| { |
| "best_global_step": 500, |
| "best_metric": 1.0366302728652954, |
| "best_model_checkpoint": "Assignment4_Distilled_ModernBERT/run-1/checkpoint-500", |
| "epoch": 1.0482180293501049, |
| "eval_steps": 100, |
| "global_step": 500, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.20964360587002095, |
| "grad_norm": 24.706209182739258, |
| "learning_rate": 5.990041263622974e-05, |
| "loss": 12.0071, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.20964360587002095, |
| "eval_accuracy": 0.7661290322580645, |
| "eval_loss": 5.098243236541748, |
| "eval_runtime": 24.2956, |
| "eval_samples_per_second": 127.595, |
| "eval_steps_per_second": 15.97, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4192872117400419, |
| "grad_norm": 13.007184982299805, |
| "learning_rate": 5.959829353527136e-05, |
| "loss": 3.4751, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4192872117400419, |
| "eval_accuracy": 0.9196774193548387, |
| "eval_loss": 2.054624557495117, |
| "eval_runtime": 24.5401, |
| "eval_samples_per_second": 126.324, |
| "eval_steps_per_second": 15.811, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.6289308176100629, |
| "grad_norm": 6.618763446807861, |
| "learning_rate": 5.9095679050071424e-05, |
| "loss": 1.8181, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6289308176100629, |
| "eval_accuracy": 0.9454838709677419, |
| "eval_loss": 1.4840706586837769, |
| "eval_runtime": 24.5263, |
| "eval_samples_per_second": 126.395, |
| "eval_steps_per_second": 15.82, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.8385744234800838, |
| "grad_norm": 17.116268157958984, |
| "learning_rate": 5.839597383246284e-05, |
| "loss": 1.3857, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8385744234800838, |
| "eval_accuracy": 0.9558064516129032, |
| "eval_loss": 1.2064718008041382, |
| "eval_runtime": 24.6049, |
| "eval_samples_per_second": 125.991, |
| "eval_steps_per_second": 15.769, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.0482180293501049, |
| "grad_norm": 10.49691104888916, |
| "learning_rate": 5.750391760388572e-05, |
| "loss": 1.0929, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0482180293501049, |
| "eval_accuracy": 0.9603225806451613, |
| "eval_loss": 1.0366302728652954, |
| "eval_runtime": 24.6779, |
| "eval_samples_per_second": 125.619, |
| "eval_steps_per_second": 15.723, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 3816, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 224151802852992.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": { |
| "alpha": 0.29055745323517945, |
| "num_train_epochs": 8, |
| "temperature": 5 |
| } |
| } |
|
|
