mobilebert_500exs_10timesteps_run0

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

• Loss: 0.7313
• Accuracy: 0.48

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: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	63	0.7190	0.53
No log	2.0	126	0.7219	0.47
No log	3.0	189	0.6946	0.53
No log	4.0	252	0.7081	0.46
No log	5.0	315	0.7062	0.47
No log	6.0	378	0.7014	0.47
No log	7.0	441	0.7058	0.46
70646.992	8.0	504	0.6969	0.54
70646.992	9.0	567	0.7082	0.44
70646.992	10.0	630	0.8435	0.47
70646.992	11.0	693	0.7574	0.47
70646.992	12.0	756	0.6926	0.55
70646.992	13.0	819	0.7150	0.47
70646.992	14.0	882	0.7133	0.51
70646.992	15.0	945	0.7492	0.47
0.6741	16.0	1008	0.7313	0.48

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0+cu118
• Datasets 2.17.1
• Tokenizers 0.15.2