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: 400
eval_table_size: null
flash_attention: false
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/193d36cc-cbc9-404d-89a3-86641a6de3b3
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: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
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: 4023
micro_batch_size: 2
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: 400
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

193d36cc-cbc9-404d-89a3-86641a6de3b3

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: 0.0010

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: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
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: 4023

Training results

Training Loss	Epoch	Step	Validation Loss
3.0659	0.0000	1	0.5929
0.1153	0.0157	400	0.0078
0.0044	0.0315	800	0.0039
0.0017	0.0472	1200	0.0031
0.0008	0.0629	1600	0.0028
0.0082	0.0786	2000	0.0022
0.0013	0.0944	2400	0.0019
0.0043	0.1101	2800	0.0013
0.0061	0.1258	3200	0.0013
0.0002	0.1415	3600	0.0011
0.0005	0.1573	4000	0.0010

Framework versions

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