| { | |
| "best_metric": 0.6926829268292682, | |
| "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finetuned-gardner-exp-max/checkpoint-130", | |
| "epoch": 9.655172413793103, | |
| "eval_steps": 500, | |
| "global_step": 140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 1.6002, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.5024390243902439, | |
| "eval_loss": 1.4557533264160156, | |
| "eval_runtime": 10.833, | |
| "eval_samples_per_second": 18.924, | |
| "eval_steps_per_second": 0.646, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 1.4093, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5024390243902439, | |
| "eval_loss": 1.2319719791412354, | |
| "eval_runtime": 4.0581, | |
| "eval_samples_per_second": 50.516, | |
| "eval_steps_per_second": 1.725, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 4.3650793650793655e-05, | |
| "loss": 1.232, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 1.1068, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_accuracy": 0.5951219512195122, | |
| "eval_loss": 1.0739854574203491, | |
| "eval_runtime": 4.0516, | |
| "eval_samples_per_second": 50.598, | |
| "eval_steps_per_second": 1.728, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.9988, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6048780487804878, | |
| "eval_loss": 0.9966912865638733, | |
| "eval_runtime": 3.5184, | |
| "eval_samples_per_second": 58.266, | |
| "eval_steps_per_second": 1.99, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 1.0171, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.9099, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.9247760772705078, | |
| "eval_runtime": 3.5711, | |
| "eval_samples_per_second": 57.405, | |
| "eval_steps_per_second": 1.96, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.8674, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6780487804878049, | |
| "eval_loss": 0.8766470551490784, | |
| "eval_runtime": 3.5697, | |
| "eval_samples_per_second": 57.428, | |
| "eval_steps_per_second": 1.961, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 1.984126984126984e-05, | |
| "loss": 0.8807, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.8638, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_accuracy": 0.6731707317073171, | |
| "eval_loss": 0.865567684173584, | |
| "eval_runtime": 3.828, | |
| "eval_samples_per_second": 53.553, | |
| "eval_steps_per_second": 1.829, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.833, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6731707317073171, | |
| "eval_loss": 0.8395170569419861, | |
| "eval_runtime": 3.5828, | |
| "eval_samples_per_second": 57.218, | |
| "eval_steps_per_second": 1.954, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.8396, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 3.968253968253968e-06, | |
| "loss": 0.8211, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "eval_accuracy": 0.6926829268292682, | |
| "eval_loss": 0.8203723430633545, | |
| "eval_runtime": 3.633, | |
| "eval_samples_per_second": 56.427, | |
| "eval_steps_per_second": 1.927, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 0.0, | |
| "loss": 0.8236, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "eval_accuracy": 0.6780487804878049, | |
| "eval_loss": 0.8203750848770142, | |
| "eval_runtime": 3.5738, | |
| "eval_samples_per_second": 57.361, | |
| "eval_steps_per_second": 1.959, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "step": 140, | |
| "total_flos": 5.78085766574506e+17, | |
| "train_loss": 1.0145302023206437, | |
| "train_runtime": 896.6945, | |
| "train_samples_per_second": 20.509, | |
| "train_steps_per_second": 0.156 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 5.78085766574506e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |