Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-3.2-1B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3.2
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- dpo
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: llama3.2-1B-dpo-v1
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# llama3.2-1B-dpo-v1
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.5037
|
| 22 |
+
- Rewards/chosen: -1.5976
|
| 23 |
+
- Rewards/rejected: -4.4612
|
| 24 |
+
- Rewards/accuracies: 0.7913
|
| 25 |
+
- Rewards/margins: 2.8637
|
| 26 |
+
- Logps/rejected: -449.0548
|
| 27 |
+
- Logps/chosen: -492.4157
|
| 28 |
+
- Logits/rejected: -0.4987
|
| 29 |
+
- Logits/chosen: -0.2456
|
| 30 |
+
|
| 31 |
+
## Model description
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Intended uses & limitations
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training and evaluation data
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training procedure
|
| 44 |
+
|
| 45 |
+
### Training hyperparameters
|
| 46 |
+
|
| 47 |
+
The following hyperparameters were used during training:
|
| 48 |
+
- learning_rate: 5e-05
|
| 49 |
+
- train_batch_size: 6
|
| 50 |
+
- eval_batch_size: 4
|
| 51 |
+
- seed: 42
|
| 52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
+
- lr_scheduler_type: cosine
|
| 54 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 55 |
+
- num_epochs: 1
|
| 56 |
+
|
| 57 |
+
### Training results
|
| 58 |
+
|
| 59 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
| 60 |
+
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
| 61 |
+
| 0.5478 | 0.0763 | 700 | 0.5414 | -0.1038 | -1.2895 | 0.7302 | 1.1857 | -417.3377 | -477.4783 | 0.2274 | 0.3639 |
|
| 62 |
+
| 0.5243 | 0.1527 | 1400 | 0.6105 | -1.3917 | -3.5270 | 0.7313 | 2.1353 | -439.7127 | -490.3575 | 0.3525 | 0.5136 |
|
| 63 |
+
| 0.6483 | 0.2290 | 2100 | 0.6370 | -3.1503 | -5.7506 | 0.7482 | 2.6003 | -461.9483 | -507.9432 | 0.2785 | 0.4243 |
|
| 64 |
+
| 0.687 | 0.3053 | 2800 | 0.5835 | -0.2196 | -2.3802 | 0.7391 | 2.1606 | -428.2447 | -478.6364 | 0.3201 | 0.4561 |
|
| 65 |
+
| 0.5813 | 0.3816 | 3500 | 0.5808 | -0.6116 | -3.0983 | 0.7609 | 2.4868 | -435.4256 | -482.5557 | 0.0172 | 0.2140 |
|
| 66 |
+
| 0.7066 | 0.4580 | 4200 | 0.5681 | -1.1058 | -3.4796 | 0.7564 | 2.3738 | -439.2385 | -487.4986 | 0.0611 | 0.2653 |
|
| 67 |
+
| 0.6408 | 0.5343 | 4900 | 0.5910 | -0.7319 | -3.5281 | 0.7659 | 2.7962 | -439.7232 | -483.7594 | -0.0603 | 0.1582 |
|
| 68 |
+
| 0.4565 | 0.6106 | 5600 | 0.5367 | -1.0688 | -3.9321 | 0.7867 | 2.8633 | -443.7639 | -487.1283 | -0.1924 | 0.0583 |
|
| 69 |
+
| 0.5482 | 0.6869 | 6300 | 0.5267 | -1.4234 | -4.2466 | 0.7888 | 2.8232 | -446.9083 | -490.6742 | -0.4528 | -0.2006 |
|
| 70 |
+
| 0.5196 | 0.7633 | 7000 | 0.5322 | -2.2017 | -5.1279 | 0.7888 | 2.9261 | -455.7211 | -498.4576 | -0.6046 | -0.3654 |
|
| 71 |
+
| 0.4858 | 0.8396 | 7700 | 0.5116 | -2.0986 | -5.0640 | 0.7938 | 2.9653 | -455.0820 | -497.4264 | -0.5200 | -0.2768 |
|
| 72 |
+
| 0.4581 | 0.9159 | 8400 | 0.5051 | -1.6669 | -4.5613 | 0.7913 | 2.8944 | -450.0557 | -493.1090 | -0.5097 | -0.2589 |
|
| 73 |
+
| 0.3934 | 0.9923 | 9100 | 0.5037 | -1.5976 | -4.4612 | 0.7913 | 2.8637 | -449.0548 | -492.4157 | -0.4987 | -0.2456 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- PEFT 0.8.2
|
| 79 |
+
- Transformers 4.45.1
|
| 80 |
+
- Pytorch 2.1.2+cu121
|
| 81 |
+
- Datasets 2.16.1
|
| 82 |
+
- Tokenizers 0.20.0
|