<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
guten_norm_rarity_neg_log_rarity_1p5k_end_19p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1152
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.3344 | 0.29 | 500 | 5.3350 |
| 5.0278 | 0.59 | 1000 | 4.9259 |
| 4.6963 | 0.88 | 1500 | 4.6852 |
| 4.4453 | 1.18 | 2000 | 4.5488 |
| 4.2936 | 1.47 | 2500 | 4.4345 |
| 4.1865 | 1.76 | 3000 | 4.3321 |
| 4.0639 | 2.06 | 3500 | 4.2618 |
| 3.8866 | 2.35 | 4000 | 4.2158 |
| 3.864 | 2.65 | 4500 | 4.1589 |
| 3.8292 | 2.94 | 5000 | 4.1066 |
| 3.6241 | 3.23 | 5500 | 4.1024 |
| 3.5838 | 3.53 | 6000 | 4.0697 |
| 3.5595 | 3.82 | 6500 | 4.0401 |
| 3.4547 | 4.12 | 7000 | 4.0415 |
| 3.3147 | 4.41 | 7500 | 4.0359 |
| 3.3064 | 4.7 | 8000 | 4.0221 |
| 3.3014 | 5.0 | 8500 | 4.0101 |
| 3.1322 | 5.29 | 9000 | 4.0233 |
| 3.1304 | 5.58 | 9500 | 4.0225 |
| 3.1282 | 5.88 | 10000 | 4.0221 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
