Hugging Face's logo

brixeus
/
9695f043-7d58-4d3b-b9d1-2e999211dbdc

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
9695f043-7d58-4d3b-b9d1-2e999211dbdc / README.md
brixeus's picture
brixeus
End of training
cc055cc verified
preview code
|
raw
history blame contribute delete
4.3 kB
metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 9695f043-7d58-4d3b-b9d1-2e999211dbdc
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - fb3c1139cf76f78a_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/fb3c1139cf76f78a_train_data.json
  type:
    field_instruction: premise
    field_output: hypothesis
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: brixeus/9695f043-7d58-4d3b-b9d1-2e999211dbdc
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: 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_memory:
  0: 75GB
max_steps: 400
micro_batch_size: 8
mlflow_experiment_name: /tmp/fb3c1139cf76f78a_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
saves_per_epoch: null
sequence_len: 1024
strict: false
tf32: true
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: afa23e14-8c14-45d1-9caf-bd1bb8f81c4e
wandb_project: Gradients-On-Three
wandb_run: your_name
wandb_runid: afa23e14-8c14-45d1-9caf-bd1bb8f81c4e
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

9695f043-7d58-4d3b-b9d1-2e999211dbdc

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

  • Loss: 1.7319

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: 4
  • 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=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-05
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 400

Training results

Training Loss Epoch Step Validation Loss
2.9428 0.0002 1 4.0574
2.1764 0.0100 50 1.8240
2.1889 0.0199 100 1.8153
2.0585 0.0299 150 1.7751
1.8792 0.0398 200 1.7603
2.1116 0.0498 250 1.7502
2.0537 0.0598 300 1.7397
1.8879 0.0697 350 1.7323
1.9717 0.0797 400 1.7319

Framework versions

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