metadata
tags:
- generated_from_trainer
model-index:
- name: passive-transformer-1
results: []
passive-transformer-1
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8708
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 3052726
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.2233 | 0.03 | 76320 | 4.2009 |
| 4.0186 | 1.03 | 152640 | 4.0327 |
| 3.9093 | 0.03 | 228960 | 3.9579 |
| 3.8464 | 0.03 | 305280 | 3.9175 |
| 3.7922 | 1.03 | 381600 | 3.8925 |
| 3.7538 | 0.03 | 457920 | 3.8767 |
| 3.7207 | 1.03 | 534240 | 3.8663 |
| 3.6892 | 0.03 | 610560 | 3.8588 |
| 3.6577 | 0.03 | 686880 | 3.8554 |
| 3.6329 | 0.03 | 763200 | 3.8524 |
| 3.6085 | 0.03 | 839520 | 3.8515 |
| 3.5871 | 1.03 | 915840 | 3.8497 |
| 3.5675 | 0.03 | 992160 | 3.8501 |
| 3.5461 | 0.03 | 1068480 | 3.8502 |
| 3.5295 | 1.03 | 1144800 | 3.8507 |
| 3.5249 | 0.03 | 1221120 | 3.8521 |
| 3.5096 | 1.03 | 1297440 | 3.8524 |
| 3.4973 | 0.03 | 1373760 | 3.8528 |
| 3.4814 | 1.03 | 1450080 | 3.8544 |
| 3.4748 | 0.03 | 1526400 | 3.8569 |
| 3.466 | 1.03 | 1602720 | 3.8589 |
| 3.4584 | 0.03 | 1679040 | 3.8598 |
| 3.4465 | 1.03 | 1755360 | 3.8605 |
| 3.4372 | 0.03 | 1831680 | 3.8623 |
| 3.4203 | 1.03 | 1908000 | 3.8628 |
| 3.4095 | 0.03 | 1984320 | 3.8649 |
| 3.3955 | 1.03 | 2060640 | 3.8660 |
| 3.385 | 0.03 | 2136960 | 3.8678 |
| 3.3718 | 1.03 | 2213280 | 3.8686 |
| 3.3586 | 0.03 | 2289600 | 3.8694 |
| 3.3473 | 1.03 | 2365920 | 3.8713 |
| 3.3472 | 0.03 | 2442240 | 3.8706 |
| 3.3381 | 1.03 | 2518560 | 3.8725 |
| 3.3276 | 0.03 | 2594880 | 3.8720 |
| 3.3171 | 0.03 | 2671200 | 3.8721 |
| 3.3129 | 0.03 | 2747520 | 3.8727 |
| 3.3068 | 1.03 | 2823840 | 3.8731 |
| 3.3017 | 0.03 | 2900160 | 3.8719 |
| 3.2974 | 1.03 | 2976480 | 3.8718 |
| 3.2884 | 0.02 | 3052726 | 3.8708 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3