Hugging Face's logo

robiulawaldev
/
0500d330-04bb-4f34-8098-fa82b37d034e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
0500d330-04bb-4f34-8098-fa82b37d034e / README.md
robiulawaldev's picture
robiulawaldev
End of training
f566579 verified
preview code
|
raw
history blame
5.16 kB
metadata
library_name: peft
license: cc-by-sa-4.0
base_model: defog/sqlcoder-7b-2
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 0500d330-04bb-4f34-8098-fa82b37d034e
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: defog/sqlcoder-7b-2
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 996120a1458c75c0_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/996120a1458c75c0_train_data.json
  type:
    field_input: chosen
    field_instruction: prompt
    field_output: rejected
    format: '{instruction} {input}'
    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: 300
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: robiulawaldev/0500d330-04bb-4f34-8098-fa82b37d034e
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: 8884
micro_batch_size: 4
mlflow_experiment_name: /tmp/996120a1458c75c0_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: 300
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: 1516f5b9-e950-43d8-b8e5-89b1b7b87690
wandb_project: SN56-36
wandb_run: your_name
wandb_runid: 1516f5b9-e950-43d8-b8e5-89b1b7b87690
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

0500d330-04bb-4f34-8098-fa82b37d034e

This model is a fine-tuned version of defog/sqlcoder-7b-2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6436

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: 8884

Training results

Training Loss Epoch Step Validation Loss
No log 0.0003 1 0.9930
0.6963 0.0819 300 0.7392
0.6672 0.1639 600 0.7069
0.6857 0.2458 900 0.6906
0.6471 0.3277 1200 0.6816
0.663 0.4097 1500 0.6697
0.6423 0.4916 1800 0.6693
0.649 0.5735 2100 0.6612
0.6386 0.6555 2400 0.6559
0.623 0.7374 2700 0.6499
0.6216 0.8193 3000 0.6462
0.6363 0.9013 3300 0.6501
0.6333 0.9832 3600 0.6404
0.5435 1.0651 3900 0.6415
0.5375 1.1471 4200 0.6323
0.5575 1.2290 4500 0.6342
0.5651 1.3109 4800 0.6326
0.5408 1.3929 5100 0.6281
0.5521 1.4748 5400 0.6309
0.5557 1.5567 5700 0.6316
0.5502 1.6387 6000 0.6255
0.5558 1.7206 6300 0.6257
0.5438 1.8025 6600 0.6208
0.5485 1.8845 6900 0.6270
0.5442 1.9664 7200 0.6258
0.4385 2.0483 7500 0.6436

Framework versions

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