TinyLlama-1.1B-Chat-v1.0-reasoning-v2

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 1.0186

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: 4e-05
• train_batch_size: 10
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 10
• total_train_batch_size: 100
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
1.0456	1.0	347	1.0360
0.9714	2.0	695	1.0180
0.9335	3.0	1042	1.0176
0.9348	3.99	1388	1.0186

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.15.0