metadata
license: mit
tags:
- generated_from_trainer
datasets:
- sst2
model-index:
- name: finetuned_gpt2-medium_sst2_negation0.01_pretrainedFalse_epochs10
results: []
finetuned_gpt2-medium_sst2_negation0.01_pretrainedFalse_epochs10
This model is a fine-tuned version of gpt2-medium on the sst2 dataset. It achieves the following results on the evaluation set:
- Loss: 4.0937
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 |
|---|---|---|---|
| 2.2693 | 1.0 | 1323 | 2.9043 |
| 1.8782 | 2.0 | 2646 | 3.0877 |
| 1.6671 | 3.0 | 3969 | 3.3430 |
| 1.4607 | 4.0 | 5292 | 3.5276 |
| 1.3258 | 5.0 | 6615 | 3.7558 |
| 1.2423 | 6.0 | 7938 | 3.8430 |
| 1.1748 | 7.0 | 9261 | 3.9389 |
| 1.124 | 8.0 | 10584 | 4.0047 |
| 1.0988 | 9.0 | 11907 | 4.0659 |
| 1.0751 | 10.0 | 13230 | 4.0937 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.7.0
- Datasets 2.8.0
- Tokenizers 0.13.2