prthm29's picture
End of training
4087805 verified
metadata
library_name: peft
license: mit
base_model: zai-org/GLM-OCR
tags:
  - base_model:adapter:zai-org/GLM-OCR
  - llama-factory
  - lora
  - transformers
metrics:
  - accuracy
pipeline_tag: text-generation
model-index:
  - name: smoke_test_glm4v_checkpoints
    results: []

smoke_test_glm4v_checkpoints

This model is a fine-tuned version of zai-org/GLM-OCR on the gujarati_ocr_stream dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5668
  • Accuracy: 0.5594

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: 0.0001
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 1
  • training_steps: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.7841 0.6154 2 2.7496 0.5348
2.6433 1.0 4 2.5868 0.5556

Framework versions

  • PEFT 0.18.1
  • Transformers 5.2.0
  • Pytorch 2.11.0+cu130
  • Datasets 4.0.0
  • Tokenizers 0.22.2