finetuned_distilgpt2_sst2_negation0.01_pretrainedFalse_epochs10

This model is a fine-tuned version of distilgpt2 on the sst2 dataset. It achieves the following results on the evaluation set:

• Loss: 3.5445

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: 2e-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
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
2.6737	1.0	1323	3.2501
2.4583	2.0	2646	3.2498
2.3574	3.0	3969	3.2873
2.2477	4.0	5292	3.3294
2.163	5.0	6615	3.3888
2.1028	6.0	7938	3.4272
2.0517	7.0	9261	3.4665
2.0083	8.0	10584	3.5063
1.9902	9.0	11907	3.5309
1.9722	10.0	13230	3.5445

Framework versions

• Transformers 4.25.1
• Pytorch 1.7.0
• Datasets 2.8.0
• Tokenizers 0.13.2