| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.993894993894994, | |
| "eval_steps": 100, | |
| "global_step": 1227, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02442002442002442, | |
| "grad_norm": 25.41930389404297, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 0.8076, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04884004884004884, | |
| "grad_norm": 11.460826873779297, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 0.7516, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07326007326007326, | |
| "grad_norm": 7.831686973571777, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.7034, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09768009768009768, | |
| "grad_norm": 7.234014987945557, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 0.6996, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1221001221001221, | |
| "grad_norm": 5.096914768218994, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.6809, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14652014652014653, | |
| "grad_norm": 8.638614654541016, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.6892, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 13.534109115600586, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 0.6603, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19536019536019536, | |
| "grad_norm": 12.838939666748047, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 0.6225, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21978021978021978, | |
| "grad_norm": 14.190698623657227, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 0.5716, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2442002442002442, | |
| "grad_norm": 18.23443031311035, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.5403, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2442002442002442, | |
| "eval_accuracy": 0.7611484422724496, | |
| "eval_accuracy_label_negative": 0.8535353535353535, | |
| "eval_accuracy_label_positive": 0.6745562130177515, | |
| "eval_f1": 0.7596398965081889, | |
| "eval_loss": 0.5274035930633545, | |
| "eval_precision": 0.772811008310922, | |
| "eval_recall": 0.7611484422724496, | |
| "eval_runtime": 5.88, | |
| "eval_samples_per_second": 278.402, | |
| "eval_steps_per_second": 17.517, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2686202686202686, | |
| "grad_norm": 14.831952095031738, | |
| "learning_rate": 4.4e-06, | |
| "loss": 0.5022, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.29304029304029305, | |
| "grad_norm": 18.24405860900879, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 0.4786, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 16.866863250732422, | |
| "learning_rate": 5.2e-06, | |
| "loss": 0.3629, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 18.194087982177734, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 0.3523, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3663003663003663, | |
| "grad_norm": 16.094165802001953, | |
| "learning_rate": 6e-06, | |
| "loss": 0.3272, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3907203907203907, | |
| "grad_norm": 41.393802642822266, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 0.307, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.41514041514041516, | |
| "grad_norm": 23.695520401000977, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 0.2551, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "grad_norm": 30.489437103271484, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 0.2536, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.463980463980464, | |
| "grad_norm": 47.37874221801758, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 0.2622, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4884004884004884, | |
| "grad_norm": 26.136856079101562, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.2673, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4884004884004884, | |
| "eval_accuracy": 0.8979841172877214, | |
| "eval_accuracy_label_negative": 0.922979797979798, | |
| "eval_accuracy_label_positive": 0.8745562130177514, | |
| "eval_f1": 0.8979978224223449, | |
| "eval_loss": 0.2805691063404083, | |
| "eval_precision": 0.8993693797991343, | |
| "eval_recall": 0.8979841172877214, | |
| "eval_runtime": 6.3687, | |
| "eval_samples_per_second": 257.038, | |
| "eval_steps_per_second": 16.173, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 17.713157653808594, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.1874, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5372405372405372, | |
| "grad_norm": 5.685952186584473, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.2565, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5616605616605617, | |
| "grad_norm": 64.32303619384766, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 0.2763, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5860805860805861, | |
| "grad_norm": 26.14358139038086, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.2193, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6105006105006106, | |
| "grad_norm": 51.215972900390625, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2645, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "grad_norm": 77.36116027832031, | |
| "learning_rate": 1.04e-05, | |
| "loss": 0.2887, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6593406593406593, | |
| "grad_norm": 12.419713020324707, | |
| "learning_rate": 1.0800000000000002e-05, | |
| "loss": 0.2836, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 51.27354049682617, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 0.2279, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7081807081807082, | |
| "grad_norm": 15.182161331176758, | |
| "learning_rate": 1.16e-05, | |
| "loss": 0.23, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7326007326007326, | |
| "grad_norm": 20.174087524414062, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.247, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7326007326007326, | |
| "eval_accuracy": 0.902871105681124, | |
| "eval_accuracy_label_negative": 0.8434343434343434, | |
| "eval_accuracy_label_positive": 0.9585798816568047, | |
| "eval_f1": 0.9024095653522399, | |
| "eval_loss": 0.26104938983917236, | |
| "eval_precision": 0.9073823065773275, | |
| "eval_recall": 0.902871105681124, | |
| "eval_runtime": 6.46, | |
| "eval_samples_per_second": 253.406, | |
| "eval_steps_per_second": 15.944, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.757020757020757, | |
| "grad_norm": 19.257923126220703, | |
| "learning_rate": 1.2400000000000002e-05, | |
| "loss": 0.2514, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7814407814407814, | |
| "grad_norm": 13.050935745239258, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 0.216, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8058608058608059, | |
| "grad_norm": 1.8762781620025635, | |
| "learning_rate": 1.3200000000000002e-05, | |
| "loss": 0.2239, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8302808302808303, | |
| "grad_norm": 14.866827964782715, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 0.2124, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 16.646745681762695, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.2341, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 14.468786239624023, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 0.2397, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9035409035409036, | |
| "grad_norm": 16.370431900024414, | |
| "learning_rate": 1.48e-05, | |
| "loss": 0.2764, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.927960927960928, | |
| "grad_norm": 15.854681015014648, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.1964, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 19.42245101928711, | |
| "learning_rate": 1.5600000000000003e-05, | |
| "loss": 0.168, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9768009768009768, | |
| "grad_norm": 4.485373497009277, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.2357, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9768009768009768, | |
| "eval_accuracy": 0.9083689676237019, | |
| "eval_accuracy_label_negative": 0.9318181818181818, | |
| "eval_accuracy_label_positive": 0.8863905325443787, | |
| "eval_f1": 0.9083847657945654, | |
| "eval_loss": 0.2560252249240875, | |
| "eval_precision": 0.9095968991483547, | |
| "eval_recall": 0.9083689676237019, | |
| "eval_runtime": 6.4906, | |
| "eval_samples_per_second": 252.21, | |
| "eval_steps_per_second": 15.869, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 112.14476013183594, | |
| "learning_rate": 1.64e-05, | |
| "loss": 0.2322, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.0244200244200243, | |
| "grad_norm": 19.950773239135742, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.1607, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0488400488400489, | |
| "grad_norm": 14.963955879211426, | |
| "learning_rate": 1.72e-05, | |
| "loss": 0.1943, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.0732600732600732, | |
| "grad_norm": 12.724336624145508, | |
| "learning_rate": 1.76e-05, | |
| "loss": 0.1273, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0976800976800978, | |
