<!-- 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. -->
bert_12_layer_model_v1_complete_training_new_emb_compress_48_gelu
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.7019
- Accuracy: 0.3153
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 |
---|---|---|---|---|
7.1202 | 0.08 | 10000 | 7.0974 | 0.0833 |
6.6953 | 0.16 | 20000 | 6.6906 | 0.1078 |
6.549 | 0.25 | 30000 | 6.5434 | 0.1182 |
6.463 | 0.33 | 40000 | 6.4530 | 0.1247 |
6.39 | 0.41 | 50000 | 6.3876 | 0.1310 |
6.3422 | 0.49 | 60000 | 6.3315 | 0.1343 |
6.2978 | 0.57 | 70000 | 6.2912 | 0.1374 |
6.2666 | 0.66 | 80000 | 6.2620 | 0.1398 |
6.2338 | 0.74 | 90000 | 6.2298 | 0.1421 |
6.2068 | 0.82 | 100000 | 6.2109 | 0.1437 |
6.1882 | 0.9 | 110000 | 6.1852 | 0.1441 |
6.1676 | 0.98 | 120000 | 6.1647 | 0.1457 |
6.1309 | 1.07 | 130000 | 6.1335 | 0.1469 |
6.0822 | 1.15 | 140000 | 6.0727 | 0.1483 |
5.9914 | 1.23 | 150000 | 5.9807 | 0.1540 |
5.8946 | 1.31 | 160000 | 5.8634 | 0.1771 |
5.6741 | 1.39 | 170000 | 5.6228 | 0.2136 |
5.3973 | 1.47 | 180000 | 5.3334 | 0.2463 |
5.0432 | 1.56 | 190000 | 4.9868 | 0.2842 |
4.7647 | 1.64 | 200000 | 4.7019 | 0.3153 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.1
- Tokenizers 0.13.3