fr_childes_30
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8695
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 | 2.5 | 2000 | 7.2313 |
| 7.2176 | 5.0 | 4000 | 5.9545 |
| 7.2176 | 7.5 | 6000 | 5.8598 |
| 5.6874 | 10.0 | 8000 | 5.7428 |
| 5.6874 | 12.5 | 10000 | 5.6532 |
| 5.4656 | 15.0 | 12000 | 5.5699 |
| 5.4656 | 17.5 | 14000 | 5.5426 |
| 5.3133 | 20.0 | 16000 | 5.4334 |
| 5.3133 | 22.5 | 18000 | 5.3758 |
| 5.179 | 25.0 | 20000 | 5.2195 |
| 5.179 | 27.5 | 22000 | 4.9868 |
| 4.6563 | 30.0 | 24000 | 3.9624 |
| 4.6563 | 32.5 | 26000 | 3.5028 |
| 3.4598 | 35.0 | 28000 | 3.2076 |
| 3.4598 | 37.5 | 30000 | 2.9908 |
| 2.909 | 40.0 | 32000 | 2.8660 |
| 2.909 | 42.5 | 34000 | 2.7679 |
| 2.6232 | 45.0 | 36000 | 2.6570 |
| 2.6232 | 47.5 | 38000 | 2.5871 |
| 2.4203 | 50.0 | 40000 | 2.4412 |
| 2.4203 | 52.5 | 42000 | 2.4134 |
| 2.2552 | 55.0 | 44000 | 2.3494 |
| 2.2552 | 57.5 | 46000 | 2.3228 |
| 2.1296 | 60.0 | 48000 | 2.2705 |
| 2.1296 | 62.5 | 50000 | 2.2204 |
| 2.0306 | 65.0 | 52000 | 2.1760 |
| 2.0306 | 67.5 | 54000 | 2.1368 |
| 1.9511 | 70.0 | 56000 | 2.0997 |
| 1.9511 | 72.5 | 58000 | 2.0805 |
| 1.885 | 75.0 | 60000 | 2.0912 |
| 1.885 | 77.5 | 62000 | 2.0434 |
| 1.8306 | 80.0 | 64000 | 2.0201 |
| 1.8306 | 82.5 | 66000 | 2.0316 |
| 1.7868 | 85.0 | 68000 | 2.0113 |
| 1.7868 | 87.5 | 70000 | 1.9823 |
| 1.7507 | 90.0 | 72000 | 1.9737 |
| 1.7507 | 92.5 | 74000 | 1.9542 |
| 1.7196 | 95.0 | 76000 | 1.9697 |
| 1.7196 | 97.5 | 78000 | 1.9313 |
| 1.6921 | 100.0 | 80000 | 1.9157 |
| 1.6921 | 102.5 | 82000 | 1.8956 |
| 1.6628 | 105.0 | 84000 | 1.9193 |
| 1.6628 | 107.5 | 86000 | 1.9044 |
| 1.6433 | 110.0 | 88000 | 1.8990 |
| 1.6433 | 112.5 | 90000 | 1.9024 |
| 1.6247 | 115.0 | 92000 | 1.8754 |
| 1.6247 | 117.5 | 94000 | 1.8949 |
| 1.6091 | 120.0 | 96000 | 1.8928 |
| 1.6091 | 122.5 | 98000 | 1.8834 |
| 1.6018 | 125.0 | 100000 | 1.8695 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 3