|
--- |
|
license: apache-2.0 |
|
base_model: lidiya/bart-large-xsum-samsum |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: tech-dialogue-summarization-3 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# tech-dialogue-summarization-3 |
|
|
|
This model is a fine-tuned version of [lidiya/bart-large-xsum-samsum](https://huggingface.co./lidiya/bart-large-xsum-samsum) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3468 |
|
- Rouge1: 52.6316 |
|
- Rouge2: 32.4324 |
|
- Rougel: 47.3684 |
|
- Rougelsum: 47.3684 |
|
- Gen Len: 38.0 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| No log | 1.0 | 1 | 1.4146 | 52.6316 | 32.4324 | 47.3684 | 47.3684 | 38.0 | |
|
| No log | 2.0 | 2 | 1.3652 | 52.6316 | 32.4324 | 47.3684 | 47.3684 | 38.0 | |
|
| No log | 3.0 | 3 | 1.3468 | 52.6316 | 32.4324 | 47.3684 | 47.3684 | 38.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
