metadata

license: apache-2.0
base_model: bigscience/mt0-small
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: mt0-small-query-extraction-v4
    results: []

mt0-small-query-extraction-v4

This model is a fine-tuned version of bigscience/mt0-small on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0016
Rouge1: 55.6206
Rouge2: 48.0808
Rougel: 55.6125
Rougelsum: 55.6119
Gen Len: 19.0

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: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.0121	1.0	110364	0.0040	55.607	48.038	55.5908	55.5903	19.0
0.0045	2.0	220728	0.0021	55.6226	48.0812	55.6123	55.6125	19.0
0.003	3.0	331092	0.0016	55.6206	48.0808	55.6125	55.6119	19.0

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1