Hugging Face's logo

dsakerkwq
/
4616dd30-0309-4496-adc2-62fe53420323

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
4616dd30-0309-4496-adc2-62fe53420323 / README.md
dsakerkwq's picture
dsakerkwq
End of training
1ea479d verified
preview code
|
raw
history blame contribute delete
4.02 kB
metadata
library_name: peft
license: apache-2.0
base_model: unsloth/Qwen2-0.5B
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 4616dd30-0309-4496-adc2-62fe53420323
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Qwen2-0.5B
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 1e7bb670723eee7d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/1e7bb670723eee7d_train_data.json
  type:
    field_input: source
    field_instruction: prompt
    field_output: response
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: true
hub_model_id: dsakerkwq/4616dd30-0309-4496-adc2-62fe53420323
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 75GiB
max_steps: 30
micro_batch_size: 2
mlflow_experiment_name: /tmp/1e7bb670723eee7d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
s2_attention: false
sample_packing: false
saves_per_epoch: 4
sequence_len: 2048
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: 4616dd30-0309-4496-adc2-62fe53420323
wandb_project: Gradients-On-Demand
wandb_runid: 4616dd30-0309-4496-adc2-62fe53420323
warmup_steps: 100
weight_decay: 0.01
xformers_attention: false

4616dd30-0309-4496-adc2-62fe53420323

This model is a fine-tuned version of unsloth/Qwen2-0.5B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: nan

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH 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: 100
  • training_steps: 30

Training results

Training Loss Epoch Step Validation Loss
0.0 0.0020 1 nan
0.0 0.0059 3 nan
0.0 0.0118 6 nan
0.0 0.0177 9 nan
0.0 0.0236 12 nan
0.0 0.0295 15 nan
0.0 0.0354 18 nan
0.0 0.0413 21 nan
0.0 0.0472 24 nan
0.0 0.0531 27 nan
0.0 0.0590 30 nan

Framework versions

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