| { | |
| "best_metric": 0.6115919254751536, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-tekno24-highdata-90-3rd/checkpoint-858", | |
| "epoch": 29.357798165137616, | |
| "eval_steps": 500, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24464831804281345, | |
| "grad_norm": 6.330469131469727, | |
| "learning_rate": 2.4999999999999998e-06, | |
| "loss": 1.4219, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4892966360856269, | |
| "grad_norm": 4.396063327789307, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 1.3862, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "grad_norm": 8.383111000061035, | |
| "learning_rate": 7.5e-06, | |
| "loss": 1.3539, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9785932721712538, | |
| "grad_norm": 4.335956573486328, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 1.3622, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9785932721712538, | |
| "eval_accuracy": 0.3686635944700461, | |
| "eval_f1": 0.24531431172017315, | |
| "eval_loss": 1.345871925354004, | |
| "eval_precision": 0.2573782313691113, | |
| "eval_recall": 0.3686635944700461, | |
| "eval_runtime": 0.8809, | |
| "eval_samples_per_second": 246.332, | |
| "eval_steps_per_second": 15.892, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2232415902140672, | |
| "grad_norm": 4.0306572914123535, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.3462, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4678899082568808, | |
| "grad_norm": 5.952158451080322, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.3484, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.7125382262996942, | |
| "grad_norm": 4.490999698638916, | |
| "learning_rate": 1.7500000000000002e-05, | |
| "loss": 1.3272, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.9571865443425076, | |
| "grad_norm": 4.4648823738098145, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 1.335, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.981651376146789, | |
| "eval_accuracy": 0.3778801843317972, | |
| "eval_f1": 0.36347086798868594, | |
| "eval_loss": 1.329477310180664, | |
| "eval_precision": 0.35923465537774313, | |
| "eval_recall": 0.3778801843317972, | |
| "eval_runtime": 0.858, | |
| "eval_samples_per_second": 252.915, | |
| "eval_steps_per_second": 16.317, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.2018348623853212, | |
| "grad_norm": 3.4146816730499268, | |
| "learning_rate": 2.25e-05, | |
| "loss": 1.3282, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.4464831804281344, | |
| "grad_norm": 2.6035099029541016, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.3004, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.691131498470948, | |
| "grad_norm": 4.214941024780273, | |
| "learning_rate": 2.75e-05, | |
| "loss": 1.2825, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.9357798165137616, | |
| "grad_norm": 4.834983825683594, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2404, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.984709480122324, | |
| "eval_accuracy": 0.5023041474654378, | |
| "eval_f1": 0.4893126350217038, | |
| "eval_loss": 1.1256120204925537, | |
| "eval_precision": 0.5048490267556228, | |
| "eval_recall": 0.5023041474654378, | |
| "eval_runtime": 0.8434, | |
| "eval_samples_per_second": 257.293, | |
| "eval_steps_per_second": 16.6, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 3.180428134556575, | |
| "grad_norm": 3.794398784637451, | |
| "learning_rate": 2.9993654251233013e-05, | |
| "loss": 1.2474, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.4250764525993884, | |
| "grad_norm": 5.768642425537109, | |
| "learning_rate": 2.9974622374069024e-05, | |
| "loss": 1.195, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.669724770642202, | |
| "grad_norm": 3.9253504276275635, | |
| "learning_rate": 2.9942920471376185e-05, | |
| "loss": 1.2086, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.914373088685015, | |
| "grad_norm": 4.371098518371582, | |
| "learning_rate": 2.9898575366129145e-05, | |
| "loss": 1.2113, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.9877675840978593, | |
| "eval_accuracy": 0.5345622119815668, | |
| "eval_f1": 0.49180767021976945, | |
| "eval_loss": 1.10813570022583, | |
| "eval_precision": 0.5409206372379718, | |
| "eval_recall": 0.5345622119815668, | |
| "eval_runtime": 0.8699, | |
| "eval_samples_per_second": 249.465, | |
| "eval_steps_per_second": 16.095, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 4.159021406727828, | |
| "grad_norm": 2.8948540687561035, | |
| "learning_rate": 2.9841624578714165e-05, | |
| "loss": 1.1962, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.4036697247706424, | |
| "grad_norm": 4.7834649085998535, | |
| "learning_rate": 2.977211629518312e-05, | |
| "loss": 1.2218, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.648318042813456, | |
| "grad_norm": 7.953682899475098, | |
| "learning_rate": 2.9690109326483276e-05, | |
| "loss": 1.1939, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.892966360856269, | |
| "grad_norm": 4.670468807220459, | |
| "learning_rate": 2.959567305869736e-05, | |
| "loss": 1.1617, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.990825688073395, | |
| "eval_accuracy": 0.5299539170506913, | |
| "eval_f1": 0.4937854301455633, | |
| "eval_loss": 1.0666954517364502, | |
| "eval_precision": 0.5204300879512693, | |
| "eval_recall": 0.5299539170506913, | |
| "eval_runtime": 0.8676, | |
| "eval_samples_per_second": 250.129, | |
| "eval_steps_per_second": 16.137, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 5.137614678899083, | |
| "grad_norm": 3.710249662399292, | |
| "learning_rate": 2.9488887394336025e-05, | |
| "loss": 1.1513, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.382262996941896, | |
| "grad_norm": 5.402332305908203, | |
| "learning_rate": 2.9369842684732334e-05, | |
| "loss": 1.1615, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 5.626911314984709, | |
| "grad_norm": 5.203404426574707, | |
| "learning_rate": 2.923863965359551e-05, | |
| "loss": 1.1667, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 5.871559633027523, | |
| "grad_norm": 3.1625759601593018, | |
| "learning_rate": 2.9095389311788626e-05, | |
| "loss": 1.1758, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.99388379204893, | |
| "eval_accuracy": 0.47465437788018433, | |
| "eval_f1": 0.471263567537793, | |
| "eval_loss": 1.1505143642425537, | |
| "eval_precision": 0.5074166187040903, | |
| "eval_recall": 0.47465437788018433, | |
| "eval_runtime": 0.8615, | |
| "eval_samples_per_second": 251.9, | |
| "eval_steps_per_second": 16.252, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 6.116207951070336, | |
| "grad_norm": 3.6149017810821533, | |
| "learning_rate": 2.8940212863402334e-05, | |
| "loss": 1.1593, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.36085626911315, | |
| "grad_norm": 5.2453718185424805, | |
| "learning_rate": 2.877324160320411e-05, | |
| "loss": 1.1709, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 6.605504587155964, | |
| "grad_norm": 2.8466713428497314, | |
| "learning_rate": 2.8594616805549752e-05, | |
| "loss": 1.1796, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.850152905198777, | |
| "grad_norm": 5.2934489250183105, | |
| "learning_rate": 2.8404489604851186e-05, | |
| "loss": 1.1618, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 6.996941896024465, | |
| "eval_accuracy": 0.4930875576036866, | |
| "eval_f1": 0.4779433197425019, | |
| "eval_loss": 1.1315704584121704, | |
| "eval_precision": 0.49500033007529604, | |
| "eval_recall": 0.4930875576036866, | |
| "eval_runtime": 0.8521, | |
| "eval_samples_per_second": 254.672, | |
| "eval_steps_per_second": 16.43, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 7.09480122324159, | |
| "grad_norm": 2.6427509784698486, | |
| "learning_rate": 2.8203020867701665e-05, | |
| "loss": 1.1743, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 7.339449541284404, | |
| "grad_norm": 4.475164890289307, | |
| "learning_rate": 2.7990381056766583e-05, | |
| "loss": 1.145, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.584097859327217, | |
| "grad_norm": 6.199124813079834, | |
| "learning_rate": 2.7766750086554997e-05, | |
| "loss": 1.1746, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 7.82874617737003, | |
| "grad_norm": 2.8797366619110107, | |
| "learning_rate": 2.753231717119405e-05, | |
| "loss": 1.1748, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5161290322580645, | |
| "eval_f1": 0.48266751828493326, | |
| "eval_loss": 1.068114995956421, | |
| "eval_precision": 0.5256066050304817, | |
| "eval_recall": 0.5161290322580645, | |
| "eval_runtime": 0.9022, | |
| "eval_samples_per_second": 240.519, | |
| "eval_steps_per_second": 15.517, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 8.073394495412844, | |
| "grad_norm": 3.447052001953125, | |
| "learning_rate": 2.728728066433488e-05, | |
| "loss": 1.1551, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 8.318042813455657, | |
| "grad_norm": 8.132365226745605, | |
| "learning_rate": 2.7031847891325658e-05, | |
| "loss": 1.1553, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 8.562691131498472, | |
| "grad_norm": 4.7136969566345215, | |
| "learning_rate": 2.6766234973793638e-05, | |
| "loss": 1.1417, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 8.807339449541285, | |
| "grad_norm": 5.761626243591309, | |
| "learning_rate": 2.649066664678467e-05, | |
| "loss": 1.1421, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 8.978593272171254, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_f1": 0.5445015753271358, | |
| "eval_loss": 0.9743120670318604, | |
| "eval_precision": 0.5487771652399015, | |
| "eval_recall": 0.5714285714285714, | |
| "eval_runtime": 0.8766, | |
| "eval_samples_per_second": 247.558, | |
| "eval_steps_per_second": 15.971, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 9.051987767584098, | |
| "grad_norm": 4.3898138999938965, | |
| "learning_rate": 2.620537606861494e-05, | |
| "loss": 1.1345, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 9.296636085626911, | |
| "grad_norm": 4.993420600891113, | |
| "learning_rate": 2.5910604623595732e-05, | |
| "loss": 1.1397, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 9.541284403669724, | |
| "grad_norm": 4.071462631225586, | |
| "learning_rate": 2.5606601717798212e-05, | |
| "loss": 1.1463, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 9.785932721712538, | |
| "grad_norm": 9.125846862792969, | |
| "learning_rate": 2.5293624568031008e-05, | |
| "loss": 1.1565, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 9.98165137614679, | |
| "eval_accuracy": 0.5622119815668203, | |
| "eval_f1": 0.5142422921536122, | |
| "eval_loss": 0.9705408215522766, | |
| "eval_precision": 0.5428585184675699, | |
| "eval_recall": 0.5622119815668203, | |
| "eval_runtime": 0.8818, | |
| "eval_samples_per_second": 246.084, | |
| "eval_steps_per_second": 15.876, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 10.030581039755353, | |
| "grad_norm": 3.2460174560546875, | |
| "learning_rate": 2.4971937984209064e-05, | |
| "loss": 1.1213, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 10.275229357798166, | |
| "grad_norm": 3.74979829788208, | |
| "learning_rate": 2.464181414529809e-05, | |
| "loss": 1.1653, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 10.519877675840979, | |
| "grad_norm": 4.549282073974609, | |
| "learning_rate": 2.43035323690239e-05, | |
| "loss": 1.1195, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 10.764525993883792, | |
| "grad_norm": 5.184534549713135, | |
| "learning_rate": 2.3957378875541795e-05, | |
| "loss": 1.1297, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 10.984709480122325, | |
| "eval_accuracy": 0.5529953917050692, | |
| "eval_f1": 0.5365471718335717, | |
| "eval_loss": 0.9878734350204468, | |
| "eval_precision": 0.5343152202928371, | |
| "eval_recall": 0.5529953917050692, | |
| "eval_runtime": 0.8858, | |
| "eval_samples_per_second": 244.969, | |
| "eval_steps_per_second": 15.804, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 11.009174311926605, | |
| "grad_norm": 5.1757049560546875, | |
| "learning_rate": 2.360364654526569e-05, | |
| "loss": 1.1315, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 11.253822629969418, | |
| "grad_norm": 4.584784507751465, | |
| "learning_rate": 2.324263467106209e-05, | |
| "loss": 1.0953, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 11.498470948012232, | |
| "grad_norm": 5.368664264678955, | |
| "learning_rate": 2.28746487050184e-05, | |
| "loss": 1.1434, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 11.743119266055047, | |
| "grad_norm": 3.2927210330963135, | |
| "learning_rate": 2.25e-05, | |
| "loss": 1.1204, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 11.98776758409786, | |
| "grad_norm": 2.96950626373291, | |
| "learning_rate": 2.2119005546214607e-05, | |
| "loss": 1.1249, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 11.98776758409786, | |
| "eval_accuracy": 0.576036866359447, | |
| "eval_f1": 0.5401449505661916, | |
| "eval_loss": 0.9852494597434998, | |
| "eval_precision": 0.6055202291285648, | |
| "eval_recall": 0.576036866359447, | |
| "eval_runtime": 0.8582, | |
| "eval_samples_per_second": 252.863, | |
| "eval_steps_per_second": 16.314, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 12.232415902140673, | |
| "grad_norm": 4.752162456512451, | |
| "learning_rate": 2.1731987703006933e-05, | |
| "loss": 1.0875, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 12.477064220183486, | |
| "grad_norm": 4.843075275421143, | |
| "learning_rate": 2.1339273926110493e-05, | |
| "loss": 1.1289, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 12.7217125382263, | |
| "grad_norm": 3.870483636856079, | |
| "learning_rate": 2.0941196490587352e-05, | |
| "loss": 1.0987, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 12.966360856269112, | |
| "grad_norm": 5.1215081214904785, | |
| "learning_rate": 2.0538092209690267e-05, | |
| "loss": 1.1289, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 12.990825688073395, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_f1": 0.53625493827214, | |
| "eval_loss": 0.9554733037948608, | |
| "eval_precision": 0.5409489632358654, | |
| "eval_recall": 0.5714285714285714, | |
| "eval_runtime": 0.8589, | |
| "eval_samples_per_second": 252.652, | |
| "eval_steps_per_second": 16.3, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 13.211009174311927, | |
| "grad_norm": 3.453106164932251, | |
| "learning_rate": 2.0130302149885033e-05, | |
| "loss": 1.1112, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 13.45565749235474, | |
| "grad_norm": 3.6579651832580566, | |
| "learning_rate": 1.9718171342274207e-05, | |
| "loss": 1.093, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 13.700305810397554, | |
| "grad_norm": 4.116721153259277, | |
| "learning_rate": 1.9302048490666356e-05, | |
| "loss": 1.071, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 13.944954128440367, | |
| "grad_norm": 4.801394939422607, | |
| "learning_rate": 1.888228567653781e-05, | |
| "loss": 1.1102, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 13.99388379204893, | |
| "eval_accuracy": 0.5990783410138248, | |
| "eval_f1": 0.5795304519070373, | |
| "eval_loss": 0.9438399076461792, | |
| "eval_precision": 0.6032853066292203, | |
| "eval_recall": 0.5990783410138248, | |
| "eval_runtime": 0.8683, | |
| "eval_samples_per_second": 249.915, | |
| "eval_steps_per_second": 16.124, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 14.18960244648318, | |
| "grad_norm": 3.2803945541381836, | |
| "learning_rate": 1.8459238061136604e-05, | |
| "loss": 1.0885, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 14.434250764525993, | |
| "grad_norm": 4.159581661224365, | |
| "learning_rate": 1.8033263584980572e-05, | |
| "loss": 1.0843, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 14.678899082568808, | |
| "grad_norm": 4.556077480316162, | |
| "learning_rate": 1.760472266500396e-05, | |
| "loss": 1.1073, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 14.923547400611621, | |
| "grad_norm": 5.622644901275635, | |
| "learning_rate": 1.7173977889608698e-05, | |
| "loss": 1.1011, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 14.996941896024465, | |
| "eval_accuracy": 0.5990783410138248, | |
| "eval_f1": 0.5839986401752663, | |
| "eval_loss": 0.9491886496543884, | |
| "eval_precision": 0.6015877856086249, | |
| "eval_recall": 0.5990783410138248, | |
| "eval_runtime": 0.8608, | |
| "eval_samples_per_second": 252.096, | |
| "eval_steps_per_second": 16.264, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 15.168195718654435, | |
| "grad_norm": 4.210937976837158, | |
| "learning_rate": 1.6741393711878455e-05, | |
| "loss": 1.105, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 15.412844036697248, | |
| "grad_norm": 4.558620452880859, | |
| "learning_rate": 1.6307336141214877e-05, | |
| "loss": 1.1142, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 15.65749235474006, | |
| "grad_norm": 4.51144552230835, | |
| "learning_rate": 1.587217243365714e-05, | |
| "loss": 1.0468, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 15.902140672782874, | |
| "grad_norm": 4.054220199584961, | |
| "learning_rate": 1.543627078114667e-05, | |
| "loss": 1.1293, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_f1": 0.5547707796966923, | |
| "eval_loss": 0.9825624823570251, | |
| "eval_precision": 0.5999554049946036, | |
| "eval_recall": 0.5714285714285714, | |
| "eval_runtime": 0.886, | |
| "eval_samples_per_second": 244.909, | |
| "eval_steps_per_second": 15.801, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 16.146788990825687, | |
| "grad_norm": 4.0673298835754395, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.1229, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 16.3914373088685, | |
| "grad_norm": 4.635714530944824, | |
| "learning_rate": 1.4563729218853329e-05, | |
| "loss": 1.1104, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 16.636085626911314, | |
| "grad_norm": 5.1717610359191895, | |
| "learning_rate": 1.4127827566342864e-05, | |
| "loss": 1.0871, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 16.88073394495413, | |
| "grad_norm": 3.7032668590545654, | |
| "learning_rate": 1.3692663858785127e-05, | |
| "loss": 1.0706, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 16.978593272171253, | |
| "eval_accuracy": 0.5944700460829493, | |
| "eval_f1": 0.5739258278528425, | |
| "eval_loss": 0.9465323686599731, | |
| "eval_precision": 0.6001352759137449, | |
| "eval_recall": 0.5944700460829493, | |
| "eval_runtime": 0.8837, | |
| "eval_samples_per_second": 245.555, | |
| "eval_steps_per_second": 15.842, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 17.125382262996943, | |
| "grad_norm": 3.981715440750122, | |
| "learning_rate": 1.3258606288121545e-05, | |
| "loss": 1.0666, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 17.370030581039757, | |
| "grad_norm": 4.0711846351623535, | |
| "learning_rate": 1.2826022110391301e-05, | |
| "loss": 1.0819, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 17.61467889908257, | |
| "grad_norm": 4.841401100158691, | |
| "learning_rate": 1.2395277334996045e-05, | |
| "loss": 1.0992, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 17.859327217125383, | |
| "grad_norm": 4.324009418487549, | |
| "learning_rate": 1.1966736415019434e-05, | |
| "loss": 1.0825, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 17.98165137614679, | |
| "eval_accuracy": 0.6082949308755761, | |
| "eval_f1": 0.5860764206601137, | |
| "eval_loss": 0.9267781972885132, | |
| "eval_precision": 0.608336555917201, | |
| "eval_recall": 0.6082949308755761, | |
| "eval_runtime": 0.8665, | |
| "eval_samples_per_second": 250.427, | |
| "eval_steps_per_second": 16.157, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 18.103975535168196, | |
| "grad_norm": 5.315589427947998, | |
| "learning_rate": 1.1540761938863397e-05, | |
| "loss": 1.0897, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 18.34862385321101, | |
| "grad_norm": 5.192884922027588, | |
| "learning_rate": 1.1117714323462188e-05, | |
| "loss": 1.0724, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 18.593272171253822, | |
| "grad_norm": 4.687433242797852, | |
| "learning_rate": 1.069795150933365e-05, | |
| "loss": 1.079, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 18.837920489296636, | |
| "grad_norm": 5.24461555480957, | |
| "learning_rate": 1.0281828657725798e-05, | |
| "loss": 1.0989, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 18.984709480122323, | |
| "eval_accuracy": 0.6082949308755761, | |
| "eval_f1": 0.5900226152184301, | |
| "eval_loss": 0.9349210262298584, | |
| "eval_precision": 0.616806148489978, | |
| "eval_recall": 0.6082949308755761, | |
| "eval_runtime": 0.8555, | |
| "eval_samples_per_second": 253.66, | |
| "eval_steps_per_second": 16.365, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 19.08256880733945, | |
| "grad_norm": 4.098168849945068, | |
| "learning_rate": 9.86969785011497e-06, | |
| "loss": 1.0785, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 19.327217125382262, | |
| "grad_norm": 4.730178356170654, | |
| "learning_rate": 9.461907790309735e-06, | |
| "loss": 1.069, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 19.571865443425075, | |
| "grad_norm": 5.353407859802246, | |
| "learning_rate": 9.058803509412647e-06, | |
| "loss": 1.0864, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 19.81651376146789, | |
| "grad_norm": 5.941184043884277, | |
| "learning_rate": 8.66072607388951e-06, | |
| "loss": 1.0541, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 19.98776758409786, | |
| "eval_accuracy": 0.6175115207373272, | |
| "eval_f1": 0.6103037127467525, | |
| "eval_loss": 0.9407837986946106, | |
| "eval_precision": 0.6331867057673509, | |
| "eval_recall": 0.6175115207373272, | |
| "eval_runtime": 0.8803, | |
| "eval_samples_per_second": 246.5, | |
| "eval_steps_per_second": 15.903, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 20.061162079510705, | |
| "grad_norm": 5.963148593902588, | |
| "learning_rate": 8.268012296993067e-06, | |
| "loss": 1.0919, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 20.30581039755352, | |
| "grad_norm": 5.1851606369018555, | |
| "learning_rate": 7.880994453785394e-06, | |
| "loss": 1.0722, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 20.55045871559633, | |
| "grad_norm": 4.50276517868042, | |
| "learning_rate": 7.500000000000004e-06, | |
| "loss": 1.0523, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 20.795107033639145, | |
| "grad_norm": 4.3782453536987305, | |
| "learning_rate": 7.1253512949815995e-06, | |
| "loss": 1.0883, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 20.990825688073393, | |
| "eval_accuracy": 0.6221198156682027, | |
| "eval_f1": 0.6115919254751536, | |
| "eval_loss": 0.9107956886291504, | |
| "eval_precision": 0.616963195553811, | |
| "eval_recall": 0.6221198156682027, | |
| "eval_runtime": 0.8511, | |
| "eval_samples_per_second": 254.955, | |
| "eval_steps_per_second": 16.449, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 21.039755351681958, | |
| "grad_norm": 5.798299312591553, | |
| "learning_rate": 6.75736532893791e-06, | |
| "loss": 1.0634, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 21.28440366972477, | |
| "grad_norm": 4.693358421325684, | |
| "learning_rate": 6.3963534547343126e-06, | |
| "loss": 1.0804, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 21.529051987767584, | |
| "grad_norm": 5.018470764160156, | |
| "learning_rate": 6.0426211244582105e-06, | |
| "loss": 1.0485, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 21.773700305810397, | |
| "grad_norm": 4.43956995010376, | |
| "learning_rate": 5.696467630976101e-06, | |
| "loss": 1.0828, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 21.99388379204893, | |
| "eval_accuracy": 0.5990783410138248, | |
| "eval_f1": 0.5912505275453264, | |
| "eval_loss": 0.9411961436271667, | |
| "eval_precision": 0.6205200942687754, | |
| "eval_recall": 0.5990783410138248, | |
| "eval_runtime": 0.8609, | |
| "eval_samples_per_second": 252.076, | |
| "eval_steps_per_second": 16.263, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 22.01834862385321, | |
| "grad_norm": 4.936504364013672, | |
| "learning_rate": 5.3581858547019095e-06, | |
| "loss": 1.0715, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 22.262996941896024, | |
| "grad_norm": 5.165542125701904, | |
| "learning_rate": 5.0280620157909316e-06, | |
| "loss": 1.06, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 22.507645259938837, | |
| "grad_norm": 4.64872407913208, | |
| "learning_rate": 4.706375431968998e-06, | |
| "loss": 1.0631, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 22.75229357798165, | |
| "grad_norm": 4.921236991882324, | |
| "learning_rate": 4.393398282201788e-06, | |
| "loss": 1.0601, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 22.996941896024463, | |
| "grad_norm": 4.369044780731201, | |
| "learning_rate": 4.089395376404269e-06, | |
| "loss": 1.0492, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 22.996941896024463, | |
| "eval_accuracy": 0.6129032258064516, | |
| "eval_f1": 0.6002888307021196, | |
| "eval_loss": 0.9262792468070984, | |
| "eval_precision": 0.6441948258190624, | |
| "eval_recall": 0.6129032258064516, | |
| "eval_runtime": 0.8685, | |
| "eval_samples_per_second": 249.843, | |
| "eval_steps_per_second": 16.119, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 23.24159021406728, | |
| "grad_norm": 5.06370735168457, | |
| "learning_rate": 3.7946239313850626e-06, | |
| "loss": 1.0591, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 23.486238532110093, | |
| "grad_norm": 5.190964698791504, | |
| "learning_rate": 3.5093333532153316e-06, | |
| "loss": 1.0401, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 23.730886850152906, | |
| "grad_norm": 6.742732524871826, | |
| "learning_rate": 3.2337650262063646e-06, | |
| "loss": 1.0891, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 23.97553516819572, | |
| "grad_norm": 4.73397159576416, | |
| "learning_rate": 2.9681521086743426e-06, | |
| "loss": 1.0486, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6129032258064516, | |
| "eval_f1": 0.6069089976834864, | |
| "eval_loss": 0.9253664016723633, | |
| "eval_precision": 0.6137060060993463, | |
| "eval_recall": 0.6129032258064516, | |
| "eval_runtime": 0.883, | |
| "eval_samples_per_second": 245.748, | |
| "eval_steps_per_second": 15.855, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 24.220183486238533, | |
| "grad_norm": 4.736702919006348, | |
| "learning_rate": 2.7127193356651214e-06, | |
| "loss": 1.0439, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 24.464831804281346, | |
| "grad_norm": 4.618147373199463, | |
| "learning_rate": 2.467682828805956e-06, | |
| "loss": 1.0428, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 24.70948012232416, | |
| "grad_norm": 5.107517719268799, | |
| "learning_rate": 2.233249913445004e-06, | |
| "loss": 1.0535, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 24.954128440366972, | |
| "grad_norm": 5.802303314208984, | |
| "learning_rate": 2.0096189432334194e-06, | |
| "loss": 1.0648, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 24.978593272171253, | |
| "eval_accuracy": 0.5990783410138248, | |
| "eval_f1": 0.5880284966872402, | |
| "eval_loss": 0.9164543747901917, | |
| "eval_precision": 0.6001504954993327, | |
| "eval_recall": 0.5990783410138248, | |
| "eval_runtime": 0.8507, | |
| "eval_samples_per_second": 255.079, | |
| "eval_steps_per_second": 16.457, | |
| "step": 1021 | |
| }, | |
| { | |
| "epoch": 25.198776758409785, | |
| "grad_norm": 4.453035831451416, | |
| "learning_rate": 1.7969791322983354e-06, | |
| "loss": 1.0255, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 25.4434250764526, | |
| "grad_norm": 5.172535419464111, | |
| "learning_rate": 1.5955103951488177e-06, | |
| "loss": 1.0636, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 25.68807339449541, | |
| "grad_norm": 4.380440711975098, | |
| "learning_rate": 1.4053831944502509e-06, | |
| "loss": 1.0454, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 25.932721712538225, | |
| "grad_norm": 4.616762638092041, | |
| "learning_rate": 1.2267583967958918e-06, | |
| "loss": 1.079, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 25.98165137614679, | |
| "eval_accuracy": 0.5898617511520737, | |
| "eval_f1": 0.5794668921596123, | |
| "eval_loss": 0.9294114112854004, | |
| "eval_precision": 0.6006132884013068, | |
| "eval_recall": 0.5898617511520737, | |
| "eval_runtime": 0.8875, | |
| "eval_samples_per_second": 244.511, | |
| "eval_steps_per_second": 15.775, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 26.17737003058104, | |
| "grad_norm": 4.948554992675781, | |
| "learning_rate": 1.059787136597662e-06, | |
| "loss": 1.0615, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 26.422018348623855, | |
| "grad_norm": 5.786351680755615, | |
| "learning_rate": 9.046106882113753e-07, | |
| "loss": 1.0472, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 4.639774322509766, | |
| "learning_rate": 7.613603464044916e-07, | |
| "loss": 1.0473, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 26.91131498470948, | |
| "grad_norm": 5.199443340301514, | |
| "learning_rate": 6.301573152676665e-07, | |
| "loss": 1.0459, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 26.984709480122323, | |
| "eval_accuracy": 0.6082949308755761, | |
| "eval_f1": 0.5953286856512663, | |
| "eval_loss": 0.923698902130127, | |
| "eval_precision": 0.6167649855641182, | |
| "eval_recall": 0.6082949308755761, | |
| "eval_runtime": 0.8646, | |
| "eval_samples_per_second": 250.99, | |
| "eval_steps_per_second": 16.193, | |
| "step": 1103 | |
| }, | |
| { | |
| "epoch": 27.155963302752294, | |
| "grad_norm": 5.868374824523926, | |
| "learning_rate": 5.11112605663977e-07, | |
| "loss": 1.0628, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 27.400611620795107, | |
| "grad_norm": 4.410027980804443, | |
| "learning_rate": 4.043269413026429e-07, | |
| "loss": 1.0471, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 27.64525993883792, | |
| "grad_norm": 4.9952192306518555, | |
| "learning_rate": 3.0989067351672783e-07, | |
| "loss": 1.0557, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 27.889908256880734, | |
| "grad_norm": 4.651206970214844, | |
| "learning_rate": 2.278837048168797e-07, | |
| "loss": 1.057, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 27.98776758409786, | |
| "eval_accuracy": 0.6082949308755761, | |
| "eval_f1": 0.5953286856512663, | |
| "eval_loss": 0.9232858419418335, | |
| "eval_precision": 0.6167649855641182, | |
| "eval_recall": 0.6082949308755761, | |
| "eval_runtime": 0.8831, | |
| "eval_samples_per_second": 245.732, | |
| "eval_steps_per_second": 15.854, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 28.134556574923547, | |
| "grad_norm": 4.553572177886963, | |
| "learning_rate": 1.5837542128583294e-07, | |
| "loss": 1.0341, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 28.37920489296636, | |
| "grad_norm": 5.814303398132324, | |
| "learning_rate": 1.0142463387085465e-07, | |
| "loss": 1.0547, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 28.623853211009173, | |
| "grad_norm": 4.839509963989258, | |
| "learning_rate": 5.7079528623816824e-08, | |
| "loss": 1.0585, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 28.868501529051986, | |
| "grad_norm": 4.723291873931885, | |
| "learning_rate": 2.5377625930977367e-08, | |
| "loss": 1.0496, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 28.990825688073393, | |
| "eval_accuracy": 0.5990783410138248, | |
| "eval_f1": 0.5874155589819042, | |
| "eval_loss": 0.923707902431488, | |
| "eval_precision": 0.6076854618844824, | |
| "eval_recall": 0.5990783410138248, | |
| "eval_runtime": 0.8527, | |
| "eval_samples_per_second": 254.495, | |
| "eval_steps_per_second": 16.419, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 29.1131498470948, | |
| "grad_norm": 4.5172576904296875, | |
| "learning_rate": 6.345748766991011e-09, | |
| "loss": 1.0385, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 29.357798165137616, | |
| "grad_norm": 4.991288661956787, | |
| "learning_rate": 0.0, | |
| "loss": 1.0509, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 29.357798165137616, | |
| "eval_accuracy": 0.5990783410138248, | |
| "eval_f1": 0.5874155589819042, | |
| "eval_loss": 0.9237886071205139, | |
| "eval_precision": 0.6076854618844824, | |
| "eval_recall": 0.5990783410138248, | |
| "eval_runtime": 0.8997, | |
| "eval_samples_per_second": 241.202, | |
| "eval_steps_per_second": 15.561, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 29.357798165137616, | |
| "step": 1200, | |
| "total_flos": 3.8130472219998413e+18, | |
| "train_loss": 1.1265972677866618, | |
| "train_runtime": 2449.5651, | |
| "train_samples_per_second": 63.991, | |
| "train_steps_per_second": 0.49 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "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": 3.8130472219998413e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |