| { | |
| "best_metric": 0.6728110599078341, | |
| "best_model_checkpoint": "convnextv2-base-22k-224-finetuned-tekno24-highdata-90/checkpoint-1553", | |
| "epoch": 29.724770642201836, | |
| "eval_steps": 500, | |
| "global_step": 2430, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12232415902140673, | |
| "grad_norm": 15.331552505493164, | |
| "learning_rate": 2.05761316872428e-06, | |
| "loss": 1.3954, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24464831804281345, | |
| "grad_norm": 13.410693168640137, | |
| "learning_rate": 4.11522633744856e-06, | |
| "loss": 1.3826, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3669724770642202, | |
| "grad_norm": 14.4244966506958, | |
| "learning_rate": 5.967078189300412e-06, | |
| "loss": 1.3692, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4892966360856269, | |
| "grad_norm": 13.09442138671875, | |
| "learning_rate": 8.02469135802469e-06, | |
| "loss": 1.3596, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6116207951070336, | |
| "grad_norm": 14.526571273803711, | |
| "learning_rate": 1.008230452674897e-05, | |
| "loss": 1.3519, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "grad_norm": 21.34126091003418, | |
| "learning_rate": 1.2139917695473252e-05, | |
| "loss": 1.3338, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8562691131498471, | |
| "grad_norm": 17.52889060974121, | |
| "learning_rate": 1.3991769547325103e-05, | |
| "loss": 1.3236, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9785932721712538, | |
| "grad_norm": 17.072633743286133, | |
| "learning_rate": 1.604938271604938e-05, | |
| "loss": 1.3277, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9908256880733946, | |
| "eval_accuracy": 0.4147465437788018, | |
| "eval_f1": 0.32804846883348265, | |
| "eval_loss": 1.2870396375656128, | |
| "eval_precision": 0.3713606931606389, | |
| "eval_recall": 0.4147465437788018, | |
| "eval_runtime": 2.1883, | |
| "eval_samples_per_second": 99.163, | |
| "eval_steps_per_second": 6.398, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.1009174311926606, | |
| "grad_norm": 22.833921432495117, | |
| "learning_rate": 1.8106995884773663e-05, | |
| "loss": 1.3091, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.2232415902140672, | |
| "grad_norm": 10.650703430175781, | |
| "learning_rate": 2.016460905349794e-05, | |
| "loss": 1.3123, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.345565749235474, | |
| "grad_norm": 9.893655776977539, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.2944, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.4678899082568808, | |
| "grad_norm": 54.886756896972656, | |
| "learning_rate": 2.3868312757201647e-05, | |
| "loss": 1.2842, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.5902140672782874, | |
| "grad_norm": 16.818227767944336, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 1.2572, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.7125382262996942, | |
| "grad_norm": 9.368868827819824, | |
| "learning_rate": 2.7983539094650207e-05, | |
| "loss": 1.2222, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.834862385321101, | |
| "grad_norm": 12.728253364562988, | |
| "learning_rate": 3.0041152263374488e-05, | |
| "loss": 1.2346, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.9571865443425076, | |
| "grad_norm": 13.562764167785645, | |
| "learning_rate": 3.209876543209876e-05, | |
| "loss": 1.2024, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.9938837920489296, | |
| "eval_accuracy": 0.47465437788018433, | |
| "eval_f1": 0.3906684622928812, | |
| "eval_loss": 1.0890263319015503, | |
| "eval_precision": 0.49441907661085743, | |
| "eval_recall": 0.47465437788018433, | |
| "eval_runtime": 2.1621, | |
| "eval_samples_per_second": 100.363, | |
| "eval_steps_per_second": 6.475, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 2.079510703363914, | |
| "grad_norm": 10.129838943481445, | |
| "learning_rate": 3.4156378600823045e-05, | |
| "loss": 1.2231, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.2018348623853212, | |
| "grad_norm": 10.82052230834961, | |
| "learning_rate": 3.6213991769547327e-05, | |
| "loss": 1.2082, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.324159021406728, | |
| "grad_norm": 15.055948257446289, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 1.1827, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.4464831804281344, | |
| "grad_norm": 14.08010196685791, | |
| "learning_rate": 4.032921810699588e-05, | |
| "loss": 1.1564, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.5688073394495414, | |
| "grad_norm": 19.530576705932617, | |
| "learning_rate": 4.2386831275720165e-05, | |
| "loss": 1.1508, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.691131498470948, | |
| "grad_norm": 17.710391998291016, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.2407, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.8134556574923546, | |
| "grad_norm": 19.007694244384766, | |
| "learning_rate": 4.650205761316873e-05, | |
| "loss": 1.1333, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.9357798165137616, | |
| "grad_norm": 11.404845237731934, | |
| "learning_rate": 4.855967078189301e-05, | |
| "loss": 1.2067, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.996941896024465, | |
| "eval_accuracy": 0.543778801843318, | |
| "eval_f1": 0.49651048113106194, | |
| "eval_loss": 1.060142993927002, | |
| "eval_precision": 0.5083802142557903, | |
| "eval_recall": 0.543778801843318, | |
| "eval_runtime": 2.1941, | |
| "eval_samples_per_second": 98.904, | |
| "eval_steps_per_second": 6.381, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.058103975535168, | |
| "grad_norm": 7.823658466339111, | |
| "learning_rate": 4.993141289437586e-05, | |
| "loss": 1.1512, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.180428134556575, | |
| "grad_norm": 7.272976875305176, | |
| "learning_rate": 4.970278920896205e-05, | |
| "loss": 1.2064, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.302752293577982, | |
| "grad_norm": 8.453497886657715, | |
| "learning_rate": 4.9474165523548245e-05, | |
| "loss": 1.1758, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.4250764525993884, | |
| "grad_norm": 6.063063144683838, | |
| "learning_rate": 4.924554183813443e-05, | |
| "loss": 1.1481, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.547400611620795, | |
| "grad_norm": 11.22547435760498, | |
| "learning_rate": 4.901691815272063e-05, | |
| "loss": 1.1818, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.669724770642202, | |
| "grad_norm": 8.580599784851074, | |
| "learning_rate": 4.8788294467306815e-05, | |
| "loss": 1.1345, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.7920489296636086, | |
| "grad_norm": 16.203880310058594, | |
| "learning_rate": 4.855967078189301e-05, | |
| "loss": 1.1451, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.914373088685015, | |
