Hugging Face's logo

ardaspear
/
791b0035-ff48-42a1-ba16-1c53402e5220

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
791b0035-ff48-42a1-ba16-1c53402e5220 / README.md
ardaspear's picture
ardaspear
End of training
0150cde verified
preview code
|
raw
history blame contribute delete
4.31 kB
metadata
library_name: peft
license: apache-2.0
base_model: unsloth/Qwen2.5-Math-1.5B-Instruct
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 791b0035-ff48-42a1-ba16-1c53402e5220
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Qwen2.5-Math-1.5B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 0347e5be1c3bc1c1_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/0347e5be1c3bc1c1_train_data.json
  type:
    field_input: evidence
    field_instruction: question
    field_output: SQL
    format: '{instruction} {input}'
    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: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: ardaspear/791b0035-ff48-42a1-ba16-1c53402e5220
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
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: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/0347e5be1c3bc1c1_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 1024
strict: false
tf32: false
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: fbbaa3c9-5f26-464c-acf6-f08b215d0c32
wandb_project: Gradients-On-Five
wandb_run: your_name
wandb_runid: fbbaa3c9-5f26-464c-acf6-f08b215d0c32
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

791b0035-ff48-42a1-ba16-1c53402e5220

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

  • Loss: 2.0743

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • 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=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 100

Training results

Training Loss Epoch Step Validation Loss
No log 0.0202 1 4.9803
4.7838 0.1818 9 4.7569
3.689 0.3636 18 3.8252
3.3348 0.5455 27 3.3226
2.9187 0.7273 36 2.8548
2.5997 0.9091 45 2.5247
2.2329 1.0909 54 2.3284
2.1025 1.2727 63 2.2063
2.0875 1.4545 72 2.1309
1.9271 1.6364 81 2.0925
2.0393 1.8182 90 2.0765
2.2999 2.0 99 2.0743

Framework versions

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