初始化项目，由ModelHub XC社区提供模型
Model: PKU-Alignment/ProgressGym-HistLlama3-8B-C018-pretrain-v0.2 Source: Original Platform
This commit is contained in:
ModelHub XC
39
.gitattributes
vendored
Normal file
39
.gitattributes
vendored
Normal 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
|
||||
112
README.md
Normal file
112
README.md
Normal file
@@ -0,0 +1,112 @@
|
||||
---
|
||||
license: cc-by-4.0
|
||||
tags:
|
||||
- alignment
|
||||
- value alignment
|
||||
- AI safety
|
||||
- safety
|
||||
- LLM
|
||||
- history
|
||||
datasets:
|
||||
- PKU-Alignment/ProgressGym-HistText
|
||||
base_model:
|
||||
- meta-llama/Meta-Llama-3-8B
|
||||
---
|
||||
|
||||
# ProgressGym-HistLlama3-8B-C018-pretrain
|
||||
|
||||
## Overview
|
||||
|
||||
#### The ProgressGym Framework
|
||||
|
||||
|
||||
|
||||
**ProgressGym-HistLlama3-8B-C018-pretrain** 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-C018-pretrain
|
||||
|
||||
ProgressGym-HistLlama3-8B-C018-pretrain is one of the **36 historical language models** in the ProgressGym framework. It is a pretrained model without instruction-tuning. For the instruction-tuned version, see [ProgressGym-HistLlama3-8B-C018-instruct](https://huggingface.co/PKU-Alignment/ProgressGym-HistLlama3-8B-C018-instruct).
|
||||
|
||||
**ProgressGym-HistLlama3-8B-C018-pretrain 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-C018-pretrain is a 18th-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 18th-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 |
|
||||
|:-------------:|:------:|:----:|:---------------:|
|
||||
| 2.3701 | 0.2186 | 200 | 2.3702 |
|
||||
| 2.3183 | 0.4372 | 400 | 2.3160 |
|
||||
| 2.2634 | 0.6557 | 600 | 2.2863 |
|
||||
| 2.2522 | 0.8743 | 800 | 2.2706 |
|
||||
| 2.0306 | 1.0929 | 1000 | 2.2777 |
|
||||
| 2.0095 | 1.3115 | 1200 | 2.2760 |
|
||||
| 2.0539 | 1.5301 | 1400 | 2.2746 |
|
||||
| 2.0338 | 1.7486 | 1600 | 2.2743 |
|
||||
| 2.0648 | 1.9672 | 1800 | 2.2737 |
|
||||
| 2.0297 | 2.1858 | 2000 | 2.2766 |
|
||||
| 2.0487 | 2.4044 | 2200 | 2.2767 |
|
||||
| 2.0329 | 2.6230 | 2400 | 2.2770 |
|
||||
| 2.0213 | 2.8415 | 2600 | 2.2766 |
|
||||
| 2.0559 | 3.0601 | 2800 | 2.2771 |
|
||||
| 2.0543 | 3.2787 | 3000 | 2.2773 |
|
||||
| 2.0317 | 3.4973 | 3200 | 2.2772 |
|
||||
| 1.988 | 3.7158 | 3400 | 2.2770 |
|
||||
| 2.0355 | 3.9344 | 3600 | 2.2772 |
|
||||
|
||||
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.
