Hugging Face's logo

robiulawaldev
/
fdade4ae-5353-4ed7-a954-e89ea189fbc6

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
fdade4ae-5353-4ed7-a954-e89ea189fbc6 / README.md
robiulawaldev's picture
robiulawaldev
End of training
b2bb0c2 verified
preview code
|
raw
history blame
4.26 kB
metadata
library_name: peft
base_model: NousResearch/CodeLlama-7b-hf-flash
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: fdade4ae-5353-4ed7-a954-e89ea189fbc6
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/CodeLlama-7b-hf-flash
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 68126dc6c922929d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/68126dc6c922929d_train_data.json
  type:
    field_input: metadata
    field_instruction: topic
    field_output: prompt
    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: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 150
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: robiulawaldev/fdade4ae-5353-4ed7-a954-e89ea189fbc6
hub_strategy: end
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: constant
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 7330
micro_batch_size: 4
mlflow_experiment_name: /tmp/68126dc6c922929d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
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: 150
saves_per_epoch: null
sequence_len: 512
special_tokens:
  pad_token: </s>
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: online
wandb_name: d6e52fb4-2684-483d-9de0-7fc8ced2855c
wandb_project: SN56-36
wandb_run: your_name
wandb_runid: d6e52fb4-2684-483d-9de0-7fc8ced2855c
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

fdade4ae-5353-4ed7-a954-e89ea189fbc6

This model is a fine-tuned version of NousResearch/CodeLlama-7b-hf-flash on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.3219

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • 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-5
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 50
  • training_steps: 5956

Training results

Training Loss Epoch Step Validation Loss
No log 0.0017 1 3.0169
9.0413 0.2518 150 2.4368
8.9908 0.5036 300 2.4454
8.7721 0.7554 450 2.3292
8.3238 1.0080 600 2.2419
7.1648 1.2598 750 2.3182
7.208 1.5115 900 2.3605
7.0023 1.7633 1050 2.3219

Framework versions

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