Hugging Face's logo

oldiday
/
a247d3e9-78ac-4414-b064-a537801bdca0

PEFT
Safetensors
phi3
axolotl
Generated from Trainer
custom_code
Model card Files Community
a247d3e9-78ac-4414-b064-a537801bdca0 / README.md
oldiday's picture
oldiday
End of training
efc47b3 verified
preview code
|
raw
history blame
4.55 kB
metadata
library_name: peft
license: mit
base_model: microsoft/Phi-3-mini-128k-instruct
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: a247d3e9-78ac-4414-b064-a537801bdca0
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: microsoft/Phi-3-mini-128k-instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 2cd88be2401b69b4_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2cd88be2401b69b4_train_data.json
  type:
    field_input: ner_words
    field_instruction: dates
    field_output: article
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: oldiday/a247d3e9-78ac-4414-b064-a537801bdca0
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: 10
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 600
micro_batch_size: 8
mlflow_experiment_name: /tmp/2cd88be2401b69b4_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
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: 50
saves_per_epoch: null
sequence_len: 512
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: techspear-hub
wandb_mode: online
wandb_name: cdbccf02-f81c-4a62-9727-89ffc66d06d8
wandb_project: Gradients-On-Six
wandb_run: your_name
wandb_runid: cdbccf02-f81c-4a62-9727-89ffc66d06d8
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

a247d3e9-78ac-4414-b064-a537801bdca0

This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7396

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: 8
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-05
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 600

Training results

Training Loss Epoch Step Validation Loss
No log 0.0012 1 1.4336
1.7989 0.0588 50 0.9343
1.5895 0.1177 100 0.8447
1.4454 0.1765 150 0.8176
1.4239 0.2354 200 0.7979
1.3427 0.2942 250 0.7788
1.3585 0.3530 300 0.7667
1.3171 0.4119 350 0.7573
1.3135 0.4707 400 0.7501
1.3062 0.5296 450 0.7452
1.221 0.5884 500 0.7422
1.2469 0.6472 550 0.7403
1.2265 0.7061 600 0.7396

Framework versions

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