| { | |
| "best_metric": 0.9763313609467456, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset-buddhika-weerasinghe/checkpoint-1620", | |
| "epoch": 9.1, | |
| "global_step": 1800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 2.4105, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.46153846153846156, | |
| "eval_loss": 1.6308622360229492, | |
| "eval_runtime": 77.3029, | |
| "eval_samples_per_second": 4.372, | |
| "eval_steps_per_second": 2.186, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 1.8958, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.9175, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_accuracy": 0.878698224852071, | |
| "eval_loss": 0.4374070167541504, | |
| "eval_runtime": 78.2783, | |
| "eval_samples_per_second": 4.318, | |
| "eval_steps_per_second": 2.159, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.6119, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 4.012345679012346e-05, | |
| "loss": 0.5086, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_accuracy": 0.8905325443786982, | |
| "eval_loss": 0.38013187050819397, | |
| "eval_runtime": 74.0577, | |
| "eval_samples_per_second": 4.564, | |
| "eval_steps_per_second": 2.282, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.4112, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.395061728395062e-05, | |
| "loss": 0.2994, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_accuracy": 0.8816568047337278, | |
| "eval_loss": 0.346200168132782, | |
| "eval_runtime": 77.9704, | |
| "eval_samples_per_second": 4.335, | |
| "eval_steps_per_second": 2.167, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.2183, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1555, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "eval_accuracy": 0.9230769230769231, | |
| "eval_loss": 0.3273673951625824, | |
| "eval_runtime": 77.1136, | |
| "eval_samples_per_second": 4.383, | |
| "eval_steps_per_second": 2.192, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.1337, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "eval_accuracy": 0.9615384615384616, | |
| "eval_loss": 0.1434585154056549, | |
| "eval_runtime": 77.4654, | |
| "eval_samples_per_second": 4.363, | |
| "eval_steps_per_second": 2.182, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 2.1604938271604937e-05, | |
| "loss": 0.0749, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.021, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "eval_accuracy": 0.9615384615384616, | |
| "eval_loss": 0.18787238001823425, | |
| "eval_runtime": 77.5975, | |
| "eval_samples_per_second": 4.356, | |
| "eval_steps_per_second": 2.178, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 1.54320987654321e-05, | |
| "loss": 0.003, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.0485, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 0.9674556213017751, | |
| "eval_loss": 0.10547798126935959, | |
| "eval_runtime": 76.9785, | |
| "eval_samples_per_second": 4.391, | |
| "eval_steps_per_second": 2.195, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.0021, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.0019, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "eval_accuracy": 0.9763313609467456, | |
| "eval_loss": 0.08644197881221771, | |
| "eval_runtime": 78.2696, | |
| "eval_samples_per_second": 4.318, | |
| "eval_steps_per_second": 2.159, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 3.0864197530864196e-06, | |
| "loss": 0.0038, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 0.0, | |
| "loss": 0.0054, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_accuracy": 0.9763313609467456, | |
| "eval_loss": 0.08389929682016373, | |
| "eval_runtime": 77.5761, | |
| "eval_samples_per_second": 4.357, | |
| "eval_steps_per_second": 2.179, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "step": 1800, | |
| "total_flos": 4.4862325749448704e+18, | |
| "train_loss": 0.42906751138468585, | |
| "train_runtime": 2457.281, | |
| "train_samples_per_second": 1.465, | |
| "train_steps_per_second": 0.733 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 8.188952445983887, | |
| "eval_runtime": 2.195, | |
| "eval_samples_per_second": 3.645, | |
| "eval_steps_per_second": 1.822, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 8.188952445983887, | |
| "eval_runtime": 1.8553, | |
| "eval_samples_per_second": 4.312, | |
| "eval_steps_per_second": 2.156, | |
| "step": 1800 | |
| } | |
| ], | |
| "max_steps": 1800, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 4.4862325749448704e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |