metadata

license: apache-2.0
base_model: google/mt5-base
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: mT5-TextSimp-LT-BatchSize12-lr1e-4
    results: []

mT5-TextSimp-LT-BatchSize12-lr1e-4

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

Loss: 0.1611
Rouge1: 0.4599
Rouge2: 0.2777
Rougel: 0.4471
Gen Len: 39.0358

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: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Gen Len
36.6446	0.48	200	31.2765	0.0004	0.0	0.0004	512.0
11.5223	0.96	400	6.7786	0.003	0.0	0.0031	89.2816
2.2686	1.44	600	0.6729	0.0053	0.0	0.0053	39.0501
0.7009	1.91	800	0.6529	0.0029	0.0	0.0027	41.401
0.6213	2.39	1000	0.5630	0.0057	0.0002	0.0056	39.0334
0.6435	2.87	1200	0.4697	0.0685	0.0084	0.0611	39.0453
0.4154	3.35	1400	10.4655	0.2093	0.1217	0.2006	350.0334
0.6289	3.83	1600	1.9257	0.317	0.1946	0.3064	138.7494
3.5542	4.31	1800	0.8459	0.3735	0.204	0.3613	59.8568
8.1736	4.78	2000	7.2350	0.3144	0.1819	0.3037	289.1432
2.3987	5.26	2200	0.8361	0.3621	0.1911	0.351	61.0668
0.9853	5.74	2400	0.4219	0.3634	0.2008	0.352	46.494
0.3575	6.22	2600	0.3516	0.3805	0.2128	0.3689	46.1623
0.4497	6.7	2800	0.2597	0.4388	0.2698	0.4269	42.2697
0.2582	7.18	3000	0.1583	0.4444	0.2587	0.4316	38.1671
0.2629	7.66	3200	0.1611	0.4599	0.2777	0.4471	39.0358

Framework versions

Transformers 4.33.0
Pytorch 2.1.2+cu121
Datasets 2.14.4
Tokenizers 0.13.3