| "grad_norm": 7.94223165512085, | |
| "learning_rate": 4.83310470964792e-05, | |
| "loss": 1.206, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5391705069124424, | |
| "eval_f1": 0.515930279628824, | |
| "eval_loss": 1.0142838954925537, | |
| "eval_precision": 0.5180022054326838, | |
| "eval_recall": 0.5391705069124424, | |
| "eval_runtime": 2.1844, | |
| "eval_samples_per_second": 99.339, | |
| "eval_steps_per_second": 6.409, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 4.036697247706422, | |
| "grad_norm": 7.936139106750488, | |
| "learning_rate": 4.810242341106539e-05, | |
| "loss": 1.1749, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.159021406727828, | |
| "grad_norm": 6.124804496765137, | |
| "learning_rate": 4.787379972565158e-05, | |
| "loss": 1.1473, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.281345565749236, | |
| "grad_norm": 9.12104320526123, | |
| "learning_rate": 4.764517604023777e-05, | |
| "loss": 1.1809, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.4036697247706424, | |
| "grad_norm": 6.582239627838135, | |
| "learning_rate": 4.741655235482396e-05, | |
| "loss": 1.1728, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.525993883792049, | |
| "grad_norm": 7.613648891448975, | |
| "learning_rate": 4.718792866941015e-05, | |
| "loss": 1.1315, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.648318042813456, | |
| "grad_norm": 11.376667976379395, | |
| "learning_rate": 4.6959304983996346e-05, | |
| "loss": 1.1481, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.770642201834862, | |
| "grad_norm": 6.794886112213135, | |
| "learning_rate": 4.6730681298582534e-05, | |
| "loss": 1.0927, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.892966360856269, | |
| "grad_norm": 7.452205657958984, | |
| "learning_rate": 4.650205761316873e-05, | |
| "loss": 1.1049, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.990825688073395, | |
| "eval_accuracy": 0.576036866359447, | |
| "eval_f1": 0.5450544928742728, | |
| "eval_loss": 0.968787431716919, | |
| "eval_precision": 0.5467442569565754, | |
| "eval_recall": 0.576036866359447, | |
| "eval_runtime": 2.1812, | |
| "eval_samples_per_second": 99.488, | |
| "eval_steps_per_second": 6.419, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 5.015290519877676, | |
| "grad_norm": 6.982997417449951, | |
| "learning_rate": 4.6273433927754916e-05, | |
| "loss": 1.1165, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.137614678899083, | |
| "grad_norm": 7.05279541015625, | |
| "learning_rate": 4.604481024234111e-05, | |
| "loss": 1.0755, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.259938837920489, | |
| "grad_norm": 9.04000186920166, | |
| "learning_rate": 4.58161865569273e-05, | |
| "loss": 1.1144, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.382262996941896, | |
| "grad_norm": 5.530284881591797, | |
| "learning_rate": 4.558756287151349e-05, | |
| "loss": 1.088, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.504587155963303, | |
| "grad_norm": 11.77010440826416, | |
| "learning_rate": 4.535893918609968e-05, | |
| "loss": 1.0805, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.626911314984709, | |
| "grad_norm": 9.45374870300293, | |
| "learning_rate": 4.513031550068587e-05, | |
| "loss": 1.1098, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.749235474006117, | |
| "grad_norm": 9.706932067871094, | |
| "learning_rate": 4.4901691815272064e-05, | |
| "loss": 1.0726, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.871559633027523, | |
| "grad_norm": 9.147931098937988, | |
| "learning_rate": 4.467306812985825e-05, | |
| "loss": 1.0934, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.99388379204893, | |
| "grad_norm": 6.612918376922607, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.0931, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.99388379204893, | |
| "eval_accuracy": 0.5622119815668203, | |
| "eval_f1": 0.5562044726083856, | |
| "eval_loss": 1.0351340770721436, | |
| "eval_precision": 0.5939199765927876, | |
| "eval_recall": 0.5622119815668203, | |
| "eval_runtime": 2.1678, | |
| "eval_samples_per_second": 100.104, | |
| "eval_steps_per_second": 6.458, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.116207951070336, | |
| "grad_norm": 10.358129501342773, | |
| "learning_rate": 4.4215820759030634e-05, | |
| "loss": 1.0469, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.238532110091743, | |
| "grad_norm": 5.924838542938232, | |
| "learning_rate": 4.398719707361683e-05, | |
| "loss": 1.0814, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.36085626911315, | |
| "grad_norm": 7.012035369873047, | |
| "learning_rate": 4.3758573388203024e-05, | |
| "loss": 1.1091, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 6.483180428134556, | |
| "grad_norm": 6.860468864440918, | |
| "learning_rate": 4.352994970278921e-05, | |
| "loss": 1.091, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 6.605504587155964, | |
| "grad_norm": 6.236204624176025, | |
| "learning_rate": 4.3301326017375406e-05, | |
| "loss": 1.1033, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.72782874617737, | |
| "grad_norm": 11.546574592590332, | |
| "learning_rate": 4.3072702331961594e-05, | |
| "loss": 1.067, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.850152905198777, | |
| "grad_norm": 10.157209396362305, | |
| "learning_rate": 4.284407864654779e-05, | |
| "loss": 1.054, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.972477064220183, | |
| "grad_norm": 7.421886444091797, | |
| "learning_rate": 4.261545496113398e-05, | |
| "loss": 1.0752, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.996941896024465, | |
| "eval_accuracy": 0.5898617511520737, | |
| "eval_f1": 0.5592428280600323, | |
| "eval_loss": 0.9370155930519104, | |
| "eval_precision": 0.5730448203692986, | |
| "eval_recall": 0.5898617511520737, | |
| "eval_runtime": 2.1864, | |
| "eval_samples_per_second": 99.25, | |
| "eval_steps_per_second": 6.403, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 7.09480122324159, | |
| "grad_norm": 8.062494277954102, | |
| "learning_rate": 4.2386831275720165e-05, | |
| "loss": 1.0298, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.217125382262997, | |
| "grad_norm": 7.170814514160156, | |
| "learning_rate": 4.215820759030636e-05, | |
| "loss": 1.0451, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 7.339449541284404, | |
| "grad_norm": 7.2061662673950195, | |
| "learning_rate": 4.192958390489255e-05, | |
| "loss": 1.0586, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.461773700305811, | |
| "grad_norm": 5.97224760055542, | |
| "learning_rate": 4.170096021947874e-05, | |
| "loss": 1.0543, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 7.584097859327217, | |
| "grad_norm": 7.366073131561279, | |
| "learning_rate": 4.147233653406493e-05, | |
