Tukan-1.1B-Chat-v0.1

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: 1.0546

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: 6
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 36
• total_train_batch_size: 216
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.1912	0.28	10	1.1099
1.1238	0.55	20	1.0655
1.1258	0.83	30	1.0550

Framework versions

• Transformers 4.36.2
• Pytorch 2.2.0a0+gitd925d94
• Datasets 2.14.6
• Tokenizers 0.15.0

Training procedure

The following bitsandbytes quantization config was used during training:

• quant_method: bitsandbytes
• load_in_8bit: False
• load_in_4bit: True
• 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: nf4
• bnb_4bit_use_double_quant: False
• bnb_4bit_compute_dtype: float16

Framework versions

• PEFT 0.6.1