| { | |
| "best_metric": 0.09375, | |
| "best_model_checkpoint": "videomae-base-finetuned-NOSTRO-Nuovo-subset/checkpoint-280", | |
| "epoch": 3.0625, | |
| "eval_steps": 500, | |
| "global_step": 448, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022321428571428572, | |
| "grad_norm": 10.661712646484375, | |
| "learning_rate": 0.004888392857142857, | |
| "loss": 3.7577, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.044642857142857144, | |
| "grad_norm": 11.643506050109863, | |
| "learning_rate": 0.004776785714285714, | |
| "loss": 3.8846, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06696428571428571, | |
| "grad_norm": 6.997533321380615, | |
| "learning_rate": 0.004665178571428572, | |
| "loss": 3.5104, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08928571428571429, | |
| "grad_norm": 3.857959270477295, | |
| "learning_rate": 0.0045535714285714285, | |
| "loss": 3.0997, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11160714285714286, | |
| "grad_norm": 7.694955348968506, | |
| "learning_rate": 0.004441964285714285, | |
| "loss": 3.0891, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13392857142857142, | |
| "grad_norm": 6.335569858551025, | |
| "learning_rate": 0.004330357142857143, | |
| "loss": 3.1063, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "grad_norm": 6.71449089050293, | |
| "learning_rate": 0.00421875, | |
| "loss": 2.9859, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 3.177128553390503, | |
| "learning_rate": 0.004107142857142857, | |
| "loss": 3.0683, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20089285714285715, | |
| "grad_norm": 3.323209285736084, | |
| "learning_rate": 0.0039955357142857145, | |
| "loss": 2.7508, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22321428571428573, | |
| "grad_norm": 3.6122429370880127, | |
| "learning_rate": 0.0038839285714285716, | |
| "loss": 2.6113, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24553571428571427, | |
| "grad_norm": 2.3688178062438965, | |
| "learning_rate": 0.0037723214285714287, | |
| "loss": 1.987, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.26785714285714285, | |
| "grad_norm": 4.9541215896606445, | |
| "learning_rate": 0.0036607142857142854, | |
| "loss": 3.0538, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.29017857142857145, | |
| "grad_norm": 2.793215751647949, | |
| "learning_rate": 0.003549107142857143, | |
| "loss": 2.9083, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 2.4145069122314453, | |
| "learning_rate": 0.0034375, | |
| "loss": 2.8766, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "eval_accuracy": 0.0625, | |
| "eval_loss": 2.7276196479797363, | |
| "eval_runtime": 43.9026, | |
| "eval_samples_per_second": 1.458, | |
| "eval_steps_per_second": 0.364, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0223214285714286, | |
| "grad_norm": 3.8258724212646484, | |
| "learning_rate": 0.003325892857142857, | |
| "loss": 2.7419, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0446428571428572, | |
| "grad_norm": 2.8611817359924316, | |
| "learning_rate": 0.0032142857142857147, | |
| "loss": 2.9858, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0669642857142858, | |
| "grad_norm": 1.5673381090164185, | |
| "learning_rate": 0.0031026785714285718, | |
| "loss": 2.7431, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0892857142857142, | |
| "grad_norm": 1.6212363243103027, | |
| "learning_rate": 0.0029910714285714284, | |
| "loss": 2.6825, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.1116071428571428, | |
| "grad_norm": 2.7107715606689453, | |
| "learning_rate": 0.0028794642857142855, | |
| "loss": 2.4267, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.1339285714285714, | |
| "grad_norm": 2.5624172687530518, | |
| "learning_rate": 0.002767857142857143, | |
| "loss": 2.4435, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.15625, | |
| "grad_norm": 1.173656940460205, | |
| "learning_rate": 0.00265625, | |
| "loss": 2.8848, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.1785714285714286, | |
| "grad_norm": 1.2296289205551147, | |
| "learning_rate": 0.002544642857142857, | |
| "loss": 2.7724, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2008928571428572, | |
| "grad_norm": 1.0573370456695557, | |
| "learning_rate": 0.0024330357142857144, | |
| "loss": 2.7356, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.2232142857142858, | |
| "grad_norm": 0.9930482506752014, | |
| "learning_rate": 0.0023214285714285715, | |
| "loss": 2.5956, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.2455357142857142, | |
| "grad_norm": 0.8850785493850708, | |
| "learning_rate": 0.0022098214285714286, | |
| "loss": 2.6961, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.2678571428571428, | |
| "grad_norm": 1.2825168371200562, | |
