saiga13summary_v20LORA

This model is a fine-tuned version of meta-llama/Llama-2-13b-hf on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1261

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: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 10
• total_train_batch_size: 20
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
1.5616	0.8621	20	1.5150
1.2729	1.7241	40	1.3544
1.0355	2.5862	60	1.2262
0.8974	3.4483	80	1.1656
0.7686	4.3103	100	1.1302
0.7841	5.1724	120	1.1226
0.73	6.0345	140	1.1187
0.7067	6.8966	160	1.1217
0.6758	7.7586	180	1.1218
0.6644	8.6207	200	1.1261

Framework versions

• PEFT 0.12.1.dev0
• Transformers 4.45.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.17.1
• Tokenizers 0.19.1