Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: peft-internal-testing/tiny-dummy-qwen2
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - c6ee6b58716ff9fb_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/c6ee6b58716ff9fb_train_data.json
  type:
    field_input: text
    field_instruction: category
    field_output: level
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: sn56b2/19f71fb4-2196-4757-82a0-8634ca0903c0
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_steps: 500
micro_batch_size: 8
mlflow_experiment_name: /tmp/c6ee6b58716ff9fb_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: false
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: 19f71fb4-2196-4757-82a0-8634ca0903c0
wandb_project: god
wandb_run: m191
wandb_runid: 19f71fb4-2196-4757-82a0-8634ca0903c0
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

19f71fb4-2196-4757-82a0-8634ca0903c0

This model is a fine-tuned version of peft-internal-testing/tiny-dummy-qwen2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 11.7725

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • total_eval_batch_size: 32
  • 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: 500

Training results

Training Loss Epoch Step Validation Loss
No log 0.0044 1 11.9346
11.8393 0.1828 42 11.8348
11.7945 0.3656 84 11.7937
11.7808 0.5484 126 11.7788
11.7829 0.7312 168 11.7756
11.7772 0.9140 210 11.7743
11.7765 1.0990 252 11.7737
11.7772 1.2818 294 11.7731
11.7743 1.4646 336 11.7727
11.7797 1.6474 378 11.7727
11.7757 1.8303 420 11.7725
11.7768 2.0152 462 11.7725

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1
Downloads last month
10
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for sn56b2/19f71fb4-2196-4757-82a0-8634ca0903c0

Adapter
(108)
this model