|
||||
|
||||
## 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.
|
||||
13
all_results.json
Normal file
13
all_results.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"eval_loss": 2.2968251705169678,
|
||||
"eval_runtime": 40.9962,
|
||||
"eval_samples_per_second": 203.629,
|
||||
"eval_steps_per_second": 1.61,
|
||||
"perplexity": 9.942566340729925,
|
||||
"total_flos": 490890602741760.0,
|
||||
"train_loss": 2.2402087043862937,
|
||||
"train_runtime": 7138.091,
|
||||
"train_samples_per_second": 42.101,
|
||||
"train_steps_per_second": 0.658
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "/aifs4su/yaodong/models/Meta-Llama-3-8B",
|
||||
"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}
|
||||
8
eval_results.json
Normal file
8
eval_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"eval_loss": 2.2968251705169678,
|
||||
"eval_runtime": 40.9962,
|
||||
"eval_samples_per_second": 203.629,
|
||||
"eval_steps_per_second": 1.61,
|
||||
"perplexity": 9.942566340729925
|
||||
}
|
||||
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 sha256:33bb0e57ac436e8ac171215ac8cdf0058d5aea55db4be3f6b8a0f42f3822709b
|
||||
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 sha256:22cec82ed870b545b362621b2d21d7bd450767796adae48e1001328870bb65dd
|
||||
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 sha256:577a80848bb85de6faaa40edd47d97cbc44f820a4b6053b50db51937ba0a7a30
|
||||
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 sha256:7dc51bb5585c767d3e643d567edef079813819b55ee01337d7ea84199538b19a
|
||||
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 |
17
special_tokens_map.json
Normal file
17
special_tokens_map.json
Normal file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"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": "<|end_of_text|>"
|
||||
}
|
||||
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": 4.0,
|
||||
"total_flos": 490890602741760.0,
|
||||
"train_loss": 2.2402087043862937,
|
||||
"train_runtime": 7138.091,
|
||||
"train_samples_per_second": 42.101,
|
||||
"train_steps_per_second": 0.658
|
||||
}
|
||||
31
trainer_log.jsonl
Normal file
31
trainer_log.jsonl
Normal file
@@ -0,0 +1,31 @@
|
||||
{"current_steps": 1, "total_steps": 4696, "loss": 2.4637, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.0008517887563884157, "percentage": 0.02, "elapsed_time": "0:00:07", "remaining_time": "9:26:27"}
|
||||
{"current_steps": 235, "total_steps": 4696, "loss": 2.4082, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9546742209631728e-06, "epoch": 0.20017035775127767, "percentage": 5.0, "elapsed_time": "0:05:31", "remaining_time": "1:44:47"}
|
||||
{"current_steps": 470, "total_steps": 4696, "loss": 2.3529, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2631312554186003e-06, "epoch": 0.40034071550255534, "percentage": 10.01, "elapsed_time": "0:10:55", "remaining_time": "1:38:16"}
|
||||
{"current_steps": 470, "total_steps": 4696, "loss": null, "eval_loss": 2.341965675354004, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.40034071550255534, "percentage": 10.01, "elapsed_time": "0:10:55", "remaining_time": "1:38:16"}
|
||||
{"current_steps": 705, "total_steps": 4696, "loss": 2.3196, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2303591421466819e-06, "epoch": 0.600511073253833, "percentage": 15.01, "elapsed_time": "0:17:37", "remaining_time": "1:39:44"}
|
||||
{"current_steps": 940, "total_steps": 4696, "loss": 2.3053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.559971206312988e-07, "epoch": 0.8006814310051107, "percentage": 20.02, "elapsed_time": "0:22:52", "remaining_time": "1:31:23"}
|
||||
{"current_steps": 940, "total_steps": 4696, "loss": null, "eval_loss": 2.307070732116699, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8006814310051107, "percentage": 20.02, "elapsed_time": "0:22:52", "remaining_time": "1:31:23"}
|
||||
{"current_steps": 1175, "total_steps": 4696, "loss": 2.2905, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4801579366796346e-07, "epoch": 1.0008517887563884, "percentage": 25.02, "elapsed_time": "0:29:33", "remaining_time": "1:28:34"}
|
