metadata
license: apache-2.0
base_model: RazinAleks/working
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: working
results: []
working
This model is a fine-tuned version of RazinAleks/working on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.2209
- Rouge1: 0.0485
- Rouge2: 0.0137
- Rougel: 0.0481
- Rougelsum: 0.0484
- Gen Len: 17.5748
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 4.267 | 1.0 | 938 | 3.3590 | 0.0423 | 0.0117 | 0.042 | 0.0421 | 17.3022 |
| 3.9878 | 2.0 | 1876 | 3.2691 | 0.0437 | 0.0116 | 0.0435 | 0.0437 | 17.3476 |
| 3.9117 | 3.0 | 2814 | 3.2318 | 0.0483 | 0.014 | 0.0479 | 0.0481 | 17.61 |
| 3.8808 | 4.0 | 3752 | 3.2209 | 0.0485 | 0.0137 | 0.0481 | 0.0484 | 17.5748 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3