Instructions to use verz/qwenfi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use verz/qwenfi with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-3B-Instruct") model = PeftModel.from_pretrained(base_model, "verz/qwenfi") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 308, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16260162601626016, | |
| "grad_norm": 0.37675046920776367, | |
| "learning_rate": 0.0001681818181818182, | |
| "loss": 1.7515, | |
| "mean_token_accuracy": 0.6049755607545376, | |
| "num_tokens": 204800.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3252032520325203, | |
| "grad_norm": 0.3089984357357025, | |
| "learning_rate": 0.00013571428571428572, | |
| "loss": 1.3323, | |
| "mean_token_accuracy": 0.6925122183561325, | |
| "num_tokens": 409600.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 0.3363010883331299, | |
| "learning_rate": 0.00010324675324675325, | |
| "loss": 1.2756, | |
| "mean_token_accuracy": 0.7040957960486413, | |
| "num_tokens": 614400.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6504065040650406, | |
| "grad_norm": 0.335611492395401, | |
| "learning_rate": 7.077922077922077e-05, | |
| "loss": 1.2833, | |
| "mean_token_accuracy": 0.7033577680587768, | |
| "num_tokens": 819200.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8130081300813008, | |
| "grad_norm": 0.3524633049964905, | |
| "learning_rate": 3.831168831168831e-05, | |
| "loss": 1.2286, | |
| "mean_token_accuracy": 0.7145161288976669, | |
| "num_tokens": 1024000.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.34292736649513245, | |
| "learning_rate": 5.844155844155844e-06, | |
| "loss": 1.2549, | |
| "mean_token_accuracy": 0.7073900297284126, | |
| "num_tokens": 1228800.0, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 308, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.09971568443392e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |