| { | |
| "best_metric": 0.7295733911785972, | |
| "best_model_checkpoint": "Ernie-3.0-large-chinese-finetuned-ner/checkpoint-9072", | |
| "epoch": 36.0, | |
| "eval_steps": 500, | |
| "global_step": 9072, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.9600000000000002e-05, | |
| "loss": 0.7619, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8891147174729265, | |
| "eval_f1": 0.5908584169453734, | |
| "eval_loss": 0.371647447347641, | |
| "eval_precision": 0.5302120848339336, | |
| "eval_recall": 0.6671701913393756, | |
| "eval_runtime": 30.5213, | |
| "eval_samples_per_second": 16.48, | |
| "eval_steps_per_second": 2.064, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.3277, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9043503894250163, | |
| "eval_f1": 0.6514158800666296, | |
| "eval_loss": 0.31230422854423523, | |
| "eval_precision": 0.5827538247566064, | |
| "eval_recall": 0.7384189325276939, | |
| "eval_runtime": 30.3199, | |
| "eval_samples_per_second": 16.59, | |
| "eval_steps_per_second": 2.078, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.88e-05, | |
| "loss": 0.2539, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9070344741986534, | |
| "eval_f1": 0.6798141221806642, | |
| "eval_loss": 0.3259331285953522, | |
| "eval_precision": 0.6182230467944754, | |
| "eval_recall": 0.7550352467270897, | |
| "eval_runtime": 31.8667, | |
| "eval_samples_per_second": 15.785, | |
| "eval_steps_per_second": 1.977, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 0.209, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.899121854345735, | |
| "eval_f1": 0.6714031971580817, | |
| "eval_loss": 0.3699039816856384, | |
| "eval_precision": 0.6004765687053217, | |
| "eval_recall": 0.7613293051359517, | |
| "eval_runtime": 29.8895, | |
| "eval_samples_per_second": 16.829, | |
| "eval_steps_per_second": 2.108, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.1696, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9081980947652589, | |
| "eval_f1": 0.7022252810277587, | |
| "eval_loss": 0.35198503732681274, | |
| "eval_precision": 0.6449641803624104, | |
| "eval_recall": 0.7706445115810675, | |
| "eval_runtime": 31.5563, | |
| "eval_samples_per_second": 15.94, | |
| "eval_steps_per_second": 1.996, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.76e-05, | |
| "loss": 0.1394, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9099047382629473, | |
| "eval_f1": 0.6968929804372841, | |
| "eval_loss": 0.36153343319892883, | |
| "eval_precision": 0.6417973717676981, | |
| "eval_recall": 0.7623363544813696, | |
| "eval_runtime": 30.5397, | |
| "eval_samples_per_second": 16.47, | |
| "eval_steps_per_second": 2.063, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 1.72e-05, | |
| "loss": 0.1184, | |
| "step": 1764 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9082911844105874, | |
| "eval_f1": 0.7067113318701628, | |
| "eval_loss": 0.37900495529174805, | |
| "eval_precision": 0.6529348986125934, | |
| "eval_recall": 0.7701409869083585, | |
| "eval_runtime": 30.8222, | |
| "eval_samples_per_second": 16.319, | |
| "eval_steps_per_second": 2.044, | |
| "step": 1764 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.1011, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9137214137214137, | |
| "eval_f1": 0.7153439153439154, | |
| "eval_loss": 0.38163959980010986, | |
| "eval_precision": 0.671078755790867, | |
| "eval_recall": 0.7658610271903323, | |
| "eval_runtime": 30.6484, | |
| "eval_samples_per_second": 16.412, | |
| "eval_steps_per_second": 2.056, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.64e-05, | |
| "loss": 0.0853, | |
| "step": 2268 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9104477611940298, | |
| "eval_f1": 0.7113811638233232, | |
| "eval_loss": 0.4221731722354889, | |
| "eval_precision": 0.6637592673353685, | |
| "eval_recall": 0.7663645518630413, | |
| "eval_runtime": 29.8305, | |
| "eval_samples_per_second": 16.862, | |
| "eval_steps_per_second": 2.112, | |
| "step": 2268 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0726, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9108201197753436, | |
| "eval_f1": 0.7088488276187108, | |
| "eval_loss": 0.45063257217407227, | |
| "eval_precision": 0.6662236987818383, | |
| "eval_recall": 0.75730110775428, | |
| "eval_runtime": 31.119, | |
| "eval_samples_per_second": 16.164, | |
| "eval_steps_per_second": 2.024, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 1.5600000000000003e-05, | |
| "loss": 0.0625, | |
| "step": 2772 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9118596208148447, | |
| "eval_f1": 0.7197667638483967, | |
| "eval_loss": 0.465919554233551, | |
| "eval_precision": 0.6704323267434282, | |
| "eval_recall": 0.7769385699899295, | |
| "eval_runtime": 30.3792, | |
| "eval_samples_per_second": 16.557, | |
| "eval_steps_per_second": 2.074, | |
| "step": 2772 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.0554, | |
| "step": 3024 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9138920780711826, | |
| "eval_f1": 0.7228513529622126, | |
| "eval_loss": 0.4619043469429016, | |
| "eval_precision": 0.6864387593389178, | |
| "eval_recall": 0.7633434038267876, | |
| "eval_runtime": 32.0505, | |
| "eval_samples_per_second": 15.694, | |
| "eval_steps_per_second": 1.966, | |
| "step": 3024 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 1.48e-05, | |
| "loss": 0.0468, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9101840071989326, | |
| "eval_f1": 0.7200470311581422, | |
| "eval_loss": 0.5248007774353027, | |
| "eval_precision": 0.6754908449150673, | |
| "eval_recall": 0.770896273917422, | |
| "eval_runtime": 30.3642, | |
| "eval_samples_per_second": 16.566, | |
| "eval_steps_per_second": 2.075, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 0.0416, | |
| "step": 3528 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9106649703664629, | |
| "eval_f1": 0.7144713526284701, | |
| "eval_loss": 0.5338897109031677, | |
| "eval_precision": 0.6730469619407968, | |
| "eval_recall": 0.7613293051359517, | |
| "eval_runtime": 30.627, | |
| "eval_samples_per_second": 16.423, | |
| "eval_steps_per_second": 2.057, | |
| "step": 3528 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0349, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9078877959474975, | |
| "eval_f1": 0.71319108805847, | |
| "eval_loss": 0.5588390827178955, | |
| "eval_precision": 0.6705830192861894, | |
| "eval_recall": 0.7615810674723061, | |
| "eval_runtime": 30.9024, | |
| "eval_samples_per_second": 16.277, | |
| "eval_steps_per_second": 2.039, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 0.0301, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9083687591150278, | |
| "eval_f1": 0.7168475696083058, | |
| "eval_loss": 0.5909355878829956, | |
| "eval_precision": 0.6745115452930728, | |
| "eval_recall": 0.7648539778449144, | |
| "eval_runtime": 31.5608, | |
| "eval_samples_per_second": 15.938, | |
| "eval_steps_per_second": 1.996, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.3200000000000002e-05, | |
| "loss": 0.0293, | |
| "step": 4284 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9139075930120706, | |
| "eval_f1": 0.7264906201457759, | |
| "eval_loss": 0.557870090007782, | |
| "eval_precision": 0.6913804866954741, | |
| "eval_recall": 0.7653575025176234, | |
| "eval_runtime": 31.1498, | |
| "eval_samples_per_second": 16.148, | |
| "eval_steps_per_second": 2.022, | |
| "step": 4284 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 0.0264, | |
| "step": 4536 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9099047382629473, | |
| "eval_f1": 0.7172199665631717, | |
| "eval_loss": 0.5989866256713867, | |
| "eval_precision": 0.682189913675602, | |
| "eval_recall": 0.7560422960725075, | |
| "eval_runtime": 29.8647, | |
| "eval_samples_per_second": 16.843, | |
| "eval_steps_per_second": 2.11, | |
| "step": 4536 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 1.2400000000000002e-05, | |
| "loss": 0.0223, | |
| "step": 4788 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9099357681447233, | |
| "eval_f1": 0.718458082062197, | |
| "eval_loss": 0.6070677638053894, | |
| "eval_precision": 0.6773690078037904, | |
| "eval_recall": 0.7648539778449144, | |
| "eval_runtime": 30.5876, | |
| "eval_samples_per_second": 16.445, | |
| "eval_steps_per_second": 2.06, | |
| "step": 4788 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0195, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9119992552828373, | |
| "eval_f1": 0.720656439529076, | |
| "eval_loss": 0.6215817928314209, | |
| "eval_precision": 0.68289384719405, | |
| "eval_recall": 0.7628398791540786, | |
| "eval_runtime": 30.3859, | |
| "eval_samples_per_second": 16.554, | |
| "eval_steps_per_second": 2.073, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.16e-05, | |
| "loss": 0.0181, | |
| "step": 5292 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9089428119278865, | |
| "eval_f1": 0.7139341380522678, | |
| "eval_loss": 0.6391084790229797, | |
| "eval_precision": 0.6678360008770007, | |
| "eval_recall": 0.7668680765357503, | |
| "eval_runtime": 31.753, | |
| "eval_samples_per_second": 15.841, | |
| "eval_steps_per_second": 1.984, | |
| "step": 5292 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 0.016, | |
| "step": 5544 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9129766965587861, | |
| "eval_f1": 0.7200477326968974, | |
| "eval_loss": 0.6382994055747986, | |
| "eval_precision": 0.684437386569873, | |
| "eval_recall": 0.7595669687814703, | |
| "eval_runtime": 30.7224, | |
| "eval_samples_per_second": 16.372, | |
| "eval_steps_per_second": 2.051, | |
| "step": 5544 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 1.0800000000000002e-05, | |
| "loss": 0.0153, | |
| "step": 5796 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9136903838396375, | |
| "eval_f1": 0.7225759942328487, | |
| "eval_loss": 0.6503807902336121, | |
| "eval_precision": 0.6911054929901173, | |
| "eval_recall": 0.7570493454179255, | |
| "eval_runtime": 30.4671, | |
| "eval_samples_per_second": 16.51, | |
| "eval_steps_per_second": 2.068, | |
| "step": 5796 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.04e-05, | |
| "loss": 0.0135, | |
| "step": 6048 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.911083873770441, | |
| "eval_f1": 0.7179244165383247, | |
| "eval_loss": 0.6738658547401428, | |
| "eval_precision": 0.6780040277466994, | |
| "eval_recall": 0.7628398791540786, | |
| "eval_runtime": 31.8247, | |
| "eval_samples_per_second": 15.805, | |
| "eval_steps_per_second": 1.98, | |
| "step": 6048 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0103, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.9127284575045769, | |
| "eval_f1": 0.7242580800192239, | |
| "eval_loss": 0.677778422832489, | |
| "eval_precision": 0.6927143185474604, | |
| "eval_recall": 0.7588116817724069, | |
| "eval_runtime": 31.5342, | |
| "eval_samples_per_second": 15.951, | |
| "eval_steps_per_second": 1.998, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.0109, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9117665311695162, | |
| "eval_f1": 0.7213822894168466, | |
| "eval_loss": 0.6734189987182617, | |
| "eval_precision": 0.6891334250343879, | |
| "eval_recall": 0.756797583081571, | |
| "eval_runtime": 30.9002, | |
| "eval_samples_per_second": 16.278, | |
| "eval_steps_per_second": 2.039, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 0.0097, | |
| "step": 6804 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.9124647035094796, | |
| "eval_f1": 0.7231973434535104, | |
| "eval_loss": 0.6837841272354126, | |
| "eval_precision": 0.6836322869955157, | |
| "eval_recall": 0.7676233635448136, | |
| "eval_runtime": 30.4438, | |
| "eval_samples_per_second": 16.522, | |
| "eval_steps_per_second": 2.069, | |
| "step": 6804 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.0092, | |
| "step": 7056 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9118130759921804, | |
| "eval_f1": 0.7228887320630439, | |
| "eval_loss": 0.7063636183738708, | |
| "eval_precision": 0.6783664459161148, | |
| "eval_recall": 0.7736656596173213, | |
| "eval_runtime": 32.0989, | |
| "eval_samples_per_second": 15.67, | |
| "eval_steps_per_second": 1.963, | |
| "step": 7056 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.0079, | |
| "step": 7308 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.9113941725882024, | |
| "eval_f1": 0.7218511450381679, | |
| "eval_loss": 0.6944219470024109, | |
| "eval_precision": 0.685856754306437, | |
| "eval_recall": 0.7618328298086606, | |
| "eval_runtime": 31.0056, | |
| "eval_samples_per_second": 16.223, | |
| "eval_steps_per_second": 2.032, | |
| "step": 7308 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0078, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.9092220808638719, | |
| "eval_f1": 0.717688679245283, | |
| "eval_loss": 0.7390450835227966, | |
| "eval_precision": 0.6750221827861579, | |
| "eval_recall": 0.7661127895266868, | |
| "eval_runtime": 32.0929, | |
| "eval_samples_per_second": 15.673, | |
| "eval_steps_per_second": 1.963, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 0.0066, | |
| "step": 7812 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.9112235082384336, | |
| "eval_f1": 0.7232323232323231, | |
| "eval_loss": 0.7528515458106995, | |
| "eval_precision": 0.6848975917173081, | |
| "eval_recall": 0.7661127895266868, | |
| "eval_runtime": 31.1215, | |
| "eval_samples_per_second": 16.162, | |
| "eval_steps_per_second": 2.024, | |
| "step": 7812 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 0.0061, | |
| "step": 8064 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.9128680919725696, | |
| "eval_f1": 0.7292161520190024, | |
| "eval_loss": 0.7525067925453186, | |
| "eval_precision": 0.6901978417266187, | |
| "eval_recall": 0.7729103726082578, | |
| "eval_runtime": 30.5355, | |
| "eval_samples_per_second": 16.473, | |
| "eval_steps_per_second": 2.063, | |
| "step": 8064 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 0.005, | |
| "step": 8316 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.9131939057312192, | |
| "eval_f1": 0.7289473684210527, | |
| "eval_loss": 0.7354016304016113, | |
| "eval_precision": 0.6943938012762079, | |
| "eval_recall": 0.7671198388721048, | |
| "eval_runtime": 30.6675, | |
| "eval_samples_per_second": 16.402, | |
| "eval_steps_per_second": 2.054, | |
| "step": 8316 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 0.0059, | |
| "step": 8568 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.9108666645980079, | |
| "eval_f1": 0.723687336659539, | |
| "eval_loss": 0.7652931809425354, | |
| "eval_precision": 0.6851102114260009, | |
| "eval_recall": 0.7668680765357503, | |
| "eval_runtime": 31.9436, | |
| "eval_samples_per_second": 15.747, | |
| "eval_steps_per_second": 1.972, | |
| "step": 8568 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0047, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.9116113817606355, | |
| "eval_f1": 0.7277705035114866, | |
| "eval_loss": 0.7705232501029968, | |
| "eval_precision": 0.6902235267554753, | |
| "eval_recall": 0.7696374622356495, | |
| "eval_runtime": 30.572, | |
| "eval_samples_per_second": 16.453, | |
| "eval_steps_per_second": 2.061, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 0.0049, | |
| "step": 9072 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.9124336736277034, | |
| "eval_f1": 0.7295733911785972, | |
| "eval_loss": 0.7525166273117065, | |
| "eval_precision": 0.6997226074895978, | |
| "eval_recall": 0.7620845921450151, | |
| "eval_runtime": 30.7353, | |
| "eval_samples_per_second": 16.366, | |
| "eval_steps_per_second": 2.05, | |
| "step": 9072 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 12600, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 3.469062692905536e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |