DeGrimer/finetune_rag_t_lite

tmp

This model is a fine-tuned version of t-bank-ai/T-lite-instruct-0.1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0736

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: 8e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 3
• training_steps: 20

Training results

Training Loss	Epoch	Step	Validation Loss
1.0658	0.0002	1	1.0817
0.9432	0.0004	2	1.0814
1.1006	0.0006	3	1.0809
0.8838	0.0008	4	1.0801
1.1528	0.0010	5	1.0793
0.8889	0.0012	6	1.0786
1.1655	0.0014	7	1.0780
1.0079	0.0016	8	1.0774
1.1685	0.0018	9	1.0768
1.1659	0.0020	10	1.0763
1.1395	0.0022	11	1.0758
0.9426	0.0024	12	1.0753
0.9772	0.0026	13	1.0750
1.3758	0.0028	14	1.0746
0.7022	0.0030	15	1.0743
1.5761	0.0032	16	1.0741
1.2847	0.0034	17	1.0739
1.1528	0.0036	18	1.0737
0.8362	0.0038	19	1.0736
0.9096	0.0040	20	1.0736

Framework versions

• PEFT 0.13.2
• Transformers 4.45.2
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0