91bb0563c9744c2a19a50e8df2fab361cf26babd0c2747535418b90a21de759
|
||||||
|
size 6904
|
||||||
BIN
training_eval_loss.png
Normal file
BIN
training_eval_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 37 KiB |
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 44 KiB |
604
zero_to_fp32.py
Normal file
604
zero_to_fp32.py
Normal file
@@ -0,0 +1,604 @@
|
|||||||
|
#!/usr/bin/env python
|
||||||
|
|
||||||
|
# Copyright (c) Microsoft Corporation.
|
||||||
|
# SPDX-License-Identifier: Apache-2.0
|
||||||
|
|
||||||
|
# DeepSpeed Team
|
||||||
|
|
||||||
|
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
||||||
|
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
||||||
|
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
||||||
|
# application.
|
||||||
|
#
|
||||||
|
# example: python zero_to_fp32.py . pytorch_model.bin
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import torch
|
||||||
|
import glob
|
||||||
|
import math
|
||||||
|
import os
|
||||||
|
import re
|
||||||
|
from collections import OrderedDict
|
||||||
|
from dataclasses import dataclass
|
||||||
|
|
||||||
|
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
||||||
|
# DeepSpeed data structures it has to be available in the current python environment.
|
||||||
|
from deepspeed.utils import logger
|
||||||
|
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
||||||
|
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
||||||
|
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass
|
||||||
|
class zero_model_state:
|
||||||
|
buffers: dict()
|
||||||
|
param_shapes: dict()
|
||||||
|
shared_params: list
|
||||||
|
ds_version: int
|
||||||
|
frozen_param_shapes: dict()
|
||||||
|
frozen_param_fragments: dict()
|
||||||
|
|
||||||
|
|
||||||
|
debug = 0
|
||||||
|
|
||||||
|
# load to cpu
|
||||||
|
device = torch.device('cpu')
|
||||||
|
|
||||||
|
|
||||||
|
def atoi(text):
|
||||||
|
return int(text) if text.isdigit() else text
|
||||||
|
|
||||||
|
|
||||||
|
def natural_keys(text):
|
||||||
|
'''
|
||||||
|
alist.sort(key=natural_keys) sorts in human order
|
||||||
|
http://nedbatchelder.com/blog/200712/human_sorting.html
|
||||||
|
(See Toothy's implementation in the comments)
|
||||||
|
'''
|
||||||
|
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
||||||
|
|
||||||
|
|
||||||
|
def get_model_state_file(checkpoint_dir, zero_stage):
|
||||||
|
if not os.path.isdir(checkpoint_dir):
|
||||||
|
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
||||||
|
|
||||||
|
# there should be only one file
|
||||||
|
if zero_stage <= 2:
|
||||||
|
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
||||||
|
elif zero_stage == 3:
|
||||||
|
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
||||||
|
|
||||||
|
if not os.path.exists(file):
|
||||||
|
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
||||||
|
|
||||||
|
return file
|
||||||
|
|
||||||
|
|
||||||
|
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
||||||
|
# XXX: need to test that this simple glob rule works for multi-node setup too
|
||||||
|
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
||||||
|
|
||||||
|
if len(ckpt_files) == 0:
|
||||||
|
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
||||||
|
|
||||||
|
return ckpt_files
|
||||||
|
|
||||||
|
|
||||||
|
def get_optim_files(checkpoint_dir):
|
||||||
|
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
||||||
|
|
||||||
|
|
||||||
|
def get_model_state_files(checkpoint_dir):
|
||||||
|
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
||||||
|
|
||||||
|
|
||||||
|
def parse_model_states(files):
|
||||||
|
zero_model_states = []
|
||||||
|
for file in files:
|
||||||
|
state_dict = torch.load(file, map_location=device)
|
||||||
|
|
||||||
|
if BUFFER_NAMES not in state_dict:
|
||||||
|
raise ValueError(f"{file} is not a model state checkpoint")
|
||||||
|
buffer_names = state_dict[BUFFER_NAMES]
|
||||||
|
if debug:
|
||||||
|
print("Found buffers:", buffer_names)
|
||||||
|
|
||||||
|
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
||||||
|
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
||||||
|
param_shapes = state_dict[PARAM_SHAPES]
|
||||||
|
|
||||||
|
# collect parameters that are included in param_shapes
|
||||||
|
param_names = []
|
||||||
|
for s in param_shapes:
|
||||||
|
for name in s.keys():
|
||||||
|
param_names.append(name)
|
||||||
|
|
||||||
|
# update with frozen parameters
|
||||||
|
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
||||||
|
if frozen_param_shapes is not None:
|
||||||
|
if debug:
|
||||||
|
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
||||||
|
param_names += list(frozen_param_shapes.keys())
|
||||||
|
|
||||||
|
# handle shared params
|
||||||
|
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
||||||
|
|
||||||
|
ds_version = state_dict.get(DS_VERSION, None)
|
||||||
|
|
||||||
|
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
||||||
|
|
||||||
|
z_model_state = zero_model_state(buffers=buffers,
|
||||||
|
param_shapes=param_shapes,
|
||||||
|
shared_params=shared_params,
|
||||||
|
ds_version=ds_version,
|
||||||
|
frozen_param_shapes=frozen_param_shapes,
|
||||||
|
frozen_param_fragments=frozen_param_fragments)
|
||||||
|
zero_model_states.append(z_model_state)
|
||||||
|
|
||||||
|
return zero_model_states
|
||||||
|
|
||||||
|
|
||||||
|
def parse_optim_states(files, ds_checkpoint_dir):
|
||||||
|
|
||||||
|
total_files = len(files)
|
||||||
|
state_dicts = []
|
||||||
|
for f in files:
|
||||||
|
state_dict = torch.load(f, map_location=device)
|
||||||
|
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
||||||
|
# and also handle the case where it was already removed by another helper script
|
||||||
|
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
||||||
|
state_dicts.append(state_dict)
|
||||||
|
|
||||||
|
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
||||||
|
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
||||||
|
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
||||||
|
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
||||||
|
|
||||||
|
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
||||||
|
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
||||||
|
# use the max of the partition_count to get the dp world_size.
|
||||||
|
|
||||||
|
if type(world_size) is list:
|
||||||
|
world_size = max(world_size)
|
||||||
|
|
||||||
|
if world_size != total_files:
|
||||||
|
raise ValueError(
|
||||||
|
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
||||||
|
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
||||||
|
)
|
||||||
|
|
||||||
|
# the groups are named differently in each stage
|
||||||
|
if zero_stage <= 2:
|
||||||
|
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
||||||
|
elif zero_stage == 3:
|
||||||
|
fp32_groups_key = FP32_FLAT_GROUPS
|
||||||
|
else:
|
||||||
|
raise ValueError(f"unknown zero stage {zero_stage}")
|
||||||
|
|
||||||
|
if zero_stage <= 2:
|
||||||
|
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
||||||
|
elif zero_stage == 3:
|
||||||
|
# if there is more than one param group, there will be multiple flattened tensors - one
|
||||||
|
# flattened tensor per group - for simplicity merge them into a single tensor
|
||||||
|
#
|
||||||
|
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
||||||
|
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
||||||
|
|
||||||
|
fp32_flat_groups = [
|
||||||
|
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
||||||
|
]
|
||||||
|
|
||||||
|
return zero_stage, world_size, fp32_flat_groups
|
||||||
|
|
||||||
|
|
||||||
|
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
||||||
|
"""
|
||||||
|
Returns fp32 state_dict reconstructed from ds checkpoint
|
||||||
|
|
||||||
|
Args:
|
||||||
|
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
||||||
|
|
||||||
|
"""
|
||||||
|
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
||||||
|
|
||||||
|
optim_files = get_optim_files(ds_checkpoint_dir)
|
||||||
|
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
||||||
|
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
||||||
|
|
||||||
|
model_files = get_model_state_files(ds_checkpoint_dir)
|
||||||
|
|
||||||
|
zero_model_states = parse_model_states(model_files)
|
||||||
|
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
||||||
|
|
||||||
|
if zero_stage <= 2:
|
||||||
|
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||||
|
exclude_frozen_parameters)
|
||||||
|
elif zero_stage == 3:
|
||||||
|
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||||
|
exclude_frozen_parameters)
|
||||||
|
|
||||||
|
|
||||||
|
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
||||||
|
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||||
|
return
|
||||||
|
|
||||||
|
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||||
|
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
||||||
|
|
||||||
|
if debug:
|
||||||
|
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
||||||
|
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||||
|
|
||||||
|
wanted_params = len(frozen_param_shapes)
|
||||||
|
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||||
|
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
||||||
|
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||||
|
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||||
|
|
||||||
|
total_params = 0
|
||||||
|
total_numel = 0
|
||||||
|
for name, shape in frozen_param_shapes.items():
