t5-base_cola_moe_ex38_epochs-3_decoder_all_sparsity20_mare_mlp – AI Model by thrunlab | AlphaNeural AI

You can deploy this model and start earning money today!

thrunlab/
t5-base_cola_moe_ex38_epochs-3_decoder_all_sparsity20_mare_mlp

like

0

text-classification

generated_from_trainer

google-t5/t5-base

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

t5-base_cola_moe_ex38_epochs-3_decoder_all_sparsity20_mare_mlp

This model is a fine-tuned version of t5-base on the glue dataset. It achieves the following results on the evaluation set:

Loss: 0.6107
Accuracy: 0.8351

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: 16
eval_batch_size: 32
seed: 1
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
lr_scheduler_warmup_steps: 20
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.54	0.19	50	0.9351	0.8178
0.508	0.37	100	0.7150	0.8332
0.5206	0.56	150	0.6512	0.8265
0.4831	0.75	200	0.6504	0.8274
0.5094	0.93	250	0.5474	0.8313
0.3632	1.12	300	0.6911	0.8226
0.3467	1.31	350	0.6089	0.8303
0.3803	1.5	400	0.5704	0.8360
0.3281	1.68	450	0.6079	0.8313
0.3239	1.87	500	0.5792	0.8284
0.2903	2.06	550	0.5910	0.8293
0.3892	2.24	600	0.6007	0.8341
0.2846	2.43	650	0.5993	0.8351
0.3209	2.62	700	0.6508	0.8360
0.2325	2.8	750	0.6217	0.8341
0.3949	2.99	800	0.6201	0.8341

Framework versions

Transformers 4.34.1
Pytorch 2.0.1+cu117
Datasets 2.9.0
Tokenizers 0.14.1