unlearn-cl_samsum_t5-large_neggrad_10_42 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-cl_samsum_t5-large_neggrad_10_42

like

0

generated_from_trainer

google/t5-v1_1-large

Views

No views yet

samsum_42

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

Loss: 1.1398
Rouge1: 14.8692
Rouge2: 6.897
Rougel: 13.627
Rougelsum: 13.9536
Gen Len: 126.3337
Test Rougel: 13.627
Df Rougel: 13.4531
Unlearn Overall Rougel: 0.5870
Unlearn Time: 12970.9118

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: 4
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2.5

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	0.7782	21.9035	11.1308	19.2342	20.5667	117.375	0.3210	0.3210	-1
No log	2.0	92	1.1398	14.8692	6.897	13.4531	13.9536	126.3337	0.5870	0.5870	-1
No log	2.5	115	1.2293	13.8989	6.3323	12.8057	13.1132	126.6262	0.5410	0.5410	-1

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.18.0
Tokenizers 0.15.2