2881d5f1-d13c-46c4-81bf-9eaf30b70da4

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

• Loss: 0.7602

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: 0.000202
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0000	1	1.1155
0.9016	0.0025	50	0.8417
0.8241	0.0050	100	0.8312
0.8734	0.0075	150	0.8162
0.8532	0.0100	200	0.8077
0.8097	0.0125	250	0.7950
0.8244	0.0149	300	0.7856
0.8286	0.0174	350	0.7753
0.7971	0.0199	400	0.7664
0.8052	0.0224	450	0.7621
0.7977	0.0249	500	0.7602

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1