README.md

metadata

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

empathy_model

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0043
• Mse: 0.0043

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: 5e-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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Mse
0.0109	0.05	50	0.0050	0.0050
0.0063	0.11	100	0.0092	0.0092
0.0074	0.16	150	0.0045	0.0045
0.0056	0.22	200	0.0060	0.0060
0.0082	0.27	250	0.0046	0.0046
0.0055	0.32	300	0.0056	0.0056
0.0061	0.38	350	0.0045	0.0045
0.0079	0.43	400	0.0060	0.0060
0.0061	0.48	450	0.0043	0.0043
0.0078	0.54	500	0.0046	0.0046
0.0066	0.59	550	0.0043	0.0043
0.0055	0.65	600	0.0044	0.0044
0.0059	0.7	650	0.0043	0.0043
0.0048	0.75	700	0.0056	0.0056
0.0051	0.81	750	0.0043	0.0043
0.0046	0.86	800	0.0043	0.0043
0.0055	0.92	850	0.0043	0.0043
0.0053	0.97	900	0.0043	0.0043

Framework versions

• Transformers 4.39.1
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2