fr_wiki_clm_13
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4708
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: 13
- 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 | 1.7190 | 2000 | 7.1490 |
| 7.2211 | 3.4379 | 4000 | 5.8869 |
| 7.2211 | 5.1569 | 6000 | 5.4206 |
| 5.4603 | 6.8758 | 8000 | 5.0644 |
| 5.4603 | 8.5948 | 10000 | 4.7704 |
| 4.8205 | 10.3137 | 12000 | 4.5274 |
| 4.8205 | 12.0327 | 14000 | 4.3241 |
| 4.369 | 13.7516 | 16000 | 4.1509 |
| 4.369 | 15.4706 | 18000 | 4.0131 |
| 4.039 | 17.1895 | 20000 | 3.8967 |
| 4.039 | 18.9085 | 22000 | 3.7902 |
| 3.792 | 20.6274 | 24000 | 3.7083 |
| 3.792 | 22.3464 | 26000 | 3.6318 |
| 3.5988 | 24.0653 | 28000 | 3.5716 |
| 3.5988 | 25.7843 | 30000 | 3.5175 |
| 3.4366 | 27.5032 | 32000 | 3.4818 |
| 3.4366 | 29.2222 | 34000 | 3.4478 |
| 3.303 | 30.9411 | 36000 | 3.4144 |
| 3.303 | 32.6601 | 38000 | 3.3936 |
| 3.1808 | 34.3790 | 40000 | 3.3769 |
| 3.1808 | 36.0980 | 42000 | 3.3654 |
| 3.0681 | 37.8169 | 44000 | 3.3452 |
| 3.0681 | 39.5359 | 46000 | 3.3394 |
| 2.9562 | 41.2548 | 48000 | 3.3389 |
| 2.9562 | 42.9738 | 50000 | 3.3301 |
| 2.8647 | 44.6927 | 52000 | 3.3356 |
| 2.8647 | 46.4117 | 54000 | 3.3422 |
| 2.7848 | 48.1306 | 56000 | 3.3468 |
| 2.7848 | 49.8496 | 58000 | 3.3467 |
| 2.713 | 51.5685 | 60000 | 3.3575 |
| 2.713 | 53.2875 | 62000 | 3.3672 |
| 2.6546 | 55.0064 | 64000 | 3.3688 |
| 2.6546 | 56.7254 | 66000 | 3.3764 |
| 2.5942 | 58.4443 | 68000 | 3.3907 |
| 2.5942 | 60.1633 | 70000 | 3.3962 |
| 2.5486 | 61.8823 | 72000 | 3.4000 |
| 2.5486 | 63.6012 | 74000 | 3.4071 |
| 2.5009 | 65.3202 | 76000 | 3.4164 |
| 2.5009 | 67.0391 | 78000 | 3.4277 |
| 2.4625 | 68.7581 | 80000 | 3.4293 |
| 2.4625 | 70.4770 | 82000 | 3.4382 |
| 2.4249 | 72.1960 | 84000 | 3.4481 |
| 2.4249 | 73.9149 | 86000 | 3.4495 |
| 2.3918 | 75.6339 | 88000 | 3.4554 |
| 2.3918 | 77.3528 | 90000 | 3.4596 |
| 2.3637 | 79.0718 | 92000 | 3.4637 |
| 2.3637 | 80.7907 | 94000 | 3.4666 |
| 2.337 | 82.5097 | 96000 | 3.4702 |
| 2.337 | 84.2286 | 98000 | 3.4712 |
| 2.3163 | 85.9476 | 100000 | 3.4708 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1