cantillation/Teamim-large-v2_Random-True_OldData_date-07-06-2024_16-07-57

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

he-cantillation

This model is a fine-tuned version of Teamim-large-v2_Random-True_date-06-06-2024_21-59-43 on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 0.1326
• —Wer: 13.4139
• —Avg Precision Exact: 0.9006
• —Avg Recall Exact: 0.9003
• —Avg F1 Exact: 0.8998
• —Avg Precision Letter Shift: 0.9238
• —Avg Recall Letter Shift: 0.9240
• —Avg F1 Letter Shift: 0.9232
• —Avg Precision Word Level: 0.9256
• —Avg Recall Word Level: 0.9251
• —Avg F1 Word Level: 0.9246
• —Avg Precision Word Shift: 0.9608
• —Avg Recall Word Shift: 0.9621
• —Avg F1 Word Shift: 0.9608
• —Precision Median Exact: 0.9286
• —Recall Median Exact: 0.9286
• —F1 Median Exact: 0.9524
• —Precision Max Exact: 1.0
• —Recall Max Exact: 1.0
• —F1 Max Exact: 1.0
• —Precision Min Exact: 0.0
• —Recall Min Exact: 0.0
• —F1 Min Exact: 0.0
• —Precision Min Letter Shift: 0.0
• —Recall Min Letter Shift: 0.0
• —F1 Min Letter Shift: 0.0
• —Precision Min Word Level: 0.0
• —Recall Min Word Level: 0.0
• —F1 Min Word Level: 0.0
• —Precision Min Word Shift: 0.6364
• —Recall Min Word Shift: 0.5833
• —F1 Min Word Shift: 0.6087

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: 1e-05
• —trainbatchsize: 8
• —evalbatchsize: 32
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 50
• —training_steps: 8000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.42.0.dev0
• —Pytorch 1.13.1+cu117
• —Datasets 2.16.1
• —Tokenizers 0.19.1