metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: mentalcaption-gen
results: []
mentalcaption-gen
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 7.9737
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.9964 | 103 | 15.2992 |
| No log | 1.9927 | 206 | 13.3893 |
| No log | 2.9988 | 310 | 12.0359 |
| No log | 3.9952 | 413 | 10.7522 |
| No log | 4.9915 | 516 | 9.6566 |
| No log | 5.9976 | 620 | 8.9572 |
| No log | 6.9940 | 723 | 8.5702 |
| No log | 8.0 | 827 | 8.3065 |
| No log | 8.9964 | 930 | 8.1143 |
| No log | 9.9637 | 1030 | 7.9737 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1