See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: microsoft/Phi-3-mini-4k-instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - f41b37633fb01f30_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f41b37633fb01f30_train_data.json
  type:
    field_input: span_labels
    field_instruction: source_text
    field_output: target_text
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
device_map:
  ? ''
  : 0,1,2,3,4,5,6,7
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: false
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/b744a4e2-1fac-4703-8edc-982cf0ff0956
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: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 969
micro_batch_size: 4
mlflow_experiment_name: /tmp/f41b37633fb01f30_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: 100
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.023985301807052637
wandb_entity: null
wandb_mode: online
wandb_name: 1f7400e6-dda1-4dad-bbf6-182d355c9cb5
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 1f7400e6-dda1-4dad-bbf6-182d355c9cb5
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

b744a4e2-1fac-4703-8edc-982cf0ff0956

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

• Loss: 0.0009

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
• gradient_accumulation_steps: 8
• total_train_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: 969

Training results

Training Loss	Epoch	Step	Validation Loss
4.7446	0.0002	1	0.5791
0.0774	0.0157	100	0.0062
0.0676	0.0315	200	0.0046
0.0041	0.0472	300	0.0027
0.0143	0.0629	400	0.0035
0.008	0.0786	500	0.0017
0.004	0.0944	600	0.0013
0.001	0.1101	700	0.0011
0.0082	0.1258	800	0.0009
0.0013	0.1415	900	0.0009

Framework versions

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