roberta

AlekseyKorshuk/roberta

roberta is a text classification model from AlekseyKorshuk. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.

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

Downloads · 30 days

3% of all-time downloads

All-time downloads

339

Public

Repo size

29.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin711 MB · 100%

At a glance

Task: Text Classification
Library: transformers
License: mit
Model type: roberta
Access: Public
Created: Mar 19, 2023
Updated: May 13, 2023
SHA: af62b8b3

Try a prompt

Model card

From the Hugging Face model README

roberta

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

Loss: 1.5264
Ndcg: 0.4471
Accuracy: 0.2959

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 64
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Ndcg	Accuracy
1.5844	0.07	413	1.5508	0.4255	0.2786
1.5709	0.13	826	1.5537	0.4204	0.2854
1.5581	0.2	1239	1.5557	0.4252	0.2777
1.5723	0.27	1652	1.5498	0.4329	0.2833
1.5543	0.33	2065	1.5430	0.4272	0.2872
1.549	0.4	2478	1.5391	0.4371	0.2899
1.5527	0.47	2891	1.5420	0.4328	0.2838
1.5583	0.53	3304	1.5430	0.4371	0.2882
1.537	0.6	3717	1.5371	0.4395	0.2904
1.5381	0.67	4130	1.5410	0.4391	0.2897
1.5876	0.73	4543	1.7871	0.3264	0.2005
1.5573	0.8	4956	1.5430	0.4400	0.2917
1.5577	0.87	5369	1.5576	0.4319	0.2830
1.5398	0.93	5782	1.5557	0.4140	0.2657
1.5414	1.0	6195	1.5986	0.4037	0.2617
1.5439	1.07	6608	1.5459	0.4303	0.2834
1.5344	1.13	7021	1.5439	0.4325	0.2838
1.544	1.2	7434	1.5498	0.4335	0.2861
1.5414	1.27	7847	1.5342	0.4422	0.2910
1.5358	1.33	8260	1.5312	0.4428	0.2940
1.5347	1.4	8673	1.5303	0.4457	0.2955
1.5305	1.47	9086	1.5283	0.4454	0.2944
1.5406	1.53	9499	1.5283	0.4462	0.2952
1.5316	1.6	9912	1.5283	0.4445	0.2949
1.5252	1.67	10325	1.5283	0.4465	0.2958
1.5202	1.73	10738	1.5264	0.4469	0.2949
1.5313	1.8	11151	1.5273	0.4469	0.2959
1.5279	1.87	11564	1.5264	0.4470	0.2963
1.5317	1.93	11977	1.5264	0.4474	0.2964
1.5208	2.0	12390	1.5264	0.4471	0.2959

Framework versions

Transformers 4.29.1
Pytorch 2.0.0-rc1
Datasets 2.12.0
Tokenizers 0.13.3

Task: Text Classification
Library: transformers
Type: roberta
License: mit
Created: Mar 19, 2023
Updated: May 13, 2023