Hugging Face's logo

fedovtt
/
8281ac79-b7a0-4889-a9fa-6961426775d3

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
8281ac79-b7a0-4889-a9fa-6961426775d3 / README.md
fedovtt's picture
fedovtt
End of training
7531048 verified
preview code
|
raw
history blame contribute delete
4.21 kB
metadata
library_name: peft
license: apache-2.0
base_model: Maykeye/TinyLLama-v0
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 8281ac79-b7a0-4889-a9fa-6961426775d3
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Maykeye/TinyLLama-v0
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - f23038e56c240d0a_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f23038e56c240d0a_train_data.json
  type:
    field_input: ''
    field_instruction: query
    field_output: answer
    format: '{instruction}'
    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: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: fedovtt/8281ac79-b7a0-4889-a9fa-6961426775d3
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: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 76GiB
max_steps: 20
micro_batch_size: 2
mlflow_experiment_name: /tmp/f23038e56c240d0a_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 10
sequence_len: 2048
special_tokens:
  pad_token: </s>
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: 8281ac79-b7a0-4889-a9fa-6961426775d3
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 8281ac79-b7a0-4889-a9fa-6961426775d3
warmup_steps: 10
weight_decay: 0.1
xformers_attention: true

8281ac79-b7a0-4889-a9fa-6961426775d3

This model is a fine-tuned version of Maykeye/TinyLLama-v0 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 8.2830

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_TORCH 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: 20

Training results

Training Loss Epoch Step Validation Loss
8.6163 0.0001 1 8.4795
8.5938 0.0002 2 8.4794
8.7145 0.0003 4 8.4753
8.6569 0.0005 6 8.4589
8.2834 0.0007 8 8.4295
9.0077 0.0009 10 8.3933
8.3223 0.0010 12 8.3530
8.5098 0.0012 14 8.3183
8.3398 0.0014 16 8.2969
8.0738 0.0016 18 8.2854
8.5815 0.0017 20 8.2830

Framework versions

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