Hugging Face's logo

0x1202
/
769f6c0e-9a41-483a-919d-9e4828a1a4a0

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
769f6c0e-9a41-483a-919d-9e4828a1a4a0 / README.md
0x1202's picture
0x1202
End of training
16458dc verified
preview code
|
raw
history blame contribute delete
4.33 kB
metadata
library_name: peft
base_model: NousResearch/CodeLlama-7b-hf-flash
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 769f6c0e-9a41-483a-919d-9e4828a1a4a0
    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
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - d191cc991f4fa8fd_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/d191cc991f4fa8fd_train_data.json
  type:
    field_instruction: query
    field_output: response
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 1
eval_batch_size: 1
eval_max_new_tokens: 128
eval_steps: 25
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: true
hub_model_id: 0x1202/769f6c0e-9a41-483a-919d-9e4828a1a4a0
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
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: 70GB
max_steps: 200
micro_batch_size: 1
mlflow_experiment_name: /tmp/d191cc991f4fa8fd_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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
saves_per_epoch: null
sequence_len: 1028
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: null
wandb_mode: online
wandb_name: 769f6c0e-9a41-483a-919d-9e4828a1a4a0
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 769f6c0e-9a41-483a-919d-9e4828a1a4a0
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

769f6c0e-9a41-483a-919d-9e4828a1a4a0

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: 0.9611

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: 0.0003
  • 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: 10
  • training_steps: 200

Training results

Training Loss Epoch Step Validation Loss
33.294 0.0005 1 1.2786
30.7856 0.0134 25 1.0777
33.5111 0.0268 50 1.0827
31.0323 0.0402 75 1.0009
32.2653 0.0536 100 1.0161
30.9478 0.0670 125 0.9712
29.0595 0.0804 150 0.9702
30.1167 0.0938 175 0.9618
21.8853 0.1072 200 0.9611

Framework versions

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