f8145be948
Model: devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_conj_ratio_0p50_mix_0p25_43 Source: Original Platform
tags, model-index
| tags | model-index | ||||||
|---|---|---|---|---|---|---|---|
|
|
gpt2_small_expandedbabyLM_100M_exp3_conj_ratio_0p50_mix_0p25_43
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6265
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: 0.0001
- train_batch_size: 256
- eval_batch_size: 256
- seed: 43
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 4000
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.667 | 1.0 | 4328 | 4.3338 |
| 3.311 | 2.0 | 8656 | 3.8057 |
| 3.1759 | 3.0 | 12984 | 3.6760 |
| 3.0974 | 4.0 | 17312 | 3.6680 |
| 3.0396 | 5.0 | 21640 | 3.6388 |
| 2.9897 | 6.0 | 25968 | 3.6473 |
| 2.9565 | 7.0 | 30296 | 3.6265 |
| 2.9261 | 8.0 | 34624 | 3.6763 |
| 2.8945 | 9.0 | 38952 | 3.6619 |
| 2.8724 | 10.0 | 43280 | 3.7177 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.11.0+cu130
- Datasets 4.1.1
- Tokenizers 0.13.3