<!-- 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. -->
pretrain-gpt2-large-2
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4854
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 32
- total_train_batch_size: 1024
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 167 | 2.5651 |
| No log | 2.0 | 335 | 2.5465 |
| No log | 3.0 | 502 | 2.5311 |
| No log | 4.0 | 670 | 2.5183 |
| No log | 4.99 | 837 | 2.5078 |
| No log | 6.0 | 1005 | 2.4995 |
| 2.5339 | 7.0 | 1173 | 2.4932 |
| 2.5339 | 8.0 | 1340 | 2.4888 |
| 2.5339 | 9.0 | 1508 | 2.4862 |
| 2.5339 | 9.96 | 1670 | 2.4854 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