| "loss": 1.0903, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 7.706422018348624, | |
| "grad_norm": 6.186879634857178, | |
| "learning_rate": 4.1243712848651125e-05, | |
| "loss": 1.0919, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.82874617737003, | |
| "grad_norm": 8.208704948425293, | |
| "learning_rate": 4.101508916323731e-05, | |
| "loss": 1.1254, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 7.951070336391437, | |
| "grad_norm": 13.736848831176758, | |
| "learning_rate": 4.078646547782351e-05, | |
| "loss": 1.03, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.576036866359447, | |
| "eval_f1": 0.5509975224553819, | |
| "eval_loss": 0.9416872262954712, | |
| "eval_precision": 0.5414011052041612, | |
| "eval_recall": 0.576036866359447, | |
| "eval_runtime": 2.1964, | |
| "eval_samples_per_second": 98.796, | |
| "eval_steps_per_second": 6.374, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 8.073394495412844, | |
| "grad_norm": 7.8366546630859375, | |
| "learning_rate": 4.0557841792409695e-05, | |
| "loss": 1.0581, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.19571865443425, | |
| "grad_norm": 6.876219272613525, | |
| "learning_rate": 4.032921810699588e-05, | |
| "loss": 1.04, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 8.318042813455657, | |
| "grad_norm": 7.931809902191162, | |
| "learning_rate": 4.010059442158208e-05, | |
| "loss": 1.0319, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 8.440366972477065, | |
| "grad_norm": 11.545510292053223, | |
| "learning_rate": 3.9871970736168266e-05, | |
| "loss": 1.0027, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 8.562691131498472, | |
| "grad_norm": 7.059225559234619, | |
| "learning_rate": 3.964334705075446e-05, | |
| "loss": 1.0164, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.685015290519878, | |
| "grad_norm": 6.870743751525879, | |
| "learning_rate": 3.941472336534065e-05, | |
| "loss": 1.0063, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 8.807339449541285, | |
| "grad_norm": 7.4264631271362305, | |
| "learning_rate": 3.918609967992684e-05, | |
| "loss": 1.0359, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 8.929663608562691, | |
| "grad_norm": 8.050666809082031, | |
| "learning_rate": 3.895747599451303e-05, | |
| "loss": 0.988, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 8.990825688073395, | |
| "eval_accuracy": 0.5990783410138248, | |
| "eval_f1": 0.5772079574092954, | |
| "eval_loss": 0.8942155838012695, | |
| "eval_precision": 0.5818760258445811, | |
| "eval_recall": 0.5990783410138248, | |
| "eval_runtime": 2.178, | |
| "eval_samples_per_second": 99.631, | |
| "eval_steps_per_second": 6.428, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 9.051987767584098, | |
| "grad_norm": 6.86763858795166, | |
| "learning_rate": 3.8728852309099226e-05, | |
| "loss": 0.9927, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 9.174311926605505, | |
| "grad_norm": 7.786592483520508, | |
| "learning_rate": 3.8500228623685414e-05, | |
| "loss": 0.976, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.296636085626911, | |
| "grad_norm": 9.186685562133789, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 1.0239, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 9.418960244648318, | |
| "grad_norm": 8.555779457092285, | |
| "learning_rate": 3.8042981252857796e-05, | |
| "loss": 0.9526, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 9.541284403669724, | |
| "grad_norm": 9.215676307678223, | |
| "learning_rate": 3.7814357567443984e-05, | |
| "loss": 1.0258, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 9.663608562691131, | |
| "grad_norm": 7.625224590301514, | |
| "learning_rate": 3.758573388203018e-05, | |
| "loss": 1.0042, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 9.785932721712538, | |
| "grad_norm": 9.265899658203125, | |
| "learning_rate": 3.7357110196616373e-05, | |
| "loss": 1.008, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.908256880733944, | |
| "grad_norm": 7.059952735900879, | |
| "learning_rate": 3.712848651120257e-05, | |
| "loss": 0.9692, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 9.99388379204893, | |
| "eval_accuracy": 0.6082949308755761, | |
| "eval_f1": 0.5936874933582452, | |
| "eval_loss": 0.9091479182243347, | |
| "eval_precision": 0.5980988666361812, | |
| "eval_recall": 0.6082949308755761, | |
| "eval_runtime": 2.1969, | |
| "eval_samples_per_second": 98.777, | |
| "eval_steps_per_second": 6.373, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 10.030581039755353, | |
| "grad_norm": 8.655425071716309, | |
| "learning_rate": 3.6899862825788756e-05, | |
| "loss": 1.0144, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 10.15290519877676, | |
| "grad_norm": 7.1922607421875, | |
| "learning_rate": 3.6671239140374944e-05, | |
| "loss": 0.9994, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 10.275229357798166, | |
| "grad_norm": 7.687134265899658, | |
| "learning_rate": 3.644261545496114e-05, | |
| "loss": 0.9879, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 10.397553516819572, | |
| "grad_norm": 9.036182403564453, | |
| "learning_rate": 3.6213991769547327e-05, | |
| "loss": 0.9218, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 10.519877675840979, | |
| "grad_norm": 11.018427848815918, | |
| "learning_rate": 3.598536808413352e-05, | |
| "loss": 1.0079, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 10.642201834862385, | |
| "grad_norm": 9.172164916992188, | |
| "learning_rate": 3.575674439871971e-05, | |
| "loss": 0.9795, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 10.764525993883792, | |
| "grad_norm": 10.210972785949707, | |
| "learning_rate": 3.5528120713305904e-05, | |
| "loss": 0.9675, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 10.886850152905199, | |
| "grad_norm": 9.860912322998047, | |
| "learning_rate": 3.529949702789209e-05, | |
| "loss": 0.9896, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 10.996941896024465, | |
| "eval_accuracy": 0.6036866359447005, | |
| "eval_f1": 0.5904668698923761, | |
| "eval_loss": 0.8689674139022827, | |
| "eval_precision": 0.5936795435008436, | |
| "eval_recall": 0.6036866359447005, | |
| "eval_runtime": 2.1973, | |
| "eval_samples_per_second": 98.756, | |
| "eval_steps_per_second": 6.371, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 11.009174311926605, | |
| "grad_norm": 9.831244468688965, | |
| "learning_rate": 3.5070873342478286e-05, | |
| "loss": 0.9261, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.131498470948012, | |
| "grad_norm": 11.262879371643066, | |
| "learning_rate": 3.4842249657064474e-05, | |
| "loss": 0.9191, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 11.253822629969418, | |
| "grad_norm": 9.582681655883789, | |
| "learning_rate": 3.461362597165066e-05, | |
| "loss": 0.9026, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 11.376146788990825, | |
| "grad_norm": 9.12176513671875, | |
| "learning_rate": 3.438500228623686e-05, | |
| "loss": 0.9882, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 11.498470948012232, | |
| "grad_norm": 10.87016773223877, | |
| "learning_rate": 3.4156378600823045e-05, | |
| "loss": 0.9379, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 11.62079510703364, | |
| "grad_norm": 8.557551383972168, | |
| "learning_rate": 3.392775491540924e-05, | |
| "loss": 0.9312, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 11.743119266055047, | |
| "grad_norm": 8.361717224121094, | |
| "learning_rate": 3.369913122999543e-05, | |
| "loss": 0.9085, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 11.865443425076453, | |
| "grad_norm": 7.925179958343506, | |
| "learning_rate": 3.347050754458162e-05, | |
| "loss": 1.0008, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 11.98776758409786, | |
| "grad_norm": 9.740839004516602, | |
| "learning_rate": 3.324188385916781e-05, | |
| "loss": 0.9479, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6405529953917051, | |
| "eval_f1": 0.6268359763707001, | |
| "eval_loss": 0.8705018162727356, | |
| "eval_precision": 0.6307341542199126, | |
| "eval_recall": 0.6405529953917051, | |
| "eval_runtime": 2.1984, | |
| "eval_samples_per_second": 98.71, | |
| "eval_steps_per_second": 6.368, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 12.110091743119266, | |
| "grad_norm": 9.437625885009766, | |
| "learning_rate": 3.3013260173754005e-05, | |
| "loss": 0.8172, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 12.232415902140673, | |
| "grad_norm": 8.812919616699219, | |
| "learning_rate": 3.278463648834019e-05, | |
| "loss": 0.8996, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 12.35474006116208, | |
| "grad_norm": 8.750353813171387, | |
| "learning_rate": 3.255601280292638e-05, | |
| "loss": 0.9655, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 12.477064220183486, | |
| "grad_norm": 7.671780586242676, | |
| "learning_rate": 3.2327389117512575e-05, | |
| "loss": 0.9139, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 12.599388379204893, | |
| "grad_norm": 9.657299041748047, | |
| "learning_rate": 3.209876543209876e-05, | |
| "loss": 0.9269, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 12.7217125382263, | |
| "grad_norm": 9.090998649597168, | |
| "learning_rate": 3.187014174668496e-05, | |
| "loss": 0.8867, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 12.844036697247706, | |
| "grad_norm": 9.977676391601562, | |
| "learning_rate": 3.1641518061271146e-05, | |
| "loss": 0.89, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 12.966360856269112, | |
| "grad_norm": 10.456171035766602, | |
| "learning_rate": 3.141289437585734e-05, | |
| "loss": 0.898, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 12.990825688073395, | |
| "eval_accuracy": 0.6497695852534562, | |
| "eval_f1": 0.6439767898106951, | |
| "eval_loss": 0.8568853735923767, | |
| "eval_precision": 0.6465264959675692, | |
| "eval_recall": 0.6497695852534562, | |
| "eval_runtime": 2.1871, | |
| "eval_samples_per_second": 99.216, | |
| "eval_steps_per_second": 6.401, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 13.08868501529052, | |
| "grad_norm": 9.029878616333008, | |
| "learning_rate": 3.118427069044353e-05, | |
| "loss": 0.9008, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 13.211009174311927, | |
| "grad_norm": 11.082198143005371, | |
| "learning_rate": 3.095564700502972e-05, | |
| "loss": 0.8678, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 8.106987953186035, | |
| "learning_rate": 3.072702331961592e-05, | |
| "loss": 0.8724, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 13.45565749235474, | |
| "grad_norm": 9.417874336242676, | |
| "learning_rate": 3.0498399634202106e-05, | |
| "loss": 0.8435, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 13.577981651376147, | |
| "grad_norm": 10.039156913757324, | |
| "learning_rate": 3.0269775948788297e-05, | |
| "loss": 0.7984, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 13.700305810397554, | |
| "grad_norm": 10.906753540039062, | |
| "learning_rate": 3.0041152263374488e-05, | |
| "loss": 0.8578, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 13.82262996941896, | |
| "grad_norm": 9.698974609375, | |
| "learning_rate": 2.981252857796068e-05, | |
| "loss": 0.8699, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 13.944954128440367, | |
| "grad_norm": 9.868678092956543, | |
| "learning_rate": 2.958390489254687e-05, | |
| "loss": 0.9101, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 13.99388379204893, | |
| "eval_accuracy": 0.6129032258064516, | |
| "eval_f1": 0.6090804206647874, | |
| "eval_loss": 0.8736193180084229, | |
| "eval_precision": 0.6179152160718983, | |
| "eval_recall": 0.6129032258064516, | |
| "eval_runtime": 2.1919, | |
| "eval_samples_per_second": 99.002, | |
| "eval_steps_per_second": 6.387, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 14.067278287461773, | |
| "grad_norm": 8.79443645477295, | |
| "learning_rate": 2.9355281207133062e-05, | |
| "loss": 0.8439, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 14.18960244648318, | |
| "grad_norm": 9.417186737060547, | |
| "learning_rate": 2.9126657521719253e-05, | |
| "loss": 0.8763, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 14.311926605504587, | |
| "grad_norm": 11.611254692077637, | |
| "learning_rate": 2.8898033836305445e-05, | |
| "loss": 0.8305, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 14.434250764525993, | |
| "grad_norm": 10.025824546813965, | |
| "learning_rate": 2.8669410150891636e-05, | |
| "loss": 0.7743, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 14.5565749235474, | |
| "grad_norm": 10.79056453704834, | |
| "learning_rate": 2.8440786465477824e-05, | |
| "loss": 0.8414, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 14.678899082568808, | |
| "grad_norm": 8.00452709197998, | |
| "learning_rate": 2.8212162780064015e-05, | |
| "loss": 0.8934, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 14.801223241590215, | |
| "grad_norm": 11.359430313110352, | |
| "learning_rate": 2.7983539094650207e-05, | |
| "loss": 0.8844, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 14.923547400611621, | |
| "grad_norm": 10.003506660461426, | |
| "learning_rate": 2.7754915409236398e-05, | |
| "loss": 0.8431, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 14.996941896024465, | |
| "eval_accuracy": 0.6451612903225806, | |
| "eval_f1": 0.6418579664744979, | |
| "eval_loss": 0.8684141039848328, | |
| "eval_precision": 0.6447143927349024, | |
| "eval_recall": 0.6451612903225806, | |
| "eval_runtime": 2.1833, | |
| "eval_samples_per_second": 99.392, | |
| "eval_steps_per_second": 6.412, | |
| "step": 1226 | |
| }, | |
| { | |
| "epoch": 15.045871559633028, | |
| "grad_norm": 8.596139907836914, | |
| "learning_rate": 2.752629172382259e-05, | |
| "loss": 0.8224, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 15.168195718654435, | |
| "grad_norm": 11.239164352416992, | |
| "learning_rate": 2.729766803840878e-05, | |
| "loss": 0.8407, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 15.290519877675841, | |
| "grad_norm": 13.581149101257324, | |
| "learning_rate": 2.7069044352994972e-05, | |
| "loss": 0.7794, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 15.412844036697248, | |
| "grad_norm": 10.948393821716309, | |
| "learning_rate": 2.6840420667581163e-05, | |
| "loss": 0.8199, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 15.535168195718654, | |
| "grad_norm": 9.145750999450684, | |
| "learning_rate": 2.6611796982167354e-05, | |
| "loss": 0.7257, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 15.65749235474006, | |
| "grad_norm": 11.599444389343262, | |
| "learning_rate": 2.6383173296753542e-05, | |
| "loss": 0.7847, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 15.779816513761467, | |
| "grad_norm": 11.259026527404785, | |
| "learning_rate": 2.6154549611339734e-05, | |
| "loss": 0.8404, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 15.902140672782874, | |
| "grad_norm": 11.746826171875, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.8187, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6221198156682027, | |
| "eval_f1": 0.6198809621231663, | |
| "eval_loss": 0.9032032489776611, | |
| "eval_precision": 0.6206784143654135, | |
| "eval_recall": 0.6221198156682027, | |
| "eval_runtime": 2.1909, | |
| "eval_samples_per_second": 99.047, | |
| "eval_steps_per_second": 6.39, | |
| "step": 1308 | |
| }, | |
| { | |
| "epoch": 16.02446483180428, | |
| "grad_norm": 9.55320930480957, | |
| "learning_rate": 2.5697302240512116e-05, | |
| "loss": 0.7986, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 16.146788990825687, | |
| "grad_norm": 10.655790328979492, | |
| "learning_rate": 2.5468678555098308e-05, | |
| "loss": 0.7589, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 16.269113149847094, | |
| "grad_norm": 10.707428932189941, | |
| "learning_rate": 2.52400548696845e-05, | |
| "loss": 0.7315, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 16.3914373088685, | |
| "grad_norm": 12.252084732055664, | |
| "learning_rate": 2.501143118427069e-05, | |
| "loss": 0.7892, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 16.513761467889907, | |
| "grad_norm": 9.307701110839844, | |
| "learning_rate": 2.4782807498856885e-05, | |
| "loss": 0.7698, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 16.636085626911314, | |
| "grad_norm": 10.571149826049805, | |
| "learning_rate": 2.4554183813443073e-05, | |
| "loss": 0.7547, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 16.75840978593272, | |
| "grad_norm": 11.456555366516113, | |
| "learning_rate": 2.4325560128029264e-05, | |
| "loss": 0.7723, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 16.88073394495413, | |
| "grad_norm": 11.944501876831055, | |
| "learning_rate": 2.4096936442615455e-05, | |
| "loss": 0.7614, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 16.990825688073393, | |
| "eval_accuracy": 0.6359447004608295, | |
| "eval_f1": 0.6305311465399625, | |
| "eval_loss": 0.9012994170188904, | |
| "eval_precision": 0.6433955302551128, | |
| "eval_recall": 0.6359447004608295, | |
| "eval_runtime": 2.1782, | |
| "eval_samples_per_second": 99.624, | |
| "eval_steps_per_second": 6.427, | |
| "step": 1389 | |
| }, | |
| { | |
| "epoch": 17.003058103975537, | |
| "grad_norm": 11.058562278747559, | |
| "learning_rate": 2.3868312757201647e-05, | |
| "loss": 0.7566, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 17.125382262996943, | |
| "grad_norm": 12.137784004211426, | |
| "learning_rate": 2.3639689071787838e-05, | |
| "loss": 0.6842, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 17.24770642201835, | |
| "grad_norm": 12.046640396118164, | |
| "learning_rate": 2.341106538637403e-05, | |
| "loss": 0.7126, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 17.370030581039757, | |
| "grad_norm": 13.35624885559082, | |
| "learning_rate": 2.318244170096022e-05, | |
| "loss": 0.721, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 17.492354740061163, | |
| "grad_norm": 10.566619873046875, | |
| "learning_rate": 2.2953818015546412e-05, | |
| "loss": 0.7424, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 17.61467889908257, | |
| "grad_norm": 11.238773345947266, | |
| "learning_rate": 2.2725194330132603e-05, | |
| "loss": 0.7375, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 17.737003058103976, | |
| "grad_norm": 11.583772659301758, | |
| "learning_rate": 2.2496570644718794e-05, | |
| "loss": 0.7177, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 17.859327217125383, | |
| "grad_norm": 11.983872413635254, | |
| "learning_rate": 2.2267946959304986e-05, | |
| "loss": 0.7393, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 17.98165137614679, | |
| "grad_norm": 9.852224349975586, | |
| "learning_rate": 2.2039323273891177e-05, | |
| "loss": 0.725, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 17.99388379204893, | |
| "eval_accuracy": 0.5990783410138248, | |
| "eval_f1": 0.5975030533834751, | |
| "eval_loss": 0.9701642394065857, | |
| "eval_precision": 0.6072043560801691, | |
| "eval_recall": 0.5990783410138248, | |
| "eval_runtime": 2.1744, | |
| "eval_samples_per_second": 99.798, | |
| "eval_steps_per_second": 6.439, | |
| "step": 1471 | |
| }, | |
| { | |
| "epoch": 18.103975535168196, | |
| "grad_norm": 10.969733238220215, | |
| "learning_rate": 2.1810699588477368e-05, | |
| "loss": 0.6728, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 18.226299694189603, | |
| "grad_norm": 11.671346664428711, | |
| "learning_rate": 2.158207590306356e-05, | |
| "loss": 0.6974, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 18.34862385321101, | |
| "grad_norm": 8.975910186767578, | |
| "learning_rate": 2.135345221764975e-05, | |
| "loss": 0.6503, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 18.470948012232416, | |
| "grad_norm": 13.026418685913086, | |
| "learning_rate": 2.1124828532235942e-05, | |
| "loss": 0.6879, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 18.593272171253822, | |
| "grad_norm": 15.196861267089844, | |
| "learning_rate": 2.089620484682213e-05, | |
| "loss": 0.6912, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 18.71559633027523, | |
| "grad_norm": 8.060693740844727, | |
| "learning_rate": 2.066758116140832e-05, | |
| "loss": 0.7287, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 18.837920489296636, | |
| "grad_norm": 10.259760856628418, | |
| "learning_rate": 2.0438957475994513e-05, | |
| "loss": 0.6657, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 18.960244648318042, | |
| "grad_norm": 10.083440780639648, | |
| "learning_rate": 2.0210333790580704e-05, | |
| "loss": 0.6938, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 18.996941896024463, | |
| "eval_accuracy": 0.6728110599078341, | |
| "eval_f1": 0.6659537595021466, | |
| "eval_loss": 0.9598256349563599, | |
| "eval_precision": 0.683992662820187, | |
| "eval_recall": 0.6728110599078341, | |
| "eval_runtime": 2.1821, | |
| "eval_samples_per_second": 99.445, | |
| "eval_steps_per_second": 6.416, | |
| "step": 1553 | |
| }, | |
| { | |
| "epoch": 19.08256880733945, | |
| "grad_norm": 13.321717262268066, | |
| "learning_rate": 1.9981710105166895e-05, | |
| "loss": 0.6849, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 19.204892966360855, | |
| "grad_norm": 9.200907707214355, | |
| "learning_rate": 1.9753086419753087e-05, | |
| "loss": 0.6397, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 19.327217125382262, | |
| "grad_norm": 12.469816207885742, | |
| "learning_rate": 1.9524462734339278e-05, | |
| "loss": 0.6554, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 19.44954128440367, | |
| "grad_norm": 10.692110061645508, | |
| "learning_rate": 1.929583904892547e-05, | |
| "loss": 0.656, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 19.571865443425075, | |
| "grad_norm": 11.429883003234863, | |
| "learning_rate": 1.906721536351166e-05, | |
| "loss": 0.6959, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 19.69418960244648, | |
| "grad_norm": 10.087126731872559, | |
| "learning_rate": 1.8838591678097852e-05, | |
| "loss": 0.6632, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 19.81651376146789, | |
| "grad_norm": 16.846824645996094, | |
| "learning_rate": 1.8609967992684043e-05, | |
| "loss": 0.6307, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 19.938837920489295, | |
| "grad_norm": 12.659772872924805, | |
| "learning_rate": 1.8381344307270234e-05, | |
| "loss": 0.6761, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6082949308755761, | |
| "eval_f1": 0.6112076266773331, | |
| "eval_loss": 0.9886434078216553, | |
| "eval_precision": 0.6242090052989822, | |
| "eval_recall": 0.6082949308755761, | |
| "eval_runtime": 2.1998, | |
| "eval_samples_per_second": 98.647, | |
| "eval_steps_per_second": 6.364, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 20.061162079510705, | |
| "grad_norm": 11.294504165649414, | |
| "learning_rate": 1.8152720621856426e-05, | |
| "loss": 0.6726, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 20.18348623853211, | |
| "grad_norm": 10.856670379638672, | |
| "learning_rate": 1.7924096936442617e-05, | |
| "loss": 0.626, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 20.30581039755352, | |
| "grad_norm": 13.345258712768555, | |
| "learning_rate": 1.769547325102881e-05, | |
| "loss": 0.6446, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 20.428134556574925, | |
| "grad_norm": 9.459267616271973, | |
| "learning_rate": 1.7466849565615e-05, | |
| "loss": 0.6125, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 20.55045871559633, | |
| "grad_norm": 14.87169361114502, | |
| "learning_rate": 1.723822588020119e-05, | |
| "loss": 0.575, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 20.672782874617738, | |
| "grad_norm": 14.521281242370605, | |
| "learning_rate": 1.700960219478738e-05, | |
| "loss": 0.6999, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 20.795107033639145, | |
| "grad_norm": 12.60116195678711, | |
| "learning_rate": 1.678097850937357e-05, | |
| "loss": 0.5862, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 20.91743119266055, | |
| "grad_norm": 10.943224906921387, | |
| "learning_rate": 1.655235482395976e-05, | |
| "loss": 0.5865, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 20.990825688073393, | |
| "eval_accuracy": 0.6497695852534562, | |
| "eval_f1": 0.6428003832696357, | |
| "eval_loss": 0.9367409348487854, | |
| "eval_precision": 0.6431866677852993, | |
| "eval_recall": 0.6497695852534562, | |
| "eval_runtime": 2.1726, | |
| "eval_samples_per_second": 99.881, | |
| "eval_steps_per_second": 6.444, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 21.039755351681958, | |
| "grad_norm": 11.365513801574707, | |
| "learning_rate": 1.6323731138545953e-05, | |
| "loss": 0.6488, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 21.162079510703364, | |
| "grad_norm": 8.919206619262695, | |
| "learning_rate": 1.6095107453132147e-05, | |
| "loss": 0.6201, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 21.28440366972477, | |
| "grad_norm": 12.377992630004883, | |
| "learning_rate": 1.586648376771834e-05, | |
| "loss": 0.5806, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 21.406727828746178, | |
| "grad_norm": 12.146440505981445, | |
| "learning_rate": 1.563786008230453e-05, | |
| "loss": 0.5506, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 21.529051987767584, | |
| "grad_norm": 11.200637817382812, | |
| "learning_rate": 1.5409236396890718e-05, | |
| "loss": 0.5667, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 21.65137614678899, | |
| "grad_norm": 14.65993595123291, | |
| "learning_rate": 1.5180612711476911e-05, | |
| "loss": 0.5936, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 21.773700305810397, | |
| "grad_norm": 14.228142738342285, | |
| "learning_rate": 1.49519890260631e-05, | |
| "loss": 0.5791, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 21.896024464831804, | |
| "grad_norm": 12.14127254486084, | |
| "learning_rate": 1.4723365340649292e-05, | |
| "loss": 0.5857, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 21.99388379204893, | |
| "eval_accuracy": 0.631336405529954, | |
| "eval_f1": 0.6321523990020061, | |
| "eval_loss": 0.9693921208381653, | |
| "eval_precision": 0.6331329862312, | |
| "eval_recall": 0.631336405529954, | |
| "eval_runtime": 2.1772, | |
| "eval_samples_per_second": 99.669, | |
| "eval_steps_per_second": 6.43, | |
| "step": 1798 | |
| }, | |
| { | |
| "epoch": 22.01834862385321, | |
| "grad_norm": 8.9346342086792, | |
| "learning_rate": 1.4494741655235483e-05, | |
| "loss": 0.553, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 22.140672782874617, | |
| "grad_norm": 15.74846363067627, | |
| "learning_rate": 1.4266117969821674e-05, | |
| "loss": 0.5693, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 22.262996941896024, | |
| "grad_norm": 17.549697875976562, | |
| "learning_rate": 1.4037494284407866e-05, | |
| "loss": 0.5955, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 22.38532110091743, | |
| "grad_norm": 12.935697555541992, | |
| "learning_rate": 1.3808870598994055e-05, | |
| "loss": 0.5184, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 22.507645259938837, | |
| "grad_norm": 14.531293869018555, | |
| "learning_rate": 1.3580246913580247e-05, | |
| "loss": 0.5873, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 22.629969418960243, | |
| "grad_norm": 11.71330451965332, | |
| "learning_rate": 1.3351623228166438e-05, | |
| "loss": 0.538, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 22.75229357798165, | |
| "grad_norm": 11.269133567810059, | |
| "learning_rate": 1.312299954275263e-05, | |
| "loss": 0.5819, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 22.874617737003057, | |
| "grad_norm": 9.762799263000488, | |
| "learning_rate": 1.2894375857338819e-05, | |
| "loss": 0.5612, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 22.996941896024463, | |
| "grad_norm": 9.858174324035645, | |
| "learning_rate": 1.2665752171925014e-05, | |
| "loss": 0.556, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 22.996941896024463, | |
| "eval_accuracy": 0.6359447004608295, | |
| "eval_f1": 0.629638753332476, | |
| "eval_loss": 1.021164059638977, | |
| "eval_precision": 0.6574294916995147, | |
| "eval_recall": 0.6359447004608295, | |
| "eval_runtime": 2.1738, | |
| "eval_samples_per_second": 99.824, | |
| "eval_steps_per_second": 6.44, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 23.119266055045873, | |
| "grad_norm": 18.760498046875, | |
| "learning_rate": 1.2437128486511203e-05, | |
| "loss": 0.5428, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 23.24159021406728, | |
| "grad_norm": 12.281718254089355, | |
| "learning_rate": 1.2208504801097394e-05, | |
| "loss": 0.5557, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 23.363914373088686, | |
| "grad_norm": 11.702547073364258, | |
| "learning_rate": 1.1979881115683586e-05, | |
| "loss": 0.547, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 23.486238532110093, | |
| "grad_norm": 9.12270450592041, | |
| "learning_rate": 1.1751257430269777e-05, | |
| "loss": 0.4957, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 23.6085626911315, | |
| "grad_norm": 12.279609680175781, | |
| "learning_rate": 1.1522633744855968e-05, | |
| "loss": 0.5025, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 23.730886850152906, | |
| "grad_norm": 12.506765365600586, | |
| "learning_rate": 1.129401005944216e-05, | |
| "loss": 0.5863, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 23.853211009174313, | |
| "grad_norm": 13.289384841918945, | |
| "learning_rate": 1.106538637402835e-05, | |
| "loss": 0.5533, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 23.97553516819572, | |
| "grad_norm": 12.350972175598145, | |
| "learning_rate": 1.083676268861454e-05, | |
| "loss": 0.4871, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.5944700460829493, | |
| "eval_f1": 0.587885178704199, | |
| "eval_loss": 1.032782793045044, | |
| "eval_precision": 0.5950577616931705, | |
| "eval_recall": 0.5944700460829493, | |
| "eval_runtime": 2.183, | |
| "eval_samples_per_second": 99.404, | |
| "eval_steps_per_second": 6.413, | |
| "step": 1962 | |
| }, | |
| { | |
| "epoch": 24.097859327217126, | |
| "grad_norm": 9.447975158691406, | |
| "learning_rate": 1.0608139003200732e-05, | |
| "loss": 0.4881, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 24.220183486238533, | |
| "grad_norm": 11.92766284942627, | |
| "learning_rate": 1.0379515317786923e-05, | |
| "loss": 0.5066, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 24.34250764525994, | |
| "grad_norm": 11.550183296203613, | |
| "learning_rate": 1.0150891632373114e-05, | |
| "loss": 0.4547, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 24.464831804281346, | |
| "grad_norm": 10.570334434509277, | |
| "learning_rate": 9.922267946959306e-06, | |
| "loss": 0.504, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 24.587155963302752, | |
| "grad_norm": 12.56131362915039, | |
| "learning_rate": 9.693644261545497e-06, | |
| "loss": 0.4765, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 24.70948012232416, | |
| "grad_norm": 10.12960433959961, | |
| "learning_rate": 9.465020576131688e-06, | |
| "loss": 0.4862, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 24.831804281345565, | |
| "grad_norm": 14.820987701416016, | |
| "learning_rate": 9.236396890717878e-06, | |
| "loss": 0.4748, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 24.954128440366972, | |
| "grad_norm": 13.520421981811523, | |
| "learning_rate": 9.00777320530407e-06, | |
| "loss": 0.5254, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 24.990825688073393, | |
| "eval_accuracy": 0.5944700460829493, | |
| "eval_f1": 0.5917457657549822, | |
| "eval_loss": 1.0132023096084595, | |
| "eval_precision": 0.5968091048736209, | |
| "eval_recall": 0.5944700460829493, | |
| "eval_runtime": 2.1697, | |
| "eval_samples_per_second": 100.012, | |
| "eval_steps_per_second": 6.452, | |
| "step": 2043 | |
| }, | |
| { | |
| "epoch": 25.07645259938838, | |
| "grad_norm": 11.470428466796875, | |
| "learning_rate": 8.77914951989026e-06, | |
| "loss": 0.4879, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 25.198776758409785, | |
| "grad_norm": 12.04905891418457, | |
| "learning_rate": 8.550525834476454e-06, | |
| "loss": 0.4719, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 25.321100917431192, | |
| "grad_norm": 14.935491561889648, | |
| "learning_rate": 8.321902149062643e-06, | |
| "loss": 0.4989, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 25.4434250764526, | |
| "grad_norm": 13.884613037109375, | |
| "learning_rate": 8.093278463648834e-06, | |
| "loss": 0.4718, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 25.565749235474005, | |
| "grad_norm": 14.0990629196167, | |
| "learning_rate": 7.864654778235026e-06, | |
| "loss": 0.4833, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 25.68807339449541, | |
| "grad_norm": 15.498763084411621, | |
| "learning_rate": 7.636031092821217e-06, | |
| "loss": 0.4719, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 25.810397553516818, | |
| "grad_norm": 17.733688354492188, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.5214, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 25.932721712538225, | |
| "grad_norm": 12.92156982421875, | |
| "learning_rate": 7.178783721993598e-06, | |
| "loss": 0.5054, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 25.99388379204893, | |
| "eval_accuracy": 0.5944700460829493, | |
| "eval_f1": 0.5943911153011756, | |
| "eval_loss": 1.038478136062622, | |
| "eval_precision": 0.5987861045709855, | |
| "eval_recall": 0.5944700460829493, | |
| "eval_runtime": 2.2069, | |
| "eval_samples_per_second": 98.326, | |
| "eval_steps_per_second": 6.344, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 26.05504587155963, | |
| "grad_norm": 12.785786628723145, | |
| "learning_rate": 6.950160036579791e-06, | |
| "loss": 0.5009, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 26.17737003058104, | |
| "grad_norm": 12.252779006958008, | |
| "learning_rate": 6.721536351165981e-06, | |
| "loss": 0.4896, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 26.299694189602448, | |
| "grad_norm": 8.970731735229492, | |
| "learning_rate": 6.492912665752173e-06, | |
| "loss": 0.4409, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 26.422018348623855, | |
| "grad_norm": 14.119239807128906, | |
| "learning_rate": 6.264288980338363e-06, | |
| "loss": 0.4685, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 26.54434250764526, | |
| "grad_norm": 13.817703247070312, | |
| "learning_rate": 6.0356652949245544e-06, | |
| "loss": 0.423, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 11.813767433166504, | |
| "learning_rate": 5.807041609510746e-06, | |
| "loss": 0.4338, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 26.788990825688074, | |
| "grad_norm": 10.11328411102295, | |
| "learning_rate": 5.578417924096937e-06, | |
| "loss": 0.4317, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 26.91131498470948, | |
| "grad_norm": 12.501155853271484, | |
| "learning_rate": 5.3497942386831275e-06, | |
| "loss": 0.4706, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 26.996941896024463, | |
| "eval_accuracy": 0.6036866359447005, | |
| "eval_f1": 0.5983142033282286, | |
| "eval_loss": 1.0625784397125244, | |
| "eval_precision": 0.6100467719653185, | |
| "eval_recall": 0.6036866359447005, | |
| "eval_runtime": 2.1672, | |
| "eval_samples_per_second": 100.128, | |
| "eval_steps_per_second": 6.46, | |
| "step": 2207 | |
| }, | |
| { | |
| "epoch": 27.033639143730888, | |
| "grad_norm": 12.064492225646973, | |
| "learning_rate": 5.121170553269319e-06, | |
| "loss": 0.4762, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 27.155963302752294, | |
| "grad_norm": 12.347169876098633, | |
| "learning_rate": 4.89254686785551e-06, | |
| "loss": 0.4493, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 27.2782874617737, | |
| "grad_norm": 12.065176010131836, | |
| "learning_rate": 4.663923182441701e-06, | |
| "loss": 0.4341, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 27.400611620795107, | |
| "grad_norm": 12.744647979736328, | |
| "learning_rate": 4.435299497027892e-06, | |
| "loss": 0.4373, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 27.522935779816514, | |
| "grad_norm": 14.091771125793457, | |
| "learning_rate": 4.206675811614083e-06, | |
| "loss": 0.4286, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 27.64525993883792, | |
| "grad_norm": 11.384113311767578, | |
| "learning_rate": 3.9780521262002744e-06, | |
| "loss": 0.4338, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 27.767584097859327, | |
| "grad_norm": 12.185340881347656, | |
| "learning_rate": 3.7494284407864657e-06, | |
| "loss": 0.4482, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 27.889908256880734, | |
| "grad_norm": 10.328293800354004, | |
| "learning_rate": 3.5208047553726566e-06, | |
| "loss": 0.418, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5806451612903226, | |
| "eval_f1": 0.5774461884155286, | |
| "eval_loss": 1.053132176399231, | |
| "eval_precision": 0.5829576016453093, | |
| "eval_recall": 0.5806451612903226, | |
| "eval_runtime": 2.1931, | |
| "eval_samples_per_second": 98.948, | |
| "eval_steps_per_second": 6.384, | |
| "step": 2289 | |
| }, | |
| { | |
| "epoch": 28.01223241590214, | |
| "grad_norm": 13.196370124816895, | |
| "learning_rate": 3.2921810699588483e-06, | |
| "loss": 0.4523, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 28.134556574923547, | |
| "grad_norm": 12.735855102539062, | |
| "learning_rate": 3.063557384545039e-06, | |
| "loss": 0.3987, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 28.256880733944953, | |
| "grad_norm": 13.810506820678711, | |
| "learning_rate": 2.83493369913123e-06, | |
| "loss": 0.4244, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 28.37920489296636, | |
| "grad_norm": 14.41588306427002, | |
| "learning_rate": 2.6063100137174214e-06, | |
| "loss": 0.4746, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 28.501529051987767, | |
| "grad_norm": 13.99752426147461, | |
| "learning_rate": 2.3776863283036123e-06, | |
| "loss": 0.4344, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 28.623853211009173, | |
| "grad_norm": 13.782439231872559, | |
| "learning_rate": 2.1490626428898036e-06, | |
| "loss": 0.4018, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 28.74617737003058, | |
| "grad_norm": 10.79996109008789, | |
| "learning_rate": 1.920438957475995e-06, | |
| "loss": 0.3779, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 28.868501529051986, | |
| "grad_norm": 12.254060745239258, | |
| "learning_rate": 1.6918152720621857e-06, | |
| "loss": 0.4671, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 28.990825688073393, | |
| "grad_norm": 12.211686134338379, | |
| "learning_rate": 1.4631915866483768e-06, | |
| "loss": 0.455, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 28.990825688073393, | |
| "eval_accuracy": 0.6082949308755761, | |
| "eval_f1": 0.6039494237985392, | |
| "eval_loss": 1.0340049266815186, | |
| "eval_precision": 0.615058251488602, | |
| "eval_recall": 0.6082949308755761, | |
| "eval_runtime": 2.21, | |
| "eval_samples_per_second": 98.191, | |
| "eval_steps_per_second": 6.335, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 29.1131498470948, | |
| "grad_norm": 12.376998901367188, | |
| "learning_rate": 1.234567901234568e-06, | |
| "loss": 0.405, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 29.235474006116206, | |
| "grad_norm": 13.317730903625488, | |
| "learning_rate": 1.0059442158207592e-06, | |
| "loss": 0.3908, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 29.357798165137616, | |
| "grad_norm": 14.004073143005371, | |
| "learning_rate": 7.773205304069502e-07, | |
| "loss": 0.4006, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 29.480122324159023, | |
| "grad_norm": 11.803933143615723, | |
| "learning_rate": 5.486968449931413e-07, | |
| "loss": 0.4255, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 29.60244648318043, | |
| "grad_norm": 13.087397575378418, | |
| "learning_rate": 3.200731595793324e-07, | |
| "loss": 0.4354, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 29.724770642201836, | |
| "grad_norm": 11.753482818603516, | |
| "learning_rate": 9.144947416552355e-08, | |
| "loss": 0.4414, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 29.724770642201836, | |
| "eval_accuracy": 0.6129032258064516, | |
| "eval_f1": 0.6087354657244137, | |
| "eval_loss": 1.0280050039291382, | |
| "eval_precision": 0.6161055592910982, | |
| "eval_recall": 0.6129032258064516, | |
| "eval_runtime": 2.2362, | |
| "eval_samples_per_second": 97.04, | |
| "eval_steps_per_second": 6.261, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 29.724770642201836, | |
| "step": 2430, | |
| "total_flos": 1.2301888231484006e+19, | |
| "train_loss": 0.8217329954414211, | |
| "train_runtime": 6060.3586, | |
| "train_samples_per_second": 25.865, | |
| "train_steps_per_second": 0.401 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2430, | |
| "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": 1.2301888231484006e+19, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |