Hugging Face's logo

error577
/
8d7fc433-2cfd-45f6-a477-d3b559fa9010

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
8d7fc433-2cfd-45f6-a477-d3b559fa9010 / README.md
error577's picture
error577
End of training
bd4e8ad verified
preview code
|
raw
history blame contribute delete
4.58 kB
metadata
library_name: peft
license: apache-2.0
base_model: unsloth/Qwen2-7B
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 8d7fc433-2cfd-45f6-a477-d3b559fa9010
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: qlora
auto_resume_from_checkpoints: true
base_model: unsloth/Qwen2-7B
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
  - b3602e9ad49c90ca_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/b3602e9ad49c90ca_train_data.json
  type:
    field_input: content
    field_instruction: document_type
    field_output: insights
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: true
hub_model_id: error577/8d7fc433-2cfd-45f6-a477-d3b559fa9010
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1000
micro_batch_size: 1
mlflow_experiment_name: /tmp/b3602e9ad49c90ca_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 50
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
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.02
wandb_entity: null
wandb_mode: online
wandb_name: 57493276-8587-4480-9e98-60342d0d4e34
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 57493276-8587-4480-9e98-60342d0d4e34
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

8d7fc433-2cfd-45f6-a477-d3b559fa9010

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: 0.3644

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: 0.0003
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 16
  • 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: 10
  • training_steps: 1000

Training results

Training Loss Epoch Step Validation Loss
1.2479 0.0017 1 0.6322
0.012 0.0849 50 0.4557
0.0091 0.1697 100 0.4276
0.0053 0.2546 150 0.4270
0.0002 0.3395 200 0.4256
0.0023 0.4244 250 0.3934
0.0001 0.5092 300 0.4081
0.0005 0.5941 350 0.4034
0.0003 0.6790 400 0.3838
0.0001 0.7638 450 0.3828
0.0007 0.8487 500 0.3721
0.0 0.9336 550 0.3720
0.6439 1.0185 600 0.3682
0.479 1.1033 650 0.3639
0.4194 1.1882 700 0.3641
0.4853 1.2731 750 0.3654
0.4158 1.3579 800 0.3644

Framework versions

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