| { | |
| "best_metric": 0.4, | |
| "best_model_checkpoint": "videomae-base-finetuned-SSBD/checkpoint-21", | |
| "epoch": 7.02, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.0586, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.1628, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.4, | |
| "eval_loss": 1.0385651588439941, | |
| "eval_runtime": 25.6134, | |
| "eval_samples_per_second": 0.976, | |
| "eval_steps_per_second": 0.117, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.9453, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 1.1777, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_accuracy": 0.4, | |
| "eval_loss": 1.0652350187301636, | |
| "eval_runtime": 18.7735, | |
| "eval_samples_per_second": 1.332, | |
| "eval_steps_per_second": 0.16, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.7404, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.0752, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_accuracy": 0.12, | |
| "eval_loss": 1.4299181699752808, | |
| "eval_runtime": 18.9817, | |
| "eval_samples_per_second": 1.317, | |
| "eval_steps_per_second": 0.158, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.9437, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.6149, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_accuracy": 0.32, | |
| "eval_loss": 1.1845195293426514, | |
| "eval_runtime": 19.1566, | |
| "eval_samples_per_second": 1.305, | |
| "eval_steps_per_second": 0.157, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.42, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.4486, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_accuracy": 0.16, | |
| "eval_loss": 1.6551308631896973, | |
| "eval_runtime": 19.0048, | |
| "eval_samples_per_second": 1.315, | |
| "eval_steps_per_second": 0.158, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.4005, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.2998, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "eval_accuracy": 0.16, | |
| "eval_loss": 1.6549692153930664, | |
| "eval_runtime": 18.768, | |
| "eval_samples_per_second": 1.332, | |
| "eval_steps_per_second": 0.16, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.1424, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.138, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "eval_accuracy": 0.2, | |
| "eval_loss": 2.170816421508789, | |
| "eval_runtime": 16.0049, | |
| "eval_samples_per_second": 1.562, | |
| "eval_steps_per_second": 0.187, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 0.0, | |
| "loss": 0.097, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_accuracy": 0.2, | |
| "eval_loss": 2.1793885231018066, | |
| "eval_runtime": 16.3019, | |
| "eval_samples_per_second": 1.534, | |
| "eval_steps_per_second": 0.184, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "step": 150, | |
| "total_flos": 2.208046144034046e+18, | |
| "train_loss": 0.6443349726994833, | |
| "train_runtime": 920.0858, | |
| "train_samples_per_second": 1.956, | |
| "train_steps_per_second": 0.163 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_accuracy": 0.4, | |
| "eval_loss": 1.0385651588439941, | |
| "eval_runtime": 16.1467, | |
| "eval_samples_per_second": 1.548, | |
| "eval_steps_per_second": 0.186, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_loss": 0.9691802263259888, | |
| "eval_runtime": 8.5111, | |
| "eval_samples_per_second": 2.467, | |
| "eval_steps_per_second": 0.235, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_loss": 0.9691803455352783, | |
| "eval_runtime": 3.4403, | |
| "eval_samples_per_second": 6.104, | |
| "eval_steps_per_second": 0.581, | |
| "step": 150 | |
| } | |
| ], | |
| "max_steps": 150, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 2.208046144034046e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |