See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Llama-3.2-1B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
dataset_processes: 12
datasets:
- data_files:
  - /workspace/axolotl/data/asd.json
  ds_type: json
  path: /workspace/axolotl/data/asd.json
  type:
    field_input: problem
    field_instruction: type
    field_output: solution
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 512
eval_table_size: null
evals_per_epoch: 2
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: ncbateman/tuning-miner-testbed-asd
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_steps: 5
micro_batch_size: 4
mlflow_experiment_name: https://5a301a635a9d0ac3cb7fcc3bf373c3c3.r2.cloudflarestorage.com/tuning/lighteval/MATH-Hard_train_data.json?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=d49fdd0cc9750a097b58ba35b2d9fbed%2F20241023%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20241023T143154Z&X-Amz-Expires=604800&X-Amz-SignedHeaders=host&X-Amz-Signature=4a7c1dcd761dd78a44d40f4535772b806d1b658d16321165e31f5e9b75617896
model_type: LlamaForCausalLM
num_epochs: 5
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 20
save_strategy: steps
sequence_len: 4096
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
val_set_size: 0.05
wandb_entity: breakfasthut
wandb_mode: online
wandb_project: tuning-miner
wandb_run: miner
wandb_runid: asd
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

tuning-miner-testbed-asd

This model is a fine-tuned version of unsloth/Llama-3.2-1B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9848

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.9943	0.0103	1	0.9864
0.9017	0.0206	2	0.9887
1.1019	0.0309	3	0.9872
0.8137	0.0412	4	0.9864
0.9198	0.0515	5	0.9848

Framework versions

• PEFT 0.13.2
• Transformers 4.45.2
• Pytorch 2.3.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1