mlm-20230406-002-5

This model is a fine-tuned version of intanm/mlm-20230405-002-3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7441

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	284	2.8540
3.1889	2.0	568	2.5429
3.1889	3.0	852	2.4145
2.5305	4.0	1136	2.2699
2.5305	5.0	1420	2.1402
2.2343	6.0	1704	2.1209
2.2343	7.0	1988	2.0147
2.0581	8.0	2272	1.9715
1.942	9.0	2556	1.9564
1.942	10.0	2840	1.9158
1.8372	11.0	3124	1.9038
1.8372	12.0	3408	1.8593
1.7595	13.0	3692	1.8076
1.7595	14.0	3976	1.8470
1.7023	15.0	4260	1.7716
1.6629	16.0	4544	1.7706
1.6629	17.0	4828	1.7681
1.629	18.0	5112	1.7283
1.629	19.0	5396	1.7673
1.5984	20.0	5680	1.7507

Framework versions

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