You can deploy this model and start earning money today!

contemmcm/
0a05d588785b01ee20592de7f296bff2

Name: 0a05d588785b01ee20592de7f296bff2
Rating: 2.5 (7 reviews)

Views

No views yet

0a05d588785b01ee20592de7f296bff2

This model is a fine-tuned version of google-bert/bert-large-uncased-whole-word-masking-finetuned-squad on the dair-ai/emotion [split] dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 50

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro
No log	0	0	1.9618	0	2.1154	0.2908	0.0751
No log	1	500	1.6267	0.0078	2.8422	0.3518	0.0910
No log	2	1000	1.5862	0.0156	3.2862	0.3488	0.0862
No log	3	1500	1.3404	0.0312	4.8420	0.5393	0.2172
No log	4	2000	1.2054	0.0625	7.1733	0.5867	0.2422
0.0711	5	2500	1.3695	0.125	11.4652	0.5403	0.2258
1.1183	6	3000	0.9427	0.25	16.8399	0.6799	0.3708
0.0716	7	3500	0.3993	0.5	28.1470	0.8795	0.7226
0.3101	8.0	4000	0.3070	1.0	51.8837	0.9083	0.8754
0.2171	9.0	4500	0.3193	1.0	51.3838	0.9143	0.8691
0.3162	10.0	5000	0.2920	1.0	51.3948	0.9173	0.8689
0.2378	11.0	5500	0.3012	1.0	50.9535	0.9168	0.8772
0.2609	12.0	6000	0.3221	1.0	51.0921	0.9073	0.8645
0.3001	13.0	6500	0.3357	1.0	50.8259	0.9103	0.8723
0.2848	14.0	7000	0.2976	1.0	51.1476	0.9224	0.8798