movie-roberta-base-finetuned-movie-p1

This model is a fine-tuned version of thatdramebaazguy/movie-roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3949

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
7.7521	1.0	108	4.7594
4.289	2.0	216	2.8672
2.5416	3.0	324	1.3464
1.2104	4.0	432	0.6174
0.596	5.0	540	0.4700
0.4817	6.0	648	0.4568
0.4701	7.0	756	0.4418
0.4308	8.0	864	0.4774
0.4157	9.0	972	0.4426
0.4256	10.0	1080	0.4752
0.4186	11.0	1188	0.4686
0.4141	12.0	1296	0.4242
0.3786	13.0	1404	0.4166
0.384	14.0	1512	0.4333
0.3734	15.0	1620	0.4548
0.3761	16.0	1728	0.3834
0.3606	17.0	1836	0.3476
0.3556	18.0	1944	0.4258
0.3692	19.0	2052	0.3336
0.3572	20.0	2160	0.4304

Framework versions

• Transformers 4.24.0
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2