You can deploy this model and start earning money today!

apriasmoro/
72423c46-21fc-4d4a-8707-6fa2850d3627

Name: 72423c46-21fc-4d4a-8707-6fa2850d3627
Availability: InStock

generated_from_trainer

samoline/9bcc5cc0-4fba-4fd6-a740-9c49004ff9cc

adapter

Views

No views yet

See axolotl config

axolotl version: 0.10.0.dev0

yaml

adapter: lora
base_model: samoline/9bcc5cc0-4fba-4fd6-a740-9c49004ff9cc
bf16: true
chat_template: llama3
datasets:
- data_files:
  - c74d579840835eb0_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/
  type:
    field_input: input
    field_instruction: instruct
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
eval_max_new_tokens: 256
evals_per_epoch: 2
flash_attention: false
fp16: false
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: true
hub_model_id: apriasmoro/72423c46-21fc-4d4a-8707-6fa2850d3627
learning_rate: 0.0002
logging_steps: 10
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: false
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 353
micro_batch_size: 8
mlflow_experiment_name: /tmp/c74d579840835eb0_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
sample_packing: false
save_steps: 44
sequence_len: 2048
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: acc19690-fab5-4194-8e8a-2a68f0c222da
wandb_project: Gradients-On-Demand
wandb_run: apriasmoro
wandb_runid: acc19690-fab5-4194-8e8a-2a68f0c222da
warmup_steps: 100
weight_decay: 0.01

72423c46-21fc-4d4a-8707-6fa2850d3627

This model is a fine-tuned version of samoline/9bcc5cc0-4fba-4fd6-a740-9c49004ff9cc on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.1355

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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: 100
training_steps: 353

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0159	1	1.2434
1.5566	0.9365	59	1.1902
1.4433	1.8730	118	1.1449
1.2584	2.8095	177	1.1762
1.1409	3.7460	236	1.1559
0.8793	4.6825	295	1.1355

Framework versions

PEFT 0.15.2
Transformers 4.51.3
Pytorch 2.5.1+cu124
Datasets 3.5.1
Tokenizers 0.21.1