See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Llama-3.2-1B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 1c5d8209adc13c02_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/1c5d8209adc13c02_train_data.json
  type:
    field_instruction: instruction
    field_output: response
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 5
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: false
group_by_length: false
hub_model_id: sn56m4/ce1d5ab0-9d0d-4b21-beb7-0309aff1f277
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/1c5d8209adc13c02_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: ce1d5ab0-9d0d-4b21-beb7-0309aff1f277
wandb_project: god
wandb_run: bcea
wandb_runid: ce1d5ab0-9d0d-4b21-beb7-0309aff1f277
warmup_steps: 2
weight_decay: 0.0
xformers_attention: null

ce1d5ab0-9d0d-4b21-beb7-0309aff1f277

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

• Loss: 0.9571

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 512
• total_eval_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 2
• training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0181	1	2.1752
1.9692	0.1808	10	1.5592
1.3666	0.3616	20	1.1985
1.1175	0.5424	30	1.0333
1.0006	0.7232	40	0.9682
0.9658	0.9040	50	0.9571

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1