| { |
| "best_global_step": 200, |
| "best_metric": 0.0063307080417871475, |
| "best_model_checkpoint": "./stm32-production-codegen/checkpoint-200", |
| "epoch": 3.6363636363636362, |
| "eval_steps": 50, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.45454545454545453, |
| "grad_norm": 1.4344652891159058, |
| "learning_rate": 7.2e-06, |
| "loss": 0.8828, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 0.27160438895225525, |
| "learning_rate": 1.47e-05, |
| "loss": 0.0534, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "eval_loss": 0.01262649241834879, |
| "eval_runtime": 10.799, |
| "eval_samples_per_second": 11.112, |
| "eval_steps_per_second": 1.389, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.3636363636363638, |
| "grad_norm": 0.1857883781194687, |
| "learning_rate": 2.22e-05, |
| "loss": 0.0109, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "grad_norm": 0.10685799270868301, |
| "learning_rate": 2.97e-05, |
| "loss": 0.0089, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "eval_loss": 0.008137406781315804, |
| "eval_runtime": 10.7819, |
| "eval_samples_per_second": 11.13, |
| "eval_steps_per_second": 1.391, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.2727272727272725, |
| "grad_norm": 0.09965123236179352, |
| "learning_rate": 2.6869565217391306e-05, |
| "loss": 0.0077, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "grad_norm": 0.08391156047582626, |
| "learning_rate": 2.3608695652173915e-05, |
| "loss": 0.0072, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "eval_loss": 0.006944730877876282, |
| "eval_runtime": 10.7776, |
| "eval_samples_per_second": 11.134, |
| "eval_steps_per_second": 1.392, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.1818181818181817, |
| "grad_norm": 0.07116695493459702, |
| "learning_rate": 2.034782608695652e-05, |
| "loss": 0.0068, |
| "step": 175 |
| }, |
| { |
| "epoch": 3.6363636363636362, |
| "grad_norm": 0.07140898704528809, |
| "learning_rate": 1.7086956521739133e-05, |
| "loss": 0.0065, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.6363636363636362, |
| "eval_loss": 0.0063307080417871475, |
| "eval_runtime": 10.7962, |
| "eval_samples_per_second": 11.115, |
| "eval_steps_per_second": 1.389, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 330, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 1 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8973689919897600.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
