20231207_Step_98_Retrain_Instrn_Bart-S_9ep_Loss_0.42 – AI Model by zibajoon | AlphaNeural AI

You can deploy this model and start earning money today!

zibajoon/
20231207_Step_98_Retrain_Instrn_Bart-S_9ep_Loss_0.42

like

0

text2text-generation

generated_from_trainer

linydub/bart-large-samsum

endpoints_compatible

Views

No views yet

20231207_Step_98_Retrain_Instrn_Bart-Samsun_v1.30

This model is a fine-tuned version of linydub/bart-large-samsum on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4292

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-06
train_batch_size: 1
eval_batch_size: 8
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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
1.8211	1.0	1201	0.3633
0.301	2.0	2402	0.3271
0.2527	3.0	3603	0.3320
0.2061	4.0	4804	0.3400
0.1533	5.0	6005	0.3610
0.1602	6.0	7206	0.3814
0.131	7.0	8407	0.4089
0.1213	8.0	9608	0.4255
0.1003	9.0	10809	0.4292

Framework versions

Transformers 4.34.1
Pytorch 2.1.1+cu121
Datasets 2.15.0
Tokenizers 0.14.1