See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Phi-3-medium-4k-instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 3e5a4f6858fe6f99_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/3e5a4f6858fe6f99_train_data.json
  type:
    field_input: langpair
    field_instruction: source
    field_output: good-translation
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
device_map:
  ? ''
  : 0,1,2,4
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 33
eval_table_size: null
flash_attention: false
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/eee6801d-e8e8-4bfa-89a7-86b93986a952
hub_repo: null
hub_strategy: null
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 196.0
micro_batch_size: 4
mlflow_experiment_name: /tmp/3e5a4f6858fe6f99_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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: 33
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.04
wandb_entity: null
wandb_mode: online
wandb_name: 079ce21e-1a81-4df7-a8b5-e66858d4fc9c
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 079ce21e-1a81-4df7-a8b5-e66858d4fc9c
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

eee6801d-e8e8-4bfa-89a7-86b93986a952

This model is a fine-tuned version of unsloth/Phi-3-medium-4k-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• total_eval_batch_size: 16
• 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: 196

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	0.0037	1	nan
0.0	0.1219	33	nan
0.0	0.2439	66	nan
0.0	0.3658	99	nan

Framework versions

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