| { |
| "best_metric": 0.07372047752141953, |
| "best_model_checkpoint": "/content/dnrti_our/checkpoint-1000", |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 3520, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.42, |
| "learning_rate": 1.715909090909091e-05, |
| "loss": 0.13, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.42, |
| "eval_accuracy": 0.979574031306133, |
| "eval_f1": 0.733705772811918, |
| "eval_loss": 0.08860738575458527, |
| "eval_precision": 0.7137681159420289, |
| "eval_recall": 0.7547892720306514, |
| "eval_runtime": 4.2683, |
| "eval_samples_per_second": 190.242, |
| "eval_steps_per_second": 23.897, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.84, |
| "learning_rate": 1.431818181818182e-05, |
| "loss": 0.0421, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.84, |
| "eval_accuracy": 0.9835771105978958, |
| "eval_f1": 0.7874920229738354, |
| "eval_loss": 0.07372047752141953, |
| "eval_precision": 0.7869897959183674, |
| "eval_recall": 0.7879948914431673, |
| "eval_runtime": 4.138, |
| "eval_samples_per_second": 196.232, |
| "eval_steps_per_second": 24.65, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.26, |
| "learning_rate": 1.1477272727272729e-05, |
| "loss": 0.0249, |
| "step": 1500 |
| }, |
| { |
| "epoch": 4.26, |
| "eval_accuracy": 0.9821914293045932, |
| "eval_f1": 0.7684478371501273, |
| "eval_loss": 0.08549553900957108, |
| "eval_precision": 0.7655259822560203, |
| "eval_recall": 0.7713920817369093, |
| "eval_runtime": 3.9823, |
| "eval_samples_per_second": 203.9, |
| "eval_steps_per_second": 25.613, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.68, |
| "learning_rate": 8.636363636363637e-06, |
| "loss": 0.0167, |
| "step": 2000 |
| }, |
| { |
| "epoch": 5.68, |
| "eval_accuracy": 0.9826020015396458, |
| "eval_f1": 0.77743335399876, |
| "eval_loss": 0.09457844495773315, |
| "eval_precision": 0.755421686746988, |
| "eval_recall": 0.8007662835249042, |
| "eval_runtime": 4.0013, |
| "eval_samples_per_second": 202.937, |
| "eval_steps_per_second": 25.492, |
| "step": 2000 |
| }, |
| { |
| "epoch": 7.1, |
| "learning_rate": 5.795454545454546e-06, |
| "loss": 0.0104, |
| "step": 2500 |
| }, |
| { |
| "epoch": 7.1, |
| "eval_accuracy": 0.981986143187067, |
| "eval_f1": 0.7681704260651631, |
| "eval_loss": 0.09761953353881836, |
| "eval_precision": 0.7539975399753998, |
| "eval_recall": 0.7828863346104725, |
| "eval_runtime": 4.1035, |
| "eval_samples_per_second": 197.878, |
| "eval_steps_per_second": 24.857, |
| "step": 2500 |
| }, |
| { |
| "epoch": 8.52, |
| "learning_rate": 2.954545454545455e-06, |
| "loss": 0.0066, |
| "step": 3000 |
| }, |
| { |
| "epoch": 8.52, |
| "eval_accuracy": 0.9835771105978958, |
| "eval_f1": 0.7897371714643304, |
| "eval_loss": 0.10236399620771408, |
| "eval_precision": 0.7742331288343558, |
| "eval_recall": 0.8058748403575989, |
| "eval_runtime": 3.5311, |
| "eval_samples_per_second": 229.955, |
| "eval_steps_per_second": 28.886, |
| "step": 3000 |
| }, |
| { |
| "epoch": 9.94, |
| "learning_rate": 1.1363636363636364e-07, |
| "loss": 0.0044, |
| "step": 3500 |
| }, |
| { |
| "epoch": 9.94, |
| "eval_accuracy": 0.9832691814216064, |
| "eval_f1": 0.7871536523929471, |
| "eval_loss": 0.10687276721000671, |
| "eval_precision": 0.7763975155279503, |
| "eval_recall": 0.7982120051085568, |
| "eval_runtime": 3.5664, |
| "eval_samples_per_second": 227.682, |
| "eval_steps_per_second": 28.6, |
| "step": 3500 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 3520, |
| "total_flos": 1150724100209448.0, |
| "train_loss": 0.03344021574170752, |
| "train_runtime": 609.2851, |
| "train_samples_per_second": 46.12, |
| "train_steps_per_second": 5.777 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 3520, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "total_flos": 1150724100209448.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
