openaccess-ai-collective/tinyllama-airoboros

airoboros-lora-out

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T on the jondurbin/airoboros-3.1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7230

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

https://wandb.ai/wing-lian/airoboros-tinyllama

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 16
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.999,0.95) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.9777	0.0	1	1.0628
0.6566	0.5	379	0.7230

Framework versions

• Transformers 4.36.2
• Pytorch 2.0.1+cu117
• Datasets 2.16.0
• Tokenizers 0.15.0

Training procedure

The following bitsandbytes quantization config was used during training:

• quant_method: bitsandbytes
• load_in_8bit: True
• load_in_4bit: False
• llm_int8_threshold: 6.0
• llm_int8_skip_modules: None
• llm_int8_enable_fp32_cpu_offload: False
• llm_int8_has_fp16_weight: False
• bnb_4bit_quant_type: fp4
• bnb_4bit_use_double_quant: False
• bnb_4bit_compute_dtype: float32

Framework versions

• PEFT 0.6.0