metadata
license: other
base_model: facebook/opt-350m
tags:
- trl
- reward-trainer
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_first_reward_modeling
results: []
my_first_reward_modeling
This model is a fine-tuned version of 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