scenario-TCR-XLMV-XCOPA-2_data-xcopa_all

haryoaw/scenario-TCR-XLMV-XCOPA-2_data-xcopa_all

scenario-TCR-XLMV-XCOPA-2_data-xcopa_all is a multiple choice model from haryoaw. Use it for the multiple choice task on the model card, and read the license before you ship it in a product. 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

16% of all-time downloads

All-time downloads

Public

Repo size

9.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin3.1 GB · 98%

At a glance

Task: multiple choice
Library: transformers
License: mit
Model type: xlm-roberta
Access: Public
Created: Mar 8, 2024
Updated: Mar 12, 2024
SHA: a9d30086

Base models

facebook/xlm-v-base

Model card

From the Hugging Face model README

scenario-TCR-XLMV-XCOPA-2_data-xcopa_all

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

Loss: 0.6931
Accuracy: 0.5
F1: 0.4671

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: 32
eval_batch_size: 32
seed: 34
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.38	5	0.6932	0.4858	0.4767
No log	0.77	10	0.6931	0.515	0.5134
No log	1.15	15	0.6931	0.5158	0.5038
No log	1.54	20	0.6931	0.5108	0.5021
No log	1.92	25	0.6931	0.5217	0.5035
No log	2.31	30	0.6931	0.525	0.5069
No log	2.69	35	0.6931	0.5283	0.5070
No log	3.08	40	0.6931	0.5292	0.5125
No log	3.46	45	0.6931	0.5333	0.5122
No log	3.85	50	0.6930	0.5125	0.4970
No log	4.23	55	0.6930	0.5342	0.5251
No log	4.62	60	0.6931	0.5417	0.5217
No log	5.0	65	0.6931	0.5592	0.5482
No log	5.38	70	0.6931	0.5667	0.5517
No log	5.77	75	0.6931	0.5458	0.5362
No log	6.15	80	0.6931	0.535	0.5311
No log	6.54	85	0.6930	0.5433	0.5276
No log	6.92	90	0.6931	0.5025	0.4731
No log	7.31	95	0.6931	0.505	0.4715
No log	7.69	100	0.6931	0.5017	0.4514
No log	8.08	105	0.6931	0.5042	0.4831
No log	8.46	110	0.6931	0.5058	0.4785
No log	8.85	115	0.6931	0.5158	0.4872
No log	9.23	120	0.6931	0.5158	0.4890
No log	9.62	125	0.6931	0.5075	0.4829
No log	10.0	130	0.6931	0.505	0.4780
No log	10.38	135	0.6931	0.5	0.4709
No log	10.77	140	0.6931	0.485	0.4579
No log	11.15	145	0.6931	0.4858	0.4592
No log	11.54	150	0.6931	0.485	0.4569
No log	11.92	155	0.6931	0.4917	0.4611
No log	12.31	160	0.6931	0.4908	0.4664
No log	12.69	165	0.6931	0.4858	0.4602
No log	13.08	170	0.6931	0.4983	0.4756
No log	13.46	175	0.6931	0.4992	0.4788
No log	13.85	180	0.6931	0.4942	0.4717
No log	14.23	185	0.6931	0.4958	0.4735
No log	14.62	190	0.6931	0.5017	0.48
No log	15.0	195	0.6931	0.4942	0.4633
No log	15.38	200	0.6931	0.4942	0.4527
No log	15.77	205	0.6931	0.4925	0.4509
No log	16.15	210	0.6931	0.495	0.4570
No log	16.54	215	0.6931	0.4933	0.4581
No log	16.92	220	0.6931	0.5	0.4671

Framework versions

Transformers 4.33.3
Pytorch 2.1.1+cu121
Datasets 2.14.5
Tokenizers 0.13.3

Task: multiple choice
Library: transformers
Type: xlm-roberta
License: mit
Created: Mar 8, 2024
Updated: Mar 12, 2024