xlm-roberta-base_seed42_esp-hau-eng_train

shanhy/xlm-roberta-base_seed42_esp-hau-eng_train

xlm-roberta-base_seed42_esp-hau-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

3% 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 5, 2024
Updated: Feb 5, 2024
SHA: f8464123

Try a prompt

Base models

FacebookAI/xlm-roberta-base

Model card

From the Hugging Face model README

xlm-roberta-base_seed42_esp-hau-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: 0.0152
Spearman Corr: 0.8636

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	0.54	200	0.0275	0.7044
No log	1.08	400	0.0237	0.7348
No log	1.62	600	0.0258	0.7480
0.0358	2.15	800	0.0260	0.7627
0.0358	2.69	1000	0.0337	0.7743
0.0358	3.23	1200	0.0228	0.7731
0.0358	3.77	1400	0.0191	0.7915
0.0212	4.31	1600	0.0302	0.7898
0.0212	4.85	1800	0.0220	0.8003
0.0212	5.38	2000	0.0221	0.8042
0.0212	5.92	2200	0.0247	0.8105
0.0144	6.46	2400	0.0199	0.8130
0.0144	7.0	2600	0.0203	0.8177
0.0144	7.54	2800	0.0261	0.8170
0.0101	8.08	3000	0.0174	0.8251
0.0101	8.61	3200	0.0221	0.8260
0.0101	9.15	3400	0.0220	0.8312
0.0101	9.69	3600	0.0179	0.8316
0.0075	10.23	3800	0.0178	0.8359
0.0075	10.77	4000	0.0220	0.8330
0.0075	11.31	4200	0.0168	0.8409
0.0075	11.84	4400	0.0184	0.8394
0.0059	12.38	4600	0.0182	0.8402
0.0059	12.92	4800	0.0171	0.8390
0.0059	13.46	5000	0.0161	0.8446
0.0048	14.0	5200	0.0179	0.8449
0.0048	14.54	5400	0.0173	0.8456
0.0048	15.07	5600	0.0162	0.8484
0.0048	15.61	5800	0.0180	0.8470
0.0041	16.15	6000	0.0190	0.8500
0.0041	16.69	6200	0.0167	0.8525
0.0041	17.23	6400	0.0159	0.8515
0.0041	17.77	6600	0.0174	0.8526
0.0036	18.3	6800	0.0175	0.8519
0.0036	18.84	7000	0.0158	0.8553
0.0036	19.38	7200	0.0154	0.8551
0.0036	19.92	7400	0.0159	0.8548
0.0032	20.46	7600	0.0165	0.8546
0.0032	21.0	7800	0.0152	0.8570
0.0032	21.53	8000	0.0163	0.8566
0.0029	22.07	8200	0.0150	0.8574
0.0029	22.61	8400	0.0161	0.8574
0.0029	23.15	8600	0.0163	0.8588
0.0029	23.69	8800	0.0156	0.8563
0.0026	24.23	9000	0.0164	0.8594
0.0026	24.76	9200	0.0175	0.8598
0.0026	25.3	9400	0.0145	0.8611
0.0026	25.84	9600	0.0152	0.8623
0.0024	26.38	9800	0.0162	0.8618
0.0024	26.92	10000	0.0155	0.8615
0.0024	27.46	10200	0.0157	0.8615
0.0023	27.99	10400	0.0158	0.8618
0.0023	28.53	10600	0.0147	0.8627
0.0023	29.07	10800	0.0149	0.8632
0.0023	29.61	11000	0.0152	0.8636

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 5, 2024
Updated: Feb 5, 2024