Groq_Llama-3-Tool-Use-VisitorRequest-Lora

This model is a fine-tuned version of Groq/Llama-3-Groq-8B-Tool-Use on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6920

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: 0.0003
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
2.3852	0.0635	1	5.9455
5.9202	0.1270	2	2.0524
2.1422	0.1905	3	1.2710
1.32	0.2540	4	1.1640
1.1839	0.3175	5	0.8947
0.9042	0.3810	6	0.9210
0.8737	0.4444	7	0.8815
0.8936	0.5079	8	0.7752
0.7229	0.5714	9	0.7938
0.8039	0.6349	10	0.8019
0.8014	0.6984	11	0.7562
0.749	0.7619	12	0.7280
0.71	0.8254	13	0.7346
0.7461	0.8889	14	0.7208
0.6635	0.9524	15	0.7096
0.7271	1.0159	16	0.7038
0.6691	1.0794	17	0.7117
0.6672	1.1429	18	0.7996
0.7766	1.2063	19	0.7333
0.6818	1.2698	20	0.7651
0.684	1.3333	21	0.7110
0.6575	1.3968	22	0.7213
0.6146	1.4603	23	0.7275
0.6245	1.5238	24	0.7908
0.7224	1.5873	25	0.7301
0.6472	1.6508	26	0.7082
0.6066	1.7143	27	0.7114
0.6735	1.7778	28	0.6984
0.6263	1.8413	29	0.6899
0.5998	1.9048	30	0.6920

Framework versions

• PEFT 0.5.0
• Transformers 4.44.0
• Pytorch 2.1.0+cu118
• Datasets 2.16.0
• Tokenizers 0.19.1