Llams_3.1_8B_instruct_behaviour_cloning_extra_things_updated_grouped

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1928
• Model Preparation Time: 0.0065

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: True
• bnb_4bit_compute_dtype: bfloat16
• bnb_4bit_quant_storage: uint8
• load_in_4bit: True
• load_in_8bit: False

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
0.0929	0.9996	1236	0.1423	0.0065
0.0689	2.0	2473	0.1724	0.0065
0.0588	2.9988	3708	0.1928	0.0065

Framework versions

• PEFT 0.4.0
• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.13.0
• Tokenizers 0.19.1