| { | |
| "best_metric": 0.8883415435139573, | |
| "best_model_checkpoint": "efficientnet-b0-finetuned-noh\\checkpoint-184", | |
| "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": 8.235955238342285, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.6411, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 7.751129150390625, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.6146, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.729064039408867, | |
| "eval_loss": 0.6138808727264404, | |
| "eval_runtime": 88.9218, | |
| "eval_samples_per_second": 6.849, | |
| "eval_steps_per_second": 0.439, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3111111111111111, | |
| "grad_norm": 6.260272979736328, | |
| "learning_rate": 4.797979797979798e-05, | |
| "loss": 0.5289, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7555555555555555, | |
| "grad_norm": 5.691160202026367, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.5116, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8308702791461412, | |
| "eval_loss": 0.47041037678718567, | |
| "eval_runtime": 85.525, | |
| "eval_samples_per_second": 7.121, | |
| "eval_steps_per_second": 0.456, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.1777777777777776, | |
| "grad_norm": 5.566213130950928, | |
| "learning_rate": 4.292929292929293e-05, | |
| "loss": 0.4151, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.6222222222222222, | |
| "grad_norm": 5.660247325897217, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.4655, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8587848932676518, | |
| "eval_loss": 0.4233274757862091, | |
| "eval_runtime": 62.7576, | |
| "eval_samples_per_second": 9.704, | |
| "eval_steps_per_second": 0.621, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.0444444444444443, | |
| "grad_norm": 5.13922119140625, | |
| "learning_rate": 3.787878787878788e-05, | |
| "loss": 0.4394, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.488888888888889, | |
| "grad_norm": 5.63355827331543, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.4292, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.9333333333333336, | |
| "grad_norm": 6.373378276824951, | |
| "learning_rate": 3.282828282828283e-05, | |
| "loss": 0.4331, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8604269293924466, | |
| "eval_loss": 0.41187092661857605, | |
| "eval_runtime": 62.2366, | |
| "eval_samples_per_second": 9.785, | |
| "eval_steps_per_second": 0.627, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 4.355555555555555, | |
| "grad_norm": 5.6973114013671875, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.388, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 6.741119861602783, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.4281, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8752052545155994, | |
| "eval_loss": 0.38966891169548035, | |
| "eval_runtime": 62.2405, | |
| "eval_samples_per_second": 9.785, | |
| "eval_steps_per_second": 0.627, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 5.222222222222222, | |
| "grad_norm": 5.320347785949707, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.3975, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.666666666666667, | |
| "grad_norm": 5.142993927001953, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.4001, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8719211822660099, | |
| "eval_loss": 0.4011945426464081, | |
| "eval_runtime": 63.0341, | |
| "eval_samples_per_second": 9.661, | |
| "eval_steps_per_second": 0.619, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 6.088888888888889, | |
| "grad_norm": 4.859269142150879, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.34, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.533333333333333, | |
| "grad_norm": 6.196608066558838, | |
| "learning_rate": 1.7676767676767676e-05, | |
| "loss": 0.4207, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.977777777777778, | |
| "grad_norm": 6.519267559051514, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.3721, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8817733990147784, | |
| "eval_loss": 0.38614729046821594, | |
| "eval_runtime": 62.6292, | |
| "eval_samples_per_second": 9.724, | |
| "eval_steps_per_second": 0.623, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "grad_norm": 4.774895668029785, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.3456, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 7.844444444444444, | |
| "grad_norm": 6.236260890960693, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.3979, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8883415435139573, | |
| "eval_loss": 0.3784164488315582, | |
| "eval_runtime": 62.8885, | |
| "eval_samples_per_second": 9.684, | |
| "eval_steps_per_second": 0.62, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 8.266666666666667, | |
| "grad_norm": 7.606906890869141, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.3784, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 8.71111111111111, | |
| "grad_norm": 4.811132907867432, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.3376, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8604269293924466, | |
| "eval_loss": 0.4170529246330261, | |
| "eval_runtime": 62.9062, | |
| "eval_samples_per_second": 9.681, | |
| "eval_steps_per_second": 0.62, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 9.133333333333333, | |
| "grad_norm": 5.669275760650635, | |
| "learning_rate": 2.5252525252525253e-06, | |
| "loss": 0.3526, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 9.577777777777778, | |
| "grad_norm": 6.406429767608643, | |
| "learning_rate": 0.0, | |
| "loss": 0.3984, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 9.577777777777778, | |
| "eval_accuracy": 0.8620689655172413, | |
| "eval_loss": 0.4138999581336975, | |
| "eval_runtime": 63.2813, | |
| "eval_samples_per_second": 9.624, | |
| "eval_steps_per_second": 0.616, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 9.577777777777778, | |
| "step": 220, | |
| "total_flos": 4.991931114153984e+16, | |
| "train_loss": 0.42888181643052536, | |
| "train_runtime": 2265.5727, | |
| "train_samples_per_second": 6.352, | |
| "train_steps_per_second": 0.097 | |
| } | |
| ], | |
| "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": 4.991931114153984e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |