<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
model_v1_complete_training_wt_init_48_small
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5728
- Accuracy: 0.5268
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: 1e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
3.7567 | 0.25 | 30000 | 3.5433 | 0.4111 |
3.3711 | 0.49 | 60000 | 3.1762 | 0.4519 |
3.1874 | 0.74 | 90000 | 3.0125 | 0.4709 |
3.0895 | 0.98 | 120000 | 2.9136 | 0.4832 |
3.0097 | 1.23 | 150000 | 2.8447 | 0.4919 |
2.9567 | 1.47 | 180000 | 2.7906 | 0.4985 |
2.9172 | 1.72 | 210000 | 2.7519 | 0.5034 |
2.8781 | 1.97 | 240000 | 2.7183 | 0.5079 |
2.8467 | 2.21 | 270000 | 2.6916 | 0.5113 |
2.8156 | 2.46 | 300000 | 2.6691 | 0.5142 |
2.7975 | 2.7 | 330000 | 2.6503 | 0.5168 |
2.7806 | 2.95 | 360000 | 2.6341 | 0.5189 |
2.7637 | 3.2 | 390000 | 2.6222 | 0.5204 |
2.7629 | 3.44 | 420000 | 2.6085 | 0.5223 |
2.7457 | 3.69 | 450000 | 2.5993 | 0.5235 |
2.7393 | 3.93 | 480000 | 2.5901 | 0.5247 |
2.7285 | 4.18 | 510000 | 2.5829 | 0.5256 |
2.7204 | 4.42 | 540000 | 2.5792 | 0.5260 |
2.7213 | 4.67 | 570000 | 2.5758 | 0.5266 |
2.716 | 4.92 | 600000 | 2.5728 | 0.5268 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3