Hugging Face's logo

error577
/
0fbfb23b-c3ed-4087-9035-12ed75edce4a

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
0fbfb23b-c3ed-4087-9035-12ed75edce4a / README.md
error577's picture
error577
End of training
816c509 verified
preview code
|
raw
history blame contribute delete
4.65 kB
metadata
library_name: peft
license: apache-2.0
base_model: unsloth/gemma-1.1-2b-it
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 0fbfb23b-c3ed-4087-9035-12ed75edce4a
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_resume_from_checkpoints: true
base_model: unsloth/gemma-1.1-2b-it
bf16: auto
chat_template: llama3
dataset_prepared_path: null
dataset_processes: 6
datasets:
- data_files:
  - 8b5afe50837b255a_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/8b5afe50837b255a_train_data.json
  type:
    field_input: distractor-0
    field_instruction: startphrase
    field_output: gold-ending
    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: 200
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: error577/0fbfb23b-c3ed-4087-9035-12ed75edce4a
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.1
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: null
micro_batch_size: 4
mlflow_experiment_name: /tmp/8b5afe50837b255a_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: null
sample_packing: false
save_steps: 200
sequence_len: 256
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.005
wandb_entity: null
wandb_mode: online
wandb_name: 628eefeb-6b62-454a-9537-12242629b85d
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 628eefeb-6b62-454a-9537-12242629b85d
warmup_steps: 30
weight_decay: 0.0
xformers_attention: null

0fbfb23b-c3ed-4087-9035-12ed75edce4a

This model is a fine-tuned version of unsloth/gemma-1.1-2b-it on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.6509

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=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 30
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
5.9428 0.0002 1 6.1052
2.5262 0.0347 200 2.7630
2.956 0.0693 400 2.7125
2.7371 0.1040 600 2.7114
2.7291 0.1387 800 2.6787
2.9438 0.1734 1000 2.6667
2.5104 0.2080 1200 2.6644
2.2874 0.2427 1400 2.6748
2.5989 0.2774 1600 2.6692
2.7873 0.3121 1800 2.6559
2.742 0.3467 2000 2.6614
2.8575 0.3814 2200 2.6694
2.4323 0.4161 2400 2.6472
2.6942 0.4508 2600 2.6358
2.5881 0.4854 2800 2.6310
3.1393 0.5201 3000 2.6596
2.943 0.5548 3200 2.6602
2.6964 0.5895 3400 2.6509

Framework versions

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