metadata
license: apache-2.0
base_model: bigscience/mt0-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mt0-base-headline_WithIp
results: []
mt0-base-headline_WithIp
This model is a fine-tuned version of bigscience/mt0-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5591
- Rouge1: 0.0
- Rouge2: 0.0
- Rougel: 0.0
- Rougelsum: 0.0
- Gen Len: 16.8015
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.9054 | 1.0 | 202 | 1.5802 | 0.0 | 0.0 | 0.0 | 0.0 | 16.8511 |
| 1.7765 | 2.0 | 404 | 1.5663 | 0.0 | 0.0 | 0.0 | 0.0 | 17.464 |
| 1.4716 | 3.0 | 606 | 1.5465 | 0.0 | 0.0 | 0.0 | 0.0 | 17.1216 |
| 1.2112 | 4.0 | 808 | 1.5591 | 0.0 | 0.0 | 0.0 | 0.0 | 16.8015 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1