Hugging Face's logo

aleegis12
/
66972ef7-b54f-48e3-9bb7-5c1261c0cd59

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
66972ef7-b54f-48e3-9bb7-5c1261c0cd59 / README.md
aleegis12's picture
aleegis12
End of training
4f30625 verified
preview code
|
raw
history blame contribute delete
4.09 kB
metadata
library_name: peft
license: apache-2.0
base_model: unsloth/SmolLM2-360M
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 66972ef7-b54f-48e3-9bb7-5c1261c0cd59
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/SmolLM2-360M
bf16: true
chat_template: llama3
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - f6f2b0985d34f3bb_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f6f2b0985d34f3bb_train_data.json
  type:
    field_input: response
    field_instruction: context
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
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: true
hub_model_id: aleegis12/66972ef7-b54f-48e3-9bb7-5c1261c0cd59
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
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_memory:
  0: 75GB
max_steps: 200
micro_batch_size: 8
mlflow_experiment_name: /tmp/f6f2b0985d34f3bb_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
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: 1024
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: b9c4e88d-ca00-4f32-99bc-d66385339bce
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b9c4e88d-ca00-4f32-99bc-d66385339bce
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

66972ef7-b54f-48e3-9bb7-5c1261c0cd59

This model is a fine-tuned version of unsloth/SmolLM2-360M on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1569

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: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 200

Training results

Training Loss Epoch Step Validation Loss
0.685 0.0014 1 3.1940
1.5405 0.0687 50 1.5880
1.5702 0.1374 100 1.2335
1.3212 0.2061 150 1.1653
1.4588 0.2748 200 1.1569

Framework versions

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