| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 28.125, | |
| "eval_steps": 100, | |
| "global_step": 900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 8.958333333333334e-07, | |
| "loss": 0.5457, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_accuracy": 0.783256880733945, | |
| "eval_f1": 0.8134254689042448, | |
| "eval_loss": 0.4702916741371155, | |
| "eval_precision": 0.8477366255144033, | |
| "eval_recall": 0.7817836812144212, | |
| "eval_runtime": 8.092, | |
| "eval_samples_per_second": 107.761, | |
| "eval_steps_per_second": 1.73, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 7.916666666666666e-07, | |
| "loss": 0.4347, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "eval_accuracy": 0.8279816513761468, | |
| "eval_f1": 0.8557692307692307, | |
| "eval_loss": 0.3783995807170868, | |
| "eval_precision": 0.8674463937621832, | |
| "eval_recall": 0.8444022770398482, | |
| "eval_runtime": 7.9109, | |
| "eval_samples_per_second": 110.228, | |
| "eval_steps_per_second": 1.77, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 6.875e-07, | |
| "loss": 0.3672, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "eval_accuracy": 0.8497706422018348, | |
| "eval_f1": 0.8751191611058151, | |
| "eval_loss": 0.3128945529460907, | |
| "eval_precision": 0.8793103448275862, | |
| "eval_recall": 0.8709677419354839, | |
| "eval_runtime": 7.9781, | |
| "eval_samples_per_second": 109.299, | |
| "eval_steps_per_second": 1.755, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 5.833333333333334e-07, | |
| "loss": 0.3251, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "eval_accuracy": 0.8658256880733946, | |
| "eval_f1": 0.8925619834710744, | |
| "eval_loss": 0.29092392325401306, | |
| "eval_precision": 0.8647686832740213, | |
| "eval_recall": 0.9222011385199241, | |
| "eval_runtime": 8.2084, | |
| "eval_samples_per_second": 106.233, | |
| "eval_steps_per_second": 1.706, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 15.62, | |
| "learning_rate": 4.791666666666667e-07, | |
| "loss": 0.2957, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 15.62, | |
| "eval_accuracy": 0.8715596330275229, | |
| "eval_f1": 0.8968692449355433, | |
| "eval_loss": 0.27530843019485474, | |
| "eval_precision": 0.8711985688729875, | |
| "eval_recall": 0.9240986717267552, | |
| "eval_runtime": 8.2097, | |
| "eval_samples_per_second": 106.216, | |
| "eval_steps_per_second": 1.705, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 3.75e-07, | |
| "loss": 0.2763, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "eval_accuracy": 0.8784403669724771, | |
| "eval_f1": 0.8990476190476191, | |
| "eval_loss": 0.25807398557662964, | |
| "eval_precision": 0.9024856596558317, | |
| "eval_recall": 0.8956356736242884, | |
| "eval_runtime": 8.114, | |
| "eval_samples_per_second": 107.468, | |
| "eval_steps_per_second": 1.725, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 21.88, | |
| "learning_rate": 2.708333333333333e-07, | |
| "loss": 0.2595, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 21.88, | |
| "eval_accuracy": 0.8841743119266054, | |
| "eval_f1": 0.906567992599445, | |
| "eval_loss": 0.25655582547187805, | |
| "eval_precision": 0.8844765342960289, | |
| "eval_recall": 0.9297912713472486, | |
| "eval_runtime": 8.2553, | |
| "eval_samples_per_second": 105.63, | |
| "eval_steps_per_second": 1.696, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 1.6666666666666665e-07, | |
| "loss": 0.2521, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8807339449541285, | |
| "eval_f1": 0.9017013232514178, | |
| "eval_loss": 0.24835383892059326, | |
| "eval_precision": 0.8983050847457628, | |
| "eval_recall": 0.905123339658444, | |
| "eval_runtime": 8.3369, | |
| "eval_samples_per_second": 104.595, | |
| "eval_steps_per_second": 1.679, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "learning_rate": 6.25e-08, | |
| "loss": 0.2399, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "eval_accuracy": 0.8853211009174312, | |
| "eval_f1": 0.9070631970260222, | |
| "eval_loss": 0.2506503164768219, | |
| "eval_precision": 0.8888888888888888, | |
| "eval_recall": 0.9259962049335864, | |
| "eval_runtime": 8.3716, | |
| "eval_samples_per_second": 104.161, | |
| "eval_steps_per_second": 1.672, | |
| "step": 900 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 960, | |
| "num_train_epochs": 30, | |
| "save_steps": 100, | |
| "total_flos": 3761172536371200.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |