CoolFace
Modelpublic

fpadovani/fr_child_clm_13_new

sourceHugging Faceupdated 13d agoView on Hugging Face
0likes183downloads
Model Card

<!-- 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. -->

frchildes13

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: 4.1486

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
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 13
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 32
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 40000
  • —training_steps: 100000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
No log2.520006.5946
6.54055.040004.9064
6.54057.560004.4605
4.29910.080004.2033
4.29912.5100004.0186
3.82215.0120003.8741
3.82217.5140003.7604
3.547920.0160003.6693
3.547922.5180003.5906
3.347425.0200003.5266
3.347427.5220003.4638
3.18130.0240003.4185
3.18132.5260003.3846
3.036635.0280003.3463
3.036637.5300003.3321
2.908940.0320003.3173
2.908942.5340003.3138
2.791445.0360003.3038
2.791447.5380003.3271
2.678250.0400003.3318
2.678252.5420003.3629
2.55755.0440003.3741
2.55757.5460003.4272
2.432560.0480003.4358
2.432562.5500003.4926
2.321265.0520003.5152
2.321267.5540003.5673
2.221370.0560003.5919
2.221372.5580003.6468
2.132775.0600003.6684
2.132777.5620003.7214
2.054380.0640003.7451
2.054382.5660003.7884
1.983785.0680003.8071
1.983787.5700003.8546
1.921290.0720003.8746
1.921292.5740003.9187
1.864695.0760003.9305
1.864697.5780003.9732
1.8139100.0800003.9957
1.8139102.5820004.0264
1.768105.0840004.0383
1.768107.5860004.0636
1.7271110.0880004.0798
1.7271112.5900004.1051
1.6909115.0920004.1140
1.6909117.5940004.1260
1.6597120.0960004.1355
1.6597122.5980004.1469
1.6341125.01000004.1486

Framework versions

  • —Transformers 4.45.2
  • —Pytorch 2.5.1+cu124
  • —Datasets 3.0.1
  • —Tokenizers 0.20.1