git-base-pokemon

This model is a fine-tuned version of microsoft/git-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2324
• Wer Score: 5.2456

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Score
7.3165	5.26	50	4.6355	4.8031
2.6531	10.53	100	0.8536	4.2762
0.4	15.79	150	0.2527	4.6248
0.1634	21.05	200	0.2272	4.4392
0.125	26.32	250	0.2262	4.3356
0.1054	31.58	300	0.2286	6.6022
0.0932	36.84	350	0.2305	4.6967
0.0856	42.11	400	0.2320	4.4171
0.0811	47.37	450	0.2324	5.2456

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.14.7
• Tokenizers 0.15.0