bert_12_layer_model_v1_complete_training_new_48_KD_wt_init – AI Model by gokuls | AlphaNeural AI

You can deploy this model and start earning money today!

gokuls/
bert_12_layer_model_v1_complete_training_new_48_KD_wt_init

like

0

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

bert_12_layer_model_v1_complete_training_new_48_KD_wt_init

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

Loss: 241.0859
Accuracy: 0.4099

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: 36
eval_batch_size: 36
seed: 10
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 10000
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
603.6149	0.06	10000	579.3715	0.1445
499.749	0.12	20000	507.5929	0.1449
464.2382	0.18	30000	455.9639	0.1525
402.3357	0.25	40000	394.2733	0.2312
354.8343	0.31	50000	348.3572	0.2952
323.2804	0.37	60000	315.5649	0.3318
304.7558	0.43	70000	294.0559	0.3520
291.4657	0.49	80000	282.6148	0.3669
280.9548	0.55	90000	270.2188	0.3792
271.2151	0.61	100000	260.9895	0.3888
261.6096	0.68	110000	251.4035	0.3961
256.1119	0.74	120000	243.2089	0.4041
249.2419	0.8	130000	241.0859	0.4099

Framework versions

Transformers 4.30.1
Pytorch 1.14.0a0+410ce96
Datasets 2.12.0
Tokenizers 0.13.3