You can deploy this model and start earning money today!

cpheemagazine/
ed0268ac-4c31-4826-bc82-87564574c775

Name: ed0268ac-4c31-4826-bc82-87564574c775
Availability: InStock

generated_from_trainer

deepseek-ai/deepseek-coder-6.7b-instruct

adapter

other

Views

No views yet

See axolotl config

axolotl version: 0.12.0.dev0

yaml

adapter: lora
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
bf16: true
datasets:
- data_files:
  - ecaedadc08522661_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/
  type:
    field_instruction: instruct
    field_output: output
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
eval_max_new_tokens: 128
evals_per_epoch: null
flash_attention: false
fp16: false
gradient_accumulation_steps: 1
gradient_checkpointing: true
group_by_length: true
hf_upload_public: true
hf_upload_repo_type: model
hub_model_id: cpheemagazine/ed0268ac-4c31-4826-bc82-87564574c775
learning_rate: 0.0002
load_in_4bit: false
logging_steps: 10
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
loraplus_lr_embedding: 1.0e-06
loraplus_lr_ratio: 16
lr_scheduler: cosine
max_steps: 100
micro_batch_size: 60
mlflow_experiment_name: /tmp/ecaedadc08522661_train_data.json
model_card: false
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
push_to_hub: true
rl: null
sample_packing: false
save_steps: 437
sequence_len: 1024
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trl: null
trust_remote_code: true
wandb_name: 6dd00401-5815-43fd-999d-6b30aedf53fa
wandb_project: Gradients-On-Demand
wandb_run: apriasmoro
wandb_runid: 6dd00401-5815-43fd-999d-6b30aedf53fa
warmup_steps: 291
weight_decay: 0.02

ed0268ac-4c31-4826-bc82-87564574c775

This model is a fine-tuned version of deepseek-ai/deepseek-coder-6.7b-instruct on an unknown dataset.

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: 60
eval_batch_size: 60
seed: 42
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: 291
training_steps: 100

Training results

Framework versions

PEFT 0.15.2
Transformers 4.53.1
Pytorch 2.7.1+cu128
Datasets 3.6.0
Tokenizers 0.21.2