Hugging Face's logo

lesso
/
83d3e4dd-ac1d-48e3-99a3-4d057fc4cefd

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
83d3e4dd-ac1d-48e3-99a3-4d057fc4cefd / README.md
lesso's picture
lesso
End of training
25bf253 verified
preview code
|
raw
history blame contribute delete
3.99 kB
metadata
library_name: peft
license: apache-2.0
base_model: 01-ai/Yi-1.5-9B-Chat-16K
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 83d3e4dd-ac1d-48e3-99a3-4d057fc4cefd
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: 01-ai/Yi-1.5-9B-Chat-16K
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 26d69314b78807d1_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/26d69314b78807d1_train_data.json
  type:
    field_instruction: system
    field_output: response
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 50
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: lesso/83d3e4dd-ac1d-48e3-99a3-4d057fc4cefd
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000211
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 128
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: constant
max_grad_norm: 1.0
max_steps: 400
micro_batch_size: 32
mlflow_experiment_name: /tmp/G.O.D/26d69314b78807d1_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
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: null
wandb_mode: online
wandb_name: 755da145-89e1-42ac-9dc2-8d3fa24de040
wandb_project: 11a
wandb_run: your_name
wandb_runid: 755da145-89e1-42ac-9dc2-8d3fa24de040
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

83d3e4dd-ac1d-48e3-99a3-4d057fc4cefd

This model is a fine-tuned version of 01-ai/Yi-1.5-9B-Chat-16K on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7545

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: 0.000211
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • 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: constant
  • lr_scheduler_warmup_steps: 50
  • training_steps: 400

Training results

Training Loss Epoch Step Validation Loss
No log 0.0001 1 2.0396
0.6532 0.0071 50 1.8848
0.9425 0.0142 100 1.7181
0.921 0.0213 150 1.6833
0.937 0.0284 200 1.6947
1.257 0.0355 250 1.7068
1.6691 0.0426 300 1.7545

Framework versions

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