||||
{"current_steps": 1410, "total_steps": 4696, "loss": 2.2195, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8955345667471282e-07, "epoch": 1.201022146507666, "percentage": 30.03, "elapsed_time": "0:34:46", "remaining_time": "1:21:03"}
|
||||
{"current_steps": 1410, "total_steps": 4696, "loss": null, "eval_loss": 2.3012468814849854, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.201022146507666, "percentage": 30.03, "elapsed_time": "0:34:46", "remaining_time": "1:21:03"}
|
||||
{"current_steps": 1645, "total_steps": 4696, "loss": 2.217, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1177613622113936e-07, "epoch": 1.4011925042589437, "percentage": 35.03, "elapsed_time": "0:41:28", "remaining_time": "1:16:56"}
|
||||
{"current_steps": 1880, "total_steps": 4696, "loss": 2.2134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.561933429867634e-08, "epoch": 1.6013628620102214, "percentage": 40.03, "elapsed_time": "0:46:41", "remaining_time": "1:09:56"}
|
||||
{"current_steps": 1880, "total_steps": 4696, "loss": null, "eval_loss": 2.2990095615386963, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.6013628620102214, "percentage": 40.03, "elapsed_time": "0:46:41", "remaining_time": "1:09:56"}
|
||||
{"current_steps": 2115, "total_steps": 4696, "loss": 2.2142, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.984119005303602e-08, "epoch": 1.8015332197614993, "percentage": 45.04, "elapsed_time": "0:53:23", "remaining_time": "1:05:09"}
|
||||
{"current_steps": 2350, "total_steps": 4696, "loss": 2.2183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.345074457083591e-08, "epoch": 2.0017035775127767, "percentage": 50.04, "elapsed_time": "0:58:36", "remaining_time": "0:58:31"}
|
||||
{"current_steps": 2350, "total_steps": 4696, "loss": null, "eval_loss": 2.2979490756988525, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0017035775127767, "percentage": 50.04, "elapsed_time": "0:58:36", "remaining_time": "0:58:31"}
|
||||
{"current_steps": 2585, "total_steps": 4696, "loss": 2.1996, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.108344330433012e-08, "epoch": 2.2018739352640546, "percentage": 55.05, "elapsed_time": "1:05:26", "remaining_time": "0:53:26"}
|
||||
{"current_steps": 2820, "total_steps": 4696, "loss": 2.2069, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0296763609045817e-08, "epoch": 2.402044293015332, "percentage": 60.05, "elapsed_time": "1:10:39", "remaining_time": "0:47:00"}
|
||||
{"current_steps": 2820, "total_steps": 4696, "loss": null, "eval_loss": 2.2981810569763184, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.402044293015332, "percentage": 60.05, "elapsed_time": "1:10:39", "remaining_time": "0:47:00"}
|
||||
{"current_steps": 3055, "total_steps": 4696, "loss": 2.2071, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.006836944156395e-08, "epoch": 2.60221465076661, "percentage": 65.06, "elapsed_time": "1:17:26", "remaining_time": "0:41:35"}
|
||||
{"current_steps": 3290, "total_steps": 4696, "loss": 2.205, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.001265655634458e-08, "epoch": 2.8023850085178874, "percentage": 70.06, "elapsed_time": "1:22:39", "remaining_time": "0:35:19"}
|
||||
{"current_steps": 3290, "total_steps": 4696, "loss": null, "eval_loss": 2.2976646423339844, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.8023850085178874, "percentage": 70.06, "elapsed_time": "1:22:39", "remaining_time": "0:35:19"}
|
||||
{"current_steps": 3525, "total_steps": 4696, "loss": 2.2038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000170873605877e-08, "epoch": 3.0025553662691653, "percentage": 75.06, "elapsed_time": "1:29:28", "remaining_time": "0:29:43"}
|
||||
{"current_steps": 3760, "total_steps": 4696, "loss": 2.1934, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000014746665313e-08, "epoch": 3.2027257240204428, "percentage": 80.07, "elapsed_time": "1:34:41", "remaining_time": "0:23:34"}
|
||||
{"current_steps": 3760, "total_steps": 4696, "loss": null, "eval_loss": 2.2974419593811035, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.2027257240204428, "percentage": 80.07, "elapsed_time": "1:34:41", "remaining_time": "0:23:34"}
