metadata
library_name: peft
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- base_model:adapter:distilbert/distilbert-base-uncased
- lora
- transformers
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: results
results: []
datasets:
- iam-tsr/employ_fdbk
language:
- en
results
This model is a fine-tuned version of distilbert/distilbert-base-uncased on employ feedback dataset. It achieves the following results on the evaluation set:
- Loss: 0.1520
- Accuracy: 0.9423
- Precision: 0.9181
- Recall: 0.9284
- F1: 0.9228
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.1735 | 1.0 | 172 | 0.1631 | 0.9462 | 0.9249 | 0.9297 | 0.9272 |
| 0.1824 | 2.0 | 344 | 0.1619 | 0.9385 | 0.9108 | 0.9308 | 0.9191 |
| 0.1555 | 3.0 | 516 | 0.1520 | 0.9423 | 0.9181 | 0.9284 | 0.9228 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.3.0
- Tokenizers 0.22.2