mrm8488/electricidad-small-finetuned-diagTrast

electricidad (small) fine-tuned diagTrast

This model is a fine-tuned version of mrm8488/electricidad-small-discriminator on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2070
• Precision: 0.9349
• Recall: 0.9328
• Accuracy: 0.9328
• F1: 0.9330

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 14

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	Accuracy	F1
No log	1.0	150	1.4344	0.6909	0.6045	0.6045	0.5460
No log	2.0	300	1.1666	0.8055	0.7537	0.7537	0.7211
No log	3.0	450	0.9593	0.8321	0.8134	0.8134	0.7913
1.2831	4.0	600	0.7721	0.8575	0.8433	0.8433	0.8257
1.2831	5.0	750	0.6225	0.9062	0.9030	0.9030	0.9009
1.2831	6.0	900	0.4790	0.9179	0.9179	0.9179	0.9168
0.595	7.0	1050	0.3886	0.9340	0.9328	0.9328	0.9327
0.595	8.0	1200	0.3241	0.9258	0.9254	0.9254	0.9248
0.595	9.0	1350	0.2958	0.9198	0.9179	0.9179	0.9175
0.2183	10.0	1500	0.2469	0.9191	0.9179	0.9179	0.9175
0.2183	11.0	1650	0.2352	0.9195	0.9179	0.9179	0.9176
0.2183	12.0	1800	0.2118	0.9262	0.9254	0.9254	0.9249
0.2183	13.0	1950	0.2138	0.9195	0.9179	0.9179	0.9176
0.0984	14.0	2100	0.2070	0.9349	0.9328	0.9328	0.9330

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3