README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: random_top100
    results: []

random_top100

This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.6990
• Rouge1: 0.1626
• Rouge2: 0.0339
• Rougel: 0.1405
• Rougelsum: 0.1404
• 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: 2e-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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	58	17.5159	0.0	0.0	0.0	0.0	4.0
No log	2.0	116	14.6617	0.0	0.0	0.0	0.0	4.0
No log	3.0	174	9.7296	0.0	0.0	0.0	0.0	4.0
No log	4.0	232	9.4582	0.0605	0.0114	0.0585	0.059	9.0
No log	5.0	290	7.3911	0.1321	0.0136	0.1223	0.1221	19.0
No log	6.0	348	6.0032	0.1542	0.0349	0.1313	0.1312	19.0
No log	7.0	406	5.0453	0.1542	0.0349	0.1313	0.1312	19.0
No log	8.0	464	4.8066	0.1626	0.0339	0.1405	0.1404	19.0
11.9321	9.0	522	4.7140	0.1626	0.0339	0.1405	0.1404	19.0
11.9321	10.0	580	4.6990	0.1626	0.0339	0.1405	0.1404	19.0

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3