roberta_base_results_2epochs

aoiferyan/roberta_base_results_2epochs

roberta_base_results_2epochs is a machine learning model from aoiferyan. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

15% of all-time downloads

All-time downloads

Public

Parameters

125M

3.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors499 MB · 100%

At a glance

License: mit
Model type: roberta
Access: Public
Created: Aug 22, 2024
Updated: Aug 22, 2024
SHA: bf57bc16

Base models

Model card

From the Hugging Face model README

roberta_base_results_2epochs

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

Loss: 0.6705
Accuracy: 0.8601
F1: 0.8589

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: 2
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.6763	0.0665	100	0.6149	0.5616	0.4039
0.4831	0.1331	200	0.8667	0.8266	0.8265
0.7656	0.1996	300	0.6957	0.8365	0.8321
0.8072	0.2661	400	1.1110	0.7764	0.7764
0.9597	0.3327	500	0.6359	0.8463	0.8457
0.5777	0.3992	600	0.7802	0.8443	0.8395
0.7226	0.4657	700	0.6153	0.8463	0.8458
0.7251	0.5323	800	0.7543	0.8404	0.8354
0.6586	0.5988	900	0.7304	0.8532	0.8502
0.6317	0.6653	1000	0.6227	0.8493	0.8482
0.6521	0.7319	1100	0.7053	0.8532	0.8490
0.5705	0.7984	1200	0.6369	0.8522	0.8515
0.8068	0.8649	1300	0.6535	0.8542	0.8535
0.6352	0.9315	1400	0.6711	0.8581	0.8544
0.6513	0.9980	1500	0.5913	0.8562	0.8546
0.5112	1.0645	1600	0.7082	0.8532	0.8530
0.4838	1.1311	1700	0.7106	0.8562	0.8541
0.4395	1.1976	1800	0.7028	0.8591	0.8576
0.6081	1.2641	1900	0.6388	0.8640	0.8636
0.6623	1.3307	2000	0.5702	0.8640	0.8628
0.5791	1.3972	2100	0.6550	0.8512	0.8515
0.5325	1.4637	2200	0.6143	0.8611	0.8607
0.5463	1.5303	2300	0.6260	0.8591	0.8588
0.5808	1.5968	2400	0.6129	0.8640	0.8630
0.4971	1.6633	2500	0.6283	0.8631	0.8623
0.6488	1.7299	2600	0.6144	0.8650	0.8640
0.5676	1.7964	2700	0.6394	0.8611	0.8607
0.2673	1.8629	2800	0.6781	0.8631	0.8617
0.5348	1.9295	2900	0.6731	0.8621	0.8607
0.4889	1.9960	3000	0.6705	0.8601	0.8589

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Type: roberta
License: mit
Created: Aug 22, 2024
Updated: Aug 22, 2024