finetuningnewmodule4

This model is a fine-tuned version of codellama/CodeLlama-7b-Instruct-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9178

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: 0.001
• 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: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
2.688	1.0	1	2.7462
2.261	2.0	2	2.2006
1.7646	3.0	3	1.9486
1.518	4.0	4	1.7189
1.2896	5.0	5	1.4255
0.9851	6.0	6	1.1951
0.7157	7.0	7	1.0503
0.496	8.0	8	0.9871
0.3614	9.0	9	0.9348
0.2587	10.0	10	0.9178

Framework versions

• Transformers 4.36.0
• Pytorch 2.0.1
• Datasets 2.16.1
• Tokenizers 0.15.1

Training procedure

Framework versions

• PEFT 0.6.0