| { | |
| "best_metric": 1.6441926956176758, | |
| "best_model_checkpoint": "detr-r101-cd45rb-8ah-6l-256d-4096ffn\\checkpoint-46060", | |
| "epoch": 10.0, | |
| "global_step": 46060, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.002171081198437e-06, | |
| "loss": 2.704, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.9783554077148438, | |
| "eval_runtime": 221.5023, | |
| "eval_samples_per_second": 8.041, | |
| "eval_steps_per_second": 1.007, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.002171081198438e-06, | |
| "loss": 2.4631, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.8782960176467896, | |
| "eval_runtime": 220.8326, | |
| "eval_samples_per_second": 8.065, | |
| "eval_steps_per_second": 1.01, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.002605297438124e-06, | |
| "loss": 2.3881, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.827803134918213, | |
| "eval_runtime": 221.0372, | |
| "eval_samples_per_second": 8.057, | |
| "eval_steps_per_second": 1.009, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.002822405557969e-06, | |
| "loss": 2.3314, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.8200912475585938, | |
| "eval_runtime": 221.0219, | |
| "eval_samples_per_second": 8.058, | |
| "eval_steps_per_second": 1.009, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.003039513677812e-06, | |
| "loss": 2.2787, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.7909141778945923, | |
| "eval_runtime": 220.7952, | |
| "eval_samples_per_second": 8.066, | |
| "eval_steps_per_second": 1.01, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.003690838037343e-06, | |
| "loss": 2.2413, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.7557549476623535, | |
| "eval_runtime": 222.217, | |
| "eval_samples_per_second": 8.015, | |
| "eval_steps_per_second": 1.004, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.0039079461571864e-06, | |
| "loss": 2.2084, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.7492649555206299, | |
| "eval_runtime": 221.2301, | |
| "eval_samples_per_second": 8.05, | |
| "eval_steps_per_second": 1.008, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0045592705167173e-06, | |
| "loss": 2.1547, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.6853615045547485, | |
| "eval_runtime": 220.6551, | |
| "eval_samples_per_second": 8.071, | |
| "eval_steps_per_second": 1.011, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0047763786365611e-06, | |
| "loss": 2.1162, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.655694603919983, | |
| "eval_runtime": 220.4726, | |
| "eval_samples_per_second": 8.078, | |
| "eval_steps_per_second": 1.011, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.99348675640469e-09, | |
| "loss": 2.0913, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.6441926956176758, | |
| "eval_runtime": 220.3436, | |
| "eval_samples_per_second": 8.083, | |
| "eval_steps_per_second": 1.012, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 46060, | |
| "total_flos": 1.5497980548560637e+20, | |
| "train_loss": 2.297725559223024, | |
| "train_runtime": 34588.596, | |
| "train_samples_per_second": 5.326, | |
| "train_steps_per_second": 1.332 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.5497980548560637e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |