metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: base-mlm-imdb
results: []
base-mlm-imdb
This model is a fine-tuned version of google/bert_uncased_L-12_H-768_A-12 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9103
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 200
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.1149 | 0.16 | 500 | 1.9627 |
2.0674 | 0.32 | 1000 | 1.9620 |
2.0582 | 0.48 | 1500 | 1.9502 |
2.0542 | 0.64 | 2000 | 1.9418 |
2.0398 | 0.8 | 2500 | 1.9223 |
2.037 | 0.96 | 3000 | 1.9220 |
1.9831 | 1.12 | 3500 | 1.9247 |
1.972 | 1.28 | 4000 | 1.9123 |
1.9708 | 1.44 | 4500 | 1.9122 |
1.967 | 1.6 | 5000 | 1.9097 |
1.9582 | 1.76 | 5500 | 1.9085 |
1.9715 | 1.92 | 6000 | 1.9099 |
1.9459 | 2.08 | 6500 | 1.9113 |
1.9384 | 2.24 | 7000 | 1.9103 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2