opt-babylm1-ntb-ntx_seed-42_5e-6
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1329
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: 5e-06
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 20.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.3231 | 0.4303 | 1000 | 5.3236 |
| 4.7545 | 0.8605 | 2000 | 4.7988 |
| 4.2474 | 1.2904 | 3000 | 4.3491 |
| 3.8921 | 1.7207 | 4000 | 4.0106 |
| 3.5852 | 2.1506 | 5000 | 3.7059 |
| 3.4271 | 2.5809 | 6000 | 3.5586 |
| 3.3283 | 3.0108 | 7000 | 3.4875 |
| 3.2437 | 3.4410 | 8000 | 3.3988 |
| 3.1943 | 3.8713 | 9000 | 3.3481 |
| 3.1307 | 4.3012 | 10000 | 3.3237 |
| 3.1068 | 4.7315 | 11000 | 3.2817 |
| 3.043 | 5.1614 | 12000 | 3.2612 |
| 3.0442 | 5.5916 | 13000 | 3.2444 |
| 3.0088 | 6.0215 | 14000 | 3.2330 |
| 2.9844 | 6.4518 | 15000 | 3.2144 |
| 2.9769 | 6.8821 | 16000 | 3.2002 |
| 2.9358 | 7.3119 | 17000 | 3.1929 |
| 2.9424 | 7.7422 | 18000 | 3.1871 |
| 2.8912 | 8.1721 | 19000 | 3.1839 |
| 2.913 | 8.6024 | 20000 | 3.1772 |
| 2.8701 | 9.0323 | 21000 | 3.1741 |
| 2.8744 | 9.4625 | 22000 | 3.1632 |
| 2.8711 | 9.8928 | 23000 | 3.1561 |
| 2.8372 | 10.3227 | 24000 | 3.1616 |
| 2.8433 | 10.7530 | 25000 | 3.1489 |
| 2.8125 | 11.1829 | 26000 | 3.1511 |
| 2.8185 | 11.6131 | 27000 | 3.1429 |
| 2.7773 | 12.0430 | 28000 | 3.1534 |
| 2.7967 | 12.4733 | 29000 | 3.1425 |
| 2.7985 | 12.9036 | 30000 | 3.1338 |
| 2.7654 | 13.3335 | 31000 | 3.1420 |
| 2.7764 | 13.7637 | 32000 | 3.1319 |
| 2.7477 | 14.1936 | 33000 | 3.1390 |
| 2.7554 | 14.6239 | 34000 | 3.1309 |
| 2.7253 | 15.0538 | 35000 | 3.1369 |
| 2.7369 | 15.4841 | 36000 | 3.1355 |
| 2.7425 | 15.9143 | 37000 | 3.1306 |
| 2.7087 | 16.3442 | 38000 | 3.1377 |
| 2.7185 | 16.7745 | 39000 | 3.1323 |
| 2.7039 | 17.2044 | 40000 | 3.1356 |
| 2.7014 | 17.6346 | 41000 | 3.1327 |
| 2.6871 | 18.0645 | 42000 | 3.1341 |
| 2.6857 | 18.4948 | 43000 | 3.1329 |
| 2.6857 | 18.9251 | 44000 | 3.1311 |
| 2.6794 | 19.3550 | 45000 | 3.1330 |
| 2.6808 | 19.7852 | 46000 | 3.1329 |
Framework versions
- Transformers 4.54.0
- Pytorch 2.10.0+cu128
- Datasets 3.2.0
- Tokenizers 0.21.4