|
--- |
|
license: other |
|
base_model: facebook/opt-350m |
|
tags: |
|
- trl |
|
- reward-trainer |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: my_first_reward_modeling |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# my_first_reward_modeling |
|
|
|
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6161 |
|
- Accuracy: 0.6461 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 1.41e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 1024 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 1.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.7387 | 0.07 | 10 | 0.6877 | 0.5700 | |
|
| 0.6892 | 0.14 | 20 | 0.6735 | 0.5774 | |
|
| 0.6704 | 0.21 | 30 | 0.6650 | 0.5939 | |
|
| 0.6579 | 0.28 | 40 | 0.6563 | 0.6003 | |
|
| 0.6542 | 0.35 | 50 | 0.6483 | 0.6111 | |
|
| 0.6509 | 0.42 | 60 | 0.6398 | 0.6209 | |
|
| 0.64 | 0.49 | 70 | 0.6334 | 0.6301 | |
|
| 0.6322 | 0.56 | 80 | 0.6291 | 0.6354 | |
|
| 0.6268 | 0.63 | 90 | 0.6253 | 0.6397 | |
|
| 0.6254 | 0.7 | 100 | 0.6219 | 0.6401 | |
|
| 0.6213 | 0.77 | 110 | 0.6201 | 0.6436 | |
|
| 0.6284 | 0.83 | 120 | 0.6170 | 0.6454 | |
|
| 0.6233 | 0.9 | 130 | 0.6160 | 0.6452 | |
|
| 0.6192 | 0.97 | 140 | 0.6161 | 0.6461 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|