little-llama-ft-summarize

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

• Loss: 2.1457

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

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
• load_in_4bit: True
• load_in_8bit: False

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.1026	0.6	264	2.1863
1.9835	1.2	528	2.1468
2.3005	1.8	792	2.1325
1.6247	2.4	1056	2.1457

Framework versions

• PEFT 0.5.0
• Transformers 4.38.2
• Pytorch 2.1.0+cu118
• Datasets 2.19.0
• Tokenizers 0.15.2