test_trainer

This model is a fine-tuned version of microsoft/xtremedistil-l6-h384-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1134
• Accuracy: 0.9770

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: 3e-05
• train_batch_size: 128
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 24

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	10	0.6990	0.4967
No log	2.0	20	0.6889	0.4967
No log	3.0	30	0.6503	0.7697
No log	4.0	40	0.4720	0.9276
No log	5.0	50	0.3175	0.9572
No log	6.0	60	0.2181	0.9770
No log	7.0	70	0.1761	0.9770
No log	8.0	80	0.1551	0.9770
No log	9.0	90	0.1427	0.9770
No log	10.0	100	0.1345	0.9770
No log	11.0	110	0.1341	0.9737
No log	12.0	120	0.1240	0.9770
No log	13.0	130	0.1214	0.9770
No log	14.0	140	0.1182	0.9770
No log	15.0	150	0.1164	0.9770
No log	16.0	160	0.1149	0.9770
No log	17.0	170	0.1141	0.9770
No log	18.0	180	0.1131	0.9770
No log	19.0	190	0.1127	0.9770
No log	20.0	200	0.1121	0.9770
No log	21.0	210	0.1119	0.9770
No log	22.0	220	0.1117	0.9770
No log	23.0	230	0.1128	0.9770
No log	24.0	240	0.1134	0.9770

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0