lora-roberta-large-0927

anniew666/lora-roberta-large-0927

lora-roberta-large-0927 is a machine learning model from anniew666. 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

Access

Public

Updated Sep 27, 2023

Repo size

74.1 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin7.4 MB · 68%

At a glance

License: mit
Access: Public
Created: Sep 27, 2023
Updated: Sep 27, 2023
SHA: 43a81737

Base models

Model card

From the Hugging Face model README

lora-roberta-large-0927

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

Loss: 1.5366
Accuracy: 0.4472
Prec: 0.2000
Recall: 0.4472
F1: 0.2763
B Acc: 0.1429
Micro F1: 0.4472
Prec Joy: 0.0
Recall Joy: 0.0
F1 Joy: 0.0
Prec Anger: 0.0
Recall Anger: 0.0
F1 Anger: 0.0
Prec Disgust: 0.0
Recall Disgust: 0.0
F1 Disgust: 0.0
Prec Fear: 0.0
Recall Fear: 0.0
F1 Fear: 0.0
Prec Neutral: 0.4472
Recall Neutral: 1.0
F1 Neutral: 0.6180
Prec Sadness: 0.0
Recall Sadness: 0.0
F1 Sadness: 0.0
Prec Surprise: 0.0
Recall Surprise: 0.0
F1 Surprise: 0.0

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: 0.001
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.05
num_epochs: 25.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Prec	Recall	F1	B Acc	Micro F1	Prec Neutral	Recall Neutral	F1 Neutral
0.8381	1.25	2092	1.5415	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4866	2.5	4184	1.5564	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4862	3.75	6276	1.5700	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4762	5.0	8368	1.5391	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4765	6.25	10460	1.5566	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4848	7.5	12552	1.5411	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4782	8.75	14644	1.5548	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4943	10.0	16736	1.6115	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4801	11.25	18828	1.5424	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4946	12.5	20920	1.5637	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4867	13.75	23012	1.5492	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4957	15.01	25104	1.5812	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4913	16.26	27196	1.5425	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.5007	17.51	29288	1.5446	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4919	18.76	31380	1.5616	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4895	20.01	33472	1.5502	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4946	21.26	35564	1.5398	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4754	22.51	37656	1.5307	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180
1.4824	23.76	39748	1.5356	0.4472	0.2000	0.4472	0.2763	0.1429	0.4472	0.4472	1.0	0.6180

Framework versions

Transformers 4.33.1
Pytorch 2.0.1
Datasets 2.12.0
Tokenizers 0.13.3

License: mit
Created: Sep 27, 2023
Updated: Sep 27, 2023