test_0918_upload_3

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct on the identity and the alpaca_en_demo datasets. It achieves the following results on the evaluation set:

• Loss: 1.9728

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: 0.0001
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 2
• total_eval_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.1111	1	2.5265
No log	0.2222	2	2.4336
No log	0.3333	3	2.3057
No log	0.4444	4	2.2072
No log	0.5556	5	2.1376
No log	0.6667	6	2.0650
No log	0.7778	7	2.0119
No log	0.8889	8	1.9691
No log	1.0	9	1.9728

Framework versions

• PEFT 0.12.0
• Transformers 4.45.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1