license, base_model, tags, model-index
| license | base_model | tags | model-index | ||||||
|---|---|---|---|---|---|---|---|---|---|
| mit | gpt2 |
|
|
LLM_TRAINING
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1049
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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.1795 | 0.25 | 10 | 3.6578 |
| 2.9896 | 0.5 | 20 | 2.2492 |
| 2.0979 | 0.75 | 30 | 1.7208 |
| 1.754 | 1.0 | 40 | 1.4856 |
| 1.544 | 1.25 | 50 | 1.3701 |
| 1.4369 | 1.5 | 60 | 1.2945 |
| 1.3826 | 1.76 | 70 | 1.2557 |
| 1.3657 | 2.01 | 80 | 1.2247 |
| 1.3064 | 2.26 | 90 | 1.1987 |
| 1.2619 | 2.51 | 100 | 1.1778 |
| 1.2493 | 2.76 | 110 | 1.1623 |
| 1.2498 | 3.01 | 120 | 1.1464 |
| 1.2126 | 3.26 | 130 | 1.1308 |
| 1.1972 | 3.51 | 140 | 1.1242 |
| 1.1776 | 3.76 | 150 | 1.1169 |
| 1.1826 | 4.01 | 160 | 1.1121 |
| 1.1623 | 4.26 | 170 | 1.1089 |
| 1.1468 | 4.51 | 180 | 1.1063 |
| 1.1594 | 4.76 | 190 | 1.1049 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.3
- Tokenizers 0.13.3