| { | |
| "best_metric": 0.475, | |
| "best_model_checkpoint": "videomae-base-finetuned-engine-subset/checkpoint-224", | |
| "epoch": 3.236607142857143, | |
| "global_step": 224, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.173913043478261e-05, | |
| "loss": 2.8816, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 2.8286, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.82587064676617e-05, | |
| "loss": 2.6244, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.577114427860697e-05, | |
| "loss": 2.3974, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.328358208955224e-05, | |
| "loss": 2.6687, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.15, | |
| "eval_loss": 2.5947723388671875, | |
| "eval_runtime": 65.3974, | |
| "eval_samples_per_second": 1.223, | |
| "eval_steps_per_second": 0.306, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.079601990049751e-05, | |
| "loss": 2.6448, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.830845771144278e-05, | |
| "loss": 2.5092, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.582089552238806e-05, | |
| "loss": 2.4746, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.5698, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.084577114427861e-05, | |
| "loss": 2.3483, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.835820895522388e-05, | |
| "loss": 2.3001, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.175, | |
| "eval_loss": 2.2452101707458496, | |
| "eval_runtime": 61.8887, | |
| "eval_samples_per_second": 1.293, | |
| "eval_steps_per_second": 0.323, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.5870646766169153e-05, | |
| "loss": 2.0974, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.338308457711443e-05, | |
| "loss": 2.0862, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.0895522388059702e-05, | |
| "loss": 2.0094, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.8407960199004975e-05, | |
| "loss": 2.0335, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.592039800995025e-05, | |
| "loss": 1.761, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.3432835820895523e-05, | |
| "loss": 2.1531, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.3875, | |
| "eval_loss": 1.91796875, | |
| "eval_runtime": 61.6028, | |
| "eval_samples_per_second": 1.299, | |
| "eval_steps_per_second": 0.325, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.0945273631840796e-05, | |
| "loss": 1.7171, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 8.45771144278607e-06, | |
| "loss": 1.7341, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 5.970149253731343e-06, | |
| "loss": 1.711, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 3.482587064676617e-06, | |
| "loss": 1.6104, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 9.950248756218907e-07, | |
| "loss": 1.6332, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "eval_accuracy": 0.475, | |
| "eval_loss": 1.5633509159088135, | |
| "eval_runtime": 61.4445, | |
| "eval_samples_per_second": 1.302, | |
| "eval_steps_per_second": 0.325, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "step": 224, | |
| "total_flos": 1.1053874300107162e+18, | |
| "train_loss": 2.2049321063927243, | |
| "train_runtime": 1138.2528, | |
| "train_samples_per_second": 0.787, | |
| "train_steps_per_second": 0.197 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "eval_accuracy": 0.475, | |
| "eval_loss": 1.5633509159088135, | |
| "eval_runtime": 63.8635, | |
| "eval_samples_per_second": 1.253, | |
| "eval_steps_per_second": 0.313, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "eval_accuracy": 0.475, | |
| "eval_loss": 1.5633509159088135, | |
| "eval_runtime": 62.0235, | |
| "eval_samples_per_second": 1.29, | |
| "eval_steps_per_second": 0.322, | |
| "step": 224 | |
| } | |
| ], | |
| "max_steps": 224, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.1053874300107162e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |