CoolFace
Modelpublic

sujayC66/PatchTSMixer_Stock_Data

sourceHugging Faceupdated 2y agoView on Hugging Face
1likes15downloads
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. -->

PatchTSMixerStockData

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3020.0154
  • Mse: 905.7340
  • Mae: 24.4882
  • Mape: 0.0316
  • Msle: 0.0014

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: 32
  • evalbatchsize: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lrschedulertype: linear
  • num_epochs: 10

Training results

Training LossEpochStepValidation LossMseMaeMapeMsle
21551.85051.0514541.3184464.591218.14780.02300.0008
17948.96322.01023327.9248938.696524.42460.03150.0015
15434.53923.01533385.0327682.479520.86180.02690.0011
13608.9244.02043158.7266917.112223.93370.03090.0015
11935.1855.02553245.8347712.854621.46480.02770.0011
11173.74266.03062985.52561128.743827.58070.03550.0018
11160.51847.03572942.48491075.286927.01850.03480.0017
10815.64348.04082908.75291069.917727.01180.03480.0017
10287.60669.04592995.2012947.197624.98320.03220.0015
10123.273910.05103020.0154905.734024.48820.03160.0014

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2