fine-tuning-code_llama_lib_4

This model is a fine-tuned version of codellama/CodeLlama-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1215

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: 5e-05
• train_batch_size: 3
• eval_batch_size: 3
• seed: 42
• gradient_accumulation_steps: 5
• total_train_batch_size: 15
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 60
• num_epochs: 11
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.7737	1.0	63	0.6034
0.4194	2.0	126	0.3423
0.2123	3.0	189	0.2168
0.1542	4.0	252	0.1721
0.1343	5.0	315	0.1508
0.1224	6.0	378	0.1395
0.1141	7.0	441	0.1321
0.1075	8.0	504	0.1273
0.1028	9.0	567	0.1243
0.0993	10.0	630	0.1220
0.0973	11.0	693	0.1215

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.1.2
• Datasets 2.15.0
• Tokenizers 0.15.2