Hugging Face's logo

sn56
/
59c2eda2-c88e-47d1-ad10-99cf5c7714cd

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
59c2eda2-c88e-47d1-ad10-99cf5c7714cd / README.md
RoyJoy's picture
RoyJoy
End of training
4b38dec verified
preview code
|
raw
history blame contribute delete
4.13 kB
metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-1.5B
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 59c2eda2-c88e-47d1-ad10-99cf5c7714cd
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2.5-1.5B
bf16: true
chat_template: llama3
datasets:
- data_files:
  - f96a5129ff7fb986_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f96a5129ff7fb986_train_data.json
  type:
    field_instruction: task_name
    field_output: meta_info
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: sn56/59c2eda2-c88e-47d1-ad10-99cf5c7714cd
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
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_memory:
  0: 77GiB
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/f96a5129ff7fb986_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 25
save_strategy: steps
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: 59c2eda2-c88e-47d1-ad10-99cf5c7714cd
wandb_project: god
wandb_run: srkv
wandb_runid: 59c2eda2-c88e-47d1-ad10-99cf5c7714cd
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

59c2eda2-c88e-47d1-ad10-99cf5c7714cd

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7098

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • 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: 50

Training results

Training Loss Epoch Step Validation Loss
2.5398 0.0084 1 2.5376
2.1979 0.0420 5 2.5045
1.6824 0.0840 10 2.2800
1.972 0.1261 15 2.0205
1.481 0.1681 20 1.8793
1.7239 0.2101 25 1.7845
1.7557 0.2521 30 1.7457
1.3495 0.2941 35 1.7243
1.4501 0.3361 40 1.7142
1.4294 0.3782 45 1.7095
1.6555 0.4202 50 1.7098

Framework versions

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