|
{ |
|
"best_metric": 0.6697247706422018, |
|
"best_model_checkpoint": "microsoft-resnet-50-cartoon-emotion-detection/checkpoint-160", |
|
"epoch": 19.96969696969697, |
|
"global_step": 160, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.97, |
|
"eval_accuracy": 0.24770642201834864, |
|
"eval_f1": 0.2041566786731761, |
|
"eval_loss": 1.3832563161849976, |
|
"eval_precision": 0.20537582488330916, |
|
"eval_recall": 0.24770642201834864, |
|
"eval_runtime": 6.8665, |
|
"eval_samples_per_second": 15.874, |
|
"eval_steps_per_second": 0.291, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 1.4276, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"eval_accuracy": 0.30275229357798167, |
|
"eval_f1": 0.19323441779945572, |
|
"eval_loss": 1.3710838556289673, |
|
"eval_precision": 0.19816345733776927, |
|
"eval_recall": 0.30275229357798167, |
|
"eval_runtime": 4.187, |
|
"eval_samples_per_second": 26.033, |
|
"eval_steps_per_second": 0.478, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 0.00011666666666666667, |
|
"loss": 1.4046, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"eval_accuracy": 0.30275229357798167, |
|
"eval_f1": 0.14071585476159712, |
|
"eval_loss": 1.3549774885177612, |
|
"eval_precision": 0.09165895126672839, |
|
"eval_recall": 0.30275229357798167, |
|
"eval_runtime": 4.1191, |
|
"eval_samples_per_second": 26.462, |
|
"eval_steps_per_second": 0.486, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 3.73, |
|
"learning_rate": 0.00010833333333333334, |
|
"loss": 1.3817, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 3.97, |
|
"eval_accuracy": 0.3119266055045872, |
|
"eval_f1": 0.15922843504338724, |
|
"eval_loss": 1.3374683856964111, |
|
"eval_precision": 0.2851681957186545, |
|
"eval_recall": 0.3119266055045872, |
|
"eval_runtime": 4.1507, |
|
"eval_samples_per_second": 26.26, |
|
"eval_steps_per_second": 0.482, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 4.97, |
|
"learning_rate": 0.0001, |
|
"loss": 1.3562, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 4.97, |
|
"eval_accuracy": 0.3211009174311927, |
|
"eval_f1": 0.17853677613274146, |
|
"eval_loss": 1.3179248571395874, |
|
"eval_precision": 0.433702613813398, |
|
"eval_recall": 0.3211009174311927, |
|
"eval_runtime": 3.9993, |
|
"eval_samples_per_second": 27.255, |
|
"eval_steps_per_second": 0.5, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 5.97, |
|
"eval_accuracy": 0.3761467889908257, |
|
"eval_f1": 0.27407584962221454, |
|
"eval_loss": 1.2991451025009155, |
|
"eval_precision": 0.5442070773263434, |
|
"eval_recall": 0.3761467889908257, |
|
"eval_runtime": 4.0689, |
|
"eval_samples_per_second": 26.789, |
|
"eval_steps_per_second": 0.492, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 6.24, |
|
"learning_rate": 9.166666666666667e-05, |
|
"loss": 1.3624, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 6.97, |
|
"eval_accuracy": 0.44954128440366975, |
|
"eval_f1": 0.36590235512607705, |
|
"eval_loss": 1.2751092910766602, |
|
"eval_precision": 0.5593305776792015, |
|
"eval_recall": 0.44954128440366975, |
|
"eval_runtime": 4.2081, |
|
"eval_samples_per_second": 25.902, |
|
"eval_steps_per_second": 0.475, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 7.48, |
|
"learning_rate": 8.333333333333333e-05, |
|
"loss": 1.2914, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 7.97, |
|
"eval_accuracy": 0.47706422018348627, |
|
"eval_f1": 0.4093504976516682, |
|
"eval_loss": 1.2494499683380127, |
|
"eval_precision": 0.5442467116171107, |
|
"eval_recall": 0.47706422018348627, |
|
"eval_runtime": 5.2925, |
|
"eval_samples_per_second": 20.595, |
|
"eval_steps_per_second": 0.378, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 8.73, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 1.2518, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 8.97, |
|
"eval_accuracy": 0.5045871559633027, |
|
"eval_f1": 0.4430477860209126, |
|
"eval_loss": 1.2278722524642944, |
|
"eval_precision": 0.5524980055843638, |
|
"eval_recall": 0.5045871559633027, |
|
"eval_runtime": 4.1494, |
|
"eval_samples_per_second": 26.269, |
|
"eval_steps_per_second": 0.482, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 9.97, |
|
"learning_rate": 6.666666666666667e-05, |
|
"loss": 1.2085, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 9.97, |
|
"eval_accuracy": 0.5321100917431193, |
|
"eval_f1": 0.457935571494903, |
|
"eval_loss": 1.1905453205108643, |
|
"eval_precision": 0.5134095764735453, |
|
"eval_recall": 0.5321100917431193, |
|
"eval_runtime": 4.0094, |
|
"eval_samples_per_second": 27.186, |
|
"eval_steps_per_second": 0.499, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 10.97, |
|
"eval_accuracy": 0.5504587155963303, |
|
"eval_f1": 0.48717462017050756, |
|
"eval_loss": 1.1602399349212646, |
|
"eval_precision": 0.515116763969975, |
|
"eval_recall": 0.5504587155963303, |
|
"eval_runtime": 4.1843, |
|
"eval_samples_per_second": 26.05, |
|
"eval_steps_per_second": 0.478, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 11.24, |
|
"learning_rate": 5.833333333333333e-05, |
|
"loss": 1.1865, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 11.97, |
|
"eval_accuracy": 0.5963302752293578, |
|
"eval_f1": 0.5416442261263603, |
|
"eval_loss": 1.130654215812683, |
|
"eval_precision": 0.5968683580403025, |
|
"eval_recall": 0.5963302752293578, |
|
"eval_runtime": 4.1467, |
|
"eval_samples_per_second": 26.286, |
|
"eval_steps_per_second": 0.482, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 12.48, |
|
"learning_rate": 5e-05, |
|
"loss": 1.122, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 12.97, |
|
"eval_accuracy": 0.5871559633027523, |
|
"eval_f1": 0.5205747436589314, |
|
"eval_loss": 1.1036800146102905, |
|
"eval_precision": 0.5069059380985986, |
|
"eval_recall": 0.5871559633027523, |
|
"eval_runtime": 4.1081, |
|
"eval_samples_per_second": 26.533, |
|
"eval_steps_per_second": 0.487, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 13.73, |
|
"learning_rate": 4.1666666666666665e-05, |
|
"loss": 1.0812, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 13.97, |
|
"eval_accuracy": 0.5688073394495413, |
|
"eval_f1": 0.506813344115706, |
|
"eval_loss": 1.0797398090362549, |
|
"eval_precision": 0.4868139278766149, |
|
"eval_recall": 0.5688073394495413, |
|
"eval_runtime": 5.1378, |
|
"eval_samples_per_second": 21.215, |
|
"eval_steps_per_second": 0.389, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 14.97, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 1.0449, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 14.97, |
|
"eval_accuracy": 0.6238532110091743, |
|
"eval_f1": 0.5641135054405804, |
|
"eval_loss": 1.0711662769317627, |
|
"eval_precision": 0.5269170849922105, |
|
"eval_recall": 0.6238532110091743, |
|
"eval_runtime": 4.0775, |
|
"eval_samples_per_second": 26.732, |
|
"eval_steps_per_second": 0.49, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 15.97, |
|
"eval_accuracy": 0.6238532110091743, |
|
"eval_f1": 0.5516990654605334, |
|
"eval_loss": 1.042523980140686, |
|
"eval_precision": 0.5122844888800522, |
|
"eval_recall": 0.6238532110091743, |
|
"eval_runtime": 4.1924, |
|
"eval_samples_per_second": 26.0, |
|
"eval_steps_per_second": 0.477, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 16.24, |
|
"learning_rate": 2.5e-05, |
|
"loss": 1.0458, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 16.97, |
|
"eval_accuracy": 0.6238532110091743, |
|
"eval_f1": 0.5782110340855532, |
|
"eval_loss": 1.0345710515975952, |
|
"eval_precision": 0.6487350569919378, |
|
"eval_recall": 0.6238532110091743, |
|
"eval_runtime": 4.1751, |
|
"eval_samples_per_second": 26.107, |
|
"eval_steps_per_second": 0.479, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 17.48, |
|
"learning_rate": 1.6666666666666667e-05, |
|
"loss": 1.004, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 17.97, |
|
"eval_accuracy": 0.6330275229357798, |
|
"eval_f1": 0.5720803372179519, |
|
"eval_loss": 1.0264408588409424, |
|
"eval_precision": 0.5471838739885577, |
|
"eval_recall": 0.6330275229357798, |
|
"eval_runtime": 4.1766, |
|
"eval_samples_per_second": 26.098, |
|
"eval_steps_per_second": 0.479, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 18.73, |
|
"learning_rate": 8.333333333333334e-06, |
|
"loss": 0.9806, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 18.97, |
|
"eval_accuracy": 0.6605504587155964, |
|
"eval_f1": 0.6069485442003585, |
|
"eval_loss": 1.0041249990463257, |
|
"eval_precision": 0.6334097859327217, |
|
"eval_recall": 0.6605504587155964, |
|
"eval_runtime": 4.1778, |
|
"eval_samples_per_second": 26.09, |
|
"eval_steps_per_second": 0.479, |
|
"step": 152 |
|
}, |
|
{ |
|
"epoch": 19.97, |
|
"learning_rate": 0.0, |
|
"loss": 0.97, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 19.97, |
|
"eval_accuracy": 0.6697247706422018, |
|
"eval_f1": 0.6086361803243947, |
|
"eval_loss": 1.0058709383010864, |
|
"eval_precision": 0.5798801171844885, |
|
"eval_recall": 0.6697247706422018, |
|
"eval_runtime": 4.221, |
|
"eval_samples_per_second": 25.824, |
|
"eval_steps_per_second": 0.474, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 19.97, |
|
"step": 160, |
|
"total_flos": 8.788316705651589e+17, |
|
"train_loss": 1.1949474394321442, |
|
"train_runtime": 951.8189, |
|
"train_samples_per_second": 43.496, |
|
"train_steps_per_second": 0.168 |
|
} |
|
], |
|
"max_steps": 160, |
|
"num_train_epochs": 20, |
|
"total_flos": 8.788316705651589e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|