test0901-5

This model is a fine-tuned version of Qwen/Qwen2-1.5B-Instruct on the identity and the alpaca_en_demo datasets. It achieves the following results on the evaluation set:

• Loss: 1.8424

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
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0082	1	2.0249
No log	0.0163	2	2.0155
No log	0.0245	3	1.9926
No log	0.0326	4	1.9594
No log	0.0408	5	1.9194
No log	0.0489	6	1.8850
No log	0.0571	7	1.8630
No log	0.0652	8	1.8497
No log	0.0734	9	1.8417
1.6809	0.0815	10	1.8424

Framework versions

• PEFT 0.12.0
• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1