| "grad_norm": 12.087287902832031, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.2392, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.122100122100122, | |
| "grad_norm": 4.449314117431641, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 0.2444, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1465201465201464, | |
| "grad_norm": 13.28513240814209, | |
| "learning_rate": 1.88e-05, | |
| "loss": 0.1995, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.170940170940171, | |
| "grad_norm": 9.664812088012695, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.2178, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1953601953601953, | |
| "grad_norm": 3.9961328506469727, | |
| "learning_rate": 1.9600000000000002e-05, | |
| "loss": 0.1269, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.2197802197802199, | |
| "grad_norm": 6.78753137588501, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2094, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2197802197802199, | |
| "eval_accuracy": 0.9089798411728772, | |
| "eval_accuracy_label_negative": 0.9507575757575758, | |
| "eval_accuracy_label_positive": 0.8698224852071006, | |
| "eval_f1": 0.9089364277932478, | |
| "eval_loss": 0.31265538930892944, | |
| "eval_precision": 0.9123227286547785, | |
| "eval_recall": 0.9089798411728772, | |
| "eval_runtime": 6.4966, | |
| "eval_samples_per_second": 251.979, | |
| "eval_steps_per_second": 15.855, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2442002442002442, | |
| "grad_norm": 4.199306488037109, | |
| "learning_rate": 1.9724896836313617e-05, | |
| "loss": 0.1993, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2686202686202686, | |
| "grad_norm": 47.193603515625, | |
| "learning_rate": 1.9449793672627236e-05, | |
| "loss": 0.1837, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.293040293040293, | |
| "grad_norm": 22.490142822265625, | |
| "learning_rate": 1.9174690508940855e-05, | |
| "loss": 0.2295, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.3174603174603174, | |
| "grad_norm": 10.449468612670898, | |
| "learning_rate": 1.889958734525447e-05, | |
| "loss": 0.2589, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.341880341880342, | |
| "grad_norm": 49.228878021240234, | |
| "learning_rate": 1.862448418156809e-05, | |
| "loss": 0.134, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3663003663003663, | |
| "grad_norm": 43.437068939208984, | |
| "learning_rate": 1.8349381017881708e-05, | |
| "loss": 0.2905, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.3907203907203907, | |
| "grad_norm": 22.296707153320312, | |
| "learning_rate": 1.8074277854195327e-05, | |
| "loss": 0.2304, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.4151404151404152, | |
| "grad_norm": 13.2725248336792, | |
| "learning_rate": 1.7799174690508942e-05, | |
| "loss": 0.2818, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.4395604395604396, | |
| "grad_norm": 4.746452808380127, | |
| "learning_rate": 1.7524071526822558e-05, | |
| "loss": 0.1635, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.463980463980464, | |
| "grad_norm": 15.717751502990723, | |
| "learning_rate": 1.7248968363136177e-05, | |
| "loss": 0.1695, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.463980463980464, | |
| "eval_accuracy": 0.9187538179596824, | |
| "eval_accuracy_label_negative": 0.9053030303030303, | |
| "eval_accuracy_label_positive": 0.9313609467455621, | |
| "eval_f1": 0.9187176730282378, | |
| "eval_loss": 0.22982099652290344, | |
| "eval_precision": 0.9188801834239158, | |
| "eval_recall": 0.9187538179596824, | |
| "eval_runtime": 6.5054, | |
| "eval_samples_per_second": 251.638, | |
| "eval_steps_per_second": 15.833, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4884004884004884, | |
| "grad_norm": 25.554302215576172, | |
| "learning_rate": 1.6973865199449796e-05, | |
| "loss": 0.1926, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.5128205128205128, | |
| "grad_norm": 6.077470779418945, | |
| "learning_rate": 1.669876203576341e-05, | |
| "loss": 0.2561, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.537240537240537, | |
| "grad_norm": 19.69429588317871, | |
| "learning_rate": 1.642365887207703e-05, | |
| "loss": 0.1501, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5616605616605617, | |
| "grad_norm": 10.95654010772705, | |
| "learning_rate": 1.614855570839065e-05, | |
| "loss": 0.1852, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.5860805860805862, | |
| "grad_norm": 24.821308135986328, | |
| "learning_rate": 1.5873452544704268e-05, | |
| "loss": 0.2113, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.6105006105006106, | |
| "grad_norm": 13.17242431640625, | |
