Hugging Face's logo

lesso06
/
ce3fbaa1-1e27-4b89-b968-003984d46bdb

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
ce3fbaa1-1e27-4b89-b968-003984d46bdb / README.md
lesso06's picture
lesso06
End of training
c0642e6 verified
preview code
|
raw
history blame contribute delete
4.33 kB
metadata
library_name: peft
license: apache-2.0
base_model: EleutherAI/pythia-410m-deduped
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: ce3fbaa1-1e27-4b89-b968-003984d46bdb
    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
do_eval: true
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 50
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
group_by_length: true
hub_model_id: lesso06/ce3fbaa1-1e27-4b89-b968-003984d46bdb
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000206
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
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_grad_norm: 1.0
max_steps: 500
micro_batch_size: 4
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
saves_per_epoch: null
seed: 60
sequence_len: 512
special_tokens:
  pad_token: <|endoftext|>
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: 475a08f0-792a-4692-9724-b9174a698759
wandb_project: 06a
wandb_run: your_name
wandb_runid: 475a08f0-792a-4692-9724-b9174a698759
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

ce3fbaa1-1e27-4b89-b968-003984d46bdb

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: 2.8724

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: 0.000206
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 60
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • 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: 50
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss
No log 0.0000 1 3.0490
7.8567 0.0005 50 3.0400
7.4368 0.0010 100 3.0624
7.9916 0.0014 150 3.3823
7.6411 0.0019 200 3.0240
7.1386 0.0024 250 2.9751
7.2314 0.0029 300 2.9116
6.5896 0.0034 350 2.8866
6.9787 0.0039 400 2.8771
6.8299 0.0043 450 2.8741
6.7968 0.0048 500 2.8724

Framework versions

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