README.md

metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
model-index:
  - name: my_model
    results: []

my_model

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 5.9953
• Start Accuracy: 0.5270
• End Accuracy: 0.5270
• Overall Accuracy: 0.5270
• Start Precision: 0.2548
• End Precision: 0.2696
• Start Recall: 0.2307
• End Recall: 0.2805
• Start F1 Score: 0.2338
• End F1 Score: 0.2644

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Start Accuracy	End Accuracy	Overall Accuracy	Start Precision	End Precision	Start Recall	End Recall	Start F1 Score	End F1 Score
0.0302	1.0	22	6.1169	0.5405	0.4865	0.5135	0.2951	0.2569	0.2669	0.2371	0.2732	0.2331
0.0331	2.0	44	6.1384	0.4730	0.4730	0.4730	0.2056	0.2529	0.1692	0.2470	0.1801	0.2376
0.0332	3.0	66	6.0663	0.5135	0.5135	0.5135	0.2168	0.2434	0.1975	0.2619	0.1974	0.2446
0.0341	4.0	88	6.0363	0.5270	0.5270	0.5270	0.2548	0.2696	0.2307	0.2805	0.2338	0.2644
0.0213	5.0	110	5.9953	0.5270	0.5270	0.5270	0.2548	0.2696	0.2307	0.2805	0.2338	0.2644

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2