tinyllama-sft-wizardlm_evol_instruct_v2-mix

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the ucla-cmllab/WizardLM_evol_instruct_V2_100k-chat-format and the ucla-cmllab/RedPajama_100k datasets. It achieves the following results on the evaluation set:

• Loss: 0.7211

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: 16
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• total_eval_batch_size: 32
• 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
0.711	0.9994	781	0.7211

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1