mobilebert_100exs_20timesteps

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: 6038.2681
• Accuracy: 0.4

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-06
• 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	13	7673916.0	0.4
No log	2.0	26	6584108.5	0.4
No log	3.0	39	5544034.0	0.4
No log	4.0	52	4472702.0	0.4
No log	5.0	65	3472884.5	0.4
No log	6.0	78	2438114.0	0.4
No log	7.0	91	1419238.5	0.4
No log	8.0	104	339111.1875	0.4
No log	9.0	117	114032.0781	0.4
No log	10.0	130	56265.6758	0.4
No log	11.0	143	28542.5312	0.4
No log	12.0	156	12412.2344	0.4
No log	13.0	169	8272.7559	0.4
No log	14.0	182	6995.5869	0.4
No log	15.0	195	6293.6924	0.4
No log	16.0	208	6038.2681	0.4

Framework versions

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