| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5055526176626124, | |
| "eval_steps": 500, | |
| "global_step": 239, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021152829190904283, | |
| "grad_norm": 3.663360357284546, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.3874, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004230565838180857, | |
| "grad_norm": 4.501073360443115, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.2804, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006345848757271285, | |
| "grad_norm": 4.990996837615967, | |
| "learning_rate": 3e-06, | |
| "loss": 1.2598, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008461131676361713, | |
| "grad_norm": 5.776909828186035, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.6224, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010576414595452142, | |
| "grad_norm": 5.360688209533691, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4513, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01269169751454257, | |
| "grad_norm": 5.100008964538574, | |
| "learning_rate": 6e-06, | |
| "loss": 1.3938, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014806980433632998, | |
| "grad_norm": 6.129480838775635, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 1.6399, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016922263352723427, | |
| "grad_norm": 6.223807334899902, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.5192, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019037546271813855, | |
| "grad_norm": 5.101447582244873, | |
| "learning_rate": 9e-06, | |
| "loss": 1.4052, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021152829190904283, | |
| "grad_norm": 5.858772277832031, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4977, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023268112109994712, | |
| "grad_norm": 5.468352794647217, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 1.4335, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02538339502908514, | |
| "grad_norm": 5.489218235015869, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.4383, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02749867794817557, | |
| "grad_norm": 5.1987624168396, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 1.4135, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.029613960867265997, | |
| "grad_norm": 5.416074275970459, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 1.3889, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03172924378635643, | |
| "grad_norm": 5.2188401222229, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.4194, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.033844526705446853, | |
| "grad_norm": 5.172801494598389, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.5219, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.035959809624537285, | |
| "grad_norm": 4.828940391540527, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 1.3965, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03807509254362771, | |
| "grad_norm": 4.481316566467285, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.3802, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04019037546271814, | |
| "grad_norm": 4.364404201507568, | |
| "learning_rate": 1.9e-05, | |
| "loss": 1.4343, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04230565838180857, | |
| "grad_norm": 4.6412177085876465, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3295, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.044420941300899, | |
| "grad_norm": 4.272985458374023, | |
| "learning_rate": 2.1e-05, | |
| "loss": 1.3726, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.046536224219989424, | |
| "grad_norm": 4.246971607208252, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 1.3176, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.048651507139079855, | |
| "grad_norm": 4.056257724761963, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 1.3644, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05076679005817028, | |
| "grad_norm": 3.9494340419769287, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.4087, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05288207297726071, | |
| "grad_norm": 3.7648792266845703, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.2293, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05499735589635114, | |
| "grad_norm": 3.988255262374878, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 1.234, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05711263881544157, | |
| "grad_norm": 3.6617515087127686, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 1.2011, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.059227921734531994, | |
| "grad_norm": 3.4993789196014404, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 1.1668, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.061343204653622425, | |
| "grad_norm": 4.011035919189453, | |
| "learning_rate": 2.9e-05, | |
| "loss": 1.3237, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06345848757271286, | |
| "grad_norm": 3.6400904655456543, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2794, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 3.648898124694824, | |
| "learning_rate": 3.1e-05, | |
| "loss": 1.182, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06768905341089371, | |
| "grad_norm": 3.6320934295654297, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.1123, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06980433632998413, | |
| "grad_norm": 4.042608737945557, | |
| "learning_rate": 3.3e-05, | |
| "loss": 1.1743, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07191961924907457, | |
| "grad_norm": 4.352260112762451, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 1.2997, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.074034902168165, | |
| "grad_norm": 4.048530101776123, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.1187, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07615018508725542, | |
| "grad_norm": 3.943918228149414, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.1385, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07826546800634585, | |
| "grad_norm": 4.064213752746582, | |
| "learning_rate": 3.7e-05, | |
| "loss": 1.1304, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08038075092543628, | |
| "grad_norm": 3.7748069763183594, | |
| "learning_rate": 3.8e-05, | |
| "loss": 1.2083, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08249603384452671, | |
| "grad_norm": 3.924967050552368, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 1.1601, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08461131676361713, | |
| "grad_norm": 3.864428758621216, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0968, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08672659968270756, | |
| "grad_norm": 4.152803897857666, | |
| "learning_rate": 4.1e-05, | |
| "loss": 1.0723, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.088841882601798, | |
| "grad_norm": 4.155374526977539, | |
| "learning_rate": 4.2e-05, | |
| "loss": 1.139, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09095716552088842, | |
| "grad_norm": 4.044234275817871, | |
| "learning_rate": 4.3e-05, | |
| "loss": 1.1796, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09307244843997885, | |
| "grad_norm": 3.951974868774414, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.2579, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09518773135906927, | |
| "grad_norm": 4.202303886413574, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.127, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09730301427815971, | |
| "grad_norm": 4.821532249450684, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.3201, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09941829719725014, | |
| "grad_norm": 4.339487075805664, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.9964, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10153358011634056, | |
| "grad_norm": 4.33770751953125, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.026, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10364886303543099, | |
| "grad_norm": 4.407140254974365, | |
| "learning_rate": 4.9e-05, | |
| "loss": 1.1072, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10576414595452142, | |
| "grad_norm": 5.298942565917969, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0666, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10787942887361185, | |
| "grad_norm": 2.503105640411377, | |
| "learning_rate": 5.1000000000000006e-05, | |
| "loss": 0.8011, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.10999471179270227, | |
| "grad_norm": 2.9427649974823, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 1.0133, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1121099947117927, | |
| "grad_norm": 2.7932252883911133, | |
| "learning_rate": 5.300000000000001e-05, | |
| "loss": 0.945, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.11422527763088314, | |
| "grad_norm": 3.1461985111236572, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 1.0524, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.11634056054997356, | |
| "grad_norm": 2.978358030319214, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.1368, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.11845584346906399, | |
| "grad_norm": 2.626965045928955, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 1.0135, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.12057112638815441, | |
| "grad_norm": 2.747119903564453, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 0.9616, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.12268640930724485, | |
| "grad_norm": 2.822309732437134, | |
| "learning_rate": 5.8e-05, | |
| "loss": 0.9357, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.12480169222633528, | |
| "grad_norm": 3.006105899810791, | |
| "learning_rate": 5.9e-05, | |
| "loss": 0.933, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.12691697514542571, | |
| "grad_norm": 3.2313544750213623, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0129, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 2.9400298595428467, | |
| "learning_rate": 6.1e-05, | |
| "loss": 1.0006, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.13114754098360656, | |
| "grad_norm": 3.390087127685547, | |
| "learning_rate": 6.2e-05, | |
| "loss": 0.9802, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.13326282390269698, | |
| "grad_norm": 3.047139883041382, | |
| "learning_rate": 6.3e-05, | |
| "loss": 1.0711, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.13537810682178741, | |
| "grad_norm": 3.0379374027252197, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.9628, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.13749338974087785, | |
| "grad_norm": 2.8749332427978516, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.9946, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.13960867265996826, | |
| "grad_norm": 2.915452003479004, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.9382, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.1417239555790587, | |
| "grad_norm": 3.1922085285186768, | |
| "learning_rate": 6.7e-05, | |
| "loss": 1.0699, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.14383923849814914, | |
| "grad_norm": 3.210163116455078, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 1.0313, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.14595452141723955, | |
| "grad_norm": 3.5844082832336426, | |
| "learning_rate": 6.9e-05, | |
| "loss": 1.1133, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.14806980433633, | |
| "grad_norm": 3.134580612182617, | |
| "learning_rate": 7e-05, | |
| "loss": 1.0114, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1501850872554204, | |
| "grad_norm": 2.9446849822998047, | |
| "learning_rate": 7.1e-05, | |
| "loss": 0.949, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.15230037017451084, | |
| "grad_norm": 3.1270101070404053, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.9519, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.15441565309360128, | |
| "grad_norm": 3.146308422088623, | |
| "learning_rate": 7.3e-05, | |
| "loss": 1.0239, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.1565309360126917, | |
| "grad_norm": 3.3636350631713867, | |
| "learning_rate": 7.4e-05, | |
| "loss": 1.0306, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.15864621893178213, | |
| "grad_norm": 3.30778431892395, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1119, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.16076150185087257, | |
| "grad_norm": 3.4229915142059326, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.9261, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.16287678476996298, | |
| "grad_norm": 3.0347306728363037, | |
| "learning_rate": 7.7e-05, | |
| "loss": 0.9614, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.16499206768905342, | |
| "grad_norm": 3.31915283203125, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 1.0835, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.16710735060814383, | |
| "grad_norm": 3.4393112659454346, | |
| "learning_rate": 7.900000000000001e-05, | |
| "loss": 0.9913, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.16922263352723427, | |
| "grad_norm": 3.4449856281280518, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8581, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1713379164463247, | |
| "grad_norm": 3.2748067378997803, | |
| "learning_rate": 8.1e-05, | |
| "loss": 1.0115, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.17345319936541512, | |
| "grad_norm": 3.2635154724121094, | |
| "learning_rate": 8.2e-05, | |
| "loss": 0.9795, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.17556848228450556, | |
| "grad_norm": 3.0997257232666016, | |
| "learning_rate": 8.3e-05, | |
| "loss": 0.9917, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.177683765203596, | |
| "grad_norm": 3.5653927326202393, | |
| "learning_rate": 8.4e-05, | |
| "loss": 1.0756, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1797990481226864, | |
| "grad_norm": 3.5017178058624268, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.0704, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.18191433104177684, | |
| "grad_norm": 3.7366182804107666, | |
| "learning_rate": 8.6e-05, | |
| "loss": 1.0626, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.18402961396086726, | |
| "grad_norm": 3.33809494972229, | |
| "learning_rate": 8.7e-05, | |
| "loss": 0.9562, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.1861448968799577, | |
| "grad_norm": 3.7696216106414795, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.9564, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.18826017979904813, | |
| "grad_norm": 3.3780527114868164, | |
| "learning_rate": 8.900000000000001e-05, | |
| "loss": 0.9696, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.19037546271813854, | |
| "grad_norm": 3.411578893661499, | |
| "learning_rate": 9e-05, | |
| "loss": 1.0817, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.19249074563722898, | |
| "grad_norm": 3.6279563903808594, | |
| "learning_rate": 9.1e-05, | |
| "loss": 0.9145, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.19460602855631942, | |
| "grad_norm": 3.7208714485168457, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 1.0407, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.19672131147540983, | |
| "grad_norm": 3.305312156677246, | |
| "learning_rate": 9.300000000000001e-05, | |
| "loss": 0.9349, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.19883659439450027, | |
| "grad_norm": 3.571962356567383, | |
| "learning_rate": 9.4e-05, | |
| "loss": 1.0338, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.20095187731359068, | |
| "grad_norm": 3.485724687576294, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.9924, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.20306716023268112, | |
| "grad_norm": 3.522717237472534, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.9256, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.20518244315177156, | |
| "grad_norm": 3.6267905235290527, | |
| "learning_rate": 9.7e-05, | |
| "loss": 0.8813, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.20729772607086197, | |
| "grad_norm": 3.9175007343292236, | |
| "learning_rate": 9.8e-05, | |
| "loss": 1.054, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2094130089899524, | |
| "grad_norm": 4.084409713745117, | |
| "learning_rate": 9.900000000000001e-05, | |
| "loss": 0.9527, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.21152829190904285, | |
| "grad_norm": 4.255803108215332, | |
| "learning_rate": 0.0001, | |
| "loss": 0.976, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21364357482813326, | |
| "grad_norm": 2.8322207927703857, | |
| "learning_rate": 9.99982170002055e-05, | |
| "loss": 0.8718, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.2157588577472237, | |
| "grad_norm": 3.1382946968078613, | |
| "learning_rate": 9.99928681279855e-05, | |
| "loss": 0.959, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.2178741406663141, | |
| "grad_norm": 2.58886456489563, | |
| "learning_rate": 9.998395376482152e-05, | |
| "loss": 0.8565, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.21998942358540455, | |
| "grad_norm": 2.7843730449676514, | |
| "learning_rate": 9.99714745464859e-05, | |
| "loss": 0.9355, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.222104706504495, | |
| "grad_norm": 2.447822332382202, | |
| "learning_rate": 9.995543136299636e-05, | |
| "loss": 0.838, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2242199894235854, | |
| "grad_norm": 2.584947347640991, | |
| "learning_rate": 9.993582535855263e-05, | |
| "loss": 0.9728, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.22633527234267584, | |
| "grad_norm": 2.7623209953308105, | |
| "learning_rate": 9.991265793145479e-05, | |
| "loss": 0.8943, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.22845055526176627, | |
| "grad_norm": 2.9683995246887207, | |
| "learning_rate": 9.988593073400354e-05, | |
| "loss": 0.8888, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.23056583818085669, | |
| "grad_norm": 2.9614081382751465, | |
| "learning_rate": 9.985564567238237e-05, | |
| "loss": 0.9477, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.23268112109994712, | |
| "grad_norm": 2.800546646118164, | |
| "learning_rate": 9.982180490652165e-05, | |
| "loss": 0.9267, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.23479640401903754, | |
| "grad_norm": 2.7987921237945557, | |
| "learning_rate": 9.978441084994453e-05, | |
| "loss": 0.9653, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.23691168693812797, | |
| "grad_norm": 2.9128034114837646, | |
| "learning_rate": 9.974346616959476e-05, | |
| "loss": 0.9898, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.2390269698572184, | |
| "grad_norm": 2.837714433670044, | |
| "learning_rate": 9.969897378564666e-05, | |
| "loss": 0.984, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.24114225277630882, | |
| "grad_norm": 3.1094441413879395, | |
| "learning_rate": 9.965093687129668e-05, | |
| "loss": 0.8232, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.24325753569539926, | |
| "grad_norm": 2.8722965717315674, | |
| "learning_rate": 9.959935885253716e-05, | |
| "loss": 0.9426, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2453728186144897, | |
| "grad_norm": 2.8371827602386475, | |
| "learning_rate": 9.954424340791196e-05, | |
| "loss": 0.9326, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.2474881015335801, | |
| "grad_norm": 2.9134371280670166, | |
| "learning_rate": 9.948559446825412e-05, | |
| "loss": 0.9904, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.24960338445267055, | |
| "grad_norm": 2.8855326175689697, | |
| "learning_rate": 9.942341621640558e-05, | |
| "loss": 0.8379, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.25171866737176096, | |
| "grad_norm": 2.910688877105713, | |
| "learning_rate": 9.935771308691871e-05, | |
| "loss": 0.9578, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.25383395029085143, | |
| "grad_norm": 3.0281407833099365, | |
| "learning_rate": 9.928848976574019e-05, | |
| "loss": 0.8464, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25594923320994184, | |
| "grad_norm": 3.0733401775360107, | |
| "learning_rate": 9.921575118987672e-05, | |
| "loss": 0.9664, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 2.8841378688812256, | |
| "learning_rate": 9.913950254704291e-05, | |
| "loss": 1.0148, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.26017979904812266, | |
| "grad_norm": 3.1016345024108887, | |
| "learning_rate": 9.905974927529135e-05, | |
| "loss": 0.9315, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 3.0234508514404297, | |
| "learning_rate": 9.897649706262473e-05, | |
| "loss": 0.9403, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.26441036488630354, | |
| "grad_norm": 2.8850417137145996, | |
| "learning_rate": 9.888975184659018e-05, | |
| "loss": 0.9036, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.26652564780539395, | |
| "grad_norm": 2.760040044784546, | |
| "learning_rate": 9.879951981385578e-05, | |
| "loss": 0.8731, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.2686409307244844, | |
| "grad_norm": 2.6963107585906982, | |
| "learning_rate": 9.870580739976935e-05, | |
| "loss": 0.8391, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.27075621364357483, | |
| "grad_norm": 3.0519609451293945, | |
| "learning_rate": 9.860862128789953e-05, | |
| "loss": 0.8089, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.27287149656266524, | |
| "grad_norm": 2.85986065864563, | |
| "learning_rate": 9.8507968409559e-05, | |
| "loss": 0.9419, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.2749867794817557, | |
| "grad_norm": 3.2540230751037598, | |
| "learning_rate": 9.840385594331022e-05, | |
| "loss": 0.9576, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2771020624008461, | |
| "grad_norm": 3.103649616241455, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9163, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.2792173453199365, | |
| "grad_norm": 2.9602162837982178, | |
| "learning_rate": 9.818528219449705e-05, | |
| "loss": 0.8656, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.281332628239027, | |
| "grad_norm": 2.9030895233154297, | |
| "learning_rate": 9.807083650061063e-05, | |
| "loss": 0.8838, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.2834479111581174, | |
| "grad_norm": 3.06990909576416, | |
| "learning_rate": 9.795296239506012e-05, | |
| "loss": 0.9112, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.2855631940772078, | |
| "grad_norm": 3.180403470993042, | |
| "learning_rate": 9.783166828462574e-05, | |
| "loss": 0.9657, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.2876784769962983, | |
| "grad_norm": 3.3117172718048096, | |
| "learning_rate": 9.770696282000244e-05, | |
| "loss": 0.9669, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.2897937599153887, | |
| "grad_norm": 3.1493141651153564, | |
| "learning_rate": 9.757885489518297e-05, | |
| "loss": 1.0193, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.2919090428344791, | |
| "grad_norm": 3.5290863513946533, | |
| "learning_rate": 9.744735364682346e-05, | |
| "loss": 0.952, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.2940243257535695, | |
| "grad_norm": 2.9906020164489746, | |
| "learning_rate": 9.731246845359186e-05, | |
| "loss": 0.8628, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.29613960867266, | |
| "grad_norm": 3.1866257190704346, | |
| "learning_rate": 9.717420893549902e-05, | |
| "loss": 0.9335, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2982548915917504, | |
| "grad_norm": 3.139331817626953, | |
| "learning_rate": 9.703258495321266e-05, | |
| "loss": 0.9351, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.3003701745108408, | |
| "grad_norm": 3.252739667892456, | |
| "learning_rate": 9.688760660735402e-05, | |
| "loss": 0.9207, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.30248545742993127, | |
| "grad_norm": 3.4457814693450928, | |
| "learning_rate": 9.673928423777756e-05, | |
| "loss": 1.1494, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.3046007403490217, | |
| "grad_norm": 3.2288053035736084, | |
| "learning_rate": 9.658762842283343e-05, | |
| "loss": 0.9069, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.3067160232681121, | |
| "grad_norm": 2.987396240234375, | |
| "learning_rate": 9.643264997861312e-05, | |
| "loss": 0.9142, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.30883130618720256, | |
| "grad_norm": 3.496523141860962, | |
| "learning_rate": 9.627435995817799e-05, | |
| "loss": 0.9341, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.31094658910629297, | |
| "grad_norm": 3.4983298778533936, | |
| "learning_rate": 9.611276965077099e-05, | |
| "loss": 0.8686, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.3130618720253834, | |
| "grad_norm": 3.702148199081421, | |
| "learning_rate": 9.594789058101153e-05, | |
| "loss": 1.0261, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.31517715494447385, | |
| "grad_norm": 4.358850002288818, | |
| "learning_rate": 9.577973450807351e-05, | |
| "loss": 1.0421, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.31729243786356426, | |
| "grad_norm": 4.173257350921631, | |
| "learning_rate": 9.560831342484667e-05, | |
