Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Genstruct-7B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - b5c2ff0f66a16b92_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/b5c2ff0f66a16b92_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: null
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: sn56c1/b0ebab3f-9722-449e-8b3e-0911eb63a612
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: 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: 75GiB
max_steps: 30
micro_batch_size: 2
mlflow_experiment_name: /tmp/b5c2ff0f66a16b92_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: sn56c1/b0ebab3f
wandb_project: god
wandb_run: 3lhd
wandb_runid: sn56c1/b0ebab3f
warmup_steps: 10
weight_decay: 0.01
xformers_attention: true

462a995d-3629-4983-955e-1227fcc35800

This model is a fine-tuned version of NousResearch/Genstruct-7B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9208

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: 30

Training results

Training Loss Epoch Step Validation Loss
No log 0.0020 1 1.3801
5.512 0.0100 5 1.2458
4.0437 0.0201 10 1.0621
4.299 0.0301 15 0.9967
3.8038 0.0402 20 0.9541
3.8103 0.0502 25 0.9262
3.7993 0.0602 30 0.9208

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1
Downloads last month
0
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for sn56c1/b0ebab3f-9722-449e-8b3e-0911eb63a612

Adapter
(91)
this model