Modelpublic

muhtasham/tiny-mlm-tweet_eval-from-scratch-target-rotten_tomatoes

sourceHugging Faceupdated 4y agoView on Hugging Face

0likes10downloads

Model Card

tiny-mlm-tweeteval-from-scratch-target-rottentomatoes

This model is a fine-tuned version of muhtasham/tiny-mlm-tweet_eval-from-scratch on the None dataset. It achieves the following results on the evaluation set:

—Loss: 1.0877
—Accuracy: 0.7514
—F1: 0.7514

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: 3e-05
—trainbatchsize: 32
—evalbatchsize: 32
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: constant
—training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.6935	1.87	500	0.6934	0.5	0.3333
0.6919	3.75	1000	0.6785	0.5525	0.4670
0.4841	5.62	1500	0.5754	0.7317	0.7316
0.3008	7.49	2000	0.6330	0.7477	0.7477
0.2209	9.36	2500	0.6851	0.7505	0.7505
0.1747	11.24	3000	0.8023	0.7439	0.7434
0.1488	13.11	3500	0.9074	0.7495	0.7495
0.1274	14.98	4000	0.9746	0.7580	0.7577
0.11	16.85	4500	1.0522	0.7448	0.7445
0.0947	18.73	5000	1.0877	0.7514	0.7514

Framework versions

—Transformers 4.26.0.dev0
—Pytorch 1.13.1+cu116
—Datasets 2.8.1.dev0
—Tokenizers 0.13.2