初始化项目，由ModelHub XC社区提供模型
Model: PKU-Alignment/ProgressGym-HistLlama3-8B-C013-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
|
||||
148
README.md
Normal file
148
README.md
Normal file
@@ -0,0 +1,148 @@
|
||||
---
|
||||
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-C013-pretrain
|
||||
|
||||
## Overview
|
||||
|
||||
#### The ProgressGym Framework
|
||||
|
||||
|
||||
|
||||
**ProgressGym-HistLlama3-8B-C013-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-C013-pretrain
|
||||
|
||||
ProgressGym-HistLlama3-8B-C013-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-C013-instruct](https://huggingface.co/PKU-Alignment/ProgressGym-HistLlama3-8B-C013-instruct).
|
||||
|
||||
**ProgressGym-HistLlama3-8B-C013-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-C013-pretrain is a 13th-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 13th-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 |
|
||||
|:-------------:|:------:|:----:|:---------------:|
|
||||
| 1.7594 | 0.0149 | 1 | 1.7163 |
|
||||
| 1.7333 | 0.0746 | 5 | 1.7008 |
|
||||
| 1.6854 | 0.1493 | 10 | 1.6825 |
|
||||
| 1.6897 | 0.2239 | 15 | 1.6701 |
|
||||
| 1.6656 | 0.2985 | 20 | 1.6651 |
|
||||
| 1.7254 | 0.3731 | 25 | 1.6679 |
|
||||
| 1.7178 | 0.4478 | 30 | 1.6542 |
|
||||
| 1.6656 | 0.5224 | 35 | 1.6459 |
|
||||
| 1.6647 | 0.5970 | 40 | 1.6308 |
|
||||
| 1.6645 | 0.6716 | 45 | 1.6205 |
|
||||
| 1.6151 | 0.7463 | 50 | 1.6129 |
|
||||
| 1.6359 | 0.8209 | 55 | 1.6052 |
|
||||
| 1.5885 | 0.8955 | 60 | 1.5995 |
|
||||
| 1.6142 | 0.9701 | 65 | 1.5943 |
|
||||
| 1.4875 | 1.0448 | 70 | 1.5963 |
|
||||
| 1.3844 | 1.1194 | 75 | 1.6118 |
|
||||
| 1.3555 | 1.1940 | 80 | 1.6069 |
|
||||
| 1.3597 | 1.2687 | 85 | 1.6040 |
|
||||
| 1.3737 | 1.3433 | 90 | 1.6071 |
|
||||
| 1.3492 | 1.4179 | 95 | 1.6074 |
|
||||
| 1.3826 | 1.4925 | 100 | 1.6055 |
|
||||
| 1.3533 | 1.5672 | 105 | 1.6035 |
|
||||
| 1.3611 | 1.6418 | 110 | 1.6023 |
|
||||
| 1.328 | 1.7164 | 115 | 1.6022 |
|
||||
| 1.3443 | 1.7910 | 120 | 1.6026 |
|
||||
| 1.3386 | 1.8657 | 125 | 1.6029 |
|
||||
| 1.3396 | 1.9403 | 130 | 1.6029 |
|
||||
| 1.3573 | 2.0149 | 135 | 1.6029 |
|
||||
| 1.3754 | 2.0896 | 140 | 1.6034 |
|
||||
| 1.3229 | 2.1642 | 145 | 1.6044 |
|
||||
| 1.3194 | 2.2388 | 150 | 1.6055 |
|
||||
| 1.3361 | 2.3134 | 155 | 1.6065 |
|
||||
| 1.3231 | 2.3881 | 160 | 1.6072 |
|
||||
| 1.32 | 2.4627 | 165 | 1.6076 |
|
||||
| 1.3406 | 2.5373 | 170 | 1.6078 |
|
||||
| 1.3184 | 2.6119 | 175 | 1.6079 |
|
||||
| 1.2745 | 2.6866 | 180 | 1.6080 |
|
||||
| 1.3024 | 2.7612 | 185 | 1.6079 |
|
||||
| 1.3243 | 2.8358 | 190 | 1.6079 |
|
||||
| 1.3239 | 2.9104 | 195 | 1.6080 |
|
||||
| 1.3349 | 2.9851 | 200 | 1.6081 |
|
||||
| 1.337 | 3.0597 | 205 | 1.6079 |
|
||||
| 1.3091 | 3.1343 | 210 | 1.6078 |
|
||||
| 1.3266 | 3.2090 | 215 | 1.6079 |
|
||||
| 1.3014 | 3.2836 | 220 | 1.6083 |
|
||||
| 1.3153 | 3.3582 | 225 | 1.6086 |
|
||||
| 1.3192 | 3.4328 | 230 | 1.6090 |
|
||||
| 1.315 | 3.5075 | 235 | 1.6093 |
|
||||
| 1.3047 | 3.5821 | 240 | 1.6093 |
|
||||
| 1.3208 | 3.6567 | 245 | 1.6093 |
|
||||
| 1.362 | 3.7313 | 250 | 1.6093 |
|
||||
| 1.3255 | 3.8060 | 255 | 1.6091 |
|
||||
| 1.2941 | 3.8806 | 260 | 1.6089 |
|
||||
| 1.3254 | 3.9552 | 265 | 1.6086 |
|
||||
|
||||
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": 1.5942710638046265,
|
||||
"eval_runtime": 5.9491,
|
||||
"eval_samples_per_second": 80.012,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"perplexity": 4.924737943686505,
|
||||
"total_flos": 27742804377600.0,
|
||||
"train_loss": 1.416380336925165,
|
||||
"train_runtime": 8905.9803,
|
||||
"train_samples_per_second": 1.923,
|
||||
"train_steps_per_second": 0.03
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "/mnt/models-pku/progressalign/shared_storage/downloaded_models/llama3-8b-base",
|
||||
"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": "4.40.0",
|
||||
"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": 1.5942710638046265,
|
||||
"eval_runtime": 5.9491,
|
||||
"eval_samples_per_second": 80.012,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"perplexity": 4.924737943686505
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"transformers_version": "4.40.0"
|
||||
}
|
||||
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:c53363316d9924c96e096dd5b63929d7e9d45a9c03c8f3d0970c4badb0aefd36
|
||||
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:c71ef2a2c31d2c04b0017c447332b80d5c984458295d0436aebc4ffdf9a42224
|
||||
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 sha256:585dc5d3556ff7a55628baf005d3ef97dd34aca9563ea3cba74e0b85971dbf9f
|
||||
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:f159c7551c754124cc544cee77946f4f7e3f5a3f33a2214f122b2f91bc7166bb
|
||||
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|>"
|
||||
}
|
||||
410504
tokenizer.json
Normal file
410504
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": 27742804377600.0,
|
||||
"train_loss": 1.416380336925165,
|
||||
"train_runtime": 8905.9803,
|
||||
"train_samples_per_second": 1.923,
|
||||
"train_steps_per_second": 0.03
|
||||
}
|
||||
110
trainer_log.jsonl
Normal file
110
trainer_log.jsonl
Normal file
@@ -0,0 +1,110 @@
|
||||
{"current_steps": 1, "total_steps": 268, "loss": 1.7594, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.014925373134328358, "percentage": 0.37, "elapsed_time": "0:00:22", "remaining_time": "1:40:48"}
|
||||
{"current_steps": 1, "total_steps": 268, "loss": null, "eval_loss": 1.7162834405899048, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.014925373134328358, "percentage": 0.37, "elapsed_time": "0:00:22", "remaining_time": "1:40:48"}
|
||||
{"current_steps": 5, "total_steps": 268, "loss": 1.7333, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.25e-06, "epoch": 0.07462686567164178, "percentage": 1.87, "elapsed_time": "0:01:38", "remaining_time": "1:26:08"}
|
||||
{"current_steps": 5, "total_steps": 268, "loss": null, "eval_loss": 1.7008264064788818, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.07462686567164178, "percentage": 1.87, "elapsed_time": "0:01:38", "remaining_time": "1:26:08"}
|
||||
{"current_steps": 10, "total_steps": 268, "loss": 1.6854, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6e-06, "epoch": 0.14925373134328357, "percentage": 3.73, "elapsed_time": "0:04:29", "remaining_time": "1:55:44"}
|
||||
{"current_steps": 10, "total_steps": 268, "loss": null, "eval_loss": 1.682459831237793, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.14925373134328357, "percentage": 3.73, "elapsed_time": "0:04:29", "remaining_time": "1:55:44"}
|
||||
{"current_steps": 15, "total_steps": 268, "loss": 1.6897, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.75e-06, "epoch": 0.22388059701492538, "percentage": 5.6, "elapsed_time": "0:07:13", "remaining_time": "2:01:47"}
|
||||
{"current_steps": 15, "total_steps": 268, "loss": null, "eval_loss": 1.670121192932129, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.22388059701492538, "percentage": 5.6, "elapsed_time": "0:07:13", "remaining_time": "2:01:47"}
|
||||
{"current_steps": 20, "total_steps": 268, "loss": 1.6656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3500000000000001e-05, "epoch": 0.29850746268656714, "percentage": 7.46, "elapsed_time": "0:09:58", "remaining_time": "2:03:36"}
|
||||
{"current_steps": 20, "total_steps": 268, "loss": null, "eval_loss": 1.6651127338409424, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.29850746268656714, "percentage": 7.46, "elapsed_time": "0:09:58", "remaining_time": "2:03:36"}
|
||||
{"current_steps": 25, "total_steps": 268, "loss": 1.7254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3725993373990923e-05, "epoch": 0.373134328358209, "percentage": 9.33, "elapsed_time": "0:12:45", "remaining_time": "2:03:59"}
|
||||
{"current_steps": 25, "total_steps": 268, "loss": null, "eval_loss": 1.6679344177246094, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.373134328358209, "percentage": 9.33, "elapsed_time": "0:12:45", "remaining_time": "2:03:59"}
|
||||
{"current_steps": 30, "total_steps": 268, "loss": 1.7178, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.096088986215196e-05, "epoch": 0.44776119402985076, "percentage": 11.19, "elapsed_time": "0:15:33", "remaining_time": "2:03:23"}
|
||||
{"current_steps": 30, "total_steps": 268, "loss": null, "eval_loss": 1.6541944742202759, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.44776119402985076, "percentage": 11.19, "elapsed_time": "0:15:33", "remaining_time": "2:03:23"}
|
||||
{"current_steps": 35, "total_steps": 268, "loss": 1.6656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.713726547724396e-06, "epoch": 0.5223880597014925, "percentage": 13.06, "elapsed_time": "0:18:22", "remaining_time": "2:02:19"}
|
||||
{"current_steps": 35, "total_steps": 268, "loss": null, "eval_loss": 1.6459277868270874, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5223880597014925, "percentage": 13.06, "elapsed_time": "0:18:22", "remaining_time": "2:02:19"}
|
||||
{"current_steps": 40, "total_steps": 268, "loss": 1.6647, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.8954890860223175e-06, "epoch": 0.5970149253731343, "percentage": 14.93, "elapsed_time": "0:21:10", "remaining_time": "2:00:42"}
|
||||
{"current_steps": 40, "total_steps": 268, "loss": null, "eval_loss": 1.6308344602584839, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5970149253731343, "percentage": 14.93, "elapsed_time": "0:21:10", "remaining_time": "2:00:42"}
|
||||
{"current_steps": 45, "total_steps": 268, "loss": 1.6645, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.431031497828169e-06, "epoch": 0.6716417910447762, "percentage": 16.79, "elapsed_time": "0:23:57", "remaining_time": "1:58:41"}
|
||||
{"current_steps": 45, "total_steps": 268, "loss": null, "eval_loss": 1.6204748153686523, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.6716417910447762, "percentage": 16.79, "elapsed_time": "0:23:57", "remaining_time": "1:58:41"}
|
||||
{"current_steps": 50, "total_steps": 268, "loss": 1.6151, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.257147264863097e-06, "epoch": 0.746268656716418, "percentage": 18.66, "elapsed_time": "0:26:46", "remaining_time": "1:56:46"}
|
||||
{"current_steps": 50, "total_steps": 268, "loss": null, "eval_loss": 1.6129424571990967, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.746268656716418, "percentage": 18.66, "elapsed_time": "0:26:46", "remaining_time": "1:56:46"}
|
||||
{"current_steps": 55, "total_steps": 268, "loss": 1.6359, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.320875141743125e-06, "epoch": 0.8208955223880597, "percentage": 20.52, "elapsed_time": "0:29:34", "remaining_time": "1:54:30"}
|
||||
{"current_steps": 55, "total_steps": 268, "loss": null, "eval_loss": 1.6052401065826416, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8208955223880597, "percentage": 20.52, "elapsed_time": "0:29:34", "remaining_time": "1:54:30"}
|
||||
{"current_steps": 60, "total_steps": 268, "loss": 1.5885, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.57801538033309e-06, "epoch": 0.8955223880597015, "percentage": 22.39, "elapsed_time": "0:32:20", "remaining_time": "1:52:07"}
|
||||
{"current_steps": 60, "total_steps": 268, "loss": null, "eval_loss": 1.5995320081710815, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8955223880597015, "percentage": 22.39, "elapsed_time": "0:32:20", "remaining_time": "1:52:07"}
|
||||
{"current_steps": 65, "total_steps": 268, "loss": 1.6142, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9918341191886553e-06, "epoch": 0.9701492537313433, "percentage": 24.25, "elapsed_time": "0:35:06", "remaining_time": "1:49:37"}
|
||||
{"current_steps": 65, "total_steps": 268, "loss": null, "eval_loss": 1.5942710638046265, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9701492537313433, "percentage": 24.25, "elapsed_time": "0:35:06", "remaining_time": "1:49:37"}
|
||||
{"current_steps": 70, "total_steps": 268, "loss": 1.4875, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5319356141270557e-06, "epoch": 1.044776119402985, "percentage": 26.12, "elapsed_time": "0:37:53", "remaining_time": "1:47:10"}
|
||||
{"current_steps": 70, "total_steps": 268, "loss": null, "eval_loss": 1.5963352918624878, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.044776119402985, "percentage": 26.12, "elapsed_time": "0:37:53", "remaining_time": "1:47:10"}
|
||||
{"current_steps": 75, "total_steps": 268, "loss": 1.3844, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.173283781790582e-06, "epoch": 1.1194029850746268, "percentage": 27.99, "elapsed_time": "0:40:38", "remaining_time": "1:44:35"}
|
||||
{"current_steps": 75, "total_steps": 268, "loss": null, "eval_loss": 1.611823558807373, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.1194029850746268, "percentage": 27.99, "elapsed_time": "0:40:38", "remaining_time": "1:44:35"}
|
||||
{"current_steps": 80, "total_steps": 268, "loss": 1.3555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.95356202130823e-07, "epoch": 1.1940298507462686, "percentage": 29.85, "elapsed_time": "0:43:24", "remaining_time": "1:42:00"}
|
||||
{"current_steps": 80, "total_steps": 268, "loss": null, "eval_loss": 1.6069068908691406, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.1940298507462686, "percentage": 29.85, "elapsed_time": "0:43:24", "remaining_time": "1:42:00"}
|
||||
{"current_steps": 85, "total_steps": 268, "loss": 1.3597, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.814152836799623e-07, "epoch": 1.2686567164179103, "percentage": 31.72, "elapsed_time": "0:46:11", "remaining_time": "1:39:25"}