| "learning_rate": 1.5598349381017883e-05, | |
| "loss": 0.1237, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.6349206349206349, | |
| "grad_norm": 16.253307342529297, | |
| "learning_rate": 1.53232462173315e-05, | |
| "loss": 0.1646, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.6593406593406592, | |
| "grad_norm": 28.406679153442383, | |
| "learning_rate": 1.5048143053645119e-05, | |
| "loss": 0.2448, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6837606837606838, | |
| "grad_norm": 15.36701488494873, | |
| "learning_rate": 1.4773039889958736e-05, | |
| "loss": 0.1902, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.7081807081807083, | |
| "grad_norm": 33.92890548706055, | |
| "learning_rate": 1.4497936726272352e-05, | |
| "loss": 0.2024, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.7081807081807083, | |
| "eval_accuracy": 0.9205864386072083, | |
| "eval_accuracy_label_negative": 0.9393939393939394, | |
| "eval_accuracy_label_positive": 0.9029585798816568, | |
| "eval_f1": 0.920605585060701, | |
| "eval_loss": 0.22175996005535126, | |
| "eval_precision": 0.9214190422768549, | |
| "eval_recall": 0.9205864386072083, | |
| "eval_runtime": 7.338, | |
| "eval_samples_per_second": 223.086, | |
| "eval_steps_per_second": 14.037, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.7326007326007327, | |
| "grad_norm": 39.820068359375, | |
| "learning_rate": 1.4222833562585972e-05, | |
| "loss": 0.1628, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.757020757020757, | |
| "grad_norm": 14.987146377563477, | |
| "learning_rate": 1.3947730398899588e-05, | |
| "loss": 0.1733, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7814407814407813, | |
| "grad_norm": 7.142777442932129, | |
| "learning_rate": 1.3672627235213205e-05, | |
| "loss": 0.1429, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.8058608058608059, | |
| "grad_norm": 40.524967193603516, | |
| "learning_rate": 1.3397524071526824e-05, | |
| "loss": 0.1887, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.8302808302808304, | |
| "grad_norm": 15.210890769958496, | |
| "learning_rate": 1.3122420907840441e-05, | |
| "loss": 0.2109, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.8547008547008548, | |
| "grad_norm": 14.5702543258667, | |
| "learning_rate": 1.284731774415406e-05, | |
| "loss": 0.1397, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.879120879120879, | |
| "grad_norm": 20.027212142944336, | |
| "learning_rate": 1.2572214580467677e-05, | |
| "loss": 0.1263, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.9035409035409034, | |
| "grad_norm": 13.660886764526367, | |
| "learning_rate": 1.2297111416781292e-05, | |
| "loss": 0.2006, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.927960927960928, | |
| "grad_norm": 8.097176551818848, | |
| "learning_rate": 1.2022008253094913e-05, | |
| "loss": 0.1901, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.9523809523809523, | |
| "grad_norm": 4.4079108238220215, | |
| "learning_rate": 1.1746905089408529e-05, | |
| "loss": 0.1155, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9523809523809523, | |
| "eval_accuracy": 0.9236408063530849, | |
| "eval_accuracy_label_negative": 0.9191919191919192, | |
| "eval_accuracy_label_positive": 0.927810650887574, | |
| "eval_f1": 0.923636013636066, | |
| "eval_loss": 0.20613956451416016, | |
| "eval_precision": 0.9236374318453521, | |
| "eval_recall": 0.9236408063530849, | |
| "eval_runtime": 6.4768, | |
| "eval_samples_per_second": 252.75, | |
| "eval_steps_per_second": 15.903, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9768009768009769, | |
| "grad_norm": 16.103919982910156, | |
| "learning_rate": 1.1471801925722146e-05, | |
| "loss": 0.1695, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 26.186500549316406, | |
| "learning_rate": 1.1196698762035765e-05, | |
| "loss": 0.1878, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.0244200244200243, | |
| "grad_norm": 8.27334213256836, | |
| "learning_rate": 1.0921595598349382e-05, | |
| "loss": 0.116, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.0488400488400487, | |
| "grad_norm": 9.153972625732422, | |
| "learning_rate": 1.0646492434663e-05, | |
| "loss": 0.1331, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.0732600732600734, | |
| "grad_norm": 8.734851837158203, | |
| "learning_rate": 1.0371389270976618e-05, | |
| "loss": 0.1064, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.0976800976800978, | |
| "grad_norm": 16.807472229003906, | |
| "learning_rate": 1.0096286107290235e-05, | |
| "loss": 0.1323, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.122100122100122, | |
| "grad_norm": 7.338029861450195, | |
| "learning_rate": 9.821182943603852e-06, | |
| "loss": 0.0876, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.1465201465201464, | |
| "grad_norm": 51.00392150878906, | |
| "learning_rate": 9.54607977991747e-06, | |
| "loss": 0.0574, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.1709401709401708, | |
| "grad_norm": 15.209708213806152, | |
| "learning_rate": 9.270976616231088e-06, | |
| "loss": 0.1536, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.1953601953601956, | |
| "grad_norm": 5.431528568267822, | |
| "learning_rate": 8.995873452544705e-06, | |
| "loss": 0.1361, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.1953601953601956, | |
| "eval_accuracy": 0.921808185705559, | |
| "eval_accuracy_label_negative": 0.9406565656565656, | |
| "eval_accuracy_label_positive": 0.9041420118343195, | |
| "eval_f1": 0.9218270375982287, | |
| "eval_loss": 0.2299249768257141, | |
| "eval_precision": 0.9226412544476359, | |
| "eval_recall": 0.921808185705559, | |
| "eval_runtime": 6.4607, | |
| "eval_samples_per_second": 253.378, | |
| "eval_steps_per_second": 15.943, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.21978021978022, | |
| "grad_norm": 18.443998336791992, | |
| "learning_rate": 8.720770288858322e-06, | |
| "loss": 0.1881, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.244200244200244, | |
| "grad_norm": 18.574554443359375, | |
| "learning_rate": 8.44566712517194e-06, | |
| "loss": 0.0946, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.2686202686202686, | |
| "grad_norm": 27.33018684387207, | |
| "learning_rate": 8.170563961485558e-06, | |
| "loss": 0.1302, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.293040293040293, | |
| "grad_norm": 15.219032287597656, | |
| "learning_rate": 7.895460797799176e-06, | |
| "loss": 0.1475, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.317460317460317, | |
| "grad_norm": 23.795124053955078, | |
| "learning_rate": 7.620357634112793e-06, | |
| "loss": 0.1098, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.341880341880342, | |
| "grad_norm": 12.746439933776855, | |
| "learning_rate": 7.345254470426411e-06, | |
| "loss": 0.0811, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.3663003663003663, | |
| "grad_norm": 2.0957300662994385, | |
| "learning_rate": 7.070151306740029e-06, | |
| "loss": 0.1033, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.3907203907203907, | |
| "grad_norm": 20.963695526123047, | |
| "learning_rate": 6.795048143053645e-06, | |
| "loss": 0.1716, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.415140415140415, | |
| "grad_norm": 6.032730579376221, | |
| "learning_rate": 6.519944979367263e-06, | |
| "loss": 0.0937, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.4395604395604398, | |
| "grad_norm": 18.961658477783203, | |
| "learning_rate": 6.244841815680881e-06, | |
| "loss": 0.1235, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.4395604395604398, | |
| "eval_accuracy": 0.9211973121563837, | |
| "eval_accuracy_label_negative": 0.9633838383838383, | |
| "eval_accuracy_label_positive": 0.8816568047337278, | |
| "eval_f1": 0.9211597260760334, | |
| "eval_loss": 0.26676130294799805, | |
| "eval_precision": 0.9245979890029079, | |
| "eval_recall": 0.9211973121563837, | |
| "eval_runtime": 6.4755, | |
| "eval_samples_per_second": 252.8, | |
| "eval_steps_per_second": 15.906, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.463980463980464, | |
| "grad_norm": 11.030694961547852, | |
| "learning_rate": 5.969738651994499e-06, | |
| "loss": 0.1298, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.4884004884004884, | |
| "grad_norm": 19.397335052490234, | |
| "learning_rate": 5.6946354883081155e-06, | |
| "loss": 0.1046, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.5128205128205128, | |
| "grad_norm": 5.86328125, | |
| "learning_rate": 5.4195323246217335e-06, | |
| "loss": 0.0831, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.537240537240537, | |
| "grad_norm": 5.8682427406311035, | |
| "learning_rate": 5.1444291609353515e-06, | |
| "loss": 0.1152, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.5616605616605614, | |
| "grad_norm": 6.465247631072998, | |
| "learning_rate": 4.869325997248969e-06, | |
| "loss": 0.1316, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.586080586080586, | |
| "grad_norm": 74.92926025390625, | |
| "learning_rate": 4.594222833562587e-06, | |
| "loss": 0.0973, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.6105006105006106, | |
| "grad_norm": 4.780877590179443, | |
| "learning_rate": 4.319119669876204e-06, | |
| "loss": 0.1206, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.634920634920635, | |
| "grad_norm": 23.055227279663086, | |
| "learning_rate": 4.044016506189822e-06, | |
| "loss": 0.1001, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.659340659340659, | |
| "grad_norm": 50.33488082885742, | |
| "learning_rate": 3.768913342503439e-06, | |
| "loss": 0.1537, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.683760683760684, | |
| "grad_norm": 0.44596701860427856, | |
| "learning_rate": 3.4938101788170562e-06, | |
| "loss": 0.084, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.683760683760684, | |
| "eval_accuracy": 0.921808185705559, | |
| "eval_accuracy_label_negative": 0.9545454545454546, | |
| "eval_accuracy_label_positive": 0.8911242603550296, | |
| "eval_f1": 0.9218032836901542, | |
| "eval_loss": 0.2732768654823303, | |
| "eval_precision": 0.9239586674515976, | |
| "eval_recall": 0.921808185705559, | |
| "eval_runtime": 6.4795, | |
| "eval_samples_per_second": 252.643, | |
| "eval_steps_per_second": 15.896, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.7081807081807083, | |
| "grad_norm": 3.0834202766418457, | |
| "learning_rate": 3.2187070151306742e-06, | |
| "loss": 0.1546, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.7326007326007327, | |
| "grad_norm": 6.8805928230285645, | |
| "learning_rate": 2.943603851444292e-06, | |
| "loss": 0.0876, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.757020757020757, | |
| "grad_norm": 0.9852960109710693, | |
| "learning_rate": 2.6685006877579094e-06, | |
| "loss": 0.0884, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.7814407814407813, | |
| "grad_norm": 9.610347747802734, | |
| "learning_rate": 2.393397524071527e-06, | |
| "loss": 0.1781, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.8058608058608057, | |
| "grad_norm": 14.589119911193848, | |
| "learning_rate": 2.1182943603851446e-06, | |
| "loss": 0.1584, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.8302808302808304, | |
| "grad_norm": 5.850516319274902, | |
| "learning_rate": 1.8431911966987622e-06, | |
| "loss": 0.1266, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.8547008547008548, | |
| "grad_norm": 3.190080165863037, | |
| "learning_rate": 1.56808803301238e-06, | |
| "loss": 0.1563, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.879120879120879, | |
| "grad_norm": 8.95765209197998, | |
| "learning_rate": 1.2929848693259976e-06, | |
| "loss": 0.0896, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.9035409035409034, | |
| "grad_norm": 1.606522798538208, | |
| "learning_rate": 1.017881705639615e-06, | |
| "loss": 0.1167, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.927960927960928, | |
| "grad_norm": 31.470670700073242, | |
| "learning_rate": 7.427785419532325e-07, | |
| "loss": 0.1326, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.927960927960928, | |
| "eval_accuracy": 0.9248625534514355, | |
| "eval_accuracy_label_negative": 0.9191919191919192, | |
| "eval_accuracy_label_positive": 0.9301775147928995, | |
| "eval_f1": 0.9248544119857385, | |
| "eval_loss": 0.2394767850637436, | |
| "eval_precision": 0.9248635488205493, | |
| "eval_recall": 0.9248625534514355, | |
| "eval_runtime": 6.4694, | |
| "eval_samples_per_second": 253.036, | |
| "eval_steps_per_second": 15.921, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.9523809523809526, | |
| "grad_norm": 16.254497528076172, | |
| "learning_rate": 4.6767537826685014e-07, | |
| "loss": 0.1154, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.976800976800977, | |
| "grad_norm": 18.331233978271484, | |
| "learning_rate": 1.925722145804677e-07, | |
| "loss": 0.1268, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.993894993894994, | |
| "step": 1227, | |
| "total_flos": 157098652813440.0, | |
| "train_loss": 0.22647988077286502, | |
| "train_runtime": 692.1682, | |
| "train_samples_per_second": 56.735, | |
| "train_steps_per_second": 1.773 | |
| }, | |
| { | |
| "epoch": 2.993894993894994, | |
| "eval_accuracy": 0.9260843005497862, | |
| "eval_accuracy_label_negative": 0.9242424242424242, | |
| "eval_accuracy_label_positive": 0.927810650887574, | |
| "eval_f1": 0.9260857363073682, | |
| "eval_loss": 0.23794083297252655, | |
| "eval_precision": 0.9260878637932374, | |
| "eval_recall": 0.9260843005497862, | |
| "eval_runtime": 6.4878, | |
| "eval_samples_per_second": 252.32, | |
| "eval_steps_per_second": 15.876, | |
| "step": 1227 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1227, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 157098652813440.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |