Hugging Face's logo

error577
/
75d08bc7-3b0c-456d-b472-481534c3e08a

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
75d08bc7-3b0c-456d-b472-481534c3e08a / README.md
error577's picture
error577
End of training
cefab82 verified
preview code
|
raw
history blame contribute delete
4.16 kB
metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-7B
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 75d08bc7-3b0c-456d-b472-481534c3e08a
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: qlora
auto_resume_from_checkpoints: true
base_model: Qwen/Qwen2.5-7B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - e1d136a86ab06d08_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/e1d136a86ab06d08_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: responses
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 4
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: error577/75d08bc7-3b0c-456d-b472-481534c3e08a
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
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: cosine
max_grad_norm: 1.0
max_steps: null
micro_batch_size: 1
mlflow_experiment_name: /tmp/e1d136a86ab06d08_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch_4bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 100
sequence_len: 256
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.0005
wandb_entity: null
wandb_mode: online
wandb_name: c4fbd050-0dc5-4c85-b766-2c4450377849
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: c4fbd050-0dc5-4c85-b766-2c4450377849
warmup_steps: 30
weight_decay: 0.0
xformers_attention: null

75d08bc7-3b0c-456d-b472-481534c3e08a

This model is a fine-tuned version of Qwen/Qwen2.5-7B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3000

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
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Use OptimizerNames.ADAMW_TORCH_4BIT 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: 30
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
3.2021 0.0000 1 4.0772
0.2771 0.0015 100 0.3401
0.2088 0.0030 200 0.2947
0.593 0.0044 300 0.7117
0.2644 0.0059 400 0.3347
0.3288 0.0074 500 0.2273
0.3228 0.0089 600 0.2914
0.082 0.0103 700 0.3419
0.6424 0.0118 800 0.3045
0.2561 0.0133 900 0.3000

Framework versions

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