metadata
base_model: google/pegasus-large
tags:
- generated_from_trainer
metrics:
- rouge
- precision
- recall
- f1
model-index:
- name: LLM_Teached_Pegasus
results: []
LLM_Teached_Pegasus
This model is a fine-tuned version of google/pegasus-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6606
- Rouge1: 0.4557
- Rouge2: 0.2019
- Rougel: 0.3603
- Rougelsum: 0.3597
- Gen Len: 30.8509
- Precision: 0.9078
- Recall: 0.9053
- F1: 0.9064
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 2.0887 | 1.0 | 625 | 1.7362 | 0.4326 | 0.1871 | 0.3375 | 0.3373 | 31.2482 | 0.9035 | 0.9015 | 0.9023 |
| 1.8362 | 2.0 | 1250 | 1.6844 | 0.4466 | 0.1942 | 0.3511 | 0.3507 | 30.3036 | 0.9071 | 0.9032 | 0.905 |
| 1.7784 | 3.0 | 1875 | 1.6666 | 0.451 | 0.1992 | 0.3554 | 0.3551 | 30.7991 | 0.907 | 0.9045 | 0.9056 |
| 1.7261 | 4.0 | 2500 | 1.6606 | 0.4557 | 0.2019 | 0.3603 | 0.3597 | 30.8509 | 0.9078 | 0.9053 | 0.9064 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.15.0