metadata
library_name: transformers
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: stock-summary-model
results: []
stock-summary-model
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0047
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 17 | 3.0099 |
| No log | 2.0 | 34 | 0.8798 |
| 3.3639 | 3.0 | 51 | 0.1632 |
| 3.3639 | 4.0 | 68 | 0.0385 |
| 3.3639 | 5.0 | 85 | 0.0146 |
| 0.0802 | 6.0 | 102 | 0.0091 |
| 0.0802 | 7.0 | 119 | 0.0067 |
| 0.0802 | 8.0 | 136 | 0.0057 |
| 0.0147 | 9.0 | 153 | 0.0048 |
| 0.0147 | 10.0 | 170 | 0.0047 |
Framework versions
- Transformers 4.44.1
- Pytorch 2.4.1
- Datasets 1.18.3
- Tokenizers 0.19.1