gpt2_small_EN_unigram_65536_parallel3_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.8517
- Accuracy: 0.4553
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: 64
- eval_batch_size: 64
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 128
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|
| 3.2716 | 1.0 | 29350 | 3.1951 | 0.4140 |
| 3.1278 | 2.0 | 58700 | 3.0614 | 0.4287 |
| 3.0507 | 3.0 | 88050 | 2.9976 | 0.4358 |
| 3.0044 | 4.0 | 117400 | 2.9579 | 0.4401 |
| 2.9683 | 5.0 | 146750 | 2.9278 | 0.4444 |
| 2.9387 | 6.0 | 176100 | 2.9064 | 0.4467 |
| 2.9111 | 7.0 | 205450 | 2.8881 | 0.4503 |
| 2.8908 | 8.0 | 234800 | 2.8724 | 0.4520 |
| 2.8686 | 9.0 | 264150 | 2.8592 | 0.4546 |
| 2.8497 | 10.0 | 293500 | 2.8517 | 0.4553 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
