xlm-roberta-base_seed42_amh-esp-eng_train

shanhy/xlm-roberta-base_seed42_amh-esp-eng_train

xlm-roberta-base_seed42_amh-esp-eng_train is a text classification model from shanhy. 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

6% of all-time downloads

All-time downloads

Public

Parameters

278M

1.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.1 GB · 98%

At a glance

Task: Text Classification
Library: transformers
License: mit
Model type: xlm-roberta
Access: Public
Created: Feb 4, 2024
Updated: Feb 4, 2024
SHA: 8e6dd194

Try a prompt

Base models

FacebookAI/xlm-roberta-base

Model card

From the Hugging Face model README

xlm-roberta-base_seed42_amh-esp-eng_train

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0135
Spearman Corr: 0.8691

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: 32
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Spearman Corr
No log	0.59	200	0.0224	0.7379
No log	1.18	400	0.0205	0.7553
No log	1.76	600	0.0180	0.7818
0.0324	2.35	800	0.0208	0.7870
0.0324	2.94	1000	0.0182	0.8010
0.0324	3.53	1200	0.0172	0.7997
0.0183	4.12	1400	0.0219	0.8139
0.0183	4.71	1600	0.0158	0.8185
0.0183	5.29	1800	0.0165	0.8202
0.0183	5.88	2000	0.0158	0.8289
0.0125	6.47	2200	0.0213	0.8286
0.0125	7.06	2400	0.0163	0.8298
0.0125	7.65	2600	0.0187	0.8337
0.0088	8.24	2800	0.0162	0.8387
0.0088	8.82	3000	0.0155	0.8397
0.0088	9.41	3200	0.0155	0.8421
0.0065	10.0	3400	0.0172	0.8443
0.0065	10.59	3600	0.0167	0.8486
0.0065	11.18	3800	0.0147	0.8501
0.0065	11.76	4000	0.0145	0.8515
0.005	12.35	4200	0.0144	0.8548
0.005	12.94	4400	0.0158	0.8554
0.005	13.53	4600	0.0176	0.8516
0.0041	14.12	4800	0.0182	0.8549
0.0041	14.71	5000	0.0138	0.8580
0.0041	15.29	5200	0.0154	0.8572
0.0041	15.88	5400	0.0150	0.8600
0.0036	16.47	5600	0.0134	0.8612
0.0036	17.06	5800	0.0138	0.8628
0.0036	17.65	6000	0.0146	0.8619
0.0031	18.24	6200	0.0134	0.8656
0.0031	18.82	6400	0.0142	0.8641
0.0031	19.41	6600	0.0130	0.8648
0.0028	20.0	6800	0.0131	0.8648
0.0028	20.59	7000	0.0142	0.8660
0.0028	21.18	7200	0.0149	0.8637
0.0028	21.76	7400	0.0138	0.8662
0.0025	22.35	7600	0.0135	0.8661
0.0025	22.94	7800	0.0130	0.8673
0.0025	23.53	8000	0.0128	0.8652
0.0023	24.12	8200	0.0133	0.8677
0.0023	24.71	8400	0.0134	0.8669
0.0023	25.29	8600	0.0131	0.8679
0.0023	25.88	8800	0.0128	0.8687
0.0021	26.47	9000	0.0139	0.8692
0.0021	27.06	9200	0.0133	0.8690
0.0021	27.65	9400	0.0133	0.8686
0.002	28.24	9600	0.0135	0.8691

Framework versions

Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1

Task: Text Classification
Library: transformers
Type: xlm-roberta
License: mit
Created: Feb 4, 2024
Updated: Feb 4, 2024