llama-1b-yelp-5

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2241
• Accuracy: 0.4791
• Precision: 0.4724
• Recall: 0.4769
• F1: 0.4736

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: 0.0002
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	0.2559	100	1.6861	0.3415	0.3301	0.3398	0.3321
No log	0.5118	200	1.4513	0.3999	0.4029	0.3957	0.3946
No log	0.7678	300	1.3685	0.4308	0.4189	0.4296	0.4209
No log	1.0230	400	1.3152	0.4474	0.4399	0.4453	0.4403
6.034	1.2790	500	1.2959	0.4547	0.4483	0.4532	0.4471
6.034	1.5349	600	1.2663	0.4616	0.4559	0.4593	0.4566
6.034	1.7908	700	1.2542	0.4674	0.4630	0.4647	0.4626
6.034	2.0461	800	1.2405	0.4729	0.4673	0.4712	0.4684
6.034	2.3020	900	1.2371	0.4783	0.4763	0.4777	0.4753
4.7846	2.5579	1000	1.2266	0.4814	0.4741	0.4803	0.4762
4.7846	2.8138	1100	1.2241	0.4791	0.4724	0.4769	0.4736

Framework versions

• PEFT 0.14.0
• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0