eng_wiki_clm_42
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.2500
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40000
- training_steps: 100000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.1319 | 2000 | 7.5640 |
| 7.6485 | 2.2637 | 4000 | 6.6731 |
| 7.6485 | 3.3956 | 6000 | 6.2793 |
| 6.3325 | 4.5274 | 8000 | 6.0141 |
| 6.3325 | 5.6593 | 10000 | 5.7784 |
| 5.8281 | 6.7912 | 12000 | 5.5657 |
| 5.8281 | 7.9230 | 14000 | 5.3671 |
| 5.4204 | 9.0549 | 16000 | 5.1972 |
| 5.4204 | 10.1868 | 18000 | 5.0524 |
| 5.096 | 11.3186 | 20000 | 4.9339 |
| 5.096 | 12.4505 | 22000 | 4.8286 |
| 4.8571 | 13.5823 | 24000 | 4.7401 |
| 4.8571 | 14.7142 | 26000 | 4.6688 |
| 4.673 | 15.8461 | 28000 | 4.5988 |
| 4.673 | 16.9779 | 30000 | 4.5444 |
| 4.5211 | 18.1098 | 32000 | 4.5015 |
| 4.5211 | 19.2417 | 34000 | 4.4587 |
| 4.3937 | 20.3735 | 36000 | 4.4241 |
| 4.3937 | 21.5054 | 38000 | 4.3971 |
| 4.2867 | 22.6372 | 40000 | 4.3672 |
| 4.2867 | 23.7691 | 42000 | 4.3372 |
| 4.1863 | 24.9010 | 44000 | 4.3134 |
| 4.1863 | 26.0328 | 46000 | 4.2987 |
| 4.0881 | 27.1647 | 48000 | 4.2874 |
| 4.0881 | 28.2965 | 50000 | 4.2760 |
| 4.0082 | 29.4284 | 52000 | 4.2657 |
| 4.0082 | 30.5603 | 54000 | 4.2634 |
| 3.944 | 31.6921 | 56000 | 4.2563 |
| 3.944 | 32.8240 | 58000 | 4.2486 |
| 3.8888 | 33.9559 | 60000 | 4.2412 |
| 3.8888 | 35.0877 | 62000 | 4.2471 |
| 3.832 | 36.2196 | 64000 | 4.2460 |
| 3.832 | 37.3514 | 66000 | 4.2430 |
| 3.7879 | 38.4833 | 68000 | 4.2406 |
| 3.7879 | 39.6152 | 70000 | 4.2424 |
| 3.7498 | 40.7470 | 72000 | 4.2400 |
| 3.7498 | 41.8789 | 74000 | 4.2369 |
| 3.7133 | 43.0108 | 76000 | 4.2430 |
| 3.7133 | 44.1426 | 78000 | 4.2447 |
| 3.6755 | 45.2745 | 80000 | 4.2489 |
| 3.6755 | 46.4063 | 82000 | 4.2471 |
| 3.6472 | 47.5382 | 84000 | 4.2504 |
| 3.6472 | 48.6701 | 86000 | 4.2484 |
| 3.6212 | 49.8019 | 88000 | 4.2470 |
| 3.6212 | 50.9338 | 90000 | 4.2485 |
| 3.5958 | 52.0656 | 92000 | 4.2497 |
| 3.5958 | 53.1975 | 94000 | 4.2502 |
| 3.573 | 54.3294 | 96000 | 4.2511 |
| 3.573 | 55.4612 | 98000 | 4.2507 |
| 3.5537 | 56.5931 | 100000 | 4.2500 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1