Hugging Face's logo

havinash-ai
/
57f6dc68-4c1c-4712-a3f8-d31559c98b64

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
57f6dc68-4c1c-4712-a3f8-d31559c98b64 / README.md
havinash-ai's picture
havinash-ai
End of training
2e717c0 verified
preview code
|
raw
history blame
4.47 kB
metadata
library_name: peft
base_model: NousResearch/CodeLlama-7b-hf
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 57f6dc68-4c1c-4712-a3f8-d31559c98b64
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/CodeLlama-7b-hf
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 3eeea2777a8212e7_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/3eeea2777a8212e7_train_data.json
  type:
    field_instruction: instruction
    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: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 500
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: havinash-ai/57f6dc68-4c1c-4712-a3f8-d31559c98b64
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: 6116
micro_batch_size: 4
mlflow_experiment_name: /tmp/3eeea2777a8212e7_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: 500
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: 1cf249aa-30aa-4b8c-84ee-a1b5a0ed3381
wandb_project: SN56-2
wandb_run: your_name
wandb_runid: 1cf249aa-30aa-4b8c-84ee-a1b5a0ed3381
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

57f6dc68-4c1c-4712-a3f8-d31559c98b64

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

  • Loss: 0.6826

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: 6116

Training results

Training Loss Epoch Step Validation Loss
No log 0.0001 1 1.2331
3.3575 0.0422 500 0.8487
3.1036 0.0843 1000 0.7976
2.9454 0.1265 1500 0.7708
2.9283 0.1687 2000 0.7511
2.9176 0.2108 2500 0.7387
2.8545 0.2530 3000 0.7237
2.7958 0.2952 3500 0.7140
2.8252 0.3373 4000 0.7045
2.799 0.3795 4500 0.7010
2.7012 0.4217 5000 0.6925
2.6824 0.4639 5500 0.6878
2.6736 0.5060 6000 0.6826

Framework versions

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