Hugging Face's logo

lesso17
/
9017ccaa-678a-4990-bb34-2298e3f66057

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
9017ccaa-678a-4990-bb34-2298e3f66057 / README.md
lesso17's picture
lesso17
End of training
bdd3f2e verified
preview code
|
raw
history blame
4.29 kB
metadata
library_name: peft
license: mit
base_model: NousResearch/Nous-Capybara-7B-V1
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 9017ccaa-678a-4990-bb34-2298e3f66057
    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:
  - c697b0068be19101_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/c697b0068be19101_train_data.json
  type:
    field_input: knowledge
    field_instruction: instruction
    field_output: response
    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: lesso17/9017ccaa-678a-4990-bb34-2298e3f66057
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000217
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/c697b0068be19101_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
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: 48966215-ca4f-46eb-83b5-a4c8bf56df37
wandb_project: 17a
wandb_run: your_name
wandb_runid: 48966215-ca4f-46eb-83b5-a4c8bf56df37
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

9017ccaa-678a-4990-bb34-2298e3f66057

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: 0.6304

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: 0.000217
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • 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 0.0000 1 1.1474
0.7831 0.0021 50 0.7893
0.7393 0.0042 100 0.7602
0.7043 0.0063 150 0.7188
0.6935 0.0084 200 0.7025
0.6702 0.0105 250 0.6787
0.6508 0.0126 300 0.6603
0.6159 0.0148 350 0.6443
0.6354 0.0169 400 0.6358
0.6225 0.0190 450 0.6312
0.6781 0.0211 500 0.6304

Framework versions

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