fresh-2-layer-swag

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.2180
• Accuracy: 0.3081

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: 0.0005
• train_batch_size: 16
• eval_batch_size: 16
• seed: 321
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	63	1.3858	0.2172
No log	2.0	126	1.3860	0.2273
No log	3.0	189	1.4008	0.2424
No log	4.0	252	1.6880	0.2121
No log	5.0	315	1.7630	0.2222
No log	6.0	378	2.2180	0.3081
No log	7.0	441	2.7238	0.2727
0.7342	8.0	504	2.2261	0.2424
0.7342	9.0	567	3.3632	0.2475
0.7342	10.0	630	2.8625	0.2525
0.7342	11.0	693	2.8340	0.2677
0.7342	12.0	756	3.2504	0.2374
0.7342	13.0	819	3.2605	0.2727
0.7342	14.0	882	3.6696	0.2525
0.7342	15.0	945	3.5670	0.2374
0.0282	16.0	1008	3.8346	0.2677
0.0282	17.0	1071	3.7978	0.2727
0.0282	18.0	1134	3.7438	0.2677
0.0282	19.0	1197	3.7843	0.2727
0.0282	20.0	1260	3.8037	0.2626

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.14.0