| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 940, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10638297872340426, | |
| "grad_norm": 8.126425743103027, | |
| "learning_rate": 9.893617021276596e-05, | |
| "loss": 0.3285, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2127659574468085, | |
| "grad_norm": 6.1601433753967285, | |
| "learning_rate": 9.787234042553192e-05, | |
| "loss": 0.1592, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3191489361702128, | |
| "grad_norm": 4.860865116119385, | |
| "learning_rate": 9.680851063829788e-05, | |
| "loss": 0.0495, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 9.17108154296875, | |
| "learning_rate": 9.574468085106384e-05, | |
| "loss": 0.0527, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "grad_norm": 14.069665908813477, | |
| "learning_rate": 9.468085106382978e-05, | |
| "loss": 0.0608, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6382978723404256, | |
| "grad_norm": 4.747547626495361, | |
| "learning_rate": 9.361702127659576e-05, | |
| "loss": 0.0362, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7446808510638298, | |
| "grad_norm": 1.6759053468704224, | |
| "learning_rate": 9.25531914893617e-05, | |
| "loss": 0.0224, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 2.784752130508423, | |
| "learning_rate": 9.148936170212766e-05, | |
| "loss": 0.0147, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9574468085106383, | |
| "grad_norm": 1.5901750326156616, | |
| "learning_rate": 9.042553191489363e-05, | |
| "loss": 0.0169, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.01848638243973255, | |
| "eval_mse": 0.0184863843023777, | |
| "eval_runtime": 19.8026, | |
| "eval_samples_per_second": 9.443, | |
| "eval_steps_per_second": 1.212, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "grad_norm": 3.8150742053985596, | |
| "learning_rate": 8.936170212765958e-05, | |
| "loss": 0.0171, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1702127659574468, | |
| "grad_norm": 1.5259689092636108, | |
| "learning_rate": 8.829787234042553e-05, | |
| "loss": 0.0151, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": 2.552485704421997, | |
| "learning_rate": 8.723404255319149e-05, | |
| "loss": 0.0335, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3829787234042552, | |
| "grad_norm": 4.987245559692383, | |
| "learning_rate": 8.617021276595745e-05, | |
| "loss": 0.0126, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4893617021276595, | |
| "grad_norm": 3.1922833919525146, | |
| "learning_rate": 8.510638297872341e-05, | |
| "loss": 0.0163, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "grad_norm": 0.7118219137191772, | |
| "learning_rate": 8.404255319148937e-05, | |
| "loss": 0.0157, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.702127659574468, | |
| "grad_norm": 3.8524019718170166, | |
| "learning_rate": 8.297872340425533e-05, | |
| "loss": 0.0241, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.8085106382978724, | |
| "grad_norm": 2.0011708736419678, | |
| "learning_rate": 8.191489361702128e-05, | |
| "loss": 0.0149, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.9148936170212765, | |
| "grad_norm": 2.429314374923706, | |
| "learning_rate": 8.085106382978723e-05, | |
| "loss": 0.0096, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.035405904054641724, | |
| "eval_mse": 0.035405904054641724, | |
| "eval_runtime": 20.2256, | |
| "eval_samples_per_second": 9.246, | |
| "eval_steps_per_second": 1.187, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 2.021276595744681, | |
| "grad_norm": 8.87845516204834, | |
| "learning_rate": 7.978723404255319e-05, | |
| "loss": 0.0377, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "grad_norm": 2.39505672454834, | |
| "learning_rate": 7.872340425531916e-05, | |
| "loss": 0.0211, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.2340425531914896, | |
| "grad_norm": 8.978822708129883, | |
| "learning_rate": 7.76595744680851e-05, | |
| "loss": 0.0204, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.3404255319148937, | |
| "grad_norm": 5.196794033050537, | |
| "learning_rate": 7.659574468085106e-05, | |
| "loss": 0.0209, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.4468085106382977, | |
| "grad_norm": 0.35993799567222595, | |
| "learning_rate": 7.553191489361703e-05, | |
| "loss": 0.0181, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.5531914893617023, | |
| "grad_norm": 0.634810745716095, | |
| "learning_rate": 7.446808510638298e-05, | |
| "loss": 0.0112, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.6595744680851063, | |
| "grad_norm": 0.86403489112854, | |
| "learning_rate": 7.340425531914894e-05, | |
| "loss": 0.0053, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.7659574468085104, | |
| "grad_norm": 0.7839471697807312, | |
| "learning_rate": 7.23404255319149e-05, | |
| "loss": 0.0101, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.872340425531915, | |
| "grad_norm": 0.31476184725761414, | |
| "learning_rate": 7.127659574468085e-05, | |
| "loss": 0.0071, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.978723404255319, | |
| "grad_norm": 6.542386054992676, | |
| "learning_rate": 7.021276595744681e-05, | |
| "loss": 0.0138, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.017382489517331123, | |
| "eval_mse": 0.017382489517331123, | |
| "eval_runtime": 19.7323, | |
| "eval_samples_per_second": 9.477, | |
| "eval_steps_per_second": 1.216, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 3.0851063829787235, | |
| "grad_norm": 1.0467296838760376, | |
| "learning_rate": 6.914893617021277e-05, | |
| "loss": 0.0081, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.1914893617021276, | |
| "grad_norm": 4.260055065155029, | |
| "learning_rate": 6.808510638297873e-05, | |
| "loss": 0.008, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.297872340425532, | |
| "grad_norm": 1.8743150234222412, | |
| "learning_rate": 6.702127659574469e-05, | |
| "loss": 0.0182, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.404255319148936, | |
| "grad_norm": 1.2023850679397583, | |
| "learning_rate": 6.595744680851063e-05, | |
| "loss": 0.0062, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.5106382978723403, | |
| "grad_norm": 0.09485305100679398, | |
| "learning_rate": 6.489361702127659e-05, | |
| "loss": 0.0023, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.617021276595745, | |
| "grad_norm": 0.14307469129562378, | |
| "learning_rate": 6.382978723404256e-05, | |
| "loss": 0.0044, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.723404255319149, | |
| "grad_norm": 1.3662370443344116, | |
| "learning_rate": 6.276595744680851e-05, | |
| "loss": 0.005, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.829787234042553, | |
| "grad_norm": 1.612558364868164, | |
| "learning_rate": 6.170212765957447e-05, | |
| "loss": 0.0071, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.9361702127659575, | |
| "grad_norm": 0.9316902756690979, | |
| "learning_rate": 6.063829787234043e-05, | |
| "loss": 0.0035, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.016317620873451233, | |
| "eval_mse": 0.016317620873451233, | |
| "eval_runtime": 18.8697, | |
| "eval_samples_per_second": 9.91, | |
| "eval_steps_per_second": 1.272, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 4.042553191489362, | |
| "grad_norm": 0.5955564379692078, | |
| "learning_rate": 5.9574468085106384e-05, | |
| "loss": 0.0262, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.148936170212766, | |
| "grad_norm": 0.6957511305809021, | |
| "learning_rate": 5.851063829787234e-05, | |
| "loss": 0.0021, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.25531914893617, | |
| "grad_norm": 1.7189148664474487, | |
| "learning_rate": 5.744680851063831e-05, | |
| "loss": 0.0034, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.361702127659575, | |
| "grad_norm": 0.6659339070320129, | |
| "learning_rate": 5.638297872340426e-05, | |
| "loss": 0.018, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.468085106382979, | |
| "grad_norm": 0.5192022323608398, | |
| "learning_rate": 5.531914893617022e-05, | |
| "loss": 0.0032, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.574468085106383, | |
| "grad_norm": 0.2125098705291748, | |
| "learning_rate": 5.425531914893617e-05, | |
| "loss": 0.0026, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.680851063829787, | |
| "grad_norm": 1.9762024879455566, | |
| "learning_rate": 5.319148936170213e-05, | |
| "loss": 0.0032, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.787234042553192, | |
| "grad_norm": 0.4441240429878235, | |
| "learning_rate": 5.212765957446809e-05, | |
| "loss": 0.0068, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.8936170212765955, | |
| "grad_norm": 0.5156407356262207, | |
| "learning_rate": 5.1063829787234044e-05, | |
| "loss": 0.0031, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.0167255401611328, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0022, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.015473912470042706, | |
| "eval_mse": 0.015473911538720131, | |
| "eval_runtime": 20.1906, | |
| "eval_samples_per_second": 9.262, | |
| "eval_steps_per_second": 1.189, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.1063829787234045, | |
| "grad_norm": 2.192549705505371, | |
| "learning_rate": 4.893617021276596e-05, | |
| "loss": 0.0054, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.212765957446808, | |
| "grad_norm": 3.8224434852600098, | |
| "learning_rate": 4.787234042553192e-05, | |
| "loss": 0.0068, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.319148936170213, | |
| "grad_norm": 1.0146186351776123, | |
| "learning_rate": 4.680851063829788e-05, | |
| "loss": 0.0063, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.425531914893617, | |
| "grad_norm": 0.30157503485679626, | |
| "learning_rate": 4.574468085106383e-05, | |
| "loss": 0.0027, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.531914893617021, | |
| "grad_norm": 1.6889015436172485, | |
| "learning_rate": 4.468085106382979e-05, | |
| "loss": 0.0096, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.638297872340425, | |
| "grad_norm": 2.113478183746338, | |
| "learning_rate": 4.3617021276595746e-05, | |
| "loss": 0.0032, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.74468085106383, | |
| "grad_norm": 1.2465013265609741, | |
| "learning_rate": 4.2553191489361704e-05, | |
| "loss": 0.0119, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.851063829787234, | |
| "grad_norm": 3.655217409133911, | |
| "learning_rate": 4.148936170212766e-05, | |
| "loss": 0.006, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.957446808510638, | |
| "grad_norm": 0.4960452616214752, | |
| "learning_rate": 4.0425531914893614e-05, | |
| "loss": 0.0037, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.015477526001632214, | |
| "eval_mse": 0.015477526001632214, | |
| "eval_runtime": 19.1897, | |
| "eval_samples_per_second": 9.745, | |
| "eval_steps_per_second": 1.251, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 6.0638297872340425, | |
| "grad_norm": 0.08745921403169632, | |
| "learning_rate": 3.936170212765958e-05, | |
| "loss": 0.0016, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.170212765957447, | |
| "grad_norm": 0.9667307138442993, | |
| "learning_rate": 3.829787234042553e-05, | |
| "loss": 0.0023, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.276595744680851, | |
| "grad_norm": 0.2230611890554428, | |
| "learning_rate": 3.723404255319149e-05, | |
| "loss": 0.0013, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.382978723404255, | |
| "grad_norm": 0.9153568744659424, | |
| "learning_rate": 3.617021276595745e-05, | |
| "loss": 0.0084, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.48936170212766, | |
| "grad_norm": 0.4662020802497864, | |
| "learning_rate": 3.5106382978723407e-05, | |
| "loss": 0.0015, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.595744680851064, | |
| "grad_norm": 1.4528487920761108, | |
| "learning_rate": 3.4042553191489365e-05, | |
| "loss": 0.0042, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.702127659574468, | |
| "grad_norm": 0.8762513995170593, | |
| "learning_rate": 3.2978723404255317e-05, | |
| "loss": 0.0013, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.808510638297872, | |
| "grad_norm": 0.6134530305862427, | |
| "learning_rate": 3.191489361702128e-05, | |
| "loss": 0.0011, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.914893617021277, | |
| "grad_norm": 0.24190925061702728, | |
| "learning_rate": 3.085106382978723e-05, | |
| "loss": 0.0015, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.01572970487177372, | |
| "eval_mse": 0.01572970487177372, | |
| "eval_runtime": 20.3621, | |
| "eval_samples_per_second": 9.184, | |
| "eval_steps_per_second": 1.179, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 7.0212765957446805, | |
| "grad_norm": 0.41018059849739075, | |
| "learning_rate": 2.9787234042553192e-05, | |
| "loss": 0.0009, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 7.127659574468085, | |
| "grad_norm": 0.37687671184539795, | |
| "learning_rate": 2.8723404255319154e-05, | |
| "loss": 0.001, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 7.23404255319149, | |
| "grad_norm": 1.019307255744934, | |
| "learning_rate": 2.765957446808511e-05, | |
| "loss": 0.0007, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 7.340425531914893, | |
| "grad_norm": 1.018244743347168, | |
| "learning_rate": 2.6595744680851064e-05, | |
| "loss": 0.0009, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.446808510638298, | |
| "grad_norm": 2.739215850830078, | |
| "learning_rate": 2.5531914893617022e-05, | |
| "loss": 0.0037, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.553191489361702, | |
| "grad_norm": 0.6976016163825989, | |
| "learning_rate": 2.446808510638298e-05, | |
| "loss": 0.0028, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 7.659574468085106, | |
| "grad_norm": 0.2421257346868515, | |
| "learning_rate": 2.340425531914894e-05, | |
| "loss": 0.0005, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 7.76595744680851, | |
| "grad_norm": 0.22403240203857422, | |
| "learning_rate": 2.2340425531914894e-05, | |
| "loss": 0.0005, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 7.872340425531915, | |
| "grad_norm": 0.14943571388721466, | |
| "learning_rate": 2.1276595744680852e-05, | |
| "loss": 0.0007, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 7.9787234042553195, | |
| "grad_norm": 0.3691145181655884, | |
| "learning_rate": 2.0212765957446807e-05, | |
| "loss": 0.0005, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.015090713277459145, | |
| "eval_mse": 0.015090713277459145, | |
| "eval_runtime": 19.1297, | |
| "eval_samples_per_second": 9.775, | |
| "eval_steps_per_second": 1.255, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 8.085106382978724, | |
| "grad_norm": 0.15992891788482666, | |
| "learning_rate": 1.9148936170212766e-05, | |
| "loss": 0.0003, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 8.191489361702128, | |
| "grad_norm": 0.10835320502519608, | |
| "learning_rate": 1.8085106382978724e-05, | |
| "loss": 0.0003, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 8.297872340425531, | |
| "grad_norm": 0.36001548171043396, | |
| "learning_rate": 1.7021276595744682e-05, | |
| "loss": 0.0002, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 8.404255319148936, | |
| "grad_norm": 0.34065675735473633, | |
| "learning_rate": 1.595744680851064e-05, | |
| "loss": 0.0034, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.51063829787234, | |
| "grad_norm": 0.38518810272216797, | |
| "learning_rate": 1.4893617021276596e-05, | |
| "loss": 0.0038, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.617021276595745, | |
| "grad_norm": 0.026287797838449478, | |
| "learning_rate": 1.3829787234042554e-05, | |
| "loss": 0.0004, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 8.72340425531915, | |
| "grad_norm": 0.014783932827413082, | |
| "learning_rate": 1.2765957446808511e-05, | |
| "loss": 0.0003, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 8.829787234042554, | |
| "grad_norm": 0.19748060405254364, | |
| "learning_rate": 1.170212765957447e-05, | |
| "loss": 0.0003, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 8.936170212765958, | |
| "grad_norm": 0.8855957388877869, | |
| "learning_rate": 1.0638297872340426e-05, | |
| "loss": 0.0015, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.015240918844938278, | |
| "eval_mse": 0.015240917913615704, | |
| "eval_runtime": 19.886, | |
| "eval_samples_per_second": 9.404, | |
| "eval_steps_per_second": 1.207, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 9.042553191489361, | |
| "grad_norm": 0.37384435534477234, | |
| "learning_rate": 9.574468085106383e-06, | |
| "loss": 0.0007, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 9.148936170212766, | |
| "grad_norm": 0.43220600485801697, | |
| "learning_rate": 8.510638297872341e-06, | |
| "loss": 0.0002, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 9.25531914893617, | |
| "grad_norm": 0.024543819949030876, | |
| "learning_rate": 7.446808510638298e-06, | |
| "loss": 0.0002, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 9.361702127659575, | |
| "grad_norm": 0.2134750485420227, | |
| "learning_rate": 6.3829787234042555e-06, | |
| "loss": 0.0001, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 9.46808510638298, | |
| "grad_norm": 0.09525676816701889, | |
| "learning_rate": 5.319148936170213e-06, | |
| "loss": 0.0019, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 9.574468085106384, | |
| "grad_norm": 0.026247423142194748, | |
| "learning_rate": 4.255319148936171e-06, | |
| "loss": 0.0002, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.680851063829786, | |
| "grad_norm": 0.08234742283821106, | |
| "learning_rate": 3.1914893617021277e-06, | |
| "loss": 0.0002, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 9.787234042553191, | |
| "grad_norm": 0.04805035889148712, | |
| "learning_rate": 2.1276595744680853e-06, | |
| "loss": 0.0001, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 9.893617021276595, | |
| "grad_norm": 0.0683567151427269, | |
| "learning_rate": 1.0638297872340427e-06, | |
| "loss": 0.0005, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.2706449627876282, | |
| "learning_rate": 0.0, | |
| "loss": 0.0002, | |
| "step": 940 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 940, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |