Hugging Face's logo

cvoffer
/
b7e96d89-d751-43fd-88d4-c01379498881

Safetensors
llama
8-bit precision
bitsandbytes
Model card Files Community
b7e96d89-d751-43fd-88d4-c01379498881 / README.md
cvoffer's picture
cvoffer
End of training
96073b0 verified
preview code
|
raw
history blame
4.19 kB
metadata
library_name: peft
license: llama3
base_model: WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: b7e96d89-d751-43fd-88d4-c01379498881
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0
bf16: true
chat_template: llama3
data_processes: 8
dataset_prepared_path: null
datasets:
- data_files:
  - 7952e85c9cd96065_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/7952e85c9cd96065_train_data.json
  type:
    field_instruction: instruction
    field_output: output
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 1
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: false
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: cvoffer/b7e96d89-d751-43fd-88d4-c01379498881
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 0.0001
load_in_4bit: true
load_in_8bit: true
local_rank: null
logging_steps: 3
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_memory:
  0: 46GiB
  cpu: 100GiB
max_steps: 30
micro_batch_size: 8
mlflow_experiment_name: /tmp/7952e85c9cd96065_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 10
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: 905ddbe6-314e-4dd4-9588-b9e217590e9c
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 905ddbe6-314e-4dd4-9588-b9e217590e9c
warmup_steps: 5
weight_decay: 0.0
xformers_attention: null

b7e96d89-d751-43fd-88d4-c01379498881

This model is a fine-tuned version of WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2612

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: 5
  • training_steps: 30

Training results

Training Loss Epoch Step Validation Loss
No log 0.0001 1 0.8761
0.1393 0.0003 5 0.6653
0.0713 0.0005 10 0.7411
0.0533 0.0008 15 0.6578
0.048 0.0011 20 0.6100
1.8401 0.0014 25 0.2911
0.1634 0.0016 30 0.2612

Framework versions

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