RADME_fine_f3

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3192

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: 5e-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
• lr_scheduler_warmup_steps: 3
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.3469	0.95	5000	0.3094
0.3102	1.91	10000	0.2894
0.2806	2.86	15000	0.2793
0.2604	3.81	20000	0.2748
0.2414	4.77	25000	0.2756
0.228	5.72	30000	0.2784
0.2139	6.67	35000	0.2815
0.2016	7.63	40000	0.2848
0.1924	8.58	45000	0.2917
0.1802	9.53	50000	0.2954
0.172	10.49	55000	0.3022
0.1646	11.44	60000	0.3085
0.1586	12.4	65000	0.3114
0.1553	13.35	70000	0.3154
0.1509	14.3	75000	0.3192

Framework versions

• Transformers 4.32.1
• Pytorch 2.0.1
• Datasets 2.14.4
• Tokenizers 0.13.3