README.md

metadata

license: apache-2.0
base_model: t5-small
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: FinetunedT5Model
    results: []

FinetunedT5Model

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.6604
• Rouge1: 0.2931
• Rouge2: 0.1635
• Rougel: 0.2526
• Rougelsum: 0.253
• Gen Len: 18.9262

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	38	2.0609	0.255	0.1343	0.2236	0.2245	18.7987
No log	2.0	76	1.9133	0.2719	0.1447	0.2388	0.2388	18.9463
No log	3.0	114	1.8280	0.2784	0.1548	0.2433	0.2437	18.9262
No log	4.0	152	1.7742	0.2847	0.159	0.2481	0.2485	18.9262
No log	5.0	190	1.7346	0.2866	0.1602	0.2488	0.2492	18.9262
No log	6.0	228	1.7067	0.2888	0.162	0.25	0.2506	18.9262
No log	7.0	266	1.6846	0.2861	0.1591	0.2482	0.2489	18.9262
No log	8.0	304	1.6712	0.2922	0.1625	0.2528	0.2531	18.9262
No log	9.0	342	1.6629	0.293	0.1635	0.2528	0.2532	18.9262
No log	10.0	380	1.6604	0.2931	0.1635	0.2526	0.253	18.9262

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0