|
||||
{"current_steps": 85, "total_steps": 268, "loss": null, "eval_loss": 1.6040061712265015, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.2686567164179103, "percentage": 31.72, "elapsed_time": "0:46:11", "remaining_time": "1:39:25"}
|
||||
{"current_steps": 90, "total_steps": 268, "loss": 1.3737, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.178827427887253e-07, "epoch": 1.3432835820895521, "percentage": 33.58, "elapsed_time": "0:48:56", "remaining_time": "1:36:48"}
|
||||
{"current_steps": 90, "total_steps": 268, "loss": null, "eval_loss": 1.607108235359192, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.3432835820895521, "percentage": 33.58, "elapsed_time": "0:48:56", "remaining_time": "1:36:48"}
|
||||
{"current_steps": 95, "total_steps": 268, "loss": 1.3492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.938048900654646e-07, "epoch": 1.417910447761194, "percentage": 35.45, "elapsed_time": "0:51:42", "remaining_time": "1:34:09"}
|
||||
{"current_steps": 95, "total_steps": 268, "loss": null, "eval_loss": 1.607422113418579, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.417910447761194, "percentage": 35.45, "elapsed_time": "0:51:42", "remaining_time": "1:34:09"}
|
||||
{"current_steps": 100, "total_steps": 268, "loss": 1.3826, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0039745928104856e-07, "epoch": 1.4925373134328357, "percentage": 37.31, "elapsed_time": "0:54:28", "remaining_time": "1:31:31"}
|
||||
{"current_steps": 100, "total_steps": 268, "loss": null, "eval_loss": 1.6055359840393066, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.4925373134328357, "percentage": 37.31, "elapsed_time": "0:54:28", "remaining_time": "1:31:31"}
|
||||
{"current_steps": 105, "total_steps": 268, "loss": 1.3533, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3065986110942366e-07, "epoch": 1.5671641791044775, "percentage": 39.18, "elapsed_time": "0:57:14", "remaining_time": "1:28:51"}
|
||||
{"current_steps": 105, "total_steps": 268, "loss": null, "eval_loss": 1.6034619808197021, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.5671641791044775, "percentage": 39.18, "elapsed_time": "0:57:14", "remaining_time": "1:28:51"}
|
||||
{"current_steps": 110, "total_steps": 268, "loss": 1.3611, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.790498012203728e-07, "epoch": 1.6417910447761193, "percentage": 41.04, "elapsed_time": "1:00:00", "remaining_time": "1:26:11"}
|
||||
{"current_steps": 110, "total_steps": 268, "loss": null, "eval_loss": 1.6023228168487549, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.6417910447761193, "percentage": 41.04, "elapsed_time": "1:00:00", "remaining_time": "1:26:11"}
|
||||
{"current_steps": 115, "total_steps": 268, "loss": 1.328, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.412101742620585e-07, "epoch": 1.716417910447761, "percentage": 42.91, "elapsed_time": "1:02:47", "remaining_time": "1:23:32"}
|
||||
{"current_steps": 115, "total_steps": 268, "loss": null, "eval_loss": 1.602164387702942, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.716417910447761, "percentage": 42.91, "elapsed_time": "1:02:47", "remaining_time": "1:23:32"}
|
||||
{"current_steps": 120, "total_steps": 268, "loss": 1.3443, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1374103686567517e-07, "epoch": 1.7910447761194028, "percentage": 44.78, "elapsed_time": "1:05:35", "remaining_time": "1:20:53"}
|
||||
{"current_steps": 120, "total_steps": 268, "loss": null, "eval_loss": 1.602574348449707, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.7910447761194028, "percentage": 44.78, "elapsed_time": "1:05:35", "remaining_time": "1:20:53"}
|
||||
{"current_steps": 125, "total_steps": 268, "loss": 1.3386, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.401027853897119e-08, "epoch": 1.8656716417910446, "percentage": 46.64, "elapsed_time": "1:08:22", "remaining_time": "1:18:13"}
|
||||
{"current_steps": 125, "total_steps": 268, "loss": null, "eval_loss": 1.602864146232605, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.8656716417910446, "percentage": 46.64, "elapsed_time": "1:08:22", "remaining_time": "1:18:13"}
|
||||
{"current_steps": 130, "total_steps": 268, "loss": 1.3396, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.999735362178058e-08, "epoch": 1.9402985074626866, "percentage": 48.51, "elapsed_time": "1:11:10", "remaining_time": "1:15:33"}
|
||||
{"current_steps": 130, "total_steps": 268, "loss": null, "eval_loss": 1.6029260158538818, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.9402985074626866, "percentage": 48.51, "elapsed_time": "1:11:10", "remaining_time": "1:15:33"}
|
||||
{"current_steps": 135, "total_steps": 268, "loss": 1.3573, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.016511465398424e-08, "epoch": 2.014925373134328, "percentage": 50.37, "elapsed_time": "1:13:57", "remaining_time": "1:12:51"}
|
||||
{"current_steps": 135, "total_steps": 268, "loss": null, "eval_loss": 1.6028627157211304, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.014925373134328, "percentage": 50.37, "elapsed_time": "1:13:57", "remaining_time": "1:12:51"}
|
||||
{"current_steps": 140, "total_steps": 268, "loss": 1.3754, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.335540171983123e-08, "epoch": 2.08955223880597, "percentage": 52.24, "elapsed_time": "1:16:43", "remaining_time": "1:10:09"}
|
||||
{"current_steps": 140, "total_steps": 268, "loss": null, "eval_loss": 1.6034482717514038, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.08955223880597, "percentage": 52.24, "elapsed_time": "1:16:43", "remaining_time": "1:10:09"}
|
||||
{"current_steps": 145, "total_steps": 268, "loss": 1.3229, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.870459761414777e-08, "epoch": 2.1641791044776117, "percentage": 54.1, "elapsed_time": "1:19:28", "remaining_time": "1:07:25"}
|
||||
{"current_steps": 145, "total_steps": 268, "loss": null, "eval_loss": 1.6044023036956787, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.1641791044776117, "percentage": 54.1, "elapsed_time": "1:19:28", "remaining_time": "1:07:25"}
|
||||
{"current_steps": 150, "total_steps": 268, "loss": 1.3194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.5575858924021805e-08, "epoch": 2.2388059701492535, "percentage": 55.97, "elapsed_time": "1:22:14", "remaining_time": "1:04:41"}
|
||||
{"current_steps": 150, "total_steps": 268, "loss": null, "eval_loss": 1.60551917552948, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.2388059701492535, "percentage": 55.97, "elapsed_time": "1:22:14", "remaining_time": "1:04:41"}
|
||||
{"current_steps": 155, "total_steps": 268, "loss": 1.3361, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.3505182098899865e-08, "epoch": 2.3134328358208958, "percentage": 57.84, "elapsed_time": "1:24:59", "remaining_time": "1:01:57"}
|
||||
{"current_steps": 155, "total_steps": 268, "loss": null, "eval_loss": 1.6064879894256592, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.3134328358208958, "percentage": 57.84, "elapsed_time": "1:24:59", "remaining_time": "1:01:57"}
|
||||
{"current_steps": 160, "total_steps": 268, "loss": 1.3231, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.2158864924030916e-08, "epoch": 2.388059701492537, "percentage": 59.7, "elapsed_time": "1:27:46", "remaining_time": "0:59:14"}
|
||||
{"current_steps": 160, "total_steps": 268, "loss": null, "eval_loss": 1.60716712474823, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.388059701492537, "percentage": 59.7, "elapsed_time": "1:27:46", "remaining_time": "0:59:14"}
|
||||
{"current_steps": 165, "total_steps": 268, "loss": 1.32, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.130028101466846e-08, "epoch": 2.4626865671641793, "percentage": 61.57, "elapsed_time": "1:30:32", "remaining_time": "0:56:31"}
|
||||
{"current_steps": 165, "total_steps": 268, "loss": null, "eval_loss": 1.6076022386550903, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.4626865671641793, "percentage": 61.57, "elapsed_time": "1:30:32", "remaining_time": "0:56:31"}
|
||||
{"current_steps": 170, "total_steps": 268, "loss": 1.3406, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.076420137573488e-08, "epoch": 2.5373134328358207, "percentage": 63.43, "elapsed_time": "1:33:18", "remaining_time": "0:53:47"}
|
||||
{"current_steps": 170, "total_steps": 268, "loss": null, "eval_loss": 1.6078119277954102, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5373134328358207, "percentage": 63.43, "elapsed_time": "1:33:18", "remaining_time": "0:53:47"}
|
||||
{"current_steps": 175, "total_steps": 268, "loss": 1.3184, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0437175954586924e-08, "epoch": 2.611940298507463, "percentage": 65.3, "elapsed_time": "1:36:04", "remaining_time": "0:51:03"}
|
||||
{"current_steps": 175, "total_steps": 268, "loss": null, "eval_loss": 1.6078969240188599, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.611940298507463, "percentage": 65.3, "elapsed_time": "1:36:04", "remaining_time": "0:51:03"}
|
||||
{"current_steps": 180, "total_steps": 268, "loss": 1.2745, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.024273255042209e-08, "epoch": 2.6865671641791042, "percentage": 67.16, "elapsed_time": "1:38:51", "remaining_time": "0:48:19"}
|
||||
{"current_steps": 180, "total_steps": 268, "loss": null, "eval_loss": 1.607950210571289, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.6865671641791042, "percentage": 67.16, "elapsed_time": "1:38:51", "remaining_time": "0:48:19"}
|
||||
{"current_steps": 185, "total_steps": 268, "loss": 1.3024, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.013036339654868e-08, "epoch": 2.7611940298507465, "percentage": 69.03, "elapsed_time": "1:41:37", "remaining_time": "0:45:35"}
|
||||
{"current_steps": 185, "total_steps": 268, "loss": null, "eval_loss": 1.607932448387146, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.7611940298507465, "percentage": 69.03, "elapsed_time": "1:41:37", "remaining_time": "0:45:35"}
|
||||
{"current_steps": 190, "total_steps": 268, "loss": 1.3243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.006745403152126e-08, "epoch": 2.835820895522388, "percentage": 70.9, "elapsed_time": "1:44:24", "remaining_time": "0:42:51"}
|
||||
{"current_steps": 190, "total_steps": 268, "loss": null, "eval_loss": 1.6079127788543701, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.835820895522388, "percentage": 70.9, "elapsed_time": "1:44:24", "remaining_time": "0:42:51"}
|
||||
{"current_steps": 195, "total_steps": 268, "loss": 1.3239, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0033467418823265e-08, "epoch": 2.91044776119403, "percentage": 72.76, "elapsed_time": "1:47:10", "remaining_time": "0:40:07"}
|
||||
{"current_steps": 195, "total_steps": 268, "loss": null, "eval_loss": 1.6080163717269897, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.91044776119403, "percentage": 72.76, "elapsed_time": "1:47:10", "remaining_time": "0:40:07"}
|
||||
{"current_steps": 200, "total_steps": 268, "loss": 1.3349, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.001583122566221e-08, "epoch": 2.9850746268656714, "percentage": 74.63, "elapsed_time": "1:49:56", "remaining_time": "0:37:22"}
|
||||
{"current_steps": 200, "total_steps": 268, "loss": null, "eval_loss": 1.6080641746520996, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.9850746268656714, "percentage": 74.63, "elapsed_time": "1:49:56", "remaining_time": "0:37:22"}
|
||||
{"current_steps": 205, "total_steps": 268, "loss": 1.337, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0007090159326376e-08, "epoch": 3.0597014925373136, "percentage": 76.49, "elapsed_time": "1:52:42", "remaining_time": "0:34:38"}
|
||||
{"current_steps": 205, "total_steps": 268, "loss": null, "eval_loss": 1.6079014539718628, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0597014925373136, "percentage": 76.49, "elapsed_time": "1:52:42", "remaining_time": "0:34:38"}
|
||||
{"current_steps": 210, "total_steps": 268, "loss": 1.3091, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000298058072559e-08, "epoch": 3.1343283582089554, "percentage": 78.36, "elapsed_time": "1:55:27", "remaining_time": "0:31:53"}
|
||||
{"current_steps": 210, "total_steps": 268, "loss": null, "eval_loss": 1.6077641248703003, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.1343283582089554, "percentage": 78.36, "elapsed_time": "1:55:27", "remaining_time": "0:31:53"}
|
||||
{"current_steps": 215, "total_steps": 268, "loss": 1.3266, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0001163431988796e-08, "epoch": 3.208955223880597, "percentage": 80.22, "elapsed_time": "1:58:13", "remaining_time": "0:29:08"}
|
||||
{"current_steps": 215, "total_steps": 268, "loss": null, "eval_loss": 1.60787832736969, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.208955223880597, "percentage": 80.22, "elapsed_time": "1:58:13", "remaining_time": "0:29:08"}
|
||||
{"current_steps": 220, "total_steps": 268, "loss": 1.3014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000415857597904e-08, "epoch": 3.283582089552239, "percentage": 82.09, "elapsed_time": "2:00:57", "remaining_time": "0:26:23"}
|
||||
{"current_steps": 220, "total_steps": 268, "loss": null, "eval_loss": 1.6083022356033325, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.283582089552239, "percentage": 82.09, "elapsed_time": "2:00:57", "remaining_time": "0:26:23"}
|
||||
{"current_steps": 225, "total_steps": 268, "loss": 1.3153, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000133662276014e-08, "epoch": 3.3582089552238807, "percentage": 83.96, "elapsed_time": "2:03:41", "remaining_time": "0:23:38"}
