| { | |
| "best_metric": 0.8801313628899836, | |
| "best_model_checkpoint": "convnext-tiny-224-finetuned-noh\\checkpoint-138", | |
| "epoch": 9.577777777777778, | |
| "eval_steps": 500, | |
| "global_step": 220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 12.379578590393066, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.6765, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 7.404582500457764, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.5518, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7619047619047619, | |
| "eval_loss": 0.5413568019866943, | |
| "eval_runtime": 71.4598, | |
| "eval_samples_per_second": 8.522, | |
| "eval_steps_per_second": 0.546, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3111111111111111, | |
| "grad_norm": 8.386245727539062, | |
| "learning_rate": 4.797979797979798e-05, | |
| "loss": 0.5133, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7555555555555555, | |
| "grad_norm": 16.09688377380371, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.5027, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7619047619047619, | |
| "eval_loss": 0.4833744764328003, | |
| "eval_runtime": 64.8574, | |
| "eval_samples_per_second": 9.39, | |
| "eval_steps_per_second": 0.601, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.1777777777777776, | |
| "grad_norm": 5.923590660095215, | |
| "learning_rate": 4.292929292929293e-05, | |
| "loss": 0.4145, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.6222222222222222, | |
| "grad_norm": 15.512758255004883, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.4616, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8357963875205254, | |
| "eval_loss": 0.40746840834617615, | |
| "eval_runtime": 64.906, | |
| "eval_samples_per_second": 9.383, | |
| "eval_steps_per_second": 0.601, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.0444444444444443, | |
| "grad_norm": 19.10196876525879, | |
| "learning_rate": 3.787878787878788e-05, | |
| "loss": 0.4314, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.488888888888889, | |
| "grad_norm": 9.849831581115723, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.395, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.9333333333333336, | |
| "grad_norm": 12.404428482055664, | |
| "learning_rate": 3.282828282828283e-05, | |
| "loss": 0.4001, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.36006566882133484, | |
| "eval_runtime": 64.5801, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 0.604, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 4.355555555555555, | |
| "grad_norm": 6.465453624725342, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.3633, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 16.73354721069336, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3698, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8768472906403941, | |
| "eval_loss": 0.34667930006980896, | |
| "eval_runtime": 64.7336, | |
| "eval_samples_per_second": 9.408, | |
| "eval_steps_per_second": 0.602, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 5.222222222222222, | |
| "grad_norm": 8.181696891784668, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.324, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.666666666666667, | |
| "grad_norm": 19.92898941040039, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.3261, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8801313628899836, | |
| "eval_loss": 0.3729628026485443, | |
| "eval_runtime": 64.4296, | |
| "eval_samples_per_second": 9.452, | |
| "eval_steps_per_second": 0.605, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 6.088888888888889, | |
| "grad_norm": 8.380843162536621, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.2833, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.533333333333333, | |
| "grad_norm": 16.5051326751709, | |
| "learning_rate": 1.7676767676767676e-05, | |
| "loss": 0.3365, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.977777777777778, | |
| "grad_norm": 13.593069076538086, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.301, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8735632183908046, | |
| "eval_loss": 0.3728314936161041, | |
| "eval_runtime": 64.0547, | |
| "eval_samples_per_second": 9.508, | |
| "eval_steps_per_second": 0.609, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "grad_norm": 13.774739265441895, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.2547, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 7.844444444444444, | |
| "grad_norm": 16.794301986694336, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.3071, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8374384236453202, | |
| "eval_loss": 0.39592304825782776, | |
| "eval_runtime": 64.354, | |
| "eval_samples_per_second": 9.463, | |
| "eval_steps_per_second": 0.606, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 8.266666666666667, | |
| "grad_norm": 15.940261840820312, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.2456, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 8.71111111111111, | |
| "grad_norm": 9.660676002502441, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.264, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8604269293924466, | |
| "eval_loss": 0.3865140974521637, | |
| "eval_runtime": 64.3562, | |
| "eval_samples_per_second": 9.463, | |
| "eval_steps_per_second": 0.606, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 9.133333333333333, | |
| "grad_norm": 13.393628120422363, | |
| "learning_rate": 2.5252525252525253e-06, | |
| "loss": 0.2452, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 9.577777777777778, | |
| "grad_norm": 12.103188514709473, | |
| "learning_rate": 0.0, | |
| "loss": 0.2769, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 9.577777777777778, | |
| "eval_accuracy": 0.8620689655172413, | |
| "eval_loss": 0.3873327076435089, | |
| "eval_runtime": 65.6598, | |
| "eval_samples_per_second": 9.275, | |
| "eval_steps_per_second": 0.594, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 9.577777777777778, | |
| "step": 220, | |
| "total_flos": 3.463342405894103e+17, | |
| "train_loss": 0.37474415627392854, | |
| "train_runtime": 2431.6129, | |
| "train_samples_per_second": 5.918, | |
| "train_steps_per_second": 0.09 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 220, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 3.463342405894103e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |