unlearn_samsum_t5-xl_neggrad_10_42 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn_samsum_t5-xl_neggrad_10_42

like

0

generated_from_trainer

google/t5-v1_1-xl

Views

No views yet

samsum_42

This model is a fine-tuned version of google/t5-v1_1-xl on the samsum dataset. It achieves the following results on the evaluation set:

Loss: 226.4730
Rouge1: 0.9699
Rouge2: 0.0069
Rougel: 0.9688
Rougelsum: 0.968
Gen Len: 126.9838
Test Rougel: 0.9688
Df Rougel: 1.023
Unlearn Overall Rougel: 0.4729
Unlearn Time: 41986.2203

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: 1e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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	Overall Rougel	Unlearn Overall Rougel	Time
No log	1.0	46	2.1119	18.8409	9.3778	17.4178	17.6837	114.115	0.3325	0.3325	-1
No log	2.0	92	97.3253	1.2783	0.0102	1.2949	1.2722	126.9038	0.4847	0.4847	-1
No log	3.0	138	193.9756	1.043	0.0069	1.0886	1.0423	126.9675	0.4765	0.4765	-1
No log	4.0	184	220.4530	0.9763	0.0069	1.0245	0.9746	126.9838	0.4751	0.4751	-1
No log	5.0	230	226.4730	0.9699	0.0069	1.023	0.968	126.9838	0.4729	0.4729	-1

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.15.2