metadata
license: mit
tags:
- generated_from_trainer
datasets:
- sst2
model-index:
- name: finetuned_gpt2-large_sst2_negation0.1_pretrainedFalse_epochs10
results: []
finetuned_gpt2-large_sst2_negation0.1_pretrainedFalse_epochs10
This model is a fine-tuned version of gpt2-large on the sst2 dataset. It achieves the following results on the evaluation set:
- Loss: 4.0544
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: 2e-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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9792 | 1.0 | 1329 | 3.0083 |
| 1.3396 | 2.0 | 2658 | 3.3183 |
| 1.0851 | 3.0 | 3987 | 3.5044 |
| 0.9187 | 4.0 | 5316 | 3.6375 |
| 0.828 | 5.0 | 6645 | 3.7741 |
| 0.7698 | 6.0 | 7974 | 3.8374 |
| 0.73 | 7.0 | 9303 | 3.9100 |
| 0.7027 | 8.0 | 10632 | 3.9658 |
| 0.6776 | 9.0 | 11961 | 4.0164 |
| 0.6614 | 10.0 | 13290 | 4.0544 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.7.0
- Datasets 2.8.0
- Tokenizers 0.13.2