S1_InstructionGeneratorDelta

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

• Loss: 0.0789

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: 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: 24

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	173	0.1487
No log	2.0	346	0.1222
0.3431	3.0	519	0.1085
0.3431	4.0	692	0.0998
0.3431	5.0	865	0.0949
0.1133	6.0	1038	0.0911
0.1133	7.0	1211	0.0889
0.1133	8.0	1384	0.0873
0.1007	9.0	1557	0.0855
0.1007	10.0	1730	0.0842
0.1007	11.0	1903	0.0831
0.095	12.0	2076	0.0823
0.095	13.0	2249	0.0817
0.095	14.0	2422	0.0810
0.0913	15.0	2595	0.0807
0.0913	16.0	2768	0.0803
0.0913	17.0	2941	0.0800
0.0892	18.0	3114	0.0797
0.0892	19.0	3287	0.0794
0.0892	20.0	3460	0.0793
0.0879	21.0	3633	0.0791
0.0879	22.0	3806	0.0790
0.0879	23.0	3979	0.0790
0.0868	24.0	4152	0.0789

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2