Hugging Face's logo

daniel40
/
3c83c7ef-bb0d-4c2f-a027-c2c1cab0d46a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
3c83c7ef-bb0d-4c2f-a027-c2c1cab0d46a / README.md
daniel40's picture
daniel40
End of training
56085fe verified
preview code
|
raw
history blame contribute delete
3.84 kB
metadata
library_name: peft
base_model: NousResearch/Yarn-Llama-2-7b-64k
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 3c83c7ef-bb0d-4c2f-a027-c2c1cab0d46a
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Yarn-Llama-2-7b-64k
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 955251e87aa4040a_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/955251e87aa4040a_train_data.json
  type:
    field_input: ''
    field_instruction: question
    field_output: context
    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: daniel40/3c83c7ef-bb0d-4c2f-a027-c2c1cab0d46a
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 5.0e-05
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_steps: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/955251e87aa4040a_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
saves_per_epoch: 4
sequence_len: 512
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: 968d2ddf-11bf-47b0-8936-8309f61eb2a1
wandb_project: Birthday-SN56-27-Gradients-On-Demand
wandb_run: your_name
wandb_runid: 968d2ddf-11bf-47b0-8936-8309f61eb2a1
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

3c83c7ef-bb0d-4c2f-a027-c2c1cab0d46a

This model is a fine-tuned version of NousResearch/Yarn-Llama-2-7b-64k on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.0318

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: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • 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: 10
  • training_steps: 50

Training results

Training Loss Epoch Step Validation Loss
13.1525 0.0002 1 3.2820
11.8233 0.0026 13 3.2339
13.0966 0.0052 26 3.0876
11.8259 0.0078 39 3.0318

Framework versions

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