clip-roberta-finetuned

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

• Loss: 3.8931

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0625	1	4.1028
No log	0.125	2	4.0244
No log	0.1875	3	4.1433
No log	0.25	4	4.1734
No log	0.3125	5	4.0117
No log	0.375	6	4.0110
No log	0.4375	7	4.0414
No log	0.5	8	4.0101
No log	0.5625	9	4.0082
No log	0.625	10	3.9981
No log	0.6875	11	3.9941
No log	0.75	12	3.9959
No log	0.8125	13	3.9887
No log	0.875	14	3.9827
No log	0.9375	15	3.9799
No log	1.0	16	3.9809
No log	1.0625	17	3.9647
No log	1.125	18	3.9486
No log	1.1875	19	3.9439
No log	1.25	20	3.9411
No log	1.3125	21	3.9339
No log	1.375	22	3.9402
No log	1.4375	23	3.9650
No log	1.5	24	3.9634
No log	1.5625	25	3.9432
No log	1.625	26	3.9293
No log	1.6875	27	3.9166
No log	1.75	28	3.9063
No log	1.8125	29	3.9020
No log	1.875	30	3.8991
No log	1.9375	31	3.8950
No log	2.0	32	3.8931

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1