|
||||
{"current_steps": 3995, "total_steps": 4696, "loss": 2.193, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000637528681e-08, "epoch": 3.4028960817717206, "percentage": 85.07, "elapsed_time": "1:41:30", "remaining_time": "0:17:48"}
|
||||
{"current_steps": 4230, "total_steps": 4696, "loss": 2.2047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000007544082e-08, "epoch": 3.6030664395229985, "percentage": 90.08, "elapsed_time": "1:46:43", "remaining_time": "0:11:45"}
|
||||
{"current_steps": 4230, "total_steps": 4696, "loss": null, "eval_loss": 2.2968251705169678, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.6030664395229985, "percentage": 90.08, "elapsed_time": "1:46:43", "remaining_time": "0:11:45"}
|
||||
{"current_steps": 4465, "total_steps": 4696, "loss": 2.2036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000003948e-08, "epoch": 3.803236797274276, "percentage": 95.08, "elapsed_time": "1:53:36", "remaining_time": "0:05:52"}
|
||||
{"current_steps": 4696, "total_steps": 4696, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:58:44", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 66, "total_steps": 66, "loss": null, "eval_loss": 2.2968251705169678, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "2:00:02", "remaining_time": "0:00:00"}
|
||||
242
trainer_state.json
Normal file
242
trainer_state.json
Normal file
@@ -0,0 +1,242 @@
|
||||
{
|
||||
"best_metric": 2.2968251705169678,
|
||||
"best_model_checkpoint": "./output/training_results/C018_Meta-Llama-3-8B_pretrain_20240726_033210/checkpoint-4230",
|
||||
"epoch": 4.0,
|
||||
"eval_steps": 470,
|
||||
"global_step": 4696,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.0008517887563884157,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 2.4637,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.20017035775127767,
|
||||
"grad_norm": 2.3409501850123138,
|
||||
"learning_rate": 1.9546742209631728e-06,
|
||||
"loss": 2.4082,
|
||||
"step": 235
|
||||
},
|
||||
{
|
||||
"epoch": 0.40034071550255534,
|
||||
"grad_norm": 2.1722293582224492,
|
||||
"learning_rate": 2.2631312554186003e-06,
|
||||
"loss": 2.3529,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 0.40034071550255534,
|
||||
"eval_loss": 2.341965675354004,
|
||||
"eval_runtime": 41.4873,
|
||||
"eval_samples_per_second": 201.218,
|
||||
"eval_steps_per_second": 1.591,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 0.600511073253833,
|
||||
"grad_norm": 2.185798119323745,
|
||||
"learning_rate": 1.2303591421466819e-06,
|
||||
"loss": 2.3196,
|
||||
"step": 705
|
||||
},
|
||||
{
|
||||
"epoch": 0.8006814310051107,
|
||||
"grad_norm": 1.9581500824387317,
|
||||
"learning_rate": 6.559971206312988e-07,
|
||||
"loss": 2.3053,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 0.8006814310051107,
|
||||
"eval_loss": 2.307070732116699,
|
||||
"eval_runtime": 41.2244,
|
||||
"eval_samples_per_second": 202.501,
|
||||
"eval_steps_per_second": 1.601,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 1.0008517887563884,
|
||||
"grad_norm": 2.0030962313242693,
|
||||
"learning_rate": 3.4801579366796346e-07,
|
||||
"loss": 2.2905,
|
||||
"step": 1175
|
||||
},
|
||||
{
|
||||
"epoch": 1.201022146507666,
|
||||
"grad_norm": 2.1511768973070087,
|
||||
"learning_rate": 1.8955345667471282e-07,
|
||||
"loss": 2.2195,
|
||||
"step": 1410
|
||||
},
|
||||
{
|
||||
"epoch": 1.201022146507666,
|
||||
"eval_loss": 2.3012468814849854,
|
||||
"eval_runtime": 41.1845,
|
||||
"eval_samples_per_second": 202.698,
|
||||
"eval_steps_per_second": 1.603,
|
||||
"step": 1410
|
||||
},
|
||||
{
|
||||
"epoch": 1.4011925042589437,
|
||||
"grad_norm": 2.038172613706977,
|
||||
"learning_rate": 1.1177613622113936e-07,
|
||||
"loss": 2.217,
|
||||
"step": 1645
|
||||
},
|
||||
{
|
||||
"epoch": 1.6013628620102214,
|
||||
"grad_norm": 2.6056027737544087,
|
||||
"learning_rate": 7.561933429867634e-08,
|
||||
"loss": 2.2134,
|
||||
"step": 1880
|
||||
},
|
||||
{
|
||||
"epoch": 1.6013628620102214,
|
||||
"eval_loss": 2.2990095615386963,
|
||||