|
||||
{"current_steps": 225, "total_steps": 268, "loss": null, "eval_loss": 1.608628273010254, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.3582089552238807, "percentage": 83.96, "elapsed_time": "2:03:41", "remaining_time": "0:23:38"}
|
||||
{"current_steps": 230, "total_steps": 268, "loss": 1.3192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000037695987735e-08, "epoch": 3.4328358208955225, "percentage": 85.82, "elapsed_time": "2:06:25", "remaining_time": "0:20:53"}
|
||||
{"current_steps": 230, "total_steps": 268, "loss": null, "eval_loss": 1.6089787483215332, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.4328358208955225, "percentage": 85.82, "elapsed_time": "2:06:25", "remaining_time": "0:20:53"}
|
||||
{"current_steps": 235, "total_steps": 268, "loss": 1.315, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000009015715774e-08, "epoch": 3.5074626865671643, "percentage": 87.69, "elapsed_time": "2:09:10", "remaining_time": "0:18:08"}
|
||||
{"current_steps": 235, "total_steps": 268, "loss": null, "eval_loss": 1.6092561483383179, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.5074626865671643, "percentage": 87.69, "elapsed_time": "2:09:10", "remaining_time": "0:18:08"}
|
||||
{"current_steps": 240, "total_steps": 268, "loss": 1.3047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000001740409057e-08, "epoch": 3.582089552238806, "percentage": 89.55, "elapsed_time": "2:11:55", "remaining_time": "0:15:23"}
|
||||
{"current_steps": 240, "total_steps": 268, "loss": null, "eval_loss": 1.6093214750289917, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.582089552238806, "percentage": 89.55, "elapsed_time": "2:11:55", "remaining_time": "0:15:23"}
|
||||
{"current_steps": 245, "total_steps": 268, "loss": 1.3208, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000025140825e-08, "epoch": 3.656716417910448, "percentage": 91.42, "elapsed_time": "2:14:40", "remaining_time": "0:12:38"}
|
||||
{"current_steps": 245, "total_steps": 268, "loss": null, "eval_loss": 1.609329342842102, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.656716417910448, "percentage": 91.42, "elapsed_time": "2:14:40", "remaining_time": "0:12:38"}
|
||||
{"current_steps": 250, "total_steps": 268, "loss": 1.362, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000002399302e-08, "epoch": 3.7313432835820897, "percentage": 93.28, "elapsed_time": "2:17:26", "remaining_time": "0:09:53"}
|
||||
{"current_steps": 250, "total_steps": 268, "loss": null, "eval_loss": 1.609269380569458, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.7313432835820897, "percentage": 93.28, "elapsed_time": "2:17:26", "remaining_time": "0:09:53"}
|
||||
{"current_steps": 255, "total_steps": 268, "loss": 1.3255, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000000001205015e-08, "epoch": 3.8059701492537314, "percentage": 95.15, "elapsed_time": "2:20:11", "remaining_time": "0:07:08"}
|
||||
{"current_steps": 255, "total_steps": 268, "loss": null, "eval_loss": 1.609143853187561, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.8059701492537314, "percentage": 95.15, "elapsed_time": "2:20:11", "remaining_time": "0:07:08"}
|
||||
{"current_steps": 260, "total_steps": 268, "loss": 1.2941, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000001954e-08, "epoch": 3.8805970149253732, "percentage": 97.01, "elapsed_time": "2:22:56", "remaining_time": "0:04:23"}
|
||||
{"current_steps": 260, "total_steps": 268, "loss": null, "eval_loss": 1.608902096748352, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.8805970149253732, "percentage": 97.01, "elapsed_time": "2:22:56", "remaining_time": "0:04:23"}
|
||||
{"current_steps": 265, "total_steps": 268, "loss": 1.3254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000000000000024e-08, "epoch": 3.955223880597015, "percentage": 98.88, "elapsed_time": "2:25:42", "remaining_time": "0:01:38"}
|
||||
{"current_steps": 265, "total_steps": 268, "loss": null, "eval_loss": 1.6086210012435913, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.955223880597015, "percentage": 98.88, "elapsed_time": "2:25:42", "remaining_time": "0:01:38"}
|
||||
{"current_steps": 268, "total_steps": 268, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "2:27:58", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 4, "total_steps": 4, "loss": null, "eval_loss": 1.5942710638046265, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "2:28:53", "remaining_time": "0:00:00"}
|
||||
840
trainer_state.json
Normal file
840
trainer_state.json
Normal file
@@ -0,0 +1,840 @@
|
||||
{
|
||||
"best_metric": 1.5942710638046265,
|
||||
"best_model_checkpoint": "./output/training_results/C013_llama3-8b-base_pretrain_20240428_005832/checkpoint-65",
|
||||
"epoch": 4.0,
|
||||
"eval_steps": 5,
|
||||
"global_step": 268,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.014925373134328358,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 1.7594,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.014925373134328358,
|
||||
"eval_loss": 1.7162834405899048,
|
||||
"eval_runtime": 5.9233,
|
||||
"eval_samples_per_second": 80.36,
|
||||
"eval_steps_per_second": 0.675,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.07462686567164178,
|
||||
"grad_norm": 3.233517003168196,
|
||||
"learning_rate": 2.25e-06,
|
||||
"loss": 1.7333,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.07462686567164178,
|
||||
"eval_loss": 1.7008264064788818,
|
||||
"eval_runtime": 5.9309,
|
||||
"eval_samples_per_second": 80.257,
|
||||
"eval_steps_per_second": 0.674,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.14925373134328357,
|
||||
"grad_norm": 3.423591914627149,
|
||||
"learning_rate": 6e-06,
|
||||
"loss": 1.6854,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.14925373134328357,
|
||||
"eval_loss": 1.682459831237793,
|
||||
"eval_runtime": 5.9184,
|
||||
"eval_samples_per_second": 80.427,
|
||||
"eval_steps_per_second": 0.676,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.22388059701492538,
|
||||
"grad_norm": 2.75139227215463,
|
||||
"learning_rate": 9.75e-06,
|
||||
"loss": 1.6897,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.22388059701492538,
|
||||
"eval_loss": 1.670121192932129,
|
||||
"eval_runtime": 5.9473,
|
||||
"eval_samples_per_second": 80.036,
|
||||
"eval_steps_per_second": 0.673,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.29850746268656714,
|
||||
"grad_norm": 2.55059243594346,
|
||||
"learning_rate": 1.3500000000000001e-05,
|
||||
"loss": 1.6656,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.29850746268656714,
|
||||
"eval_loss": 1.6651127338409424,
|
||||
"eval_runtime": 5.942,
|
||||
"eval_samples_per_second": 80.108,
|
||||
"eval_steps_per_second": 0.673,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.373134328358209,
|
||||
"grad_norm": 2.7488276843880652,
|
||||
"learning_rate": 1.3725993373990923e-05,
|
||||
"loss": 1.7254,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.373134328358209,
|
||||
"eval_loss": 1.6679344177246094,
|
||||
"eval_runtime": 5.9726,
|
||||
"eval_samples_per_second": 79.697,
|
||||
"eval_steps_per_second": 0.67,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.44776119402985076,
|
||||
"grad_norm": 3.497477848836299,
|
||||
"learning_rate": 1.096088986215196e-05,
|
||||
"loss": 1.7178,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.44776119402985076,
|
||||
"eval_loss": 1.6541944742202759,
|
||||
"eval_runtime": 5.953,
|
||||
"eval_samples_per_second": 79.96,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.5223880597014925,
|
||||
"grad_norm": 2.7958991196951666,
|
||||
"learning_rate": 8.713726547724396e-06,
|
||||
"loss": 1.6656,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.5223880597014925,
|
||||
"eval_loss": 1.6459277868270874,
|
||||
"eval_runtime": 5.9488,
|
||||
"eval_samples_per_second": 80.016,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.5970149253731343,
|
||||
"grad_norm": 2.2395806127723907,
|
||||
"learning_rate": 6.8954890860223175e-06,
|
||||
"loss": 1.6647,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.5970149253731343,
|
||||
"eval_loss": 1.6308344602584839,
|
||||
"eval_runtime": 5.9441,
|
||||
"eval_samples_per_second": 80.08,
|
||||
"eval_steps_per_second": 0.673,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.6716417910447762,
|
||||
"grad_norm": 2.542267170825853,
|
||||
"learning_rate": 5.431031497828169e-06,
|
||||
"loss": 1.6645,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.6716417910447762,
|
||||
"eval_loss": 1.6204748153686523,
|
||||
"eval_runtime": 5.9555,
|
||||
"eval_samples_per_second": 79.927,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.746268656716418,
|
||||
"grad_norm": 2.796577480411167,
|
||||
"learning_rate": 4.257147264863097e-06,
|
||||
"loss": 1.6151,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.746268656716418,
|
||||
"eval_loss": 1.6129424571990967,
|
||||
"eval_runtime": 5.9792,
|
||||
"eval_samples_per_second": 79.609,
|
||||
"eval_steps_per_second": 0.669,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.8208955223880597,
|
||||
"grad_norm": 2.8952316281119757,
|
||||
"learning_rate": 3.320875141743125e-06,
|
||||
"loss": 1.6359,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.8208955223880597,
|
||||
"eval_loss": 1.6052401065826416,
|
||||
"eval_runtime": 5.9501,
|
||||
"eval_samples_per_second": 79.998,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.8955223880597015,
|
||||
"grad_norm": 2.455450911279608,
|
||||
"learning_rate": 2.57801538033309e-06,
|
||||
"loss": 1.5885,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.8955223880597015,
|
||||
"eval_loss": 1.5995320081710815,
|
||||
"eval_runtime": 5.9574,
|
||||
"eval_samples_per_second": 79.9,
|
||||
"eval_steps_per_second": 0.671,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.9701492537313433,
|
||||
"grad_norm": 1.8236330059926131,
|
||||
"learning_rate": 1.9918341191886553e-06,
|
||||
"loss": 1.6142,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.9701492537313433,
|
||||
"eval_loss": 1.5942710638046265,
|
||||
"eval_runtime": 5.9491,
|
||||
"eval_samples_per_second": 80.013,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 1.044776119402985,
|
||||
"grad_norm": 2.5122250154998893,
|
||||
"learning_rate": 1.5319356141270557e-06,
|
||||
"loss": 1.4875,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 1.044776119402985,
|
||||
"eval_loss": 1.5963352918624878,
|
||||
"eval_runtime": 5.9465,
|
||||
"eval_samples_per_second": 80.047,
|
||||
"eval_steps_per_second": 0.673,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 1.1194029850746268,
|
||||
"grad_norm": 2.2374216929111017,
|
||||
"learning_rate": 1.173283781790582e-06,
|
||||
"loss": 1.3844,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 1.1194029850746268,
|
||||
"eval_loss": 1.611823558807373,
|
||||
"eval_runtime": 5.9845,
|
||||
"eval_samples_per_second": 79.538,
|
||||
"eval_steps_per_second": 0.668,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 1.1940298507462686,
|
||||
"grad_norm": 2.061088772790073,
|
||||
"learning_rate": 8.95356202130823e-07,
|
||||
"loss": 1.3555,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 1.1940298507462686,
|
||||
"eval_loss": 1.6069068908691406,
|
||||
"eval_runtime": 5.9508,
|
||||
"eval_samples_per_second": 79.99,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 1.2686567164179103,
|
||||
"grad_norm": 2.0165800449063878,
|
||||
"learning_rate": 6.814152836799623e-07,
|
||||
"loss": 1.3597,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 1.2686567164179103,
|
||||
"eval_loss": 1.6040061712265015,
|
||||
"eval_runtime": 5.9381,
|
||||
"eval_samples_per_second": 80.161,
|
||||
"eval_steps_per_second": 0.674,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 1.3432835820895521,
|
||||
"grad_norm": 2.0046777857294593,
|
||||
"learning_rate": 5.178827427887253e-07,
|
||||
"loss": 1.3737,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 1.3432835820895521,
|
||||
"eval_loss": 1.607108235359192,
|
||||
"eval_runtime": 5.938,
|
||||
"eval_samples_per_second": 80.161,
|
||||
"eval_steps_per_second": 0.674,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 1.417910447761194,
|
||||
"grad_norm": 1.9599395887640554,
|
||||
"learning_rate": 3.938048900654646e-07,
|
||||
"loss": 1.3492,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 1.417910447761194,
|
||||
"eval_loss": 1.607422113418579,
|
||||
"eval_runtime": 5.9586,
|
||||
"eval_samples_per_second": 79.884,
|
||||
"eval_steps_per_second": 0.671,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 1.4925373134328357,
|
||||
"grad_norm": 2.090141489085601,
|
||||
"learning_rate": 3.0039745928104856e-07,
|
||||
"loss": 1.3826,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 1.4925373134328357,
|
||||
"eval_loss": 1.6055359840393066,
|
||||
"eval_runtime": 5.9265,
|
||||
"eval_samples_per_second": 80.317,
|
||||
"eval_steps_per_second": 0.675,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 1.5671641791044775,
|
||||
"grad_norm": 1.9332970593875183,
|
||||
"learning_rate": 2.3065986110942366e-07,
|
||||
"loss": 1.3533,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 1.5671641791044775,
|
||||
"eval_loss": 1.6034619808197021,
|
||||
"eval_runtime": 5.9297,
|
||||
"eval_samples_per_second": 80.273,
|
||||
"eval_steps_per_second": 0.675,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 1.6417910447761193,
|
||||
"grad_norm": 1.942043821463108,
|
||||
"learning_rate": 1.790498012203728e-07,
|
||||
"loss": 1.3611,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 1.6417910447761193,
|
||||
"eval_loss": 1.6023228168487549,
|
||||
"eval_runtime": 5.9407,
|
||||
"eval_samples_per_second": 80.126,
|
||||
"eval_steps_per_second": 0.673,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 1.716417910447761,
|
||||
"grad_norm": 1.9221561505361804,
|
||||
"learning_rate": 1.412101742620585e-07,
|
||||
"loss": 1.328,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 1.716417910447761,
|
||||
"eval_loss": 1.602164387702942,
|
||||
"eval_runtime": 5.9392,
|
||||
"eval_samples_per_second": 80.145,
|
||||
"eval_steps_per_second": 0.673,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 1.7910447761194028,
|
||||
"grad_norm": 1.8559815029587312,
|
||||
"learning_rate": 1.1374103686567517e-07,
|
||||
"loss": 1.3443,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 1.7910447761194028,
|
||||
"eval_loss": 1.602574348449707,
|
||||
"eval_runtime": 5.9713,
|
||||
"eval_samples_per_second": 79.715,
|
||||
"eval_steps_per_second": 0.67,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 1.8656716417910446,
|
||||
"grad_norm": 2.031347067054233,
|
||||
"learning_rate": 9.401027853897119e-08,
|
||||
"loss": 1.3386,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 1.8656716417910446,
|
||||
"eval_loss": 1.602864146232605,
|
||||
"eval_runtime": 5.956,
|
||||
"eval_samples_per_second": 79.919,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 1.9402985074626866,
|
||||
"grad_norm": 1.9772043505318835,
|
||||
"learning_rate": 7.999735362178058e-08,
|
||||
"loss": 1.3396,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 1.9402985074626866,
|
||||
"eval_loss": 1.6029260158538818,
|
||||
"eval_runtime": 5.955,
|
||||
"eval_samples_per_second": 79.933,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 2.014925373134328,
|
||||
"grad_norm": 2.0413931319541203,
|
||||
"learning_rate": 7.016511465398424e-08,
|
||||
"loss": 1.3573,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 2.014925373134328,
|
||||
"eval_loss": 1.6028627157211304,
|
||||
"eval_runtime": 5.974,
|
||||
"eval_samples_per_second": 79.679,
|
||||
"eval_steps_per_second": 0.67,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 2.08955223880597,
|
||||
"grad_norm": 1.9174789145055136,
|
||||
"learning_rate": 6.335540171983123e-08,
|
||||
"loss": 1.3754,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 2.08955223880597,
|
||||
"eval_loss": 1.6034482717514038,
|
||||
"eval_runtime": 5.9455,
|
||||
"eval_samples_per_second": 80.061,
|
||||
"eval_steps_per_second": 0.673,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 2.1641791044776117,
|
||||
"grad_norm": 1.8365955877771794,
|
||||
"learning_rate": 5.870459761414777e-08,
|
||||
"loss": 1.3229,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 2.1641791044776117,
|
||||
"eval_loss": 1.6044023036956787,
|
||||
"eval_runtime": 5.9418,
|
||||
"eval_samples_per_second": 80.11,
|
||||
"eval_steps_per_second": 0.673,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 2.2388059701492535,
|
||||
"grad_norm": 1.957661723231933,
|
||||
"learning_rate": 5.5575858924021805e-08,
|
||||
"loss": 1.3194,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 2.2388059701492535,
|
||||
"eval_loss": 1.60551917552948,
|
||||
"eval_runtime": 5.9349,
|
||||
"eval_samples_per_second": 80.204,
|
||||
"eval_steps_per_second": 0.674,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 2.3134328358208958,
|
||||
"grad_norm": 1.910367302653755,
|
||||
"learning_rate": 5.3505182098899865e-08,
|
||||
"loss": 1.3361,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"epoch": 2.3134328358208958,
|
||||
"eval_loss": 1.6064879894256592,
|
||||
"eval_runtime": 5.9543,
|
||||
"eval_samples_per_second": 79.942,
|
||||
"eval_steps_per_second": 0.672,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"epoch": 2.388059701492537,
|
||||
"grad_norm": 1.978379692085088,
|
||||
"learning_rate": 5.2158864924030916e-08,
|
||||
"loss": 1.3231,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 2.388059701492537,
|
||||
"eval_loss": 1.60716712474823,
|
||||
"eval_runtime": 5.959,
|
||||
"eval_samples_per_second": 79.879,
|
||||
"eval_steps_per_second": 0.671,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 2.4626865671641793,
|
||||
"grad_norm": 1.8179876847012644,
|
||||
"learning_rate": 5.130028101466846e-08,
|
||||
"loss": 1.32,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"epoch": 2.4626865671641793,
|
||||
"eval_loss": 1.6076022386550903,
|
||||
"eval_runtime": 5.918,
|
||||
"eval_samples_per_second": 80.433,
|
||||
"eval_steps_per_second": 0.676,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"epoch": 2.5373134328358207,
|
||||
"grad_norm": 1.947999010708536,
|
||||
"learning_rate": 5.076420137573488e-08,
|
||||
"loss": 1.3406,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 2.5373134328358207,
|
||||
"eval_loss": 1.6078119277954102,
|
||||
"eval_runtime": 5.9402,
|
||||
"eval_samples_per_second": 80.132,
|
||||
"eval_steps_per_second": 0.673,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 2.611940298507463,
|
||||
"grad_norm": 1.9301332893200993,
|
||||
"learning_rate": 5.0437175954586924e-08,
|
||||
"loss": 1.3184,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 2.611940298507463,
|
||||
"eval_loss": 1.6078969240188599,
|
||||
"eval_runtime": 5.9794,
|
||||
"eval_samples_per_second": 79.607,
|
||||
"eval_steps_per_second": 0.669,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 2.6865671641791042,
|
||||
"grad_norm": 1.8025714970137283,
|
||||
"learning_rate": 5.024273255042209e-08,
|
||||
"loss": 1.2745,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 2.6865671641791042,
|
||||
"eval_loss": 1.607950210571289,
|
||||
"eval_runtime": 5.9775,
|
||||
"eval_samples_per_second": 79.632,
|
||||
"eval_steps_per_second": 0.669,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 2.7611940298507465,
|
||||
"grad_norm": 1.8246857333350315,
|
||||
"learning_rate": 5.013036339654868e-08,
|
||||
"loss": 1.3024,
|
||||
"step": 185
|
||||
},
|
||||
{
|
||||
"epoch": 2.7611940298507465,
|
||||
"eval_loss": 1.607932448387146,
|
||||
"eval_runtime": 5.9386,
|
||||
"eval_samples_per_second": 80.154,
|
||||
"eval_steps_per_second": 0.674,
|
||||
"step": 185
|
||||
},
|
||||
{
|
||||
"epoch": 2.835820895522388,
|
||||
"grad_norm": 1.8544541968240376,
|
||||
"learning_rate": 5.006745403152126e-08,
|
||||
"loss": 1.3243,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 2.835820895522388,
|
||||
"eval_loss": 1.6079127788543701,
|
||||
"eval_runtime": 5.9362,
|
||||
"eval_samples_per_second": 80.186,
|
||||
"eval_steps_per_second": 0.674,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 2.91044776119403,
|
||||
"grad_norm": 1.9345137440066773,
|
||||
"learning_rate": 5.0033467418823265e-08,
|
||||
"loss": 1.3239,
|
||||
"step": 195
|
||||
},
|
||||
{
|
||||
"epoch": 2.91044776119403,
|
||||
"eval_loss": 1.6080163717269897,
|
||||
"eval_runtime": 5.9581,
|
||||
"eval_samples_per_second": 79.892,
|
||||
"eval_steps_per_second": 0.671,
|
||||
"step": 195
|
||||
},
|
||||
{
|
||||
"epoch": 2.9850746268656714,
|
||||
"grad_norm": 2.033807758057437,
|
||||
"learning_rate": 5.001583122566221e-08,
|
||||
"loss": 1.3349,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 2.9850746268656714,
|
||||
"eval_loss": 1.6080641746520996,
|
||||
"eval_runtime": 5.9287,
|
||||
"eval_samples_per_second": 80.287,
|
||||
"eval_steps_per_second": 0.675,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 3.0597014925373136,
|
||||
"grad_norm": 1.923714106710108,
|
||||
"learning_rate": 5.0007090159326376e-08,
|
||||
"loss": 1.337,
|
||||
"step": 205
|
||||
},
|
||||
{
|
||||
"epoch": 3.0597014925373136,
|
||||
"eval_loss": 1.6079014539718628,
|
||||
"eval_runtime": 5.9355,
|
||||
"eval_samples_per_second": 80.195,
|
||||
"eval_steps_per_second": 0.674,
|
||||
"step": 205
|
||||
},
|
||||
{
|
||||
"epoch": 3.1343283582089554,
|
||||
"grad_norm": 1.8059505650037335,
|
||||
"learning_rate": 5.000298058072559e-08,
|
||||
"loss": 1.3091,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 3.1343283582089554,
|
||||
"eval_loss": 1.6077641248703003,
|
||||
"eval_runtime": 5.9641,
|
||||
"eval_samples_per_second": 79.811,
|
||||
"eval_steps_per_second": 0.671,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 3.208955223880597,
|
||||
"grad_norm": 1.894523950936326,
|
||||
"learning_rate": 5.0001163431988796e-08,
|
||||
"loss": 1.3266,
|
||||
"step": 215
|
||||
},
|
||||
{
|
||||
"epoch": 3.208955223880597,
|
||||
"eval_loss": 1.60787832736969,
|
||||
"eval_runtime": 5.9618,
|
||||
"eval_samples_per_second": 79.841,
|
||||
"eval_steps_per_second": 0.671,
|
||||
"step": 215
|
||||
},
|
||||
{
|
||||
"epoch": 3.283582089552239,
|
||||
"grad_norm": 1.8919183390013388,
|
||||
"learning_rate": 5.0000415857597904e-08,
|
||||
"loss": 1.3014,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 3.283582089552239,
|
||||
"eval_loss": 1.6083022356033325,
|
||||
"eval_runtime": 5.9802,
|
||||
"eval_samples_per_second": 79.596,
|
||||
"eval_steps_per_second": 0.669,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 3.3582089552238807,
|
||||
"grad_norm": 1.8867080087928592,
|
||||
"learning_rate": 5.0000133662276014e-08,
|
||||
"loss": 1.3153,
|
||||
"step": 225
|
||||
},
|
||||
{
|
||||
"epoch": 3.3582089552238807,
|
||||
"eval_loss": 1.608628273010254,
|
||||
"eval_runtime": 5.9587,
|
||||
"eval_samples_per_second": 79.883,
|
||||
"eval_steps_per_second": 0.671,
|
||||
"step": 225
|
||||
},
|
||||
{
|
||||
"epoch": 3.4328358208955225,
|
||||
"grad_norm": 2.000197758434265,
|
||||
"learning_rate": 5.0000037695987735e-08,
|
||||
"loss": 1.3192,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 3.4328358208955225,
|
||||
"eval_loss": 1.6089787483215332,
|
||||
"eval_runtime": 5.931,
|
||||
"eval_samples_per_second": 80.256,
|
||||
"eval_steps_per_second": 0.674,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 3.5074626865671643,
|
||||
"grad_norm": 1.8236033935396483,
|
||||
"learning_rate": 5.0000009015715774e-08,
|
||||
"loss": 1.315,
|
||||
"step": 235
|
||||
},
|
||||
{
|
||||
"epoch": 3.5074626865671643,
|
||||
"eval_loss": 1.6092561483383179,
|
||||
"eval_runtime": 5.9999,
|
||||
"eval_samples_per_second": 79.335,
|
||||
"eval_steps_per_second": 0.667,
|
||||
"step": 235
|
||||
},
|
||||
{
|
||||
"epoch": 3.582089552238806,
|
||||
"grad_norm": 1.9175089422860454,
|
||||
"learning_rate": 5.0000001740409057e-08,
|
||||
"loss": 1.3047,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 3.582089552238806,
|
||||
"eval_loss": 1.6093214750289917,
|
||||
"eval_runtime": 5.9889,
|
||||
"eval_samples_per_second": 79.481,
|
||||
"eval_steps_per_second": 0.668,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 3.656716417910448,
|
||||
"grad_norm": 1.8702465201892255,
|
||||
"learning_rate": 5.000000025140825e-08,
|
||||
"loss": 1.3208,
|
||||
"step": 245
|
||||
},
|
||||
{
|
||||
"epoch": 3.656716417910448,
|
||||
"eval_loss": 1.609329342842102,
|
||||
"eval_runtime": 5.9315,
|
||||
"eval_samples_per_second": 80.25,
|
||||
"eval_steps_per_second": 0.674,
|
||||
"step": 245
|
||||
},
|
||||
{
|
||||
"epoch": 3.7313432835820897,
|
||||
"grad_norm": 1.9567098448807434,
|
||||
"learning_rate": 5.000000002399302e-08,
|
||||
"loss": 1.362,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 3.7313432835820897,
|
||||
"eval_loss": 1.609269380569458,
|
||||
"eval_runtime": 5.9582,
|
||||
"eval_samples_per_second": 79.89,
|
||||
"eval_steps_per_second": 0.671,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 3.8059701492537314,
|
||||
"grad_norm": 1.8742551595721921,
|
||||
"learning_rate": 5.0000000001205015e-08,
|
||||
"loss": 1.3255,
|
||||
"step": 255
|
||||
},
|
||||
{
|
||||
"epoch": 3.8059701492537314,
|
||||
"eval_loss": 1.609143853187561,
|
||||
"eval_runtime": 5.9335,
|
||||
"eval_samples_per_second": 80.223,
|
||||
"eval_steps_per_second": 0.674,
|
||||
"step": 255
|
||||
},
|
||||
{
|
||||
"epoch": 3.8805970149253732,
|
||||
"grad_norm": 1.9100964620707728,
|
||||
"learning_rate": 5.000000000001954e-08,
|
||||
"loss": 1.2941,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 3.8805970149253732,
|
||||
"eval_loss": 1.608902096748352,
|
||||
"eval_runtime": 5.9228,
|
||||
"eval_samples_per_second": 80.368,
|
||||
"eval_steps_per_second": 0.675,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 3.955223880597015,
|
||||
"grad_norm": 1.959684298255238,
|
||||
"learning_rate": 5.0000000000000024e-08,
|
||||
"loss": 1.3254,
|
||||
"step": 265
|
||||
},
|
||||
{
|
||||
"epoch": 3.955223880597015,
|
||||
"eval_loss": 1.6086210012435913,
|
||||
"eval_runtime": 5.9667,
|
||||
"eval_samples_per_second": 79.776,
|
||||
"eval_steps_per_second": 0.67,
|
||||
"step": 265
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"step": 268,
|
||||
"total_flos": 27742804377600.0,
|
||||
"train_loss": 1.416380336925165,
|
||||
"train_runtime": 8905.9803,
|
||||
"train_samples_per_second": 1.923,
|
||||
"train_steps_per_second": 0.03
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 268,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 4,
|
||||
"save_steps": 5,
|
||||
"total_flos": 27742804377600.0,
|
||||
"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 sha256:757df4821b30408e0e76b69d6456366733f2cdee4e35ba6aebacd942ce0f8020
|
||||
size 6968
|
||||
BIN
training_eval_loss.png
Normal file
BIN
training_eval_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 37 KiB |
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 40 KiB |
Reference in New Issue
Block a user