|
||||||
|
total_params += 1
|
||||||
|
unpartitioned_numel = shape.numel()
|
||||||
|
total_numel += unpartitioned_numel
|
||||||
|
|
||||||
|
state_dict[name] = frozen_param_fragments[name]
|
||||||
|
|
||||||
|
if debug:
|
||||||
|
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||||
|
|
||||||
|
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||||
|
|
||||||
|
|
||||||
|
def _has_callable(obj, fn):
|
||||||
|
attr = getattr(obj, fn, None)
|
||||||
|
return callable(attr)
|
||||||
|
|
||||||
|
|
||||||
|
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||||
|
param_shapes = zero_model_states[0].param_shapes
|
||||||
|
|
||||||
|
# Reconstruction protocol:
|
||||||
|
#
|
||||||
|
# XXX: document this
|
||||||
|
|
||||||
|
if debug:
|
||||||
|
for i in range(world_size):
|
||||||
|
for j in range(len(fp32_flat_groups[0])):
|
||||||
|
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
||||||
|
|
||||||
|
# XXX: memory usage doubles here (zero2)
|
||||||
|
num_param_groups = len(fp32_flat_groups[0])
|
||||||
|
merged_single_partition_of_fp32_groups = []
|
||||||
|
for i in range(num_param_groups):
|
||||||
|
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
||||||
|
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
||||||
|
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
||||||
|
avail_numel = sum(
|
||||||
|
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
||||||
|
|
||||||
|
if debug:
|
||||||
|
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
||||||
|
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
||||||
|
# not asserting if there is a mismatch due to possible padding
|
||||||
|
print(f"Have {avail_numel} numels to process.")
|
||||||
|
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
||||||
|
|
||||||
|
# params
|
||||||
|
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||||
|
# out-of-core computing solution
|
||||||
|
total_numel = 0
|
||||||
|
total_params = 0
|
||||||
|
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
||||||
|
offset = 0
|
||||||
|
avail_numel = full_single_fp32_vector.numel()
|
||||||
|
for name, shape in shapes.items():
|
||||||
|
|
||||||
|
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
||||||
|
total_numel += unpartitioned_numel
|
||||||
|
total_params += 1
|
||||||
|
|
||||||
|
if debug:
|
||||||
|
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||||
|
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
||||||
|
offset += unpartitioned_numel
|
||||||
|
|
||||||
|
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
||||||
|
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
||||||
|
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
||||||
|
# live optimizer object, so we are checking that the numbers are within the right range
|
||||||
|
align_to = 2 * world_size
|
||||||
|
|
||||||
|
def zero2_align(x):
|
||||||
|
return align_to * math.ceil(x / align_to)
|
||||||
|
|
||||||
|
if debug:
|
||||||
|
print(f"original offset={offset}, avail_numel={avail_numel}")
|
||||||
|
|
||||||
|
offset = zero2_align(offset)
|
||||||
|
avail_numel = zero2_align(avail_numel)
|
||||||
|
|
||||||
|
if debug:
|
||||||
|
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
||||||
|
|
||||||
|
# Sanity check
|
||||||
|
if offset != avail_numel:
|
||||||
|
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||||
|
|
||||||
|
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
||||||
|
|
||||||
|
|
||||||
|
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||||
|
exclude_frozen_parameters):
|
||||||
|
state_dict = OrderedDict()
|
||||||
|
|
||||||
|
# buffers
|
||||||
|
buffers = zero_model_states[0].buffers
|
||||||
|
state_dict.update(buffers)
|
||||||
|
if debug:
|
||||||
|
print(f"added {len(buffers)} buffers")
|
||||||
|
|
||||||
|
if not exclude_frozen_parameters:
|
||||||
|
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
||||||
|
|
||||||
|
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||||
|
|
||||||
|
# recover shared parameters
|
||||||
|
for pair in zero_model_states[0].shared_params:
|
||||||
|
if pair[1] in state_dict:
|
||||||
|
state_dict[pair[0]] = state_dict[pair[1]]
|
||||||
|
|
||||||
|
return state_dict
|
||||||
|
|
||||||
|
|
||||||
|
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
||||||
|
remainder = unpartitioned_numel % world_size
|
||||||
|
padding_numel = (world_size - remainder) if remainder else 0
|
||||||
|
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
||||||
|
return partitioned_numel, padding_numel
|
||||||
|
|
||||||
|
|
||||||
|
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
||||||
|
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||||
|
return
|
||||||
|
|
||||||
|
if debug:
|
||||||
|
for i in range(world_size):
|
||||||
|
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
||||||
|
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||||
|
|
||||||
|
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||||
|
wanted_params = len(frozen_param_shapes)
|
||||||
|
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||||
|
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
||||||
|
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||||
|
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||||
|
|
||||||
|
total_params = 0
|
||||||
|
total_numel = 0
|
||||||
|
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
||||||
|
total_params += 1
|
||||||
|
unpartitioned_numel = shape.numel()
|
||||||
|
total_numel += unpartitioned_numel
|
||||||
|
|
||||||
|
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
||||||
|
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||||
|
|
||||||
|
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||||
|
|
||||||
|
if debug:
|
||||||
|
print(
|
||||||
|
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||||
|
)
|
||||||
|
|
||||||
|
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||||
|
|
||||||
|
|
||||||
|
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||||
|
param_shapes = zero_model_states[0].param_shapes
|
||||||
|
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||||
|
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
||||||
|
# param, re-consolidating each param, while dealing with padding if any
|
||||||
|
|
||||||
|
# merge list of dicts, preserving order
|
||||||
|
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
||||||
|
|
||||||
|
if debug:
|
||||||
|
for i in range(world_size):
|
||||||
|
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
||||||
|
|
||||||
|
wanted_params = len(param_shapes)
|
||||||
|
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
||||||
|
# not asserting if there is a mismatch due to possible padding
|
||||||
|
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||||
|
print(f"Trainable params: Have {avail_numel} numels to process.")
|
||||||
|
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
||||||
|
|
||||||
|
# params
|
||||||
|
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||||
|
# out-of-core computing solution
|
||||||
|
offset = 0
|
||||||
|
total_numel = 0
|
||||||
|
total_params = 0
|
||||||
|
for name, shape in param_shapes.items():
|
||||||
|
|
||||||
|
unpartitioned_numel = shape.numel()
|
||||||
|
total_numel += unpartitioned_numel
|
||||||
|
total_params += 1
|
||||||
|
|
||||||
|
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||||
|
|
||||||
|
if debug:
|
||||||
|
print(
|
||||||
|
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||||
|
)
|
||||||
|
|
||||||
|
# XXX: memory usage doubles here
|
||||||
|
state_dict[name] = torch.cat(
|
||||||
|
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
||||||
|
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||||
|
offset += partitioned_numel
|
||||||
|
|
||||||
|
offset *= world_size
|
||||||
|
|
||||||
|
# Sanity check
|
||||||
|
if offset != avail_numel:
|
||||||
|
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||||
|
|
||||||
|
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
||||||
|
|
||||||
|
|
||||||
|
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||||
|
exclude_frozen_parameters):
|
||||||
|
state_dict = OrderedDict()
|
||||||
|
|
||||||
|
# buffers
|
||||||
|
buffers = zero_model_states[0].buffers
|
||||||
|
state_dict.update(buffers)
|
||||||
|
if debug:
|
||||||
|
print(f"added {len(buffers)} buffers")
|
||||||
|
|
||||||
|
if not exclude_frozen_parameters:
|
||||||
|
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
||||||
|
|
||||||
|
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||||
|
|
||||||
|
# recover shared parameters
|
||||||
|
for pair in zero_model_states[0].shared_params:
|
||||||
|
if pair[1] in state_dict:
|
||||||
|
state_dict[pair[0]] = state_dict[pair[1]]
|
||||||
|
|
||||||
|
return state_dict
|
||||||
|
|
||||||
|
|
||||||
|
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
|
||||||
|
"""
|
||||||
|
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
||||||
|
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
||||||
|
via a model hub.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
- ``checkpoint_dir``: path to the desired checkpoint folder
|
||||||
|
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
||||||
|
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
- pytorch ``state_dict``
|
||||||
|
|
||||||
|
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
||||||
|
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
||||||
|
the checkpoint.
|
||||||
|
|
||||||
|
A typical usage might be ::
|
||||||
|
|
||||||
|
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||||
|
# do the training and checkpoint saving
|
||||||
|
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
||||||
|
model = model.cpu() # move to cpu
|
||||||
|
model.load_state_dict(state_dict)
|
||||||
|
# submit to model hub or save the model to share with others
|
||||||
|
|
||||||
|
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
||||||
|
application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||||
|
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||||
|
|
||||||
|
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
||||||
|
|
||||||
|
"""
|
||||||
|
if tag is None:
|
||||||
|
latest_path = os.path.join(checkpoint_dir, 'latest')
|
||||||
|
if os.path.isfile(latest_path):
|
||||||
|
with open(latest_path, 'r') as fd:
|
||||||
|
tag = fd.read().strip()
|
||||||
|
else:
|
||||||
|
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
||||||
|
|
||||||
|
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
||||||
|
|
||||||
|
if not os.path.isdir(ds_checkpoint_dir):
|
||||||
|
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
||||||
|
|
||||||
|
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
||||||
|
|
||||||
|
|
||||||
|
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
|
||||||
|
"""
|
||||||
|
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
||||||
|
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||||
|
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
||||||
|
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||||
|
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||||
|
"""
|
||||||
|
|
||||||
|
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
|
||||||
|
print(f"Saving fp32 state dict to {output_file}")
|
||||||
|
torch.save(state_dict, output_file)
|
||||||
|
|
||||||
|
|
||||||
|
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
||||||
|
"""
|
||||||
|
1. Put the provided model to cpu
|
||||||
|
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
||||||
|
3. Load it into the provided model
|
||||||
|
|
||||||
|
Args:
|
||||||
|
- ``model``: the model object to update
|
||||||
|
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||||
|
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
- ``model`: modified model
|
||||||
|
|
||||||
|
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
||||||
|
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
||||||
|
conveniently placed for you in the checkpoint folder.
|
||||||
|
|
||||||
|
A typical usage might be ::
|
||||||
|
|
||||||
|
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
||||||
|
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
||||||
|
# submit to model hub or save the model to share with others
|
||||||
|
|
||||||
|
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
||||||
|
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||||
|
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||||
|
|
||||||
|
"""
|
||||||
|
logger.info(f"Extracting fp32 weights")
|
||||||
|
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
||||||
|
|
||||||
|
logger.info(f"Overwriting model with fp32 weights")
|
||||||
|
model = model.cpu()
|
||||||
|
model.load_state_dict(state_dict, strict=False)
|
||||||
|
|
||||||
|
return model
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
|
||||||
|
parser = argparse.ArgumentParser()
|
||||||
|
parser.add_argument("checkpoint_dir",
|
||||||
|
type=str,
|
||||||
|
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
||||||
|
parser.add_argument(
|
||||||
|
"output_file",
|
||||||
|
type=str,
|
||||||
|
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
||||||
|
parser.add_argument("-t",
|
||||||
|
"--tag",
|
||||||
|
type=str,
|
||||||
|
default=None,
|
||||||
|
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
||||||
|
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
||||||
|
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
debug = args.debug
|
||||||
|
|
||||||
|
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
||||||
|
args.output_file,
|
||||||
|
tag=args.tag,
|
||||||
|
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
||||||
Reference in New Issue
Block a user