<!-- 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. -->
sft-trl-claim
This model is a fine-tuned version of EleutherAI/gpt-j-6b on the anli dataset. It achieves the following results on the evaluation set:
- Loss: 0.6558
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1758 | 0.2 | 1000 | 1.8749 |
| 0.9782 | 0.4 | 2000 | 1.4891 |
| 0.7268 | 0.6 | 3000 | 1.0777 |
| 0.7882 | 0.8 | 4000 | 0.7661 |
| 0.316 | 1.0 | 5000 | 0.7215 |
| 0.2962 | 1.2 | 6000 | 0.7067 |
| 0.2318 | 1.4 | 7000 | 0.6914 |
| 0.3424 | 1.6 | 8000 | 0.6558 |
| 0.216 | 1.8 | 9000 | 0.6558 |
| 0.1732 | 2.0 | 10000 | 0.6558 |
| 0.1178 | 2.2 | 11000 | 0.6558 |
| 0.202 | 2.4 | 12000 | 0.6558 |
| 0.1088 | 2.6 | 13000 | 0.6558 |
| 0.1408 | 2.8 | 14000 | 0.6558 |
| 0.1856 | 3.0 | 15000 | 0.6558 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
