fr_childes_13
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.1486
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 | 2.5 | 2000 | 6.5946 |
| 6.5405 | 5.0 | 4000 | 4.9064 |
| 6.5405 | 7.5 | 6000 | 4.4605 |
| 4.299 | 10.0 | 8000 | 4.2033 |
| 4.299 | 12.5 | 10000 | 4.0186 |
| 3.822 | 15.0 | 12000 | 3.8741 |
| 3.822 | 17.5 | 14000 | 3.7604 |
| 3.5479 | 20.0 | 16000 | 3.6693 |
| 3.5479 | 22.5 | 18000 | 3.5906 |
| 3.3474 | 25.0 | 20000 | 3.5266 |
| 3.3474 | 27.5 | 22000 | 3.4638 |
| 3.181 | 30.0 | 24000 | 3.4185 |
| 3.181 | 32.5 | 26000 | 3.3846 |
| 3.0366 | 35.0 | 28000 | 3.3463 |
| 3.0366 | 37.5 | 30000 | 3.3321 |
| 2.9089 | 40.0 | 32000 | 3.3173 |
| 2.9089 | 42.5 | 34000 | 3.3138 |
| 2.7914 | 45.0 | 36000 | 3.3038 |
| 2.7914 | 47.5 | 38000 | 3.3271 |
| 2.6782 | 50.0 | 40000 | 3.3318 |
| 2.6782 | 52.5 | 42000 | 3.3629 |
| 2.557 | 55.0 | 44000 | 3.3741 |
| 2.557 | 57.5 | 46000 | 3.4272 |
| 2.4325 | 60.0 | 48000 | 3.4358 |
| 2.4325 | 62.5 | 50000 | 3.4926 |
| 2.3212 | 65.0 | 52000 | 3.5152 |
| 2.3212 | 67.5 | 54000 | 3.5673 |
| 2.2213 | 70.0 | 56000 | 3.5919 |
| 2.2213 | 72.5 | 58000 | 3.6468 |
| 2.1327 | 75.0 | 60000 | 3.6684 |
| 2.1327 | 77.5 | 62000 | 3.7214 |
| 2.0543 | 80.0 | 64000 | 3.7451 |
| 2.0543 | 82.5 | 66000 | 3.7884 |
| 1.9837 | 85.0 | 68000 | 3.8071 |
| 1.9837 | 87.5 | 70000 | 3.8546 |
| 1.9212 | 90.0 | 72000 | 3.8746 |
| 1.9212 | 92.5 | 74000 | 3.9187 |
| 1.8646 | 95.0 | 76000 | 3.9305 |
| 1.8646 | 97.5 | 78000 | 3.9732 |
| 1.8139 | 100.0 | 80000 | 3.9957 |
| 1.8139 | 102.5 | 82000 | 4.0264 |
| 1.768 | 105.0 | 84000 | 4.0383 |
| 1.768 | 107.5 | 86000 | 4.0636 |
| 1.7271 | 110.0 | 88000 | 4.0798 |
| 1.7271 | 112.5 | 90000 | 4.1051 |
| 1.6909 | 115.0 | 92000 | 4.1140 |
| 1.6909 | 117.5 | 94000 | 4.1260 |
| 1.6597 | 120.0 | 96000 | 4.1355 |
| 1.6597 | 122.5 | 98000 | 4.1469 |
| 1.6341 | 125.0 | 100000 | 4.1486 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1