adapter: lora
base_model: microsoft/Phi-3-mini-4k-instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - ed80a926a24f5f32_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/ed80a926a24f5f32_train_data.json
  type:
    field_input: condition
    field_instruction: drugName
    field_output: review
    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: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: false
group_by_length: true
hub_model_id: DeepDream2045/119a2c00-c80e-4fc6-8bd0-8eae8bf9dfc0
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
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_grad_norm: 1.0
max_steps: 1500
micro_batch_size: 2
mlflow_experiment_name: /tmp/ed80a926a24f5f32_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: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: offline
wandb_name: 6302fdf3-9e31-4066-ba94-6a82ee005eb9
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 6302fdf3-9e31-4066-ba94-6a82ee005eb9
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

119a2c00-c80e-4fc6-8bd0-8eae8bf9dfc0

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: 2.0545

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: 16
total_train_batch_size: 32
optimizer: Use adamw_bnb_8bit 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: 1500

Training results

Training Loss	Epoch	Step	Validation Loss
2.0227	0.0588	375	2.1020
2.067	0.1176	750	2.0723
1.9247	0.1764	1125	2.0570
2.3047	0.2352	1500	2.0545

Framework versions

PEFT 0.14.0
Transformers 4.46.3
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3