| { | |
| "best_metric": 0.6363636363636364, | |
| "best_model_checkpoint": "videomae-base-finetuned-2\\checkpoint-74", | |
| "epoch": 1.4864864864864864, | |
| "eval_steps": 500, | |
| "global_step": 74, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13513513513513514, | |
| "grad_norm": 13.06977367401123, | |
| "learning_rate": 4.848484848484849e-05, | |
| "loss": 0.7158, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 11.546745300292969, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 0.6967, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.40540540540540543, | |
| "grad_norm": 13.410033226013184, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.6252, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5135135135135135, | |
| "eval_accuracy": 0.6181818181818182, | |
| "eval_loss": 0.6595810055732727, | |
| "eval_runtime": 150.5547, | |
| "eval_samples_per_second": 0.365, | |
| "eval_steps_per_second": 0.093, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.027027027027027, | |
| "grad_norm": 6.076575756072998, | |
| "learning_rate": 2.575757575757576e-05, | |
| "loss": 0.6072, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1621621621621623, | |
| "grad_norm": 2.566138982772827, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.5134, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2972972972972974, | |
| "grad_norm": 14.576709747314453, | |
| "learning_rate": 1.0606060606060607e-05, | |
| "loss": 0.4588, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.4324324324324325, | |
| "grad_norm": 22.475860595703125, | |
| "learning_rate": 3.0303030303030305e-06, | |
| "loss": 0.5187, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.4864864864864864, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_loss": 0.7526556253433228, | |
| "eval_runtime": 149.6048, | |
| "eval_samples_per_second": 0.368, | |
| "eval_steps_per_second": 0.094, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.4864864864864864, | |
| "step": 74, | |
| "total_flos": 3.65096924715221e+17, | |
| "train_loss": 0.5808639623023368, | |
| "train_runtime": 2222.6393, | |
| "train_samples_per_second": 0.133, | |
| "train_steps_per_second": 0.033 | |
| }, | |
| { | |
| "epoch": 1.4864864864864864, | |
| "eval_accuracy": 0.8322147651006712, | |
| "eval_loss": 0.3304717242717743, | |
| "eval_runtime": 358.1284, | |
| "eval_samples_per_second": 0.416, | |
| "eval_steps_per_second": 0.106, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.4864864864864864, | |
| "eval_accuracy": 0.5942028985507246, | |
| "eval_loss": 0.6942497491836548, | |
| "eval_runtime": 179.9904, | |
| "eval_samples_per_second": 0.383, | |
| "eval_steps_per_second": 0.1, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.4864864864864864, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_loss": 0.7526556253433228, | |
| "eval_runtime": 136.5776, | |
| "eval_samples_per_second": 0.403, | |
| "eval_steps_per_second": 0.103, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.4864864864864864, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_loss": 0.752655565738678, | |
| "eval_runtime": 171.0609, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.082, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.4864864864864864, | |
| "eval_accuracy": 0.5942028985507246, | |
| "eval_loss": 0.6942497491836548, | |
| "eval_runtime": 230.5496, | |
| "eval_samples_per_second": 0.299, | |
| "eval_steps_per_second": 0.078, | |
| "step": 74 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 74, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 3.65096924715221e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |