metadata
library_name: transformers
base_model: google/bert_for_seq_generation_L-24_bbc_encoder
tags:
- generated_from_trainer
model-index:
- name: bert_sp_updown
results: []
bert_sp_updown
This model is a fine-tuned version of google/bert_for_seq_generation_L-24_bbc_encoder on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0001
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0033 | 1.0 | 1429 | 0.0000 |
| 0.0005 | 2.0 | 2858 | 0.0000 |
| 0.0067 | 3.0 | 4287 | 0.0001 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1