See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: microsoft/Phi-3.5-mini-instruct
bf16: auto
chat_template: llama3
cosine_min_lr_ratio: 0.1
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - 72b8cf415c30873e_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/72b8cf415c30873e_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    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: 1
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: 32
gradient_checkpointing: true
group_by_length: true
hub_model_id: stevemonite/x33c2961
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
  1: 70GiB
  2: 70GiB
  3: 70GiB
max_steps: 476
micro_batch_size: 1
mlflow_experiment_name: /tmp/72b8cf415c30873e_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
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: false
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: null
wandb_mode: online
wandb_project: Public_TuningSN
wandb_run: miner_id_24
wandb_runid: x33c2961
warmup_raio: 0.03
warmup_ratio: 0.05
weight_decay: 0.01
xformers_attention: null

x33c2961

This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7644

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
• gradient_accumulation_steps: 32
• total_train_batch_size: 32
• 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: 23
• training_steps: 476

Training results

Training Loss	Epoch	Step	Validation Loss
26.0903	0.0006	1	1.1866
29.7126	0.0154	25	0.9018
46.7324	0.0309	50	0.8823
25.784	0.0463	75	0.8154
39.1322	0.0617	100	0.8440
26.9874	0.0771	125	0.7964
35.4935	0.0926	150	0.7965
28.869	0.1080	175	0.7871
34.382	0.1234	200	0.7839
28.0397	0.1389	225	0.7828
25.6543	0.1543	250	0.7765
27.3467	0.1697	275	0.7754
27.0192	0.1851	300	0.7613
25.9635	0.2006	325	0.7644

Framework versions

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