cola-pixel-handwritten-mean-vatrpp-256-64-4-2e-5-15000-42

This model is a fine-tuned version of noniewiem/pixel-handwritten on the GLUE COLA dataset. It achieves the following results on the evaluation set:

• Loss: 0.6182
• Matthews Correlation: 0.0

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: 64
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• training_steps: 15000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
0.655	3.03	100	0.6341	0.0029
0.6174	6.06	200	0.6282	0.0
0.6196	9.09	300	0.6198	0.0
0.6158	12.12	400	0.6199	0.0
0.6175	15.15	500	0.6181	0.0
0.6152	18.18	600	0.6191	0.0
0.617	21.21	700	0.6185	0.0
0.6191	24.24	800	0.6185	0.0
0.6162	27.27	900	0.6183	0.0
0.6166	30.3	1000	0.6183	0.0
0.6177	33.33	1100	0.6182	0.0

Framework versions

• Transformers 4.17.0
• Pytorch 2.3.0+cu121
• Datasets 2.0.0
• Tokenizers 0.13.3