Donut F21 v4 Ep3 Edit Distance Loss Retrain
This model is a fine-tuned version of yuchiahung/donutf21v4ep3editdistanceloss on the None dataset. It achieves the following results on the evaluation set: Loss: 19.6495 Char Accuracy: 0.1456 Exact Match Accuracy:...
Model source
- Kind
- Model
- File size
- 988 B–772 MB
- Base model
- yuchiahung/donut_f21_v4_ep3_edit_distance_loss
- Version
- vRevision 41e480e
- Updated
- Oct 30, 2026
- Downloads
- 8
- Source
- Hugging Face
Source description
donut_f21_v4_ep3_edit_distance_loss_retrain
This model is a fine-tuned version of yuchiahung/donut_f21_v4_ep3_edit_distance_loss on the None dataset. It achieves the following results on the evaluation set:
- Loss: 19.6495
- Char Accuracy: 0.1456
- Exact Match Accuracy: 0.0
- Avg Pred Length: 1.456
- Avg Label Length: 10.0
- Length Ratio: 0.1456
- Avg Edit Distance: 8.544
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-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 132
- 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_ratio: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Char Accuracy | Exact Match Accuracy | Avg Pred Length | Avg Label Length | Length Ratio | Avg Edit Distance |
|---|---|---|---|---|---|---|---|---|---|
| 0.7473 | 1.0 | 5000 | 19.5055 | 0.1456 | 0.0 | 1.456 | 10.0 | 0.1456 | 8.544 |
| 1.6766 | 2.0 | 10000 | 19.5939 | 0.1458 | 0.0 | 1.458 | 10.0 | 0.1458 | 8.542 |
| 1.5029 | 3.0 | 15000 | 19.6495 | 0.1456 | 0.0 | 1.456 | 10.0 | 0.1456 | 8.544 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2
Sources
1 source
Sources
1 sourceVerified Oct 30
Download files
Repository files
File inventory only; completeness is unverified.
- added_tokens.json
- checkpoint-10000/config.json
- checkpoint-10000/generation_config.json
- checkpoint-10000/model.safetensors
- checkpoint-10000/trainer_state.json
- checkpoint-10000/training_args.bin
- checkpoint-129/config.json
- checkpoint-129/generation_config.json
- checkpoint-129/model.safetensors
- checkpoint-129/trainer_state.json
- checkpoint-129/training_args.bin
- checkpoint-15000/config.json
- checkpoint-15000/generation_config.json
- checkpoint-15000/model.safetensors
- checkpoint-15000/trainer_state.json
- checkpoint-15000/training_args.bin
- checkpoint-2500/config.json
- checkpoint-2500/generation_config.json
- checkpoint-2500/model.safetensors
- checkpoint-2500/trainer_state.json
- checkpoint-2500/training_args.bin
- checkpoint-3000/config.json
- checkpoint-3000/generation_config.json
- checkpoint-3000/model.safetensors
- checkpoint-3000/trainer_state.json
- checkpoint-3000/training_args.bin
- checkpoint-43/config.json
- checkpoint-43/generation_config.json
- checkpoint-43/model.safetensors
- checkpoint-43/trainer_state.json
- checkpoint-43/training_args.bin
- checkpoint-7500/config.json
- checkpoint-7500/generation_config.json
- checkpoint-7500/model.safetensors
- checkpoint-7500/trainer_state.json
- checkpoint-7500/training_args.bin
- checkpoint-9000/config.json
- checkpoint-9000/generation_config.json
- checkpoint-9000/model.safetensors
- checkpoint-9000/trainer_state.json
- checkpoint-9000/training_args.bin
- config.json
- generation_config.json
- model.safetensors
- preprocessor_config.json
- sentencepiece.bpe.model
- special_tokens_map.json
- tokenizer.json
- tokenizer_config.json
- training_args.bin
Model artifacts
17 artifacts
Model artifacts
17 artifactscheckpoint-10000/model.safetensors
safetensors · FP32 + I64 (tensor header) · 772 MB · SHA-256 6c6df52973d4…1e8c · Hugging Face
Download filecheckpoint-129/model.safetensors
safetensors · FP32 + I64 (tensor header) · 772 MB · SHA-256 da74ce0ceb3b…c64f · Hugging Face
Download filecheckpoint-15000/model.safetensors
safetensors · FP32 + I64 (tensor header) · 772 MB · SHA-256 1e2390db997e…9685 · Hugging Face
Download filecheckpoint-2500/model.safetensors
safetensors · FP32 + I64 (tensor header) · 772 MB · SHA-256 560838aee3dc…d927 · Hugging Face
Download filecheckpoint-3000/model.safetensors
safetensors · FP32 + I64 (tensor header) · 772 MB · SHA-256 65f8c2bab429…9cf4 · Hugging Face
Download filecheckpoint-43/model.safetensors
safetensors · FP32 + I64 (tensor header) · 772 MB · SHA-256 7f0b114b1c37…9742 · Hugging Face
Download filecheckpoint-7500/model.safetensors
safetensors · FP32 + I64 (tensor header) · 772 MB · SHA-256 702a0edff7a8…afb8 · Hugging Face
Download filecheckpoint-9000/model.safetensors
safetensors · FP32 + I64 (tensor header) · 772 MB · SHA-256 0aeed9ad3a0b…190f · Hugging Face
Download filemodel.safetensors
safetensors · FP32 + I64 (tensor header) · 772 MB · SHA-256 6c6df52973d4…1e8c · Hugging Face
Download fileSource excerpts
3 excerpts
Source excerpts
3 excerpts--- library_name: transformers license: mit base_model: yuchiahung/donut_f21_v4_ep3_edit_distance_loss tags: - generated_from_trainer model-index: - name: donut_f21_v4_ep3_edit_distance_loss_retrain results: [] --- <!-- 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. --> # donut_f21_v4_ep3_edit_distance_loss_retrain This model is a fine-tuned version of [yuchiahung/donut_f21_v4_ep3_edit_distance_loss](https://huggingface.co/yuchiahung/donut_f21_v4_ep3_edit_distance_loss) on the None dataset. It achieves the following results on the evaluation set: - Loss: 19.6495 - Char Accuracy: 0.1456 - Exact Match Accuracy: 0.0 - Avg Pred Length: 1.456 - Avg Label Length: 10.0 - Length Ratio: 0.1456 - Avg Edit Distance: 8.544 ## 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-06 - train_batch_size: 1 - eval_batch_size: 1 - seed: 132 - 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_ratio: 0.1 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Char Accuracy | Exact Match Accuracy | Avg Pred Length | Avg Label Length | Length Ratio | Avg Edit Distance | |:-------------:|:-----:|:-----:|:---------------:|:-------------:|:--------------------:|:---------------:|:----------------:|:------------:|:-----------------:| | 0.7473 | 1.0 | 5000 | 19.5055 | 0.1456 | 0.0 | 1.456 | 10.0 | 0.1456 | 8.544 | | 1.6766 | 2.0 | 10000 | 19.5939 | 0.1458 | 0.0 | 1.458 | 10.0 | 0.1458 | 8.542 | | 1.5029 | 3.0 | 15000 | 19.6495 | 0.1456 | 0.0 | 1.456 | 10.0 | 0.1456 | 8.544 | ### Framework versions - Transformers 4.57.6 - Pytorch 2.10.0+cu128 - Datasets 4.5.0 - Tokenizers 0.22.2
Source context: 8 downloads · 0 likes · Pipeline image-text-to-text · Library transformers · Repo yuchiahung/donut_f21_v4_ep3_edit_distance_loss_retrain
Source context: 471 downloads · 0 likes · Pipeline image-text-to-text · Library transformers · Repo yuchiahung/donut_f21_v4_ep3_edit_distance_loss_retrain
