fewshot_10 / README.md
eightynine01's picture
End of training
3d82d51 verified
metadata
license: apache-2.0
base_model: ibm/TTM
tags:
  - generated_from_trainer
model-index:
  - name: fewshot_10
    results: []

fewshot_10

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

  • Loss: 0.0405

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: 0.001
  • train_batch_size: 512
  • eval_batch_size: 512
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss
0.1341 1.0 48 0.0386
0.1293 2.0 96 0.0383
0.1268 3.0 144 0.0382
0.1245 4.0 192 0.0382
0.1218 5.0 240 0.0383
0.1188 6.0 288 0.0389
0.1159 7.0 336 0.0395
0.1124 8.0 384 0.0399
0.1088 9.0 432 0.0402
0.105 10.0 480 0.0405

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1