Hugging Face's logo

jssky
/
1d04373e-3697-4945-b027-2f834ada86f6

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
1d04373e-3697-4945-b027-2f834ada86f6 / README.md
jssky's picture
jssky
End of training
45fb6cf verified
preview code
|
raw
history blame contribute delete
4.01 kB
metadata
library_name: peft
license: other
base_model: Qwen/Qwen1.5-0.5B-Chat
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 1d04373e-3697-4945-b027-2f834ada86f6
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen1.5-0.5B-Chat
bf16: false
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 2772e5dcce25c79d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2772e5dcce25c79d_train_data.json
  type:
    field_input: explanation
    field_instruction: question
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
devices:
- 0
- 1
- 2
- 3
- 4
- 5
- 6
- 7
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: jssky/1d04373e-3697-4945-b027-2f834ada86f6
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: 1
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_steps: 10
micro_batch_size: 1
mlflow_experiment_name: /tmp/2772e5dcce25c79d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
num_gpus: 8
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: 4056
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_batch_size: 16
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 1d04373e-3697-4945-b027-2f834ada86f6
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 1d04373e-3697-4945-b027-2f834ada86f6
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

1d04373e-3697-4945-b027-2f834ada86f6

This model is a fine-tuned version of Qwen/Qwen1.5-0.5B-Chat on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.3834

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: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • total_eval_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: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
4.7847 0.0137 1 4.8877
4.5614 0.0411 3 4.8877
4.6968 0.0822 6 4.4276
3.2615 0.1233 9 3.3834

Framework versions

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