| "learning_rate": 0.0020982142857142857, | |
| "loss": 2.6601, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.2901785714285714, | |
| "grad_norm": 1.7537394762039185, | |
| "learning_rate": 0.001986607142857143, | |
| "loss": 2.5393, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.3125, | |
| "grad_norm": 1.3740110397338867, | |
| "learning_rate": 0.001875, | |
| "loss": 2.719, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.3125, | |
| "eval_accuracy": 0.09375, | |
| "eval_loss": 2.659668445587158, | |
| "eval_runtime": 44.7095, | |
| "eval_samples_per_second": 1.431, | |
| "eval_steps_per_second": 0.358, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0223214285714284, | |
| "grad_norm": 1.630075216293335, | |
| "learning_rate": 0.0017633928571428573, | |
| "loss": 2.6041, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.044642857142857, | |
| "grad_norm": 1.299541711807251, | |
| "learning_rate": 0.0016517857142857144, | |
| "loss": 2.5322, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0669642857142856, | |
| "grad_norm": 1.2279021739959717, | |
| "learning_rate": 0.0015401785714285715, | |
| "loss": 2.7214, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.0892857142857144, | |
| "grad_norm": 0.823603630065918, | |
| "learning_rate": 0.0014285714285714286, | |
| "loss": 2.5328, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.111607142857143, | |
| "grad_norm": 1.4392638206481934, | |
| "learning_rate": 0.0013169642857142857, | |
| "loss": 2.6212, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.1339285714285716, | |
| "grad_norm": 1.9096788167953491, | |
| "learning_rate": 0.001205357142857143, | |
| "loss": 2.6821, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.15625, | |
| "grad_norm": 1.3150078058242798, | |
| "learning_rate": 0.00109375, | |
| "loss": 2.4551, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.1785714285714284, | |
| "grad_norm": 1.3114469051361084, | |
| "learning_rate": 0.0009821428571428572, | |
| "loss": 2.5904, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.200892857142857, | |
| "grad_norm": 1.3170655965805054, | |
| "learning_rate": 0.0008705357142857143, | |
| "loss": 2.5248, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.2232142857142856, | |
| "grad_norm": 1.2158620357513428, | |
| "learning_rate": 0.0007589285714285714, | |
| "loss": 2.6605, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.2455357142857144, | |
| "grad_norm": 1.0650196075439453, | |
| "learning_rate": 0.0006473214285714286, | |
| "loss": 2.7011, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.267857142857143, | |
| "grad_norm": 0.740188479423523, | |
| "learning_rate": 0.0005357142857142857, | |
| "loss": 2.6101, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.2901785714285716, | |
| "grad_norm": 0.9205682873725891, | |
| "learning_rate": 0.0004241071428571429, | |
| "loss": 2.5906, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.3125, | |
| "grad_norm": 0.952158510684967, | |
| "learning_rate": 0.0003125, | |
| "loss": 2.6488, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.3125, | |
| "eval_accuracy": 0.09375, | |
| "eval_loss": 2.63785719871521, | |
| "eval_runtime": 45.7954, | |
| "eval_samples_per_second": 1.398, | |
| "eval_steps_per_second": 0.349, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.0223214285714284, | |
| "grad_norm": 0.751361608505249, | |
| "learning_rate": 0.00020089285714285717, | |
| "loss": 2.5654, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.044642857142857, | |
| "grad_norm": 1.7467005252838135, | |
| "learning_rate": 8.928571428571429e-05, | |
| "loss": 2.573, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.0625, | |
| "eval_accuracy": 0.09375, | |
| "eval_loss": 2.6362757682800293, | |
| "eval_runtime": 46.9191, | |
| "eval_samples_per_second": 1.364, | |
| "eval_steps_per_second": 0.341, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 3.0625, | |
| "step": 448, | |
| "total_flos": 2.2294481154124677e+18, | |
| "train_loss": 2.7684556926999773, | |
| "train_runtime": 2238.8021, | |
| "train_samples_per_second": 0.8, | |
| "train_steps_per_second": 0.2 | |
| }, | |
| { | |
| "epoch": 3.0625, | |
| "eval_accuracy": 0.15853658536585366, | |
| "eval_loss": 2.5910537242889404, | |
| "eval_runtime": 69.9547, | |
| "eval_samples_per_second": 1.172, | |
| "eval_steps_per_second": 0.3, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 3.0625, | |
| "eval_accuracy": 0.15853658536585366, | |
| "eval_loss": 2.5910537242889404, | |
| "eval_runtime": 70.209, | |
| "eval_samples_per_second": 1.168, | |
| "eval_steps_per_second": 0.299, | |
| "step": 448 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 448, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2294481154124677e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |