TinyLlama-1.1B-Chat-v1.0-reasoning-sft-full

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

• Loss: 0.9013

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 10
• total_train_batch_size: 40
• 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
0.9354	0.22	92	0.9211
0.8752	1.16	160	0.9013

Framework versions

• Transformers 4.35.0
• Pytorch 2.3.0.dev20231228+rocm5.7
• Datasets 2.14.6
• Tokenizers 0.14.1