oldiday's picture
End of training
5f40c17 verified
metadata
library_name: peft
license: apache-2.0
base_model: unsloth/zephyr-sft
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 0f1d98e0-00d9-4a55-83ce-176d2ed66567
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/zephyr-sft
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - cf2fde8cf8e94dcd_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/cf2fde8cf8e94dcd_train_data.json
  type:
    field_input: distraction
    field_instruction: question
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: oldiday/0f1d98e0-00d9-4a55-83ce-176d2ed66567
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: 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_memory:
  0: 75GB
max_steps: 600
micro_batch_size: 8
mlflow_experiment_name: /tmp/cf2fde8cf8e94dcd_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
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
sequence_len: 512
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: techspear-hub
wandb_mode: online
wandb_name: 3a663e10-c37c-4bb9-a725-a32f441f1634
wandb_project: Gradients-On-Six
wandb_run: your_name
wandb_runid: 3a663e10-c37c-4bb9-a725-a32f441f1634
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

0f1d98e0-00d9-4a55-83ce-176d2ed66567

This model is a fine-tuned version of unsloth/zephyr-sft on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8600

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: 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-05
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 600

Training results

Training Loss Epoch Step Validation Loss
No log 0.0003 1 4.2364
8.9732 0.0137 50 2.3193
8.0267 0.0273 100 2.1573
8.4204 0.0410 150 2.1126
7.9481 0.0546 200 2.1126
7.8758 0.0683 250 2.0529
8.2882 0.0819 300 2.0021
8.1177 0.0956 350 1.9586
7.8605 0.1092 400 1.8982
7.9609 0.1229 450 1.8793
7.5728 0.1365 500 1.8650
7.7885 0.1502 550 1.8621
7.9429 0.1638 600 1.8600

Framework versions

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