CoolFace
Modelpublic

fpadovani/en_child_clm_13_new

sourceHugging Faceupdated 15d agoView on Hugging Face
0likes211downloads
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. -->

enclmchild13new

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: 3.6153

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 log1.395220006.7893
6.7082.790440005.2077
6.7084.185660004.7717
4.59715.580780004.5102
4.59716.9759100004.3320
4.1328.3711120004.1887
4.1329.7663140004.0636
3.854611.1615160003.9553
3.854612.5567180003.8717
3.653913.9519200003.7909
3.653915.3471220003.7243
3.490816.7422240003.6650
3.490818.1374260003.6168
3.35719.5326280003.5736
3.35720.9278300003.5349
3.246322.3230320003.5088
3.246323.7182340003.4850
3.154225.1134360003.4704
3.154226.5085380003.4511
3.074227.9037400003.4367
3.074229.2989420003.4277
2.990930.6941440003.4234
2.990932.0893460003.4258
2.914733.4845480003.4244
2.914734.8797500003.4251
2.846936.2749520003.4327
2.846937.6700540003.4350
2.787639.0652560003.4484
2.787640.4604580003.4517
2.731141.8556600003.4539
2.731143.2508620003.4776
2.679844.6460640003.4786
2.679846.0412660003.4921
2.636747.4363680003.5030
2.636748.8315700003.5099
2.597250.2267720003.5286
2.597251.6219740003.5309
2.560753.0171760003.5419
2.560754.4123780003.5555
2.52455.8075800003.5600
2.52457.2027820003.5688
2.494158.5978840003.5768
2.494159.9930860003.5802
2.46661.3882880003.5930
2.46662.7834900003.5967
2.442864.1786920003.6056
2.442865.5738940003.6085
2.419666.9690960003.6099
2.419668.3641980003.6140
2.401769.75931000003.6153

Framework versions

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