Hugging Face's logo

DeepDream2045
/
eb515b2e-97d9-42bd-995d-93a98ca47431

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
eb515b2e-97d9-42bd-995d-93a98ca47431 / README.md
DeepDream2045's picture
DeepDream2045
End of training
da371bf verified
preview code
|
raw
history blame contribute delete
4.05 kB
metadata
library_name: peft
license: llama2
base_model: codellama/CodeLlama-7b-Instruct-hf
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: eb515b2e-97d9-42bd-995d-93a98ca47431
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.5.2

adapter: lora
base_model: codellama/CodeLlama-7b-Instruct-hf
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - b65243686da5fb29_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/b65243686da5fb29_train_data.json
  type:
    field_input: "\u95A2\u9023"
    field_instruction: "\u666F\u6C17\u306E\u73FE\u72B6\u5224\u65AD"
    field_output: "\u8FFD\u52A0\u8AAC\u660E\u53CA\u3073\u5177\u4F53\u7684\u72B6\u6CC1\
      \u306E\u8AAC\u660E"
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 25
eval_table_size: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: true
hub_model_id: DeepDream2045/eb515b2e-97d9-42bd-995d-93a98ca47431
hub_repo: null
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
lr_scheduler: cosine
max_steps: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/b65243686da5fb29_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 25
sequence_len: 2048
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: eb515b2e-97d9-42bd-995d-93a98ca47431
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: eb515b2e-97d9-42bd-995d-93a98ca47431
warmup_ratio: 0.05
weight_decay: 0.01
xformers_attention: true

eb515b2e-97d9-42bd-995d-93a98ca47431

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

  • Loss: 1.4670

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: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • total_eval_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 2
  • training_steps: 50

Training results

Training Loss Epoch Step Validation Loss
1.9003 0.0004 1 2.1803
1.3772 0.0104 25 1.5409
1.2716 0.0207 50 1.4670

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.3
  • Pytorch 2.3.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3