Aller au contenu
ModelVérifiéExterne
Télécharger

Child Mlm 13 Age 6 English13000

This model is a fine-tuned version of []( on an unknown dataset. It achieves the following results on the evaluation set: Loss: 2.5507

TypeOtherModèle de baseRoBERTaVersionRevision 312dfbcÉditeur@HaerimCClasse

Source du modèle

Type
Other
Taille du fichier
66,3 MB
Modèle de base
RoBERTa
Version
vRevision 312dfbc
Mis à jour
2 oct. 2026
Éditeur
@Haerim
Téléchargements
9
Source
Hugging Face

Description de la source

child_mlm_13_age_6_english13000

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5507

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: 16
  • eval_batch_size: 16
  • seed: 13
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 40000
  • training_steps: 100000
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation Loss
7.93783.424720007.4307
6.00256.849340006.1396
5.809710.274060005.9920
5.713.698680005.8852
5.622917.1233100005.8101
5.570720.5479120005.7701
5.532523.9726140005.7250
5.510327.3973160005.7187
5.492630.8219180005.6950
5.477934.2466200005.6617
5.466737.6712220005.6535
5.454941.0959240005.6407
5.44744.5205260005.6238
5.442747.9452280005.6281
5.435751.3699300005.5902
5.427354.7945320005.6042
5.415358.2192340005.6070
5.404461.6438360005.5724
5.373265.0685380005.4713
4.047568.4932400003.9169
3.373671.9178420003.4696
3.121675.3425440003.2897
2.966278.7671460003.1836
2.861182.1918480003.0630
2.773585.6164500003.0043
2.702589.0411520002.9556
2.643792.4658540002.8897
2.593695.8904560002.8629
2.548899.3151580002.8152
2.5126102.7397600002.7620
2.4775106.1644620002.7396
2.4513109.5890640002.7507
2.4252113.0137660002.7198
2.4018116.4384680002.6986
2.3774119.8630700002.6626
2.3545123.2877720002.6517
2.3371126.7123740002.6366
2.3236130.1370760002.6254
2.3079133.5616780002.6190
2.2943136.9863800002.6061
2.2799140.4110820002.5938
2.2743143.8356840002.5870
2.2689147.2603860002.5730
2.2521150.6849880002.5595
2.2445154.1096900002.5722
2.2372157.5342920002.5529
2.2323160.9589940002.5445
2.2302164.3836960002.5487
2.2246167.8082980002.5398
2.2226171.23291000002.5507

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.11.0+cu128
  • Datasets 3.0.1
  • Tokenizers 0.20.1

Sources

1 source
Hugging FacePrincipalVersion 312dfbca40e82ee83da522257903c5c94ba873cf
huggingface.co/Haerim/child_mlm_13_age_6_english13000/tree/312dfbca40e82ee83da522257903c5c94ba873cf

Vérifié 2 oct.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 66,3 MB · SHA-256 08b885380989…b998 · Hugging Face

Télécharger

Extraits de sources

3 extraits

--- library_name: transformers tags: - generated_from_trainer model-index: - name: child_mlm_13_age_6_english13000 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. --> # child_mlm_13_age_6_english13000 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.5507 ## 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: 16 - eval_batch_size: 16 - seed: 13 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 40000 - training_steps: 100000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:--------:|:------:|:---------------:| | 7.9378 | 3.4247 | 2000 | 7.4307 | | 6.0025 | 6.8493 | 4000 | 6.1396 | | 5.8097 | 10.2740 | 6000 | 5.9920 | | 5.7 | 13.6986 | 8000 | 5.8852 | | 5.6229 | 17.1233 | 10000 | 5.8101 | | 5.5707 | 20.5479 | 12000 | 5.7701 | | 5.5325 | 23.9726 | 14000 | 5.7250 | | 5.5103 | 27.3973 | 16000 | 5.7187 | | 5.4926 | 30.8219 | 18000 | 5.6950 | | 5.4779 | 34.2466 | 20000 | 5.6617 | | 5.4667 | 37.6712 | 22000 | 5.6535 | | 5.4549 | 41.0959 | 24000 | 5.6407 | | 5.447 | 44.5205 | 26000 | 5.6238 | | 5.4427 | 47.9452 | 28000 | 5.6281 | | 5.4357 | 51.3699 | 30000 | 5.5902 | | 5.4273 | 54.7945 | 32000 | 5.6042 | | 5.4153 | 58.2192 | 34000 | 5.6070 | | 5.4044 | 61.6438 | 36000 | 5.5724 | | 5.3732 | 65.0685 | 38000 | 5.4713 | | 4.0475 | 68.4932 | 40000 | 3.9169 | | 3.3736 | 71.9178 | 42000 | 3.4696 | | 3.1216 | 75.3425 | 44000 | 3.2897 | | 2.9662 | 78.7671 | 46000 | 3.1836 | | 2.8611 | 82.1918 | 48000 | 3.0630 | | 2.7735 | 85.6164 | 50000 | 3.0043 | | 2.7025 | 89.0411 | 52000 | 2.9556 | | 2.6437 | 92.4658 | 54000 | 2.8897 | | 2.5936 | 95.8904 | 56000 | 2.8629 | | 2.5488 | 99.3151 | 58000 | 2.8152 | | 2.5126 | 102.7397 | 60000 | 2.7620 | | 2.4775 | 106.164...

Source context: 9 downloads · 0 likes · Pipeline fill-mask · Library transformers · Repo Haerim/child_mlm_13_age_6_english13000

Source context: 2 downloads · 0 likes · Pipeline fill-mask · Library transformers · Repo Haerim/child_mlm_13_age_6_english13000