distilroberta-base-finetuned-media-right

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

• Loss: 1.2664

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 32
• 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
No log	1.0	148	1.6991
No log	2.0	296	1.6279
No log	3.0	444	1.5855
1.7179	4.0	592	1.5846
1.7179	5.0	740	1.5261
1.7179	6.0	888	1.4618
1.5059	7.0	1036	1.4146
1.5059	8.0	1184	1.4289
1.5059	9.0	1332	1.4022
1.5059	10.0	1480	1.3688
1.3326	11.0	1628	1.3335
1.3326	12.0	1776	1.3669
1.3326	13.0	1924	1.2971
1.1997	14.0	2072	1.3146
1.1997	15.0	2220	1.3336
1.1997	16.0	2368	1.2793
1.1149	17.0	2516	1.2469
1.1149	18.0	2664	1.2395
1.1149	19.0	2812	1.2302
1.1149	20.0	2960	1.2664

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0