p-tuning-t2t-gpt2-large-with-sst2

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4929
• Accuracy: 0.7741

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6984	1.0	4210	0.7020	0.5138
0.6766	2.0	8420	0.6971	0.5138
0.5377	3.0	12630	0.5625	0.7087
0.5375	4.0	16840	0.5481	0.7282
0.5209	5.0	21050	0.5278	0.7420
0.5235	6.0	25260	0.5357	0.7374
0.5311	7.0	29470	0.5342	0.7294
0.5545	8.0	33680	0.5135	0.7511
0.5406	9.0	37890	0.5138	0.7397
0.523	10.0	42100	0.5192	0.7580
0.5248	11.0	46310	0.4997	0.7706
0.559	12.0	50520	0.5063	0.7649
0.582	13.0	54730	0.4958	0.7741
0.4796	14.0	58940	0.4981	0.7706
0.4173	15.0	63150	0.4911	0.7626
0.4449	16.0	67360	0.4932	0.7718
0.4697	17.0	71570	0.4917	0.7741
0.3779	18.0	75780	0.4931	0.7729
0.449	19.0	79990	0.4929	0.7729
0.4938	20.0	84200	0.4929	0.7741

Framework versions

• PEFT 0.7.1
• Transformers 4.40.1
• Pytorch 2.5.0
• Datasets 3.0.1
• Tokenizers 0.19.1