{ "best_metric": 0.9571428571428572, "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-150", "epoch": 1.5, "eval_steps": 500, "global_step": 150, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.07, "grad_norm": 0.18143892288208008, "learning_rate": 3.3333333333333335e-05, "loss": 0.0916, "step": 10 }, { "epoch": 0.13, "grad_norm": 46.98843002319336, "learning_rate": 4.814814814814815e-05, "loss": 0.2277, "step": 20 }, { "epoch": 0.2, "grad_norm": 6.724725723266602, "learning_rate": 4.4444444444444447e-05, "loss": 0.1532, "step": 30 }, { "epoch": 0.27, "grad_norm": 66.41813659667969, "learning_rate": 4.074074074074074e-05, "loss": 0.5242, "step": 40 }, { "epoch": 0.33, "grad_norm": 0.5121557116508484, "learning_rate": 3.7037037037037037e-05, "loss": 0.4777, "step": 50 }, { "epoch": 0.4, "grad_norm": 44.47030258178711, "learning_rate": 3.3333333333333335e-05, "loss": 0.7236, "step": 60 }, { "epoch": 0.47, "grad_norm": 32.01655960083008, "learning_rate": 2.962962962962963e-05, "loss": 0.1547, "step": 70 }, { "epoch": 0.5, "eval_accuracy": 0.9142857142857143, "eval_loss": 0.35459208488464355, "eval_runtime": 12.5328, "eval_samples_per_second": 5.585, "eval_steps_per_second": 1.436, "step": 75 }, { "epoch": 1.03, "grad_norm": 0.12592756748199463, "learning_rate": 2.5925925925925925e-05, "loss": 0.1536, "step": 80 }, { "epoch": 1.1, "grad_norm": 65.30023956298828, "learning_rate": 2.2222222222222223e-05, "loss": 0.1538, "step": 90 }, { "epoch": 1.17, "grad_norm": 31.011701583862305, "learning_rate": 1.8518518518518518e-05, "loss": 0.2454, "step": 100 }, { "epoch": 1.23, "grad_norm": 33.98771286010742, "learning_rate": 1.4814814814814815e-05, "loss": 0.0889, "step": 110 }, { "epoch": 1.3, "grad_norm": 0.7245432138442993, "learning_rate": 1.1111111111111112e-05, "loss": 0.0209, "step": 120 }, { "epoch": 1.37, "grad_norm": 0.1617116779088974, "learning_rate": 7.4074074074074075e-06, "loss": 0.2224, "step": 130 }, { "epoch": 1.43, "grad_norm": 3.768871545791626, "learning_rate": 3.7037037037037037e-06, "loss": 0.0144, "step": 140 }, { "epoch": 1.5, "grad_norm": 16.70306396484375, "learning_rate": 0.0, "loss": 0.1088, "step": 150 }, { "epoch": 1.5, "eval_accuracy": 0.9571428571428572, "eval_loss": 0.15032356977462769, "eval_runtime": 12.6452, "eval_samples_per_second": 5.536, "eval_steps_per_second": 1.423, "step": 150 }, { "epoch": 1.5, "step": 150, "total_flos": 7.47692094062592e+17, "train_loss": 0.22406891534725826, "train_runtime": 230.0097, "train_samples_per_second": 2.609, "train_steps_per_second": 0.652 }, { "epoch": 1.5, "eval_accuracy": 0.9161290322580645, "eval_loss": 0.23502568900585175, "eval_runtime": 27.5068, "eval_samples_per_second": 5.635, "eval_steps_per_second": 1.418, "step": 150 }, { "epoch": 1.5, "eval_accuracy": 0.9161290322580645, "eval_loss": 0.23502571880817413, "eval_runtime": 27.8973, "eval_samples_per_second": 5.556, "eval_steps_per_second": 1.398, "step": 150 } ], "logging_steps": 10, "max_steps": 150, "num_input_tokens_seen": 0, "num_train_epochs": 9223372036854775807, "save_steps": 500, "total_flos": 7.47692094062592e+17, "train_batch_size": 4, "trial_name": null, "trial_params": null }