Aller au contenu
ModelPrésentéExterne
Télécharger

Exp23 Directfit Unfrozen

This model is a fine-tuned version of cyttic/exp22-exp2warm-directfit-frozen on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.4588 Cer: 0.0245 Wer: 0.0647

Sourcehuggingface.co/cyttic/exp23-directfit-unfrozen/tree/57b28f8ac5e8e2d9ff910b7126efbda032fa2a8d
TypeCheckpointModèle de basecyttic/exp22-exp2warm-directfit-frozenVersionRevision 57b28f8DClasse

Source du modèle

Type
Checkpoint
Taille du fichier
1,12 GB
Modèle de base
cyttic/exp22-exp2warm-directfit-frozen
Version
vRevision 57b28f8
Mis à jour
1 oct. 2026
Téléchargements
173
Source
Hugging Face

Description de la source

exp23-directfit-unfrozen

This model is a fine-tuned version of cyttic/exp22-exp2warm-directfit-frozen on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4588
  • Cer: 0.0245
  • Wer: 0.0647

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: 16
  • eval_batch_size: 16
  • seed: 42
  • 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: linear
  • lr_scheduler_warmup_steps: 0.1
  • num_epochs: 1

Training results

Training LossEpochStepValidation LossCerWer
1.25770.042425001.33780.14160.2986
1.04130.084850001.24410.11500.2561
0.84360.127275001.08540.09170.2106
0.77620.1696100000.93140.07350.1700
0.70960.2120125000.89540.06270.1534
0.62050.2544150000.79070.05500.1378
0.58730.2968175000.74080.04860.1215
0.55040.3392200000.68940.04270.1112
0.48260.3816225000.65370.04060.1042
0.52240.4240250000.62450.03800.0965
0.44300.4664275000.58660.03660.0933
0.42190.5088300000.57240.03400.0873
0.35570.5512325000.55860.03180.0849
0.38660.5936350000.53990.03280.0845
0.35860.6360375000.52670.03050.0793
0.40090.6784400000.50820.03010.0769
0.31400.7208425000.50110.02890.0740
0.34350.7632450000.48740.02760.0725
0.31410.8056475000.48070.02670.0691
0.32000.8480500000.47380.02670.0687
0.32010.8904525000.46820.02500.0664
0.33140.9328550000.46330.02490.0652
0.34270.9752575000.46040.02440.0648
0.30201.0589620.45880.02450.0647

Framework versions

  • Transformers 5.12.1
  • Pytorch 2.11.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.2

Sources

1 source
Hugging FacePrincipalVersion 57b28f8ac5e8e2d9ff910b7126efbda032fa2a8d
huggingface.co/cyttic/exp23-directfit-unfrozen/tree/57b28f8ac5e8e2d9ff910b7126efbda032fa2a8d

Vérifié 1 oct.

Artefacts du modèle

2 artefacts

last-checkpoint/model.safetensors

safetensors · 1,12 GB · SHA-256 f4206fdf41f5…d1c9 · Hugging Face

Télécharger

model.safetensors

safetensors · 1,12 GB · SHA-256 f4206fdf41f5…d1c9 · Hugging Face

Télécharger

Extraits de sources

3 extraits
Readme11 juil.huggingface.co/cyttic/exp23-directfit-unfrozen

--- library_name: transformers base_model: cyttic/exp22-exp2warm-directfit-frozen tags: - generated_from_trainer metrics: - wer model-index: - name: exp23-directfit-unfrozen 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. --> # exp23-directfit-unfrozen This model is a fine-tuned version of [cyttic/exp22-exp2warm-directfit-frozen](https://huggingface.co/cyttic/exp22-exp2warm-directfit-frozen) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4588 - Cer: 0.0245 - Wer: 0.0647 ## 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: 16 - eval_batch_size: 16 - seed: 42 - 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: linear - lr_scheduler_warmup_steps: 0.1 - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Cer | Wer | |:-------------:|:------:|:-----:|:---------------:|:------:|:------:| | 1.2577 | 0.0424 | 2500 | 1.3378 | 0.1416 | 0.2986 | | 1.0413 | 0.0848 | 5000 | 1.2441 | 0.1150 | 0.2561 | | 0.8436 | 0.1272 | 7500 | 1.0854 | 0.0917 | 0.2106 | | 0.7762 | 0.1696 | 10000 | 0.9314 | 0.0735 | 0.1700 | | 0.7096 | 0.2120 | 12500 | 0.8954 | 0.0627 | 0.1534 | | 0.6205 | 0.2544 | 15000 | 0.7907 | 0.0550 | 0.1378 | | 0.5873 | 0.2968 | 17500 | 0.7408 | 0.0486 | 0.1215 | | 0.5504 | 0.3392 | 20000 | 0.6894 | 0.0427 | 0.1112 | | 0.4826 | 0.3816 | 22500 | 0.6537 | 0.0406 | 0.1042 | | 0.5224 | 0.4240 | 25000 | 0.6245 | 0.0380 | 0.0965 | | 0.4430 | 0.4664 | 27500 | 0.5866 | 0.0366 | 0.0933 | | 0.4219 | 0.5088 | 30000 | 0.5724 | 0.0340 | 0.0873 | | 0.3557 | 0.5512 | 32500 | 0.5586 | 0.0318 | 0.0849 | | 0.3866 | 0.5936 | 35000 | 0.5399 | 0.0328 | 0.0845 | | 0.3586 | 0.6360 | 37500 | 0.5267 | 0.0305 | 0.0793 | | 0.4009 | 0.6784 | 40000 | 0.5082 | 0.0301 | 0.0769 | | 0.3140 | 0.7208 | 42500 | 0.5011 | 0.0289 | 0.0740 | | 0.3435 | 0.7632 | 45000 | 0.4874 | 0.0276 | 0.0725 | | 0.314...

Note1 oct.huggingface.co/cyttic/exp23-directfit-unfrozen

Source context: 173 downloads · 1 likes · Pipeline image-text-to-text · Library transformers · Repo cyttic/exp23-directfit-unfrozen

Note16 juil.huggingface.co/cyttic/exp23-directfit-unfrozen

Source context: 467 downloads · 1 likes · Pipeline image-text-to-text · Library transformers · Repo cyttic/exp23-directfit-unfrozen