| { | |
| "best_metric": 0.5146198830409356, | |
| "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-yor/checkpoint-2000", | |
| "epoch": 44.11764705882353, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.94, | |
| "eval_accuracy_score": 0.918060435699227, | |
| "eval_f1": 0.29637305699481864, | |
| "eval_loss": 0.27648022770881653, | |
| "eval_precision": 0.23636363636363636, | |
| "eval_recall": 0.3972222222222222, | |
| "eval_runtime": 2.3819, | |
| "eval_samples_per_second": 128.049, | |
| "eval_steps_per_second": 16.373, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "eval_accuracy_score": 0.9343640196767393, | |
| "eval_f1": 0.407185628742515, | |
| "eval_loss": 0.21811498701572418, | |
| "eval_precision": 0.35789473684210527, | |
| "eval_recall": 0.4722222222222222, | |
| "eval_runtime": 2.3801, | |
| "eval_samples_per_second": 128.145, | |
| "eval_steps_per_second": 16.386, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 4.865771812080537e-05, | |
| "loss": 0.3062, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "eval_accuracy_score": 0.9374560787069571, | |
| "eval_f1": 0.42857142857142855, | |
| "eval_loss": 0.22281676530838013, | |
| "eval_precision": 0.3620689655172414, | |
| "eval_recall": 0.525, | |
| "eval_runtime": 2.3751, | |
| "eval_samples_per_second": 128.418, | |
| "eval_steps_per_second": 16.421, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "eval_accuracy_score": 0.9422347153900211, | |
| "eval_f1": 0.48, | |
| "eval_loss": 0.22548547387123108, | |
| "eval_precision": 0.4163265306122449, | |
| "eval_recall": 0.5666666666666667, | |
| "eval_runtime": 2.3756, | |
| "eval_samples_per_second": 128.388, | |
| "eval_steps_per_second": 16.417, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 4.697986577181208e-05, | |
| "loss": 0.0666, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "eval_accuracy_score": 0.9457484188334505, | |
| "eval_f1": 0.5048076923076923, | |
| "eval_loss": 0.2493690848350525, | |
| "eval_precision": 0.4449152542372881, | |
| "eval_recall": 0.5833333333333334, | |
| "eval_runtime": 2.3673, | |
| "eval_samples_per_second": 128.84, | |
| "eval_steps_per_second": 16.475, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "eval_accuracy_score": 0.9447645818692902, | |
| "eval_f1": 0.49325153374233127, | |
| "eval_loss": 0.2621992826461792, | |
| "eval_precision": 0.44175824175824174, | |
| "eval_recall": 0.5583333333333333, | |
| "eval_runtime": 2.3771, | |
| "eval_samples_per_second": 128.306, | |
| "eval_steps_per_second": 16.406, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 20.59, | |
| "eval_accuracy_score": 0.9436401967673929, | |
| "eval_f1": 0.5073891625615763, | |
| "eval_loss": 0.2808593511581421, | |
| "eval_precision": 0.4557522123893805, | |
| "eval_recall": 0.5722222222222222, | |
| "eval_runtime": 2.3795, | |
| "eval_samples_per_second": 128.177, | |
| "eval_steps_per_second": 16.39, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 22.06, | |
| "learning_rate": 4.530201342281879e-05, | |
| "loss": 0.0187, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 23.53, | |
| "eval_accuracy_score": 0.9425158116654955, | |
| "eval_f1": 0.4976190476190476, | |
| "eval_loss": 0.3069038391113281, | |
| "eval_precision": 0.4354166666666667, | |
| "eval_recall": 0.5805555555555556, | |
| "eval_runtime": 2.3752, | |
| "eval_samples_per_second": 128.408, | |
| "eval_steps_per_second": 16.419, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 26.47, | |
| "eval_accuracy_score": 0.9429374560787069, | |
| "eval_f1": 0.4959443800695249, | |
| "eval_loss": 0.2936417758464813, | |
| "eval_precision": 0.4254473161033797, | |
| "eval_recall": 0.5944444444444444, | |
| "eval_runtime": 2.3751, | |
| "eval_samples_per_second": 128.415, | |
| "eval_steps_per_second": 16.42, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 29.41, | |
| "learning_rate": 4.36241610738255e-05, | |
| "loss": 0.0071, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 29.41, | |
| "eval_accuracy_score": 0.9432185523541813, | |
| "eval_f1": 0.5146198830409356, | |
| "eval_loss": 0.3124857544898987, | |
| "eval_precision": 0.4444444444444444, | |
| "eval_recall": 0.6111111111111112, | |
| "eval_runtime": 2.3658, | |
| "eval_samples_per_second": 128.919, | |
| "eval_steps_per_second": 16.485, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 32.35, | |
| "eval_accuracy_score": 0.9450456781447646, | |
| "eval_f1": 0.49709639953542395, | |
| "eval_loss": 0.3202134370803833, | |
| "eval_precision": 0.42714570858283435, | |
| "eval_recall": 0.5944444444444444, | |
| "eval_runtime": 2.3712, | |
| "eval_samples_per_second": 128.625, | |
| "eval_steps_per_second": 16.447, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 35.29, | |
| "eval_accuracy_score": 0.9444834855938159, | |
| "eval_f1": 0.49446494464944646, | |
| "eval_loss": 0.3432020843029022, | |
| "eval_precision": 0.44370860927152317, | |
| "eval_recall": 0.5583333333333333, | |
| "eval_runtime": 2.372, | |
| "eval_samples_per_second": 128.582, | |
| "eval_steps_per_second": 16.442, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 36.76, | |
| "learning_rate": 4.194630872483222e-05, | |
| "loss": 0.0045, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 38.24, | |
| "eval_accuracy_score": 0.946170063246662, | |
| "eval_f1": 0.5048543689320388, | |
| "eval_loss": 0.33581680059432983, | |
| "eval_precision": 0.4482758620689655, | |
| "eval_recall": 0.5777777777777777, | |
| "eval_runtime": 2.3711, | |
| "eval_samples_per_second": 128.633, | |
| "eval_steps_per_second": 16.448, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 41.18, | |
| "eval_accuracy_score": 0.9467322557976107, | |
| "eval_f1": 0.5108433734939758, | |
| "eval_loss": 0.3493315279483795, | |
| "eval_precision": 0.451063829787234, | |
| "eval_recall": 0.5888888888888889, | |
| "eval_runtime": 2.3774, | |
| "eval_samples_per_second": 128.29, | |
| "eval_steps_per_second": 16.404, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 44.12, | |
| "learning_rate": 4.026845637583892e-05, | |
| "loss": 0.0024, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 44.12, | |
| "eval_accuracy_score": 0.9456078706957133, | |
| "eval_f1": 0.5047393364928909, | |
| "eval_loss": 0.3553647994995117, | |
| "eval_precision": 0.44008264462809915, | |
| "eval_recall": 0.5916666666666667, | |
| "eval_runtime": 2.3665, | |
| "eval_samples_per_second": 128.88, | |
| "eval_steps_per_second": 16.48, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 44.12, | |
| "step": 3000, | |
| "total_flos": 1.572865183079424e+16, | |
| "train_loss": 0.06757608306407928, | |
| "train_runtime": 1505.3266, | |
| "train_samples_per_second": 318.868, | |
| "train_steps_per_second": 9.965 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 221, | |
| "total_flos": 1.572865183079424e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |