metadata

library_name: transformers
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: distilhubert-finetuned-pulse
    results: []

distilhubert-finetuned-pulse

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6972	1.0	31	0.6880	0.7143
0.703	2.0	62	0.6044	0.7143
0.6737	3.0	93	0.6217	0.7143
0.6756	4.0	124	0.6400	0.7143
0.6557	5.0	155	0.6213	0.7143
0.6778	6.0	186	0.6109	0.7143
0.6884	7.0	217	0.6415	0.7143
0.6364	8.0	248	0.6205	0.7143
0.6506	9.0	279	0.6171	0.7143
0.675	10.0	310	0.6139	0.7143
0.7018	11.0	341	0.6145	0.7143
0.6766	12.0	372	0.6099	0.7143
0.6493	13.0	403	0.6131	0.7143
0.6482	14.0	434	0.6138	0.7143
0.8036	15.0	465	0.6143	0.7143