| { | |
| "best_metric": 0.027644166722893715, | |
| "best_model_checkpoint": "2025-02-10-08-48-20-convnextv2-tiny-1k-224/checkpoint-721", | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 927, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "train_accuracy": 0.7107110161733292 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 45.910255432128906, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1857, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9449090960718868, | |
| "eval_error_rate": 0.05509090392811322, | |
| "eval_f1": 0.9396413566764898, | |
| "eval_loss": 0.2268916666507721, | |
| "eval_precision": 0.9479957528297004, | |
| "eval_recall": 0.9390243902439024, | |
| "eval_runtime": 4.8967, | |
| "eval_samples_per_second": 83.73, | |
| "eval_steps_per_second": 2.655, | |
| "eval_top1_accuracy": 0.9390243902439024, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "train_accuracy": 0.9397884458909682 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 10.051138877868652, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 0.2112, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.955369087662837, | |
| "eval_error_rate": 0.04463091233716299, | |
| "eval_f1": 0.9562985530064301, | |
| "eval_loss": 0.15799950063228607, | |
| "eval_precision": 0.9583194772706968, | |
| "eval_recall": 0.9560975609756097, | |
| "eval_runtime": 4.8544, | |
| "eval_samples_per_second": 84.459, | |
| "eval_steps_per_second": 2.678, | |
| "eval_top1_accuracy": 0.9560975609756097, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "train_accuracy": 0.9688093300786548 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.49671149253845215, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 0.1067, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9571493061114761, | |
| "eval_error_rate": 0.042850693888523916, | |
| "eval_f1": 0.9613312197108163, | |
| "eval_loss": 0.11648530513048172, | |
| "eval_precision": 0.9634174720544878, | |
| "eval_recall": 0.9609756097560975, | |
| "eval_runtime": 5.102, | |
| "eval_samples_per_second": 80.36, | |
| "eval_steps_per_second": 2.548, | |
| "eval_top1_accuracy": 0.9609756097560975, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "train_accuracy": 0.9753186872796311 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 16.72035789489746, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0922, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9548521817081745, | |
| "eval_error_rate": 0.04514781829182546, | |
| "eval_f1": 0.9531851817546427, | |
| "eval_loss": 0.17496360838413239, | |
| "eval_precision": 0.9608464701303613, | |
| "eval_recall": 0.9536585365853658, | |
| "eval_runtime": 5.404, | |
| "eval_samples_per_second": 75.87, | |
| "eval_steps_per_second": 2.406, | |
| "eval_top1_accuracy": 0.9536585365853658, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "train_accuracy": 0.9861676159479251 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.07683505862951279, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.0346, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9844764656929237, | |
| "eval_error_rate": 0.015523534307076314, | |
| "eval_f1": 0.9805052378047235, | |
| "eval_loss": 0.09202897548675537, | |
| "eval_precision": 0.9827372908206812, | |
| "eval_recall": 0.9804878048780488, | |
| "eval_runtime": 5.0653, | |
| "eval_samples_per_second": 80.943, | |
| "eval_steps_per_second": 2.566, | |
| "eval_top1_accuracy": 0.9804878048780488, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "train_accuracy": 0.9940330892324383 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.008178498595952988, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.018, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9886309278080299, | |
| "eval_error_rate": 0.011369072191970142, | |
| "eval_f1": 0.9877292444031514, | |
| "eval_loss": 0.04825982823967934, | |
| "eval_precision": 0.9881249257892948, | |
| "eval_recall": 0.9878048780487805, | |
| "eval_runtime": 4.8726, | |
| "eval_samples_per_second": 84.144, | |
| "eval_steps_per_second": 2.668, | |
| "eval_top1_accuracy": 0.9878048780487805, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "train_accuracy": 0.9964740981828044 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.004987717140465975, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0114, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9952099182868414, | |
| "eval_error_rate": 0.004790081713158645, | |
| "eval_f1": 0.9951222248931835, | |
| "eval_loss": 0.027644166722893715, | |
| "eval_precision": 0.9952749788115641, | |
| "eval_recall": 0.9951219512195122, | |
| "eval_runtime": 5.3438, | |
| "eval_samples_per_second": 76.725, | |
| "eval_steps_per_second": 2.433, | |
| "eval_top1_accuracy": 0.9951219512195122, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "train_accuracy": 0.9981014374830486 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.08363453298807144, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0067, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9894357778973164, | |
| "eval_error_rate": 0.010564222102683596, | |
| "eval_f1": 0.9902614220879342, | |
| "eval_loss": 0.04231307655572891, | |
| "eval_precision": 0.9905527399429839, | |
| "eval_recall": 0.9902439024390244, | |
| "eval_runtime": 5.3475, | |
| "eval_samples_per_second": 76.672, | |
| "eval_steps_per_second": 2.431, | |
| "eval_top1_accuracy": 0.9902439024390244, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "train_accuracy": 0.9986438839164633 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.6717975735664368, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0014, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9952099182868414, | |
| "eval_error_rate": 0.004790081713158645, | |
| "eval_f1": 0.9951326195176777, | |
| "eval_loss": 0.03104478307068348, | |
| "eval_precision": 0.9953151037721557, | |
| "eval_recall": 0.9951219512195122, | |
| "eval_runtime": 5.5733, | |
| "eval_samples_per_second": 73.565, | |
| "eval_steps_per_second": 2.333, | |
| "eval_top1_accuracy": 0.9951219512195122, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "step": 927, | |
| "total_flos": 7.425498745847992e+17, | |
| "train_loss": 0.1853208835713943, | |
| "train_runtime": 773.9872, | |
| "train_samples_per_second": 42.339, | |
| "train_steps_per_second": 1.331 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1030, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.425498745847992e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |