| { | |
| "best_metric": 0.41522201895713806, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.029414648494950485, | |
| "eval_steps": 50, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019609765663300324, | |
| "grad_norm": 7.468555927276611, | |
| "learning_rate": 1.013e-05, | |
| "loss": 1.5524, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019609765663300324, | |
| "eval_loss": 1.2237062454223633, | |
| "eval_runtime": 243.2276, | |
| "eval_samples_per_second": 8.831, | |
| "eval_steps_per_second": 2.208, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003921953132660065, | |
| "grad_norm": 7.6385884284973145, | |
| "learning_rate": 2.026e-05, | |
| "loss": 1.7279, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005882929698990097, | |
| "grad_norm": 10.681758880615234, | |
| "learning_rate": 3.039e-05, | |
| "loss": 1.5164, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000784390626532013, | |
| "grad_norm": 9.887133598327637, | |
| "learning_rate": 4.052e-05, | |
| "loss": 1.1316, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009804882831650162, | |
| "grad_norm": 8.374829292297363, | |
| "learning_rate": 5.065e-05, | |
| "loss": 1.1586, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011765859397980193, | |
| "grad_norm": 7.310905456542969, | |
| "learning_rate": 6.078e-05, | |
| "loss": 0.8968, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013726835964310226, | |
| "grad_norm": 10.953272819519043, | |
| "learning_rate": 7.091e-05, | |
| "loss": 1.1154, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001568781253064026, | |
| "grad_norm": 7.230965614318848, | |
| "learning_rate": 8.104e-05, | |
| "loss": 1.0405, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0017648789096970292, | |
| "grad_norm": 8.350433349609375, | |
| "learning_rate": 9.117e-05, | |
| "loss": 1.2122, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019609765663300325, | |
| "grad_norm": 6.164297580718994, | |
| "learning_rate": 0.0001013, | |
| "loss": 0.9343, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021570742229630358, | |
| "grad_norm": 8.079084396362305, | |
| "learning_rate": 0.00010076684210526316, | |
| "loss": 0.7113, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0023531718795960386, | |
| "grad_norm": 9.09571361541748, | |
| "learning_rate": 0.0001002336842105263, | |
| "loss": 1.0389, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002549269536229042, | |
| "grad_norm": 9.438547134399414, | |
| "learning_rate": 9.970052631578946e-05, | |
| "loss": 1.2697, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002745367192862045, | |
| "grad_norm": 9.123111724853516, | |
| "learning_rate": 9.916736842105263e-05, | |
| "loss": 1.2704, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0029414648494950485, | |
| "grad_norm": 7.670680999755859, | |
| "learning_rate": 9.863421052631579e-05, | |
| "loss": 0.9233, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003137562506128052, | |
| "grad_norm": 6.911023139953613, | |
| "learning_rate": 9.810105263157895e-05, | |
| "loss": 0.8698, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003333660162761055, | |
| "grad_norm": 9.797855377197266, | |
| "learning_rate": 9.756789473684211e-05, | |
| "loss": 1.1806, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0035297578193940584, | |
| "grad_norm": 8.471273422241211, | |
| "learning_rate": 9.703473684210525e-05, | |
| "loss": 1.0096, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0037258554760270617, | |
| "grad_norm": 12.676338195800781, | |
| "learning_rate": 9.650157894736842e-05, | |
| "loss": 1.1519, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003921953132660065, | |
| "grad_norm": 7.387173652648926, | |
| "learning_rate": 9.596842105263158e-05, | |
| "loss": 0.7844, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004118050789293068, | |
| "grad_norm": 35.67609786987305, | |
| "learning_rate": 9.543526315789474e-05, | |
| "loss": 0.8251, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0043141484459260715, | |
| "grad_norm": 21.55261993408203, | |
| "learning_rate": 9.49021052631579e-05, | |
| "loss": 0.5756, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004510246102559075, | |
| "grad_norm": 17.739107131958008, | |
| "learning_rate": 9.436894736842105e-05, | |
| "loss": 1.4716, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004706343759192077, | |
| "grad_norm": 16.76211166381836, | |
| "learning_rate": 9.38357894736842e-05, | |
| "loss": 1.2926, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0049024414158250805, | |
| "grad_norm": 19.425182342529297, | |
| "learning_rate": 9.330263157894737e-05, | |
| "loss": 1.2513, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005098539072458084, | |
| "grad_norm": 5.306024074554443, | |
| "learning_rate": 9.276947368421051e-05, | |
| "loss": 0.4769, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005294636729091087, | |
| "grad_norm": 15.570332527160645, | |
| "learning_rate": 9.223631578947369e-05, | |
| "loss": 0.869, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00549073438572409, | |
| "grad_norm": 16.34988784790039, | |
| "learning_rate": 9.170315789473684e-05, | |
| "loss": 1.0487, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005686832042357094, | |
| "grad_norm": 7.214115142822266, | |
| "learning_rate": 9.117e-05, | |
| "loss": 0.6652, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005882929698990097, | |
| "grad_norm": 8.671172142028809, | |
| "learning_rate": 9.063684210526316e-05, | |
| "loss": 0.5766, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0060790273556231, | |
| "grad_norm": 14.24565315246582, | |
| "learning_rate": 9.010368421052632e-05, | |
| "loss": 0.7564, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006275125012256104, | |
| "grad_norm": 9.223489761352539, | |
| "learning_rate": 8.957052631578946e-05, | |
| "loss": 0.5476, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006471222668889107, | |
| "grad_norm": 12.95165729522705, | |
| "learning_rate": 8.903736842105263e-05, | |
| "loss": 0.7006, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00666732032552211, | |
| "grad_norm": 11.666534423828125, | |
| "learning_rate": 8.850421052631579e-05, | |
| "loss": 0.7866, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0068634179821551134, | |
| "grad_norm": 10.406961441040039, | |
| "learning_rate": 8.797105263157895e-05, | |
| "loss": 0.7515, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007059515638788117, | |
| "grad_norm": 13.311921119689941, | |
| "learning_rate": 8.743789473684211e-05, | |
| "loss": 0.6337, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00725561329542112, | |
| "grad_norm": 11.749580383300781, | |
| "learning_rate": 8.690473684210526e-05, | |
| "loss": 0.8481, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007451710952054123, | |
| "grad_norm": 6.961912155151367, | |
| "learning_rate": 8.637157894736842e-05, | |
| "loss": 0.6709, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.007647808608687127, | |
| "grad_norm": 22.275279998779297, | |
| "learning_rate": 8.583842105263158e-05, | |
| "loss": 1.2376, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00784390626532013, | |
| "grad_norm": 67.40861511230469, | |
| "learning_rate": 8.530526315789472e-05, | |
| "loss": 1.8463, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008040003921953132, | |
| "grad_norm": 11.63316822052002, | |
| "learning_rate": 8.47721052631579e-05, | |
| "loss": 1.0184, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.008236101578586136, | |
| "grad_norm": 33.797874450683594, | |
| "learning_rate": 8.423894736842105e-05, | |
| "loss": 1.7594, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008432199235219139, | |
| "grad_norm": 14.965246200561523, | |
| "learning_rate": 8.37057894736842e-05, | |
| "loss": 0.9693, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008628296891852143, | |
| "grad_norm": 10.041715621948242, | |
| "learning_rate": 8.317263157894737e-05, | |
| "loss": 0.7927, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.008824394548485145, | |
| "grad_norm": 22.70721435546875, | |
| "learning_rate": 8.263947368421053e-05, | |
| "loss": 1.3944, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00902049220511815, | |
| "grad_norm": 49.67770767211914, | |
| "learning_rate": 8.210631578947368e-05, | |
| "loss": 1.8496, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.009216589861751152, | |
| "grad_norm": 23.283432006835938, | |
| "learning_rate": 8.157315789473684e-05, | |
| "loss": 1.057, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.009412687518384154, | |
| "grad_norm": 23.300397872924805, | |
| "learning_rate": 8.104e-05, | |
| "loss": 1.0415, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.009608785175017159, | |
| "grad_norm": 14.141422271728516, | |
| "learning_rate": 8.050684210526316e-05, | |
| "loss": 1.0551, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.009804882831650161, | |
| "grad_norm": 45.43354415893555, | |
| "learning_rate": 7.997368421052632e-05, | |
| "loss": 2.293, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009804882831650161, | |
| "eval_loss": 0.5220252871513367, | |
| "eval_runtime": 242.92, | |
| "eval_samples_per_second": 8.842, | |
| "eval_steps_per_second": 2.211, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010000980488283165, | |
| "grad_norm": 6.259135723114014, | |
| "learning_rate": 7.944052631578947e-05, | |
| "loss": 1.9433, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.010197078144916168, | |
| "grad_norm": 3.87833833694458, | |
| "learning_rate": 7.890736842105263e-05, | |
| "loss": 0.925, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.010393175801549172, | |
| "grad_norm": 3.702810764312744, | |
| "learning_rate": 7.837421052631579e-05, | |
| "loss": 0.8375, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.010589273458182174, | |
| "grad_norm": 3.9069197177886963, | |
| "learning_rate": 7.784105263157893e-05, | |
| "loss": 0.7016, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.010785371114815178, | |
| "grad_norm": 4.089141845703125, | |
| "learning_rate": 7.730789473684211e-05, | |
| "loss": 0.736, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.01098146877144818, | |
| "grad_norm": 4.299583435058594, | |
| "learning_rate": 7.677473684210526e-05, | |
| "loss": 0.9623, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.011177566428081185, | |
| "grad_norm": 4.404727458953857, | |
| "learning_rate": 7.624157894736842e-05, | |
| "loss": 0.9444, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.011373664084714187, | |
| "grad_norm": 3.662179470062256, | |
| "learning_rate": 7.570842105263158e-05, | |
| "loss": 0.7267, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.011569761741347192, | |
| "grad_norm": 5.034608364105225, | |
| "learning_rate": 7.517526315789474e-05, | |
| "loss": 0.8414, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.011765859397980194, | |
| "grad_norm": 4.015024185180664, | |
| "learning_rate": 7.464210526315789e-05, | |
| "loss": 0.7682, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.011961957054613198, | |
| "grad_norm": 3.8569846153259277, | |
| "learning_rate": 7.410894736842106e-05, | |
| "loss": 0.7419, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0121580547112462, | |
| "grad_norm": 5.50112247467041, | |
| "learning_rate": 7.35757894736842e-05, | |
| "loss": 0.789, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.012354152367879203, | |
| "grad_norm": 4.346161842346191, | |
| "learning_rate": 7.304263157894737e-05, | |
| "loss": 0.7292, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.012550250024512207, | |
| "grad_norm": 12.474294662475586, | |
| "learning_rate": 7.250947368421053e-05, | |
| "loss": 0.8405, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.01274634768114521, | |
| "grad_norm": 6.171235084533691, | |
| "learning_rate": 7.197631578947368e-05, | |
| "loss": 0.9972, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.012942445337778214, | |
| "grad_norm": 10.865174293518066, | |
| "learning_rate": 7.144315789473684e-05, | |
| "loss": 0.6531, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.013138542994411216, | |
| "grad_norm": 5.450807094573975, | |
| "learning_rate": 7.091e-05, | |
| "loss": 0.9603, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.01333464065104422, | |
| "grad_norm": 5.7336015701293945, | |
| "learning_rate": 7.037684210526316e-05, | |
| "loss": 0.9774, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.013530738307677223, | |
| "grad_norm": 5.6365156173706055, | |
| "learning_rate": 6.984368421052632e-05, | |
| "loss": 0.7666, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.013726835964310227, | |
| "grad_norm": 7.478610992431641, | |
| "learning_rate": 6.931052631578947e-05, | |
| "loss": 0.7726, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01392293362094323, | |
| "grad_norm": 5.047933578491211, | |
| "learning_rate": 6.877736842105263e-05, | |
| "loss": 0.5822, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.014119031277576233, | |
| "grad_norm": 6.480734348297119, | |
| "learning_rate": 6.824421052631579e-05, | |
| "loss": 0.7629, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.014315128934209236, | |
| "grad_norm": 7.191463470458984, | |
| "learning_rate": 6.771105263157895e-05, | |
| "loss": 0.6803, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.01451122659084224, | |
| "grad_norm": 4.883853435516357, | |
| "learning_rate": 6.71778947368421e-05, | |
| "loss": 0.6785, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.014707324247475242, | |
| "grad_norm": 6.941567420959473, | |
| "learning_rate": 6.664473684210527e-05, | |
| "loss": 0.8324, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.014903421904108247, | |
| "grad_norm": 6.098438739776611, | |
| "learning_rate": 6.611157894736842e-05, | |
| "loss": 0.8325, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.015099519560741249, | |
| "grad_norm": 8.49299144744873, | |
| "learning_rate": 6.557842105263158e-05, | |
| "loss": 1.1349, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.015295617217374253, | |
| "grad_norm": 4.6161627769470215, | |
| "learning_rate": 6.504526315789474e-05, | |
| "loss": 0.3797, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.015491714874007256, | |
| "grad_norm": 5.683040142059326, | |
| "learning_rate": 6.451210526315789e-05, | |
| "loss": 0.4784, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.01568781253064026, | |
| "grad_norm": 7.138983249664307, | |
| "learning_rate": 6.397894736842105e-05, | |
| "loss": 0.6783, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01588391018727326, | |
| "grad_norm": 5.301764488220215, | |
| "learning_rate": 6.344578947368421e-05, | |
| "loss": 0.4013, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.016080007843906265, | |
| "grad_norm": 5.394726753234863, | |
| "learning_rate": 6.291263157894737e-05, | |
| "loss": 0.472, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.01627610550053927, | |
| "grad_norm": 7.571673393249512, | |
| "learning_rate": 6.237947368421053e-05, | |
| "loss": 0.6222, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.016472203157172273, | |
| "grad_norm": 13.990236282348633, | |
| "learning_rate": 6.184631578947368e-05, | |
| "loss": 1.5111, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.016668300813805274, | |
| "grad_norm": 9.939437866210938, | |
| "learning_rate": 6.131315789473684e-05, | |
| "loss": 1.2702, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.016864398470438278, | |
| "grad_norm": 11.926310539245605, | |
| "learning_rate": 6.078e-05, | |
| "loss": 0.997, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.017060496127071282, | |
| "grad_norm": 7.9521379470825195, | |
| "learning_rate": 6.024684210526315e-05, | |
| "loss": 0.8637, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.017256593783704286, | |
| "grad_norm": 11.58044147491455, | |
| "learning_rate": 5.9713684210526305e-05, | |
| "loss": 1.3852, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.017452691440337287, | |
| "grad_norm": 9.782970428466797, | |
| "learning_rate": 5.918052631578947e-05, | |
| "loss": 0.8799, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.01764878909697029, | |
| "grad_norm": 10.114582061767578, | |
| "learning_rate": 5.8647368421052634e-05, | |
| "loss": 1.1961, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.017844886753603295, | |
| "grad_norm": 12.574527740478516, | |
| "learning_rate": 5.811421052631579e-05, | |
| "loss": 1.0894, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0180409844102363, | |
| "grad_norm": 14.899230003356934, | |
| "learning_rate": 5.758105263157894e-05, | |
| "loss": 1.2862, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.0182370820668693, | |
| "grad_norm": 8.636293411254883, | |
| "learning_rate": 5.70478947368421e-05, | |
| "loss": 0.854, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.018433179723502304, | |
| "grad_norm": 11.84518814086914, | |
| "learning_rate": 5.6514736842105256e-05, | |
| "loss": 0.6895, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.01862927738013531, | |
| "grad_norm": 28.145517349243164, | |
| "learning_rate": 5.5981578947368424e-05, | |
| "loss": 1.5005, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.01882537503676831, | |
| "grad_norm": 13.958025932312012, | |
| "learning_rate": 5.544842105263158e-05, | |
| "loss": 0.4707, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.019021472693401313, | |
| "grad_norm": 14.421865463256836, | |
| "learning_rate": 5.491526315789474e-05, | |
| "loss": 1.3302, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.019217570350034317, | |
| "grad_norm": 19.330612182617188, | |
| "learning_rate": 5.438210526315789e-05, | |
| "loss": 1.0502, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.01941366800666732, | |
| "grad_norm": 16.62639045715332, | |
| "learning_rate": 5.384894736842105e-05, | |
| "loss": 1.2102, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.019609765663300322, | |
| "grad_norm": 26.352754592895508, | |
| "learning_rate": 5.331578947368421e-05, | |
| "loss": 1.9532, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.019609765663300322, | |
| "eval_loss": 0.4575375020503998, | |
| "eval_runtime": 243.2626, | |
| "eval_samples_per_second": 8.83, | |
