PKU-Alignment/ProgressGym-HistLlama3-8B-C015-instruct-v0.2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: PKU-Alignment/ProgressGym-HistLlama3-8B-C015-instruct-v0.2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-25 16:30:16 +08:00
commit 483b1ab7d6
25 changed files with 413941 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
.gitattributes vendored Normal file
View File

@@ -0,0 +1,39 @@
*.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
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

249
README.md Normal file
View File

@@ -0,0 +1,249 @@
---
license: cc-by-4.0
tags:
- alignment
- value alignment
- AI safety
- safety
- LLM
- history
datasets:
- PKU-Alignment/ProgressGym-HistText
- PKU-Alignment/ProgressGym-TimelessQA
base_model:
- PKU-Alignment/ProgressGym-HistLlama3-8B-C015-pretrain
- meta-llama/Meta-Llama-3-8B
---
# ProgressGym-HistLlama3-8B-C015-instruct
## Overview
#### The ProgressGym Framework
![Framework Diagram](./readme-assets/main-diagram.png)
**ProgressGym-HistLlama3-8B-C015-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.
To quote the paper [*ProgressGym: Alignment with a Millennium of Moral Progress*](https://arxiv.org/abs/2406.20087):
> 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.
>
> 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-C015-instruct
ProgressGym-HistLlama3-8B-C015-instruct is one of the **36 historical language models** in the ProgressGym framework.
**ProgressGym-HistLlama3-8B-C015-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-C015-instruct is a 15th-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 15th-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: 3.02
- mixed_precision_training: Native AMP
... with the following training results:
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:--------:|:----:|:---------------:|
| 2.6141 | 0.006494 | 1 | 2.6354 |
| 2.657 | 0.032468 | 5 | 2.6206 |
| 2.6337 | 0.064935 | 10 | 2.5846 |
| 2.5268 | 0.097403 | 15 | 2.5516 |
| 2.5275 | 0.129870 | 20 | 2.5321 |
| 2.5005 | 0.162338 | 25 | 2.5131 |
| 2.5339 | 0.194805 | 30 | 2.4961 |
| 2.5335 | 0.227273 | 35 | 2.4808 |
| 2.4252 | 0.259740 | 40 | 2.4643 |
| 2.4445 | 0.292208 | 45 | 2.4518 |
| 2.4594 | 0.324675 | 50 | 2.4394 |
| 2.4498 | 0.357143 | 55 | 2.4287 |
| 2.3821 | 0.389610 | 60 | 2.4184 |
| 2.4317 | 0.422078 | 65 | 2.4091 |
| 2.3931 | 0.454545 | 70 | 2.4001 |
| 2.3695 | 0.487013 | 75 | 2.3934 |
| 2.3981 | 0.519481 | 80 | 2.3855 |
| 2.3952 | 0.551948 | 85 | 2.3789 |
| 2.4137 | 0.584416 | 90 | 2.3721 |
| 2.3614 | 0.616883 | 95 | 2.3669 |
| 2.3467 | 0.649351 | 100 | 2.3612 |
| 2.4012 | 0.681818 | 105 | 2.3569 |
| 2.3224 | 0.714286 | 110 | 2.3528 |
| 2.3348 | 0.746753 | 115 | 2.3483 |
| 2.3573 | 0.779221 | 120 | 2.3448 |
| 2.306 | 0.811688 | 125 | 2.3412 |
| 2.342 | 0.844156 | 130 | 2.3382 |
| 2.3045 | 0.876623 | 135 | 2.3356 |
| 2.2959 | 0.909091 | 140 | 2.3330 |
| 2.3545 | 0.941558 | 145 | 2.3305 |
| 2.3446 | 0.974026 | 150 | 2.3285 |
| 2.2502 | 1.006494 | 155 | 2.3268 |
| 2.0791 | 1.038961 | 160 | 2.3347 |
| 2.1034 | 1.071429 | 165 | 2.3399 |
| 2.095 | 1.103896 | 170 | 2.3358 |
| 2.0627 | 1.136364 | 175 | 2.3346 |
| 2.0408 | 1.168831 | 180 | 2.3357 |
| 2.0575 | 1.201299 | 185 | 2.3364 |
| 2.0976 | 1.233766 | 190 | 2.3349 |
| 2.0668 | 1.266234 | 195 | 2.3336 |
| 2.0579 | 1.298701 | 200 | 2.3329 |
| 2.0756 | 1.331169 | 205 | 2.3326 |
| 2.1174 | 1.363636 | 210 | 2.3325 |
| 2.0663 | 1.396104 | 215 | 2.3325 |
| 2.0941 | 1.428571 | 220 | 2.3324 |
| 2.1074 | 1.461039 | 225 | 2.3324 |
| 2.1251 | 1.493506 | 230 | 2.3322 |
| 2.0629 | 1.525974 | 235 | 2.3318 |
| 2.0872 | 1.558442 | 240 | 2.3312 |
| 2.0994 | 1.590909 | 245 | 2.3310 |
| 2.0879 | 1.623377 | 250 | 2.3308 |
| 2.0623 | 1.655844 | 255 | 2.3305 |
| 2.1054 | 1.688312 | 260 | 2.3303 |
| 2.0736 | 1.720779 | 265 | 2.3301 |
| 2.1146 | 1.753247 | 270 | 2.3300 |
| 2.0444 | 1.785714 | 275 | 2.3301 |
| 2.0541 | 1.818182 | 280 | 2.3301 |
| 2.1333 | 1.850649 | 285 | 2.3300 |
| 2.1101 | 1.883117 | 290 | 2.3299 |
| 2.0234 | 1.915584 | 295 | 2.3298 |
| 2.0671 | 1.948052 | 300 | 2.3298 |
| 2.083 | 1.980519 | 305 | 2.3298 |
| 2.0417 | 2.012987 | 310 | 2.3299 |
| 2.0784 | 2.045455 | 315 | 2.3303 |
| 2.058 | 2.077922 | 320 | 2.3308 |
| 2.0524 | 2.110390 | 325 | 2.3312 |
| 2.0318 | 2.142857 | 330 | 2.3316 |
| 2.0914 | 2.175325 | 335 | 2.3318 |
| 2.0319 | 2.207792 | 340 | 2.3320 |
| 2.0099 | 2.240260 | 345 | 2.3322 |
| 2.075 | 2.272727 | 350 | 2.3323 |
| 2.0444 | 2.305195 | 355 | 2.3324 |
| 2.0428 | 2.337662 | 360 | 2.3325 |
| 2.0612 | 2.370130 | 365 | 2.3326 |
| 2.1078 | 2.402597 | 370 | 2.3327 |
| 2.0643 | 2.435065 | 375 | 2.3327 |
| 2.0667 | 2.467532 | 380 | 2.3326 |
| 2.0285 | 2.500000 | 385 | 2.3324 |
| 2.0571 | 2.532468 | 390 | 2.3322 |
| 2.0209 | 2.564935 | 395 | 2.3322 |
| 2.0537 | 2.597403 | 400 | 2.3323 |
| 2.0138 | 2.629870 | 405 | 2.3324 |
| 2.0772 | 2.662338 | 410 | 2.3324 |
| 2.039 | 2.694805 | 415 | 2.3323 |
| 2.0181 | 2.727273 | 420 | 2.3322 |
| 2.0484 | 2.759740 | 425 | 2.3320 |
| 2.0224 | 2.792208 | 430 | 2.3320 |
| 2.0732 | 2.824675 | 435 | 2.3320 |
| 2.0499 | 2.857143 | 440 | 2.3321 |
| 2.0498 | 2.889610 | 445 | 2.3321 |
| 2.0472 | 2.922078 | 450 | 2.3320 |
| 2.1327 | 2.954545 | 455 | 2.3319 |
| 2.0642 | 2.987013 | 460 | 2.3319 |
| 2.0654 | 3.019481 | 465 | - |
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-C015-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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.8675 | 0.1042 | 5 | 0.8585 |
| 0.8415 | 0.2083 | 10 | 0.8063 |
| 0.8225 | 0.3125 | 15 | 0.8210 |
| 0.806 | 0.4167 | 20 | 0.8412 |
| 0.8139 | 0.5208 | 25 | 0.8702 |
| 0.8978 | 0.625 | 30 | 0.8631 |
| 0.814 | 0.7292 | 35 | 0.8550 |
| 0.7989 | 0.8333 | 40 | 0.8473 |
| 0.8769 | 0.9375 | 45 | 0.8383 |
| 0.7244 | 1.0417 | 50 | 0.8278 |
| 0.4644 | 1.1458 | 55 | 0.8387 |
| 0.4488 | 1.25 | 60 | 0.8680 |
| 0.3973 | 1.3542 | 65 | 0.8718 |
| 0.443 | 1.4583 | 70 | 0.8596 |
| 0.4346 | 1.5625 | 75 | 0.8514 |
| 0.4701 | 1.6667 | 80 | 0.8461 |
| 0.4344 | 1.7708 | 85 | 0.8437 |
| 0.4274 | 1.875 | 90 | 0.8434 |
| 0.4771 | 1.9792 | 95 | 0.8434 |
| 0.3876 | 2.0833 | 100 | 0.8439 |
| 0.3698 | 2.1875 | 105 | 0.8451 |
| 0.407 | 2.2917 | 110 | 0.8465 |
| 0.374 | 2.3958 | 115 | 0.8482 |
| 0.3945 | 2.5 | 120 | 0.8498 |
| 0.3753 | 2.6042 | 125 | 0.8513 |
| 0.3721 | 2.7083 | 130 | 0.8528 |
| 0.3718 | 2.8125 | 135 | 0.8542 |
| 0.3773 | 2.9167 | 140 | 0.8555 |
| 0.3723 | 3.0208 | 145 | 0.8565 |
| 0.374 | 3.125 | 150 | 0.8576 |
| 0.3728 | 3.2292 | 155 | 0.8588 |
| 0.3686 | 3.3333 | 160 | 0.8598 |
| 0.3617 | 3.4375 | 165 | 0.8607 |
| 0.3546 | 3.5417 | 170 | 0.8613 |
| 0.3707 | 3.6458 | 175 | 0.8619 |
| 0.3739 | 3.75 | 180 | 0.8625 |
| 0.3617 | 3.8542 | 185 | 0.8632 |
| 0.3591 | 3.9583 | 190 | 0.8637 |
## 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}
}
```
## 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
View File

@@ -0,0 +1,12 @@
{
"epoch": 4.0,
"eval_loss": 0.8062803149223328,
"eval_runtime": 1.9823,
"eval_samples_per_second": 171.522,
"eval_steps_per_second": 1.513,
"total_flos": 5334785064960.0,
"train_loss": 0.508326952966551,
"train_runtime": 4164.2152,
"train_samples_per_second": 2.934,
"train_steps_per_second": 0.046
}

28
config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "/mnt/fl/projects/pro-align/progressalign/shared_storage/our_models/C015_llama3-8b-base_pretrain_20240428_005832",
"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
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

7
eval_results.json Normal file
View File

@@ -0,0 +1,7 @@
{
"epoch": 4.0,
"eval_loss": 0.8062803149223328,
"eval_runtime": 1.9823,
"eval_samples_per_second": 171.522,
"eval_steps_per_second": 1.513
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 128000,
"eos_token_id": 128001,
"transformers_version": "4.40.1"
}

3
model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ef6764666375baa6c70755ee998e513f62060f5b46913ae34e67abe0e31a72d
size 4976698592

3
model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f657d1353892b5d5fe5ed93998f2aa6e88c5a78fc81fb51cb9573ee86d0c8583
size 4999802616

3
model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fcb906e7483301863b75ce9e879e61afb9cf662fee8c8167b7e3221807d8eda6
size 4915916080

3
model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3adff485e0f3ece17e8f1673a10767ec1fe1aea949fad8118fe8a1e26c16d979
size 1168138808

298
model.safetensors.index.json Normal file
View 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
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 85 KiB

BIN
readme-assets/data-stats.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 210 KiB

BIN
readme-assets/main-diagram.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 178 KiB

BIN
readme-assets/moral-evals.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 218 KiB

23
special_tokens_map.json Normal file
View 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
}
}

410504
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

2065
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 4.0,
"total_flos": 5334785064960.0,
"train_loss": 0.508326952966551,
"train_runtime": 4164.2152,
"train_samples_per_second": 2.934,
"train_steps_per_second": 0.046
}

79
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,79 @@
{"current_steps": 1, "total_steps": 192, "loss": 0.8766, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.020833333333333332, "percentage": 0.52, "elapsed_time": "0:00:03", "remaining_time": "0:09:41"}
{"current_steps": 5, "total_steps": 192, "loss": 0.8675, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.25e-06, "epoch": 0.10416666666666667, "percentage": 2.6, "elapsed_time": "0:00:08", "remaining_time": "0:05:18"}
{"current_steps": 5, "total_steps": 192, "loss": null, "eval_loss": 0.8584801554679871, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.10416666666666667, "percentage": 2.6, "elapsed_time": "0:00:08", "remaining_time": "0:05:18"}
{"current_steps": 10, "total_steps": 192, "loss": 0.8415, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.25e-06, "epoch": 0.20833333333333334, "percentage": 5.21, "elapsed_time": "0:00:59", "remaining_time": "0:18:00"}
{"current_steps": 10, "total_steps": 192, "loss": null, "eval_loss": 0.8062803149223328, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.20833333333333334, "percentage": 5.21, "elapsed_time": "0:00:59", "remaining_time": "0:18:00"}
{"current_steps": 15, "total_steps": 192, "loss": 0.8225, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.25e-06, "epoch": 0.3125, "percentage": 7.81, "elapsed_time": "0:01:52", "remaining_time": "0:22:11"}
{"current_steps": 15, "total_steps": 192, "loss": null, "eval_loss": 0.820951521396637, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.3125, "percentage": 7.81, "elapsed_time": "0:01:52", "remaining_time": "0:22:11"}
{"current_steps": 20, "total_steps": 192, "loss": 0.806, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2e-05, "epoch": 0.4166666666666667, "percentage": 10.42, "elapsed_time": "0:03:49", "remaining_time": "0:32:56"}
{"current_steps": 20, "total_steps": 192, "loss": null, "eval_loss": 0.8412486910820007, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.4166666666666667, "percentage": 10.42, "elapsed_time": "0:03:49", "remaining_time": "0:32:56"}
{"current_steps": 25, "total_steps": 192, "loss": 0.8139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4071209905461127e-05, "epoch": 0.5208333333333334, "percentage": 13.02, "elapsed_time": "0:05:44", "remaining_time": "0:38:20"}
{"current_steps": 25, "total_steps": 192, "loss": null, "eval_loss": 0.8701534867286682, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5208333333333334, "percentage": 13.02, "elapsed_time": "0:05:44", "remaining_time": "0:38:20"}
{"current_steps": 30, "total_steps": 192, "loss": 0.8978, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0166196232101288e-05, "epoch": 0.625, "percentage": 15.62, "elapsed_time": "0:07:41", "remaining_time": "0:41:30"}
{"current_steps": 30, "total_steps": 192, "loss": null, "eval_loss": 0.8630704879760742, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.625, "percentage": 15.62, "elapsed_time": "0:07:41", "remaining_time": "0:41:30"}
{"current_steps": 35, "total_steps": 192, "loss": 0.814, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.276248845991498e-06, "epoch": 0.7291666666666666, "percentage": 18.23, "elapsed_time": "0:09:38", "remaining_time": "0:43:14"}
{"current_steps": 35, "total_steps": 192, "loss": null, "eval_loss": 0.8549697995185852, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7291666666666666, "percentage": 18.23, "elapsed_time": "0:09:38", "remaining_time": "0:43:14"}
{"current_steps": 40, "total_steps": 192, "loss": 0.7989, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.157388080190487e-06, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:11:33", "remaining_time": "0:43:56"}
{"current_steps": 40, "total_steps": 192, "loss": null, "eval_loss": 0.8472943902015686, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:11:33", "remaining_time": "0:43:56"}
{"current_steps": 45, "total_steps": 192, "loss": 0.8769, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6192313334626905e-06, "epoch": 0.9375, "percentage": 23.44, "elapsed_time": "0:13:28", "remaining_time": "0:44:01"}
{"current_steps": 45, "total_steps": 192, "loss": null, "eval_loss": 0.8382811546325684, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9375, "percentage": 23.44, "elapsed_time": "0:13:28", "remaining_time": "0:44:01"}
{"current_steps": 50, "total_steps": 192, "loss": 0.7244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.514391432582838e-06, "epoch": 1.0416666666666667, "percentage": 26.04, "elapsed_time": "0:15:23", "remaining_time": "0:43:43"}
{"current_steps": 50, "total_steps": 192, "loss": null, "eval_loss": 0.8277742266654968, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0416666666666667, "percentage": 26.04, "elapsed_time": "0:15:23", "remaining_time": "0:43:43"}
{"current_steps": 55, "total_steps": 192, "loss": 0.4644, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7297262757656213e-06, "epoch": 1.1458333333333333, "percentage": 28.65, "elapsed_time": "0:17:17", "remaining_time": "0:43:05"}
{"current_steps": 55, "total_steps": 192, "loss": null, "eval_loss": 0.8387134671211243, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.1458333333333333, "percentage": 28.65, "elapsed_time": "0:17:17", "remaining_time": "0:43:05"}
{"current_steps": 60, "total_steps": 192, "loss": 0.4488, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1791620375982074e-06, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:19:12", "remaining_time": "0:42:16"}
{"current_steps": 60, "total_steps": 192, "loss": null, "eval_loss": 0.8680305480957031, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:19:12", "remaining_time": "0:42:16"}
{"current_steps": 65, "total_steps": 192, "loss": 0.3973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.978466092394693e-07, "epoch": 1.3541666666666667, "percentage": 33.85, "elapsed_time": "0:21:07", "remaining_time": "0:41:15"}
{"current_steps": 65, "total_steps": 192, "loss": null, "eval_loss": 0.8717625737190247, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.3541666666666667, "percentage": 33.85, "elapsed_time": "0:21:07", "remaining_time": "0:41:15"}
{"current_steps": 70, "total_steps": 192, "loss": 0.443, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.374210410959207e-07, "epoch": 1.4583333333333333, "percentage": 36.46, "elapsed_time": "0:22:59", "remaining_time": "0:40:03"}
{"current_steps": 70, "total_steps": 192, "loss": null, "eval_loss": 0.8596016764640808, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.4583333333333333, "percentage": 36.46, "elapsed_time": "0:22:59", "remaining_time": "0:40:03"}
{"current_steps": 75, "total_steps": 192, "loss": 0.4346, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6222476698215175e-07, "epoch": 1.5625, "percentage": 39.06, "elapsed_time": "0:24:51", "remaining_time": "0:38:46"}
{"current_steps": 75, "total_steps": 192, "loss": null, "eval_loss": 0.8514222502708435, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.5625, "percentage": 39.06, "elapsed_time": "0:24:51", "remaining_time": "0:38:46"}
{"current_steps": 80, "total_steps": 192, "loss": 0.4701, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.462755297384099e-07, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "0:26:44", "remaining_time": "0:37:25"}
{"current_steps": 80, "total_steps": 192, "loss": null, "eval_loss": 0.8461114764213562, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "0:26:44", "remaining_time": "0:37:25"}
{"current_steps": 85, "total_steps": 192, "loss": 0.4344, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7088740175034947e-07, "epoch": 1.7708333333333335, "percentage": 44.27, "elapsed_time": "0:28:36", "remaining_time": "0:36:00"}
{"current_steps": 85, "total_steps": 192, "loss": null, "eval_loss": 0.8437052369117737, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.7708333333333335, "percentage": 44.27, "elapsed_time": "0:28:36", "remaining_time": "0:36:00"}
{"current_steps": 90, "total_steps": 192, "loss": 0.4274, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.228102956599465e-07, "epoch": 1.875, "percentage": 46.88, "elapsed_time": "0:30:27", "remaining_time": "0:34:31"}
{"current_steps": 90, "total_steps": 192, "loss": null, "eval_loss": 0.8434357643127441, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.875, "percentage": 46.88, "elapsed_time": "0:30:27", "remaining_time": "0:34:31"}
{"current_steps": 95, "total_steps": 192, "loss": 0.4771, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.279207916081227e-08, "epoch": 1.9791666666666665, "percentage": 49.48, "elapsed_time": "0:32:20", "remaining_time": "0:33:01"}
{"current_steps": 95, "total_steps": 192, "loss": null, "eval_loss": 0.8434197902679443, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.9791666666666665, "percentage": 49.48, "elapsed_time": "0:32:20", "remaining_time": "0:33:01"}
{"current_steps": 100, "total_steps": 192, "loss": 0.3876, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.448002404850094e-08, "epoch": 2.0833333333333335, "percentage": 52.08, "elapsed_time": "0:34:12", "remaining_time": "0:31:28"}
{"current_steps": 100, "total_steps": 192, "loss": null, "eval_loss": 0.8438728451728821, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0833333333333335, "percentage": 52.08, "elapsed_time": "0:34:12", "remaining_time": "0:31:28"}
{"current_steps": 105, "total_steps": 192, "loss": 0.3698, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.35920070839697e-08, "epoch": 2.1875, "percentage": 54.69, "elapsed_time": "0:36:01", "remaining_time": "0:29:51"}
{"current_steps": 105, "total_steps": 192, "loss": null, "eval_loss": 0.845079243183136, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.1875, "percentage": 54.69, "elapsed_time": "0:36:01", "remaining_time": "0:29:51"}
{"current_steps": 110, "total_steps": 192, "loss": 0.407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.7299804687499997e-08, "epoch": 2.2916666666666665, "percentage": 57.29, "elapsed_time": "0:37:49", "remaining_time": "0:28:12"}
{"current_steps": 110, "total_steps": 192, "loss": null, "eval_loss": 0.8465444445610046, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.2916666666666665, "percentage": 57.29, "elapsed_time": "0:37:49", "remaining_time": "0:28:12"}
{"current_steps": 115, "total_steps": 192, "loss": 0.374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.37771434967624e-08, "epoch": 2.3958333333333335, "percentage": 59.9, "elapsed_time": "0:39:40", "remaining_time": "0:26:33"}
{"current_steps": 115, "total_steps": 192, "loss": null, "eval_loss": 0.8481599688529968, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.3958333333333335, "percentage": 59.9, "elapsed_time": "0:39:40", "remaining_time": "0:26:33"}
{"current_steps": 120, "total_steps": 192, "loss": 0.3945, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.187403540619925e-08, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:41:28", "remaining_time": "0:24:53"}
{"current_steps": 120, "total_steps": 192, "loss": null, "eval_loss": 0.8498236536979675, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:41:28", "remaining_time": "0:24:53"}
{"current_steps": 125, "total_steps": 192, "loss": 0.3753, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.088648238966908e-08, "epoch": 2.6041666666666665, "percentage": 65.1, "elapsed_time": "0:43:19", "remaining_time": "0:23:13"}
{"current_steps": 125, "total_steps": 192, "loss": null, "eval_loss": 0.8512565493583679, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.6041666666666665, "percentage": 65.1, "elapsed_time": "0:43:19", "remaining_time": "0:23:13"}
{"current_steps": 130, "total_steps": 192, "loss": 0.3721, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.039701925276604e-08, "epoch": 2.7083333333333335, "percentage": 67.71, "elapsed_time": "0:45:11", "remaining_time": "0:21:32"}
{"current_steps": 130, "total_steps": 192, "loss": null, "eval_loss": 0.8527700304985046, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.7083333333333335, "percentage": 67.71, "elapsed_time": "0:45:11", "remaining_time": "0:21:32"}
{"current_steps": 135, "total_steps": 192, "loss": 0.3718, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0166900048082497e-08, "epoch": 2.8125, "percentage": 70.31, "elapsed_time": "0:47:01", "remaining_time": "0:19:51"}
{"current_steps": 135, "total_steps": 192, "loss": null, "eval_loss": 0.8541720509529114, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.8125, "percentage": 70.31, "elapsed_time": "0:47:01", "remaining_time": "0:19:51"}
{"current_steps": 140, "total_steps": 192, "loss": 0.3773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0065147322870076e-08, "epoch": 2.9166666666666665, "percentage": 72.92, "elapsed_time": "0:48:51", "remaining_time": "0:18:09"}
{"current_steps": 140, "total_steps": 192, "loss": null, "eval_loss": 0.8555252552032471, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.9166666666666665, "percentage": 72.92, "elapsed_time": "0:48:51", "remaining_time": "0:18:09"}
{"current_steps": 145, "total_steps": 192, "loss": 0.3723, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.002328628528332e-08, "epoch": 3.0208333333333335, "percentage": 75.52, "elapsed_time": "0:50:40", "remaining_time": "0:16:25"}
{"current_steps": 145, "total_steps": 192, "loss": null, "eval_loss": 0.8565484881401062, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0208333333333335, "percentage": 75.52, "elapsed_time": "0:50:40", "remaining_time": "0:16:25"}
{"current_steps": 150, "total_steps": 192, "loss": 0.374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0007484528133236e-08, "epoch": 3.125, "percentage": 78.12, "elapsed_time": "0:52:32", "remaining_time": "0:14:42"}
{"current_steps": 150, "total_steps": 192, "loss": null, "eval_loss": 0.8576194643974304, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.125, "percentage": 78.12, "elapsed_time": "0:52:32", "remaining_time": "0:14:42"}
{"current_steps": 155, "total_steps": 192, "loss": 0.3728, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0002110817570477e-08, "epoch": 3.2291666666666665, "percentage": 80.73, "elapsed_time": "0:54:21", "remaining_time": "0:12:58"}
{"current_steps": 155, "total_steps": 192, "loss": null, "eval_loss": 0.8588044047355652, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.2291666666666665, "percentage": 80.73, "elapsed_time": "0:54:21", "remaining_time": "0:12:58"}
{"current_steps": 160, "total_steps": 192, "loss": 0.3686, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000504842356326e-08, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "0:56:13", "remaining_time": "0:11:14"}
{"current_steps": 160, "total_steps": 192, "loss": null, "eval_loss": 0.859791100025177, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "0:56:13", "remaining_time": "0:11:14"}
{"current_steps": 165, "total_steps": 192, "loss": 0.3617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000009745562451e-08, "epoch": 3.4375, "percentage": 85.94, "elapsed_time": "0:58:03", "remaining_time": "0:09:29"}
{"current_steps": 165, "total_steps": 192, "loss": null, "eval_loss": 0.8607122302055359, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.4375, "percentage": 85.94, "elapsed_time": "0:58:03", "remaining_time": "0:09:29"}
{"current_steps": 170, "total_steps": 192, "loss": 0.3546, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000014077810156e-08, "epoch": 3.5416666666666665, "percentage": 88.54, "elapsed_time": "0:59:52", "remaining_time": "0:07:44"}
{"current_steps": 170, "total_steps": 192, "loss": null, "eval_loss": 0.8613293170928955, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.5416666666666665, "percentage": 88.54, "elapsed_time": "0:59:52", "remaining_time": "0:07:44"}
{"current_steps": 175, "total_steps": 192, "loss": 0.3707, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000001343508807e-08, "epoch": 3.6458333333333335, "percentage": 91.15, "elapsed_time": "1:01:40", "remaining_time": "0:05:59"}
{"current_steps": 175, "total_steps": 192, "loss": null, "eval_loss": 0.8619220852851868, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.6458333333333335, "percentage": 91.15, "elapsed_time": "1:01:40", "remaining_time": "0:05:59"}
{"current_steps": 180, "total_steps": 192, "loss": 0.3739, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000006747581e-08, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "1:03:31", "remaining_time": "0:04:14"}
{"current_steps": 180, "total_steps": 192, "loss": null, "eval_loss": 0.862490177154541, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "1:03:31", "remaining_time": "0:04:14"}
{"current_steps": 185, "total_steps": 192, "loss": 0.3617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000000001094325e-08, "epoch": 3.8541666666666665, "percentage": 96.35, "elapsed_time": "1:05:21", "remaining_time": "0:02:28"}
{"current_steps": 185, "total_steps": 192, "loss": null, "eval_loss": 0.8631939888000488, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.8541666666666665, "percentage": 96.35, "elapsed_time": "1:05:21", "remaining_time": "0:02:28"}
{"current_steps": 190, "total_steps": 192, "loss": 0.3591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000000139e-08, "epoch": 3.9583333333333335, "percentage": 98.96, "elapsed_time": "1:07:12", "remaining_time": "0:00:42"}
{"current_steps": 190, "total_steps": 192, "loss": null, "eval_loss": 0.8637197613716125, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.9583333333333335, "percentage": 98.96, "elapsed_time": "1:07:12", "remaining_time": "0:00:42"}
{"current_steps": 192, "total_steps": 192, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:08:56", "remaining_time": "0:00:00"}
{"current_steps": 3, "total_steps": 3, "loss": null, "eval_loss": 0.8062803149223328, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:09:34", "remaining_time": "0:00:00"}

607
trainer_state.json Normal file
View File

@@ -0,0 +1,607 @@
{
"best_metric": 0.8062803149223328,
"best_model_checkpoint": "./output/training_results/C015_llama3-8b-base_instruct_20240504_123713/checkpoint-10",
"epoch": 4.0,
"eval_steps": 5,
"global_step": 192,
"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": 0.8766,
"step": 1
},
{
"epoch": 0.10416666666666667,
"grad_norm": 10.34330229700748,
"learning_rate": 2.25e-06,
"loss": 0.8675,
"step": 5
},
{
"epoch": 0.10416666666666667,
"eval_loss": 0.8584801554679871,
"eval_runtime": 1.9951,
"eval_samples_per_second": 170.414,
"eval_steps_per_second": 1.504,
"step": 5
},
{
"epoch": 0.20833333333333334,
"grad_norm": 4.512014612667122,
"learning_rate": 5.25e-06,
"loss": 0.8415,
"step": 10
},
{
"epoch": 0.20833333333333334,
"eval_loss": 0.8062803149223328,
"eval_runtime": 1.9589,
"eval_samples_per_second": 173.564,
"eval_steps_per_second": 1.531,
"step": 10
},
{
"epoch": 0.3125,
"grad_norm": 5.466223920700161,
"learning_rate": 8.25e-06,
"loss": 0.8225,
"step": 15
},
{
"epoch": 0.3125,
"eval_loss": 0.820951521396637,
"eval_runtime": 1.9583,
"eval_samples_per_second": 173.62,
"eval_steps_per_second": 1.532,
"step": 15
},
{
"epoch": 0.4166666666666667,
"grad_norm": 5.091985939472258,
"learning_rate": 1.2e-05,
"loss": 0.806,
"step": 20
},
{
"epoch": 0.4166666666666667,
"eval_loss": 0.8412486910820007,
"eval_runtime": 1.9516,
"eval_samples_per_second": 174.217,
"eval_steps_per_second": 1.537,
"step": 20
},
{
"epoch": 0.5208333333333334,
"grad_norm": 4.323182492427286,
"learning_rate": 1.4071209905461127e-05,
"loss": 0.8139,
"step": 25
},
{
"epoch": 0.5208333333333334,
"eval_loss": 0.8701534867286682,
"eval_runtime": 1.956,
"eval_samples_per_second": 173.828,
"eval_steps_per_second": 1.534,
"step": 25
},
{
"epoch": 0.625,
"grad_norm": 4.430828029367158,
"learning_rate": 1.0166196232101288e-05,
"loss": 0.8978,
"step": 30
},
{
"epoch": 0.625,
"eval_loss": 0.8630704879760742,
"eval_runtime": 1.9545,
"eval_samples_per_second": 173.954,
"eval_steps_per_second": 1.535,
"step": 30
},
{
"epoch": 0.7291666666666666,
"grad_norm": 3.8459262571296122,
"learning_rate": 7.276248845991498e-06,
"loss": 0.814,
"step": 35
},
{
"epoch": 0.7291666666666666,
"eval_loss": 0.8549697995185852,
"eval_runtime": 1.9539,
"eval_samples_per_second": 174.008,
"eval_steps_per_second": 1.535,
"step": 35
},
{
"epoch": 0.8333333333333334,
"grad_norm": 4.312137758874538,
"learning_rate": 5.157388080190487e-06,
"loss": 0.7989,
"step": 40
},
{
"epoch": 0.8333333333333334,
"eval_loss": 0.8472943902015686,
"eval_runtime": 1.9515,
"eval_samples_per_second": 174.222,
"eval_steps_per_second": 1.537,
"step": 40
},
{
"epoch": 0.9375,
"grad_norm": 4.013634591695819,
"learning_rate": 3.6192313334626905e-06,
"loss": 0.8769,
"step": 45
},
{
"epoch": 0.9375,
"eval_loss": 0.8382811546325684,
"eval_runtime": 1.9527,
"eval_samples_per_second": 174.116,
"eval_steps_per_second": 1.536,
"step": 45
},
{
"epoch": 1.0416666666666667,
"grad_norm": 3.825805552811641,
"learning_rate": 2.514391432582838e-06,
"loss": 0.7244,
"step": 50
},
{
"epoch": 1.0416666666666667,
"eval_loss": 0.8277742266654968,
"eval_runtime": 1.9549,
"eval_samples_per_second": 173.925,
"eval_steps_per_second": 1.535,
"step": 50
},
{
"epoch": 1.1458333333333333,
"grad_norm": 3.0670883145044487,
"learning_rate": 1.7297262757656213e-06,
"loss": 0.4644,
"step": 55
},
{
"epoch": 1.1458333333333333,
"eval_loss": 0.8387134671211243,
"eval_runtime": 1.959,
"eval_samples_per_second": 173.561,
"eval_steps_per_second": 1.531,
"step": 55
},
{
"epoch": 1.25,
"grad_norm": 3.904758197983173,
"learning_rate": 1.1791620375982074e-06,
"loss": 0.4488,
"step": 60
},
{
"epoch": 1.25,
"eval_loss": 0.8680305480957031,
"eval_runtime": 1.953,
"eval_samples_per_second": 174.087,
"eval_steps_per_second": 1.536,
"step": 60
},
{
"epoch": 1.3541666666666667,
"grad_norm": 4.037522952699986,
"learning_rate": 7.978466092394693e-07,
"loss": 0.3973,
"step": 65
},
{
"epoch": 1.3541666666666667,
"eval_loss": 0.8717625737190247,
"eval_runtime": 1.9541,
"eval_samples_per_second": 173.996,
"eval_steps_per_second": 1.535,
"step": 65
},
{
"epoch": 1.4583333333333333,
"grad_norm": 4.006395162021574,
"learning_rate": 5.374210410959207e-07,
"loss": 0.443,
"step": 70
},
{
"epoch": 1.4583333333333333,
"eval_loss": 0.8596016764640808,
"eval_runtime": 1.9513,
"eval_samples_per_second": 174.244,
"eval_steps_per_second": 1.537,
"step": 70
},
{
"epoch": 1.5625,
"grad_norm": 4.477860740274337,
"learning_rate": 3.6222476698215175e-07,
"loss": 0.4346,
"step": 75
},
{
"epoch": 1.5625,
"eval_loss": 0.8514222502708435,
"eval_runtime": 1.9616,
"eval_samples_per_second": 173.329,
"eval_steps_per_second": 1.529,
"step": 75
},
{
"epoch": 1.6666666666666665,
"grad_norm": 3.79003494996975,
"learning_rate": 2.462755297384099e-07,
"loss": 0.4701,
"step": 80
},
{
"epoch": 1.6666666666666665,
"eval_loss": 0.8461114764213562,
"eval_runtime": 1.9519,
"eval_samples_per_second": 174.192,
"eval_steps_per_second": 1.537,
"step": 80
},
{
"epoch": 1.7708333333333335,
"grad_norm": 3.431009868136907,
"learning_rate": 1.7088740175034947e-07,
"loss": 0.4344,
"step": 85
},
{
"epoch": 1.7708333333333335,
"eval_loss": 0.8437052369117737,
"eval_runtime": 1.9548,
"eval_samples_per_second": 173.928,
"eval_steps_per_second": 1.535,
"step": 85
},
{
"epoch": 1.875,
"grad_norm": 3.4612975522103846,
"learning_rate": 1.228102956599465e-07,
"loss": 0.4274,
"step": 90
},
{
"epoch": 1.875,
"eval_loss": 0.8434357643127441,
"eval_runtime": 1.9551,
"eval_samples_per_second": 173.905,
"eval_steps_per_second": 1.534,
"step": 90
},
{
"epoch": 1.9791666666666665,
"grad_norm": 4.089060356958601,
"learning_rate": 9.279207916081227e-08,
"loss": 0.4771,
"step": 95
},
{
"epoch": 1.9791666666666665,
"eval_loss": 0.8434197902679443,
"eval_runtime": 1.9533,
"eval_samples_per_second": 174.06,
"eval_steps_per_second": 1.536,
"step": 95
},
{
"epoch": 2.0833333333333335,
"grad_norm": 3.5663107359521624,
"learning_rate": 7.448002404850094e-08,
"loss": 0.3876,
"step": 100
},
{
"epoch": 2.0833333333333335,
"eval_loss": 0.8438728451728821,
"eval_runtime": 1.957,
"eval_samples_per_second": 173.739,
"eval_steps_per_second": 1.533,
"step": 100
},
{
"epoch": 2.1875,
"grad_norm": 3.3025378175144806,
"learning_rate": 6.35920070839697e-08,
"loss": 0.3698,
"step": 105
},
{
"epoch": 2.1875,
"eval_loss": 0.845079243183136,
"eval_runtime": 1.9562,
"eval_samples_per_second": 173.803,
"eval_steps_per_second": 1.534,
"step": 105
},
{
"epoch": 2.2916666666666665,
"grad_norm": 3.4985300165216615,
"learning_rate": 5.7299804687499997e-08,
"loss": 0.407,
"step": 110
},
{
"epoch": 2.2916666666666665,
"eval_loss": 0.8465444445610046,
"eval_runtime": 1.9573,
"eval_samples_per_second": 173.708,
"eval_steps_per_second": 1.533,
"step": 110
},
{
"epoch": 2.3958333333333335,
"grad_norm": 3.394752587183079,
"learning_rate": 5.37771434967624e-08,
"loss": 0.374,
"step": 115
},
{
"epoch": 2.3958333333333335,
"eval_loss": 0.8481599688529968,
"eval_runtime": 1.9556,
"eval_samples_per_second": 173.861,
"eval_steps_per_second": 1.534,
"step": 115
},
{
"epoch": 2.5,
"grad_norm": 4.399721414998381,
"learning_rate": 5.187403540619925e-08,
"loss": 0.3945,
"step": 120
},
{
"epoch": 2.5,
"eval_loss": 0.8498236536979675,
"eval_runtime": 1.9552,
"eval_samples_per_second": 173.893,
"eval_steps_per_second": 1.534,
"step": 120
},
{
"epoch": 2.6041666666666665,
"grad_norm": 3.2768849901156845,
"learning_rate": 5.088648238966908e-08,
"loss": 0.3753,
"step": 125
},
{
"epoch": 2.6041666666666665,
"eval_loss": 0.8512565493583679,
"eval_runtime": 1.9594,
"eval_samples_per_second": 173.526,
"eval_steps_per_second": 1.531,
"step": 125
},
{
"epoch": 2.7083333333333335,
"grad_norm": 3.666595330730063,
"learning_rate": 5.039701925276604e-08,
"loss": 0.3721,
"step": 130
},
{
"epoch": 2.7083333333333335,
"eval_loss": 0.8527700304985046,
"eval_runtime": 1.9575,
"eval_samples_per_second": 173.689,
"eval_steps_per_second": 1.533,
"step": 130
},
{
"epoch": 2.8125,
"grad_norm": 3.4733320032072537,
"learning_rate": 5.0166900048082497e-08,
"loss": 0.3718,
"step": 135
},
{
"epoch": 2.8125,
"eval_loss": 0.8541720509529114,
"eval_runtime": 1.9599,
"eval_samples_per_second": 173.479,
"eval_steps_per_second": 1.531,
"step": 135
},
{
"epoch": 2.9166666666666665,
"grad_norm": 3.447696757476531,
"learning_rate": 5.0065147322870076e-08,
"loss": 0.3773,
"step": 140
},
{
"epoch": 2.9166666666666665,
"eval_loss": 0.8555252552032471,
"eval_runtime": 1.9586,
"eval_samples_per_second": 173.592,
"eval_steps_per_second": 1.532,
"step": 140
},
{
"epoch": 3.0208333333333335,
"grad_norm": 3.0052210603196237,
"learning_rate": 5.002328628528332e-08,
"loss": 0.3723,
"step": 145
},
{
"epoch": 3.0208333333333335,
"eval_loss": 0.8565484881401062,
"eval_runtime": 1.9586,
"eval_samples_per_second": 173.589,
"eval_steps_per_second": 1.532,
"step": 145
},
{
"epoch": 3.125,
"grad_norm": 3.368197941438436,
"learning_rate": 5.0007484528133236e-08,
"loss": 0.374,
"step": 150
},
{
"epoch": 3.125,
"eval_loss": 0.8576194643974304,
"eval_runtime": 1.9541,
"eval_samples_per_second": 173.993,
"eval_steps_per_second": 1.535,
"step": 150
},
{
"epoch": 3.2291666666666665,
"grad_norm": 3.3290743731904304,
"learning_rate": 5.0002110817570477e-08,
"loss": 0.3728,
"step": 155
},
{
"epoch": 3.2291666666666665,
"eval_loss": 0.8588044047355652,
"eval_runtime": 1.951,
"eval_samples_per_second": 174.273,
"eval_steps_per_second": 1.538,
"step": 155
},
{
"epoch": 3.3333333333333335,
"grad_norm": 4.793937739567796,
"learning_rate": 5.0000504842356326e-08,
"loss": 0.3686,
"step": 160
},
{
"epoch": 3.3333333333333335,
"eval_loss": 0.859791100025177,
"eval_runtime": 1.9522,
"eval_samples_per_second": 174.159,
"eval_steps_per_second": 1.537,
"step": 160
},
{
"epoch": 3.4375,
"grad_norm": 3.326342529192208,
"learning_rate": 5.000009745562451e-08,
"loss": 0.3617,
"step": 165
},
{
"epoch": 3.4375,
"eval_loss": 0.8607122302055359,
"eval_runtime": 1.958,
"eval_samples_per_second": 173.647,
"eval_steps_per_second": 1.532,
"step": 165
},
{
"epoch": 3.5416666666666665,
"grad_norm": 3.6505713497705736,
"learning_rate": 5.0000014077810156e-08,
"loss": 0.3546,
"step": 170
},
{
"epoch": 3.5416666666666665,
"eval_loss": 0.8613293170928955,
"eval_runtime": 1.9527,
"eval_samples_per_second": 174.122,
"eval_steps_per_second": 1.536,
"step": 170
},
{
"epoch": 3.6458333333333335,
"grad_norm": 3.496080458530573,
"learning_rate": 5.0000001343508807e-08,
"loss": 0.3707,
"step": 175
},
{
"epoch": 3.6458333333333335,
"eval_loss": 0.8619220852851868,
"eval_runtime": 1.9552,
"eval_samples_per_second": 173.893,
"eval_steps_per_second": 1.534,
"step": 175
},
{
"epoch": 3.75,
"grad_norm": 3.50316414527161,
"learning_rate": 5.000000006747581e-08,
"loss": 0.3739,
"step": 180
},
{
"epoch": 3.75,
"eval_loss": 0.862490177154541,
"eval_runtime": 1.9547,
"eval_samples_per_second": 173.936,
"eval_steps_per_second": 1.535,
"step": 180
},
{
"epoch": 3.8541666666666665,
"grad_norm": 3.7278057893863874,
"learning_rate": 5.0000000001094325e-08,
"loss": 0.3617,
"step": 185
},
{
"epoch": 3.8541666666666665,
"eval_loss": 0.8631939888000488,
"eval_runtime": 1.9574,
"eval_samples_per_second": 173.703,
"eval_steps_per_second": 1.533,
"step": 185
},
{
"epoch": 3.9583333333333335,
"grad_norm": 3.160928200357982,
"learning_rate": 5.000000000000139e-08,
"loss": 0.3591,
"step": 190
},
{
"epoch": 3.9583333333333335,
"eval_loss": 0.8637197613716125,
"eval_runtime": 1.9552,
"eval_samples_per_second": 173.893,
"eval_steps_per_second": 1.534,
"step": 190
},
{
"epoch": 4.0,
"step": 192,
"total_flos": 5334785064960.0,
"train_loss": 0.508326952966551,
"train_runtime": 4164.2152,
"train_samples_per_second": 2.934,
"train_steps_per_second": 0.046
}
],
"logging_steps": 5,
"max_steps": 192,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 5,
"total_flos": 5334785064960.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6847c094292a8b40cbd23c921c6bcb9cbc8346d03045e21561f149c7aa6e6569
size 6776

BIN
training_eval_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 47 KiB

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 40 KiB