Hugging Face's logo

lesso02
/
22e4f64e-ce84-44bc-ae90-1c695e284b96

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
22e4f64e-ce84-44bc-ae90-1c695e284b96 / README.md
lesso02's picture
lesso02
End of training
bf5967b verified
preview code
|
raw
history blame
4.24 kB
metadata
library_name: peft
license: apache-2.0
base_model: unsloth/Qwen2-7B
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 22e4f64e-ce84-44bc-ae90-1c695e284b96
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: unsloth/Qwen2-7B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 45ed677ac288df1b_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/45ed677ac288df1b_train_data.json
  type:
    field_input: eval_persona
    field_instruction: eval_question
    field_output: eval_whole_desc
    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: lesso02/22e4f64e-ce84-44bc-ae90-1c695e284b96
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000202
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/45ed677ac288df1b_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: a56fcd1e-0052-4003-b4a6-990998c6b86e
wandb_project: 02a
wandb_run: your_name
wandb_runid: a56fcd1e-0052-4003-b4a6-990998c6b86e
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

22e4f64e-ce84-44bc-ae90-1c695e284b96

This model is a fine-tuned version of unsloth/Qwen2-7B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3219

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: 0.000202
  • 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 0.0004 1 2.6280
1.3739 0.0184 50 1.5840
1.3833 0.0368 100 1.4967
1.3041 0.0552 150 1.4766
1.2805 0.0736 200 1.4655
1.2476 0.0920 250 1.4171
1.2002 0.1104 300 1.3866
1.24 0.1287 350 1.3594
1.2489 0.1471 400 1.3325
1.2365 0.1655 450 1.3238
1.2489 0.1839 500 1.3219

Framework versions

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