Hugging Face's logo

lesso18
/
e156e6c6-eb07-4279-9ee1-b1737317c4e8

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e156e6c6-eb07-4279-9ee1-b1737317c4e8 / README.md
lesso18's picture
lesso18
End of training
ebff419 verified
preview code
|
raw
history blame
3.98 kB
metadata
library_name: peft
license: mit
base_model: NousResearch/Nous-Capybara-7B-V1
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: e156e6c6-eb07-4279-9ee1-b1737317c4e8
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: NousResearch/Nous-Capybara-7B-V1
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - eb740de30ff7fe93_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/eb740de30ff7fe93_train_data.json
  type:
    field_input: title
    field_instruction: question
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 50
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
group_by_length: true
hub_model_id: lesso18/e156e6c6-eb07-4279-9ee1-b1737317c4e8
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000218
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 128
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 500
micro_batch_size: 4
mlflow_experiment_name: /tmp/G.O.D/eb740de30ff7fe93_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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
seed: 180
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: null
wandb_mode: online
wandb_name: e2c64dd8-ac0d-4315-9953-54dcef591325
wandb_project: 18a
wandb_run: your_name
wandb_runid: e2c64dd8-ac0d-4315-9953-54dcef591325
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

e156e6c6-eb07-4279-9ee1-b1737317c4e8

This model is a fine-tuned version of NousResearch/Nous-Capybara-7B-V1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.1722

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: 0.000218
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 180
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_BNB 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: 50
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss
No log 0.0002 1 2.9893
2.3877 0.0121 50 2.1539
2.2267 0.0241 100 2.3052
2.1741 0.0362 150 2.3203
2.2808 0.0483 200 2.1722

Framework versions

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