See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: microsoft/phi-1_5
bf16: auto
chat_template: llama3
cosine_min_lr_ratio: 0.1
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - 9c3356e9e8b0b72d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/9c3356e9e8b0b72d_train_data.json
  type:
    field_instruction: input
    field_output: output
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: '{'''':torch.cuda.current_device()}'
do_eval: true
early_stopping_patience: 30
eval_batch_size: 1
eval_sample_packing: false
eval_steps: 25
evaluation_strategy: steps
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 64
gradient_checkpointing: true
group_by_length: true
hub_model_id: sn56c2/a7d87571-d3fe-4b33-a487-fec1a9902e12
hub_repo: stevemonite
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 70GiB
max_steps: 190
micro_batch_size: 1
mlflow_experiment_name: /tmp/9c3356e9e8b0b72d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
save_strategy: steps
sequence_len: 2048
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: false
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: a7d87571-d3fe-4b33-a487-fec1a9902e12
wandb_project: god
wandb_run: iwbt
wandb_runid: a7d87571-d3fe-4b33-a487-fec1a9902e12
warmup_raio: 0.03
warmup_ratio: 0.05
weight_decay: 0.01
xformers_attention: null

a7d87571-d3fe-4b33-a487-fec1a9902e12

This model is a fine-tuned version of microsoft/phi-1_5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4804

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 64
• total_train_batch_size: 256
• total_eval_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 9
• training_steps: 190

Training results

Training Loss	Epoch	Step	Validation Loss
7.2825	0.0083	1	7.3624
0.6245	0.2071	25	0.6190
0.6068	0.4143	50	0.5666
0.575	0.6214	75	0.5254
0.539	0.8286	100	0.5237
0.4896	1.0357	125	0.5122
0.4939	1.2429	150	0.4909
0.4673	1.4500	175	0.4804

Framework versions

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