| { | |
| "best_metric": 0.3, | |
| "best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-caer-subset-5-classes\\checkpoint-250", | |
| "epoch": 1.444, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 11.369068145751953, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5655, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 11.059978485107422, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6109, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 12.424741744995117, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 1.6169, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 15.846301078796387, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 1.6663, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 6.054256439208984, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.7779, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 7.3695454597473145, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 1.6658, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 7.011582851409912, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6601, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 7.409139633178711, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 1.6056, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 9.646027565002441, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 1.7752, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 8.108616828918457, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.6162, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 4.2093586921691895, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 1.6689, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 4.784428596496582, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 1.5406, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 5.809035301208496, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 1.6206, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.2, | |
| "eval_loss": 1.577626347541809, | |
| "eval_runtime": 10.5956, | |
| "eval_samples_per_second": 2.831, | |
| "eval_steps_per_second": 1.416, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 6.738602638244629, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 1.4571, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 6.5725579261779785, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.4523, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 9.774547576904297, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4379, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 7.136582374572754, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 1.3654, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 10.755990028381348, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 1.6211, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 9.731955528259277, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.4025, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 9.016931533813477, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.4272, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 8.873564720153809, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 1.352, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 10.840998649597168, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.3692, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 6.855379581451416, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 1.3788, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 10.270050048828125, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 1.4626, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 11.716329574584961, | |
| "learning_rate": 0.0, | |
| "loss": 1.315, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.3, | |
| "eval_loss": 1.531712293624878, | |
| "eval_runtime": 9.5018, | |
| "eval_samples_per_second": 3.157, | |
| "eval_steps_per_second": 1.579, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "step": 250, | |
| "total_flos": 6.2304896360448e+17, | |
| "train_loss": 1.5372729606628417, | |
| "train_runtime": 255.4235, | |
| "train_samples_per_second": 1.958, | |
| "train_steps_per_second": 0.979 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.2191780821917808, | |
| "eval_loss": 1.581635594367981, | |
| "eval_runtime": 22.9267, | |
| "eval_samples_per_second": 3.184, | |
| "eval_steps_per_second": 1.614, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.2191780821917808, | |
| "eval_loss": 1.5816354751586914, | |
| "eval_runtime": 22.2614, | |
| "eval_samples_per_second": 3.279, | |
| "eval_steps_per_second": 1.662, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 6.2304896360448e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |