Views
No views yet
1dataset:
2- name: mervinpraison/harup-fall-axis-alpaca
3dataset_num_proc: 2
4dataset_text_field: text
5gradient_accumulation_steps: 2
6hf_model_name: mervinpraison/llama3.2-3B-harupfall-axis
7huggingface_save: 'true'
8learning_rate: 0.0001
9load_in_4bit: true
10loftq_config: null
11logging_steps: 15
12lora_alpha: 16
13lora_bias: none
14lora_dropout: 0
15lora_r: 16
16lora_target_modules:
17- q_proj
18- k_proj
19- v_proj
20- o_proj
21- gate_proj
22- up_proj
23- down_proj
24lr_scheduler_type: linear
25max_seq_length: 2048
26max_steps: 6000
27model_name: unsloth/Llama-3.2-3B-Instruct-bnb-4bit
28model_parameters: 3b
29num_train_epochs: 10
30ollama_model: mervinpraison/llama3.2-3B-harupfall-axis
31ollama_save: 'true'
32optim: lion_8bit
33output_dir: outputs
34packing: false
35per_device_train_batch_size: 1
36quantization_method:
37- q4_k_m
38random_state: 3407
39seed: 3407
40train: 'true'
41use_gradient_checkpointing: unsloth
42use_rslora: false
43warmup_steps: 100
44weight_decay: 0.05