de_childes_30
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.1942
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.5021 | 2000 | 7.0910 |
| 6.9957 | 3.0041 | 4000 | 5.8267 |
| 6.9957 | 4.5062 | 6000 | 5.4651 |
| 5.213 | 6.0083 | 8000 | 5.1717 |
| 5.213 | 7.5103 | 10000 | 4.9590 |
| 4.7279 | 9.0124 | 12000 | 4.7918 |
| 4.7279 | 10.5145 | 14000 | 4.6601 |
| 4.4214 | 12.0165 | 16000 | 4.5524 |
| 4.4214 | 13.5186 | 18000 | 4.4587 |
| 4.195 | 15.0207 | 20000 | 4.3684 |
| 4.195 | 16.5227 | 22000 | 4.2900 |
| 4.0109 | 18.0248 | 24000 | 4.2277 |
| 4.0109 | 19.5268 | 26000 | 4.1726 |
| 3.8596 | 21.0289 | 28000 | 4.1288 |
| 3.8596 | 22.5310 | 30000 | 4.0892 |
| 3.7326 | 24.0330 | 32000 | 4.0589 |
| 3.7326 | 25.5351 | 34000 | 4.0279 |
| 3.6241 | 27.0372 | 36000 | 4.0029 |
| 3.6241 | 28.5392 | 38000 | 3.9903 |
| 3.5294 | 30.0413 | 40000 | 3.9732 |
| 3.5294 | 31.5434 | 42000 | 3.9699 |
| 3.4361 | 33.0454 | 44000 | 3.9619 |
| 3.4361 | 34.5475 | 46000 | 3.9608 |
| 3.3449 | 36.0496 | 48000 | 3.9666 |
| 3.3449 | 37.5516 | 50000 | 3.9692 |
| 3.2664 | 39.0537 | 52000 | 3.9745 |
| 3.2664 | 40.5558 | 54000 | 3.9862 |
| 3.1963 | 42.0578 | 56000 | 3.9972 |
| 3.1963 | 43.5757 | 58000 | 4.0077 |
| 3.1346 | 45.0777 | 60000 | 4.0204 |
| 3.1346 | 46.5798 | 62000 | 4.0262 |
| 3.0792 | 48.0819 | 64000 | 4.0405 |
| 3.0792 | 49.5839 | 66000 | 4.0522 |
| 3.0286 | 51.0860 | 68000 | 4.0700 |
| 3.0286 | 52.5881 | 70000 | 4.0754 |
| 2.9835 | 54.0901 | 72000 | 4.0929 |
| 2.9835 | 55.5922 | 74000 | 4.1004 |
| 2.942 | 57.0943 | 76000 | 4.1144 |
| 2.942 | 58.5963 | 78000 | 4.1265 |
| 2.9043 | 60.0984 | 80000 | 4.1325 |
| 2.9043 | 61.6005 | 82000 | 4.1431 |
| 2.8693 | 63.1025 | 84000 | 4.1530 |
| 2.8693 | 64.6046 | 86000 | 4.1612 |
| 2.8393 | 66.1066 | 88000 | 4.1716 |
| 2.8393 | 67.6087 | 90000 | 4.1759 |
| 2.8118 | 69.1108 | 92000 | 4.1815 |
| 2.8118 | 70.6128 | 94000 | 4.1873 |
| 2.7874 | 72.1149 | 96000 | 4.1914 |
| 2.7874 | 73.6170 | 98000 | 4.1935 |
| 2.7676 | 75.1190 | 100000 | 4.1942 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1