de_mlm_child_30_new
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9961
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: 30
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.2096 | 2000 | 7.0624 |
| 7.0103 | 2.4191 | 4000 | 5.9907 |
| 7.0103 | 3.6287 | 6000 | 5.8268 |
| 5.5573 | 4.8382 | 8000 | 5.7135 |
| 5.5573 | 6.0478 | 10000 | 5.6182 |
| 5.3684 | 7.2573 | 12000 | 5.5548 |
| 5.3684 | 8.4669 | 14000 | 5.4931 |
| 5.2311 | 9.6764 | 16000 | 5.4276 |
| 5.2311 | 10.8860 | 18000 | 5.3897 |
| 5.1257 | 12.0956 | 20000 | 5.3456 |
| 5.1257 | 13.3051 | 22000 | 5.3070 |
| 5.0524 | 14.5147 | 24000 | 5.2622 |
| 5.0524 | 15.7242 | 26000 | 5.2159 |
| 4.9502 | 16.9338 | 28000 | 5.0671 |
| 4.9502 | 18.1433 | 30000 | 4.2052 |
| 4.0862 | 19.3529 | 32000 | 3.7250 |
| 4.0862 | 20.5624 | 34000 | 3.4164 |
| 3.2461 | 21.7720 | 36000 | 3.2153 |
| 3.2461 | 22.9816 | 38000 | 2.9981 |
| 2.8492 | 24.1911 | 40000 | 2.8842 |
| 2.8492 | 25.4007 | 42000 | 2.7470 |
| 2.5828 | 26.6102 | 44000 | 2.6714 |
| 2.5828 | 27.8198 | 46000 | 2.5692 |
| 2.4091 | 29.0293 | 48000 | 2.5008 |
| 2.4091 | 30.2389 | 50000 | 2.4384 |
| 2.2855 | 31.4484 | 52000 | 2.3737 |
| 2.2855 | 32.6580 | 54000 | 2.3480 |
| 2.1975 | 33.8676 | 56000 | 2.3211 |
| 2.1975 | 35.0771 | 58000 | 2.2830 |
| 2.1246 | 36.2867 | 60000 | 2.2453 |
| 2.1246 | 37.4962 | 62000 | 2.2185 |
| 2.0701 | 38.7058 | 64000 | 2.1977 |
| 2.0701 | 39.9153 | 66000 | 2.1722 |
| 2.0222 | 41.1249 | 68000 | 2.1386 |
| 2.0222 | 42.3344 | 70000 | 2.1359 |
| 1.9823 | 43.5440 | 72000 | 2.1266 |
| 1.9823 | 44.7536 | 74000 | 2.1028 |
| 1.9462 | 45.9631 | 76000 | 2.0943 |
| 1.9462 | 47.1727 | 78000 | 2.0773 |
| 1.9189 | 48.3822 | 80000 | 2.0864 |
| 1.9189 | 49.5918 | 82000 | 2.0530 |
| 1.8958 | 50.8013 | 84000 | 2.0451 |
| 1.8958 | 52.0109 | 86000 | 2.0476 |
| 1.8715 | 53.2204 | 88000 | 2.0231 |
| 1.8715 | 54.4300 | 90000 | 2.0168 |
| 1.8562 | 55.6396 | 92000 | 2.0104 |
| 1.8562 | 56.8491 | 94000 | 2.0088 |
| 1.8417 | 58.0587 | 96000 | 2.0087 |
| 1.8417 | 59.2858 | 98000 | 2.0008 |
| 1.8314 | 60.4953 | 100000 | 1.9961 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 14