| { | |
| "best_metric": 0.8729338842975206, | |
| "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-MM_Classification_base_V10/checkpoint-91", | |
| "epoch": 6.885245901639344, | |
| "eval_steps": 500, | |
| "global_step": 105, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 1.847607135772705, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.7948, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9836065573770492, | |
| "eval_accuracy": 0.8352272727272727, | |
| "eval_loss": 0.4498441815376282, | |
| "eval_runtime": 204.2611, | |
| "eval_samples_per_second": 9.478, | |
| "eval_steps_per_second": 0.078, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 2.3756892681121826, | |
| "learning_rate": 4.5212765957446815e-05, | |
| "loss": 0.5062, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.9672131147540983, | |
| "grad_norm": 1.4792882204055786, | |
| "learning_rate": 3.9893617021276594e-05, | |
| "loss": 0.4439, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9672131147540983, | |
| "eval_accuracy": 0.8589876033057852, | |
| "eval_loss": 0.38362234830856323, | |
| "eval_runtime": 210.2217, | |
| "eval_samples_per_second": 9.209, | |
| "eval_steps_per_second": 0.076, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "grad_norm": 2.130309581756592, | |
| "learning_rate": 3.4574468085106386e-05, | |
| "loss": 0.4024, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.9508196721311473, | |
| "eval_accuracy": 0.8600206611570248, | |
| "eval_loss": 0.36524850130081177, | |
| "eval_runtime": 204.4105, | |
| "eval_samples_per_second": 9.471, | |
| "eval_steps_per_second": 0.078, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.278688524590164, | |
| "grad_norm": 2.3738443851470947, | |
| "learning_rate": 2.925531914893617e-05, | |
| "loss": 0.3801, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.9344262295081966, | |
| "grad_norm": 3.785062074661255, | |
| "learning_rate": 2.393617021276596e-05, | |
| "loss": 0.3562, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8641528925619835, | |
| "eval_loss": 0.34744057059288025, | |
| "eval_runtime": 203.8324, | |
| "eval_samples_per_second": 9.498, | |
| "eval_steps_per_second": 0.078, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 4.590163934426229, | |
| "grad_norm": 3.449556827545166, | |
| "learning_rate": 1.8617021276595745e-05, | |
| "loss": 0.345, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.983606557377049, | |
| "eval_accuracy": 0.868801652892562, | |
| "eval_loss": 0.34286215901374817, | |
| "eval_runtime": 203.6664, | |
| "eval_samples_per_second": 9.506, | |
| "eval_steps_per_second": 0.079, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 5.245901639344262, | |
| "grad_norm": 2.114426851272583, | |
| "learning_rate": 1.3297872340425532e-05, | |
| "loss": 0.3374, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.901639344262295, | |
| "grad_norm": 4.8909759521484375, | |
| "learning_rate": 7.97872340425532e-06, | |
| "loss": 0.3379, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.967213114754099, | |
| "eval_accuracy": 0.8729338842975206, | |
| "eval_loss": 0.34267309308052063, | |
| "eval_runtime": 204.1334, | |
| "eval_samples_per_second": 9.484, | |
| "eval_steps_per_second": 0.078, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 6.557377049180328, | |
| "grad_norm": 3.155640125274658, | |
| "learning_rate": 2.6595744680851065e-06, | |
| "loss": 0.3213, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.885245901639344, | |
| "eval_accuracy": 0.8708677685950413, | |
| "eval_loss": 0.3443421423435211, | |
| "eval_runtime": 203.5472, | |
| "eval_samples_per_second": 9.511, | |
| "eval_steps_per_second": 0.079, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 6.885245901639344, | |
| "step": 105, | |
| "total_flos": 4.180411553219629e+18, | |
| "train_loss": 0.4180879854020618, | |
| "train_runtime": 6613.2188, | |
| "train_samples_per_second": 8.194, | |
| "train_steps_per_second": 0.016 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 105, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.180411553219629e+18, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |