metadata
library_name: transformers
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: ActivityNet-Captions-with-taxonomy-real-no_shift-model
results: []
ActivityNet-Captions-with-taxonomy-real-no_shift-model
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6776
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: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.8476 | 1.0 | 1339 | 2.7987 |
| 2.7997 | 2.0 | 2678 | 2.7232 |
| 2.6446 | 3.0 | 4017 | 2.6919 |
| 2.5093 | 4.0 | 5356 | 2.6823 |
| 2.578 | 5.0 | 6695 | 2.6776 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.1.2+cu121
- Datasets 2.19.1
- Tokenizers 0.20.3