unlearn_samsum_t5-xl_neggrad_2_42 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn_samsum_t5-xl_neggrad_2_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: 1.1825
Rouge1: 51.2819
Rouge2: 27.9457
Rougel: 41.9408
Rougelsum: 47.3621
Gen Len: 43.7249
Test Rougel: 41.9408
Df Rougel: 43.3119
Unlearn Overall Rougel: -0.1855
Unlearn Time: 7951.5673

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: 4
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	0.95	9	1.1115	54.9831	30.5024	49.031	50.8745	28.0257	-1.1707	-1.1707	-1
No log	2.0	19	1.1228	54.7687	30.0571	47.5416	50.6064	31.0807	-0.6141	-0.6141	-1
No log	2.95	28	1.1437	53.8321	29.4636	45.9851	49.657	35.5672	-0.3771	-0.3771	-1
No log	4.0	38	1.1730	52.0687	28.4069	43.9048	48.031	41.7873	-0.1172	-0.1172	-1
No log	4.74	45	1.1825	51.2819	27.9457	43.3119	47.3621	43.7249	-0.1855	-0.1855	-1

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.15.2