fr_childes_42
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.1449
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: 42
- 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 | 6.5725 |
| 6.5185 | 5.0 | 4000 | 4.9264 |
| 6.5185 | 7.5 | 6000 | 4.4682 |
| 4.3057 | 10.0 | 8000 | 4.2043 |
| 4.3057 | 12.5 | 10000 | 4.0196 |
| 3.8252 | 15.0 | 12000 | 3.8793 |
| 3.8252 | 17.5 | 14000 | 3.7737 |
| 3.5527 | 20.0 | 16000 | 3.6714 |
| 3.5527 | 22.5 | 18000 | 3.5939 |
| 3.3505 | 25.0 | 20000 | 3.5267 |
| 3.3505 | 27.5 | 22000 | 3.4637 |
| 3.183 | 30.0 | 24000 | 3.4215 |
| 3.183 | 32.5 | 26000 | 3.3818 |
| 3.0393 | 35.0 | 28000 | 3.3493 |
| 3.0393 | 37.5 | 30000 | 3.3345 |
| 2.9118 | 40.0 | 32000 | 3.3137 |
| 2.9118 | 42.5 | 34000 | 3.3158 |
| 2.7946 | 45.0 | 36000 | 3.3074 |
| 2.7946 | 47.5 | 38000 | 3.3315 |
| 2.682 | 50.0 | 40000 | 3.3343 |
| 2.682 | 52.5 | 42000 | 3.3576 |
| 2.5612 | 55.0 | 44000 | 3.3741 |
| 2.5612 | 57.5 | 46000 | 3.4210 |
| 2.4371 | 60.0 | 48000 | 3.4420 |
| 2.4371 | 62.5 | 50000 | 3.4921 |
| 2.3257 | 65.0 | 52000 | 3.5113 |
| 2.3257 | 67.5 | 54000 | 3.5672 |
| 2.2264 | 70.0 | 56000 | 3.5861 |
| 2.2264 | 72.5 | 58000 | 3.6404 |
| 2.1379 | 75.0 | 60000 | 3.6712 |
| 2.1379 | 77.5 | 62000 | 3.7178 |
| 2.0592 | 80.0 | 64000 | 3.7306 |
| 2.0592 | 82.5 | 66000 | 3.7847 |
| 1.9888 | 85.0 | 68000 | 3.8042 |
| 1.9888 | 87.5 | 70000 | 3.8581 |
| 1.9259 | 90.0 | 72000 | 3.8752 |
| 1.9259 | 92.5 | 74000 | 3.9158 |
| 1.8696 | 95.0 | 76000 | 3.9281 |
| 1.8696 | 97.5 | 78000 | 3.9651 |
| 1.8186 | 100.0 | 80000 | 3.9848 |
| 1.8186 | 102.5 | 82000 | 4.0198 |
| 1.7735 | 105.0 | 84000 | 4.0294 |
| 1.7735 | 107.5 | 86000 | 4.0608 |
| 1.7319 | 110.0 | 88000 | 4.0724 |
| 1.7319 | 112.5 | 90000 | 4.0939 |
| 1.6956 | 115.0 | 92000 | 4.1053 |
| 1.6956 | 117.5 | 94000 | 4.1268 |
| 1.6642 | 120.0 | 96000 | 4.1355 |
| 1.6642 | 122.5 | 98000 | 4.1429 |
| 1.639 | 125.0 | 100000 | 4.1449 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1