"eval_runtime": 41.2014,
|
||||
"eval_samples_per_second": 202.615,
|
||||
"eval_steps_per_second": 1.602,
|
||||
"step": 1880
|
||||
},
|
||||
{
|
||||
"epoch": 1.8015332197614993,
|
||||
"grad_norm": 2.3428592690655385,
|
||||
"learning_rate": 5.984119005303602e-08,
|
||||
"loss": 2.2142,
|
||||
"step": 2115
|
||||
},
|
||||
{
|
||||
"epoch": 2.0017035775127767,
|
||||
"grad_norm": 1.9738830418944124,
|
||||
"learning_rate": 5.345074457083591e-08,
|
||||
"loss": 2.2183,
|
||||
"step": 2350
|
||||
},
|
||||
{
|
||||
"epoch": 2.0017035775127767,
|
||||
"eval_loss": 2.2979490756988525,
|
||||
"eval_runtime": 41.2381,
|
||||
"eval_samples_per_second": 202.434,
|
||||
"eval_steps_per_second": 1.6,
|
||||
"step": 2350
|
||||
},
|
||||
{
|
||||
"epoch": 2.2018739352640546,
|
||||
"grad_norm": 1.9766056487629942,
|
||||
"learning_rate": 5.108344330433012e-08,
|
||||
"loss": 2.1996,
|
||||
"step": 2585
|
||||
},
|
||||
{
|
||||
"epoch": 2.402044293015332,
|
||||
"grad_norm": 1.9886986639549535,
|
||||
"learning_rate": 5.0296763609045817e-08,
|
||||
"loss": 2.2069,
|
||||
"step": 2820
|
||||
},
|
||||
{
|
||||
"epoch": 2.402044293015332,
|
||||
"eval_loss": 2.2981810569763184,
|
||||
"eval_runtime": 41.2271,
|
||||
"eval_samples_per_second": 202.488,
|
||||
"eval_steps_per_second": 1.601,
|
||||
"step": 2820
|
||||
},
|
||||
{
|
||||
"epoch": 2.60221465076661,
|
||||
"grad_norm": 2.0358858583570556,
|
||||
"learning_rate": 5.006836944156395e-08,
|
||||
"loss": 2.2071,
|
||||
"step": 3055
|
||||
},
|
||||
{
|
||||
"epoch": 2.8023850085178874,
|
||||
"grad_norm": 2.0667439556087315,
|
||||
"learning_rate": 5.001265655634458e-08,
|
||||
"loss": 2.205,
|
||||
"step": 3290
|
||||
},
|
||||
{
|
||||
"epoch": 2.8023850085178874,
|
||||
"eval_loss": 2.2976646423339844,
|
||||
"eval_runtime": 41.1148,
|
||||
"eval_samples_per_second": 203.041,
|
||||
"eval_steps_per_second": 1.605,
|
||||
"step": 3290
|
||||
},
|
||||
{
|
||||
"epoch": 3.0025553662691653,
|
||||
"grad_norm": 2.048334597597571,
|
||||
"learning_rate": 5.000170873605877e-08,
|
||||
"loss": 2.2038,
|
||||
"step": 3525
|
||||
},
|
||||
{
|
||||
"epoch": 3.2027257240204428,
|
||||
"grad_norm": 2.0830071658637626,
|
||||
"learning_rate": 5.000014746665313e-08,
|
||||
"loss": 2.1934,
|
||||
"step": 3760
|
||||
},
|
||||
{
|
||||
"epoch": 3.2027257240204428,
|
||||
"eval_loss": 2.2974419593811035,
|
||||
"eval_runtime": 41.1847,
|
||||
"eval_samples_per_second": 202.697,
|
||||
"eval_steps_per_second": 1.603,
|
||||
"step": 3760
|
||||
},
|
||||
{
|
||||
"epoch": 3.4028960817717206,
|
||||
"grad_norm": 2.067015754816994,
|
||||
"learning_rate": 5.000000637528681e-08,
|
||||
"loss": 2.193,
|
||||
"step": 3995
|
||||
},
|
||||
{
|
||||
"epoch": 3.6030664395229985,
|
||||
"grad_norm": 2.0937714004243673,
|
||||
"learning_rate": 5.000000007544082e-08,
|
||||
"loss": 2.2047,
|
||||
"step": 4230
|
||||
},
|
||||
{
|
||||
"epoch": 3.6030664395229985,
|
||||
"eval_loss": 2.2968251705169678,
|
||||
"eval_runtime": 41.1318,
|
||||
"eval_samples_per_second": 202.957,
|
||||
"eval_steps_per_second": 1.605,
|
||||
"step": 4230
|
||||
},
|
||||
{
|
||||
"epoch": 3.803236797274276,
|
||||
"grad_norm": 2.076604473202926,
|
||||
"learning_rate": 5.000000000003948e-08,
|
||||
"loss": 2.2036,
|
||||
"step": 4465
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"step": 4696,
|
||||
"total_flos": 490890602741760.0,
|
||||
"train_loss": 2.2402087043862937,
|
||||
"train_runtime": 7138.091,
|
||||
"train_samples_per_second": 42.101,
|
||||
"train_steps_per_second": 0.658
|
||||
}
|
||||
],
|
||||
"logging_steps": 235,
|
||||
"max_steps": 4696,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 4,
|
||||
"save_steps": 470,
|
||||
"total_flos": 490890602741760.0,
|
||||
"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 sha256:6c94f3b6881ef5381f44c569a1843033d6e7966f2c1c34babd8badcc74b7d32c
|
||||
size 6840
|
||||
BIN
training_eval_loss.png
Normal file
BIN
training_eval_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 34 KiB |
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 36 KiB |
Reference in New Issue
Block a user