| "eval_steps_per_second": 2.207, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.019805863319933326, | |
| "grad_norm": 4.1386566162109375, | |
| "learning_rate": 5.278263157894736e-05, | |
| "loss": 1.3238, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.02000196097656633, | |
| "grad_norm": 3.137593984603882, | |
| "learning_rate": 5.224947368421053e-05, | |
| "loss": 0.9319, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.020198058633199335, | |
| "grad_norm": 3.7397894859313965, | |
| "learning_rate": 5.171631578947368e-05, | |
| "loss": 0.9041, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.020394156289832335, | |
| "grad_norm": 2.7134053707122803, | |
| "learning_rate": 5.1183157894736844e-05, | |
| "loss": 0.7395, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.02059025394646534, | |
| "grad_norm": 4.872076988220215, | |
| "learning_rate": 5.065e-05, | |
| "loss": 1.2704, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.020786351603098344, | |
| "grad_norm": 4.066561698913574, | |
| "learning_rate": 5.011684210526315e-05, | |
| "loss": 0.8238, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.020982449259731348, | |
| "grad_norm": 2.926990032196045, | |
| "learning_rate": 4.958368421052631e-05, | |
| "loss": 0.6825, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.02117854691636435, | |
| "grad_norm": 3.305487632751465, | |
| "learning_rate": 4.9050526315789473e-05, | |
| "loss": 0.6813, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.021374644572997353, | |
| "grad_norm": 5.23881196975708, | |
| "learning_rate": 4.851736842105263e-05, | |
| "loss": 0.9895, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.021570742229630357, | |
| "grad_norm": 3.481923818588257, | |
| "learning_rate": 4.798421052631579e-05, | |
| "loss": 0.6055, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.021766839886263357, | |
| "grad_norm": 2.770195722579956, | |
| "learning_rate": 4.745105263157895e-05, | |
| "loss": 0.4307, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.02196293754289636, | |
| "grad_norm": 5.2551398277282715, | |
| "learning_rate": 4.69178947368421e-05, | |
| "loss": 1.2838, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.022159035199529366, | |
| "grad_norm": 3.3223180770874023, | |
| "learning_rate": 4.638473684210526e-05, | |
| "loss": 0.7093, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.02235513285616237, | |
| "grad_norm": 4.730376720428467, | |
| "learning_rate": 4.585157894736842e-05, | |
| "loss": 0.8399, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.02255123051279537, | |
| "grad_norm": 5.192849636077881, | |
| "learning_rate": 4.531842105263158e-05, | |
| "loss": 0.7188, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.022747328169428375, | |
| "grad_norm": 3.2309155464172363, | |
| "learning_rate": 4.478526315789473e-05, | |
| "loss": 0.5142, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.02294342582606138, | |
| "grad_norm": 4.466787815093994, | |
| "learning_rate": 4.425210526315789e-05, | |
| "loss": 0.7535, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.023139523482694383, | |
| "grad_norm": 3.1393327713012695, | |
| "learning_rate": 4.3718947368421054e-05, | |
| "loss": 0.5282, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.023335621139327384, | |
| "grad_norm": 5.505728721618652, | |
| "learning_rate": 4.318578947368421e-05, | |
| "loss": 0.9189, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.023531718795960388, | |
| "grad_norm": 3.670624017715454, | |
| "learning_rate": 4.265263157894736e-05, | |
| "loss": 0.7202, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.023727816452593392, | |
| "grad_norm": 5.582329750061035, | |
| "learning_rate": 4.211947368421052e-05, | |
| "loss": 0.716, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.023923914109226396, | |
| "grad_norm": 4.540538787841797, | |
| "learning_rate": 4.1586315789473684e-05, | |
| "loss": 0.5689, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.024120011765859397, | |
| "grad_norm": 6.913193225860596, | |
| "learning_rate": 4.105315789473684e-05, | |
| "loss": 0.985, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.0243161094224924, | |
| "grad_norm": 6.866704940795898, | |
| "learning_rate": 4.052e-05, | |
| "loss": 0.7173, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.024512207079125405, | |
| "grad_norm": 8.457905769348145, | |
| "learning_rate": 3.998684210526316e-05, | |
| "loss": 0.7499, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.024708304735758406, | |
| "grad_norm": 6.656124591827393, | |
| "learning_rate": 3.945368421052631e-05, | |
| "loss": 1.0133, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.02490440239239141, | |
| "grad_norm": 6.976663112640381, | |
| "learning_rate": 3.892052631578947e-05, | |
| "loss": 0.8715, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.025100500049024414, | |
| "grad_norm": 8.578405380249023, | |
| "learning_rate": 3.838736842105263e-05, | |
| "loss": 0.6424, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.02529659770565742, | |
| "grad_norm": 7.345449924468994, | |
| "learning_rate": 3.785421052631579e-05, | |
| "loss": 0.8932, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.02549269536229042, | |
| "grad_norm": 5.459024906158447, | |
| "learning_rate": 3.732105263157894e-05, | |
| "loss": 0.5799, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.025688793018923423, | |
| "grad_norm": 6.494460105895996, | |
| "learning_rate": 3.67878947368421e-05, | |
| "loss": 0.4163, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.025884890675556427, | |
| "grad_norm": 5.555450916290283, | |
| "learning_rate": 3.6254736842105264e-05, | |
| "loss": 0.5469, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.02608098833218943, | |
| "grad_norm": 6.8839263916015625, | |
| "learning_rate": 3.572157894736842e-05, | |
| "loss": 0.9823, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.026277085988822432, | |
| "grad_norm": 12.403116226196289, | |
| "learning_rate": 3.518842105263158e-05, | |
| "loss": 0.6406, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.026473183645455436, | |
| "grad_norm": 7.836792469024658, | |
| "learning_rate": 3.465526315789473e-05, | |
| "loss": 1.1348, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.02666928130208844, | |
| "grad_norm": 7.983771800994873, | |
| "learning_rate": 3.4122105263157894e-05, | |
| "loss": 0.803, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.026865378958721445, | |
| "grad_norm": 7.406615734100342, | |
| "learning_rate": 3.358894736842105e-05, | |
| "loss": 0.6877, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.027061476615354445, | |
| "grad_norm": 7.180506706237793, | |
| "learning_rate": 3.305578947368421e-05, | |
| "loss": 0.9407, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.02725757427198745, | |
| "grad_norm": 10.637256622314453, | |
| "learning_rate": 3.252263157894737e-05, | |
| "loss": 1.0234, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.027453671928620454, | |
| "grad_norm": 12.093735694885254, | |
| "learning_rate": 3.198947368421052e-05, | |
| "loss": 0.9802, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.027649769585253458, | |
| "grad_norm": 11.916462898254395, | |
| "learning_rate": 3.1456315789473684e-05, | |
| "loss": 0.9617, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.02784586724188646, | |
| "grad_norm": 9.011691093444824, | |
| "learning_rate": 3.092315789473684e-05, | |
| "loss": 0.4959, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.028041964898519463, | |
| "grad_norm": 5.6275954246521, | |
| "learning_rate": 3.039e-05, | |
| "loss": 0.3209, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.028238062555152467, | |
| "grad_norm": 10.726852416992188, | |
| "learning_rate": 2.9856842105263153e-05, | |
| "loss": 1.2664, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.028434160211785468, | |
| "grad_norm": 12.800682067871094, | |
| "learning_rate": 2.9323684210526317e-05, | |
| "loss": 1.4327, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.028630257868418472, | |
| "grad_norm": 8.828701972961426, | |
| "learning_rate": 2.879052631578947e-05, | |
| "loss": 0.8394, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.028826355525051476, | |
| "grad_norm": 20.543346405029297, | |
| "learning_rate": 2.8257368421052628e-05, | |
| "loss": 2.1235, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.02902245318168448, | |
| "grad_norm": 24.438735961914062, | |
| "learning_rate": 2.772421052631579e-05, | |
| "loss": 1.5965, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.02921855083831748, | |
| "grad_norm": 21.095970153808594, | |
| "learning_rate": 2.7191052631578946e-05, | |
| "loss": 1.35, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.029414648494950485, | |
| "grad_norm": 18.338863372802734, | |
| "learning_rate": 2.6657894736842104e-05, | |
| "loss": 1.7666, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.029414648494950485, | |
| "eval_loss": 0.41522201895713806, | |
| "eval_runtime": 243.3207, | |
| "eval_samples_per_second": 8.828, | |
| "eval_steps_per_second": 2.207, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.652448497421517e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |