Hugging Face's logo

infogep
/
c0fa4d77-a9c9-46e1-a9d1-b5956ab43c5d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
c0fa4d77-a9c9-46e1-a9d1-b5956ab43c5d / README.md
infogep's picture
infogep
End of training
1a55615 verified
preview code
|
raw
history blame contribute delete
4.02 kB
metadata
library_name: peft
license: cc-by-sa-4.0
base_model: defog/llama-3-sqlcoder-8b
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: c0fa4d77-a9c9-46e1-a9d1-b5956ab43c5d
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: defog/llama-3-sqlcoder-8b
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 7e29722059d9d568_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/7e29722059d9d568_train_data.json
  type:
    field_instruction: Speech
    field_output: Speech_processed
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: true
hub_model_id: infogep/c0fa4d77-a9c9-46e1-a9d1-b5956ab43c5d
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 30
micro_batch_size: 4
mlflow_experiment_name: /tmp/7e29722059d9d568_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: 10
sequence_len: 1024
special_tokens:
  pad_token: <|eot_id|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 3020def7-32ef-493e-ba2a-56aeb67fbd87
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 3020def7-32ef-493e-ba2a-56aeb67fbd87
warmup_steps: 5
weight_decay: 0.0
xformers_attention: true

c0fa4d77-a9c9-46e1-a9d1-b5956ab43c5d

This model is a fine-tuned version of defog/llama-3-sqlcoder-8b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8507

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: 5e-05
  • 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=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 5
  • training_steps: 30

Training results

Training Loss Epoch Step Validation Loss
No log 0.0001 1 2.2399
1.4587 0.0005 5 2.2229
1.5717 0.0009 10 2.1020
1.5247 0.0014 15 1.9905
1.5183 0.0019 20 1.9088
1.5404 0.0023 25 1.8610
1.7174 0.0028 30 1.8507

Framework versions

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