Hugging Face's logo

tuantmdev
/
6ff32772-0d88-46e1-b69c-b0d67c31a116

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
6ff32772-0d88-46e1-b69c-b0d67c31a116 / README.md
tuantmdev's picture
tuantmdev
End of training
247c248 verified
preview code
|
raw
history blame contribute delete
4.21 kB
metadata
library_name: peft
license: apache-2.0
base_model: EleutherAI/pythia-410m-deduped
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 6ff32772-0d88-46e1-b69c-b0d67c31a116
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: EleutherAI/pythia-410m-deduped
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 2498e7b80eaaf39a_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2498e7b80eaaf39a_train_data.json
  type:
    field_input: sub_source
    field_instruction: source
    field_output: text
    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
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: true
hub_model_id: tuantmdev/6ff32772-0d88-46e1-b69c-b0d67c31a116
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 1e-4
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 40
lora_alpha: 64
lora_dropout: 0.05
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: 400
micro_batch_size: 2
mlflow_experiment_name: /tmp/2498e7b80eaaf39a_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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
save_strategy: steps
sequence_len: 512
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 475a08f0-792a-4692-9724-b9174a698759
wandb_project: Gradients-On-Demand
wandb_run: unknown
wandb_runid: 475a08f0-792a-4692-9724-b9174a698759
warmup_steps: 80
weight_decay: 0.0
xformers_attention: null

6ff32772-0d88-46e1-b69c-b0d67c31a116

This model is a fine-tuned version of EleutherAI/pythia-410m-deduped on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.8287

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • 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: 80
  • training_steps: 400

Training results

Training Loss Epoch Step Validation Loss
No log 0.0000 1 3.0496
22.4683 0.0010 50 2.9747
23.412 0.0019 100 2.9525
23.6834 0.0029 150 2.9184
24.0095 0.0039 200 2.8847
21.6947 0.0048 250 2.8586
22.0998 0.0058 300 2.8383
23.1427 0.0068 350 2.8306
23.1161 0.0077 400 2.8287

Framework versions

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