See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: HuggingFaceM4/tiny-random-LlamaForCausalLM
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - bdf6df5da59e1fc9_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/bdf6df5da59e1fc9_train_data.json
  type:
    field_input: considerations
    field_instruction: facts
    field_output: decision_id
    format: '{instruction} {input}'
    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: 4
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: sn56a1/c9a06c09-d064-4ef3-a970-45361b738d15
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 72GB
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/bdf6df5da59e1fc9_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: false
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
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: null
wandb_project: god
wandb_run: emdt
wandb_runid: null
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

c9a06c09-d064-4ef3-a970-45361b738d15

This model is a fine-tuned version of HuggingFaceM4/tiny-random-LlamaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.3061

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: 4
• total_train_batch_size: 128
• 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: 10
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0061	1	10.3793
10.3768	0.0550	9	10.3756
10.3674	0.1099	18	10.3640
10.3497	0.1649	27	10.3450
10.3285	0.2198	36	10.3241
10.3148	0.2748	45	10.3129
10.3084	0.3298	54	10.3086
10.3078	0.3847	63	10.3071
10.3053	0.4397	72	10.3065
10.3063	0.4947	81	10.3062
10.3061	0.5496	90	10.3062
10.3056	0.6046	99	10.3061

Framework versions

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