README.md

metadata

license: apache-2.0
base_model: facebook/hubert-base-ls960
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: hubert-classifier-aug
    results: []

hubert-classifier-aug

This model is a fine-tuned version of facebook/hubert-base-ls960 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.4212
• Accuracy: 0.0162
• Precision: 0.0003
• Recall: 0.0162
• F1: 0.0005
• Binary: 0.1280

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
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Binary
No log	0.19	50	4.4254	0.0135	0.0002	0.0135	0.0004	0.1296
No log	0.38	100	4.4233	0.0135	0.0002	0.0135	0.0004	0.1261
No log	0.58	150	4.4237	0.0135	0.0002	0.0135	0.0004	0.1334
No log	0.77	200	4.4238	0.0135	0.0002	0.0135	0.0004	0.1243
No log	0.96	250	4.4228	0.0135	0.0002	0.0135	0.0004	0.1353
No log	1.15	300	4.4205	0.0135	0.0002	0.0135	0.0004	0.1216
No log	1.34	350	4.4226	0.0135	0.0002	0.0135	0.0004	0.1334
No log	1.53	400	4.4220	0.0135	0.0002	0.0135	0.0004	0.1334
No log	1.73	450	4.4209	0.0135	0.0002	0.0135	0.0004	0.1353
4.4255	1.92	500	4.4212	0.0162	0.0003	0.0162	0.0005	0.1280
4.4255	2.11	550	4.4219	0.0135	0.0002	0.0135	0.0004	0.1334
4.4255	2.3	600	4.4211	0.0135	0.0002	0.0135	0.0004	0.1315
4.4255	2.49	650	4.4216	0.0135	0.0002	0.0135	0.0004	0.1334
4.4255	2.68	700	4.4216	0.0135	0.0002	0.0135	0.0004	0.1334
4.4255	2.88	750	4.4216	0.0162	0.0003	0.0162	0.0005	0.1280
4.4255	3.07	800	4.4211	0.0162	0.0003	0.0162	0.0005	0.1280
4.4255	3.26	850	4.4215	0.0135	0.0002	0.0135	0.0004	0.1315

Framework versions

• Transformers 4.38.2
• Pytorch 2.3.0
• Datasets 2.19.1
• Tokenizers 0.15.1