| "loss": 0.915, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.31940772078265467, | |
| "grad_norm": 2.3479433059692383, | |
| "learning_rate": 9.543363955708125e-05, | |
| "loss": 0.7801, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.32152300370174514, | |
| "grad_norm": 2.8180437088012695, | |
| "learning_rate": 9.525572536251607e-05, | |
| "loss": 0.8987, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.32363828662083555, | |
| "grad_norm": 2.8835885524749756, | |
| "learning_rate": 9.507458352999001e-05, | |
| "loss": 0.9624, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.32575356953992596, | |
| "grad_norm": 2.63946270942688, | |
| "learning_rate": 9.489022697853709e-05, | |
| "loss": 0.9057, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.32786885245901637, | |
| "grad_norm": 2.484527349472046, | |
| "learning_rate": 9.470266885646503e-05, | |
| "loss": 0.8801, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.32998413537810684, | |
| "grad_norm": 2.4756839275360107, | |
| "learning_rate": 9.451192254041758e-05, | |
| "loss": 0.8307, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.33209941829719725, | |
| "grad_norm": 2.497173547744751, | |
| "learning_rate": 9.431800163442041e-05, | |
| "loss": 0.7906, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.33421470121628766, | |
| "grad_norm": 2.7058324813842773, | |
| "learning_rate": 9.412091996891096e-05, | |
| "loss": 0.9039, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.3363299841353781, | |
| "grad_norm": 2.7305657863616943, | |
| "learning_rate": 9.392069159975199e-05, | |
| "loss": 0.9251, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.33844526705446853, | |
| "grad_norm": 2.722649574279785, | |
| "learning_rate": 9.371733080722911e-05, | |
| "loss": 0.9382, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34056054997355895, | |
| "grad_norm": 2.5822291374206543, | |
| "learning_rate": 9.351085209503241e-05, | |
| "loss": 0.9322, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.3426758328926494, | |
| "grad_norm": 2.520709276199341, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9386, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.3447911158117398, | |
| "grad_norm": 2.785912275314331, | |
| "learning_rate": 9.308860003717748e-05, | |
| "loss": 0.853, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.34690639873083023, | |
| "grad_norm": 2.759871482849121, | |
| "learning_rate": 9.287285680653254e-05, | |
| "loss": 0.8206, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.3490216816499207, | |
| "grad_norm": 2.5678517818450928, | |
| "learning_rate": 9.265405588409257e-05, | |
| "loss": 0.8493, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.3511369645690111, | |
| "grad_norm": 2.4928886890411377, | |
| "learning_rate": 9.243221287473756e-05, | |
| "loss": 0.7925, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.3532522474881015, | |
| "grad_norm": 2.80059814453125, | |
| "learning_rate": 9.220734360030907e-05, | |
| "loss": 0.9222, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.355367530407192, | |
| "grad_norm": 2.5495877265930176, | |
| "learning_rate": 9.197946409848194e-05, | |
| "loss": 0.9326, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.3574828133262824, | |
| "grad_norm": 2.6717426776885986, | |
| "learning_rate": 9.174859062162038e-05, | |
| "loss": 0.8938, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.3595980962453728, | |
| "grad_norm": 2.851301908493042, | |
| "learning_rate": 9.151473963561883e-05, | |
| "loss": 0.864, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3617133791644632, | |
| "grad_norm": 2.684170722961426, | |
| "learning_rate": 9.127792781872769e-05, | |
| "loss": 0.7993, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.3638286620835537, | |
| "grad_norm": 2.6831891536712646, | |
| "learning_rate": 9.103817206036382e-05, | |
| "loss": 0.9036, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.3659439450026441, | |
| "grad_norm": 2.7455031871795654, | |
| "learning_rate": 9.079548945990593e-05, | |
| "loss": 0.8815, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.3680592279217345, | |
| "grad_norm": 2.7768361568450928, | |
| "learning_rate": 9.054989732547506e-05, | |
| "loss": 0.8734, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.370174510840825, | |
| "grad_norm": 3.000823497772217, | |
| "learning_rate": 9.030141317270026e-05, | |
| "loss": 0.901, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.3722897937599154, | |
| "grad_norm": 2.698535203933716, | |
| "learning_rate": 9.005005472346924e-05, | |
| "loss": 0.9426, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.3744050766790058, | |
| "grad_norm": 2.9230258464813232, | |
| "learning_rate": 8.979583990466454e-05, | |
| "loss": 0.9412, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.37652035959809627, | |
| "grad_norm": 2.8420345783233643, | |
| "learning_rate": 8.953878684688493e-05, | |
| "loss": 0.9279, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.3786356425171867, | |
| "grad_norm": 2.883340358734131, | |
| "learning_rate": 8.927891388315242e-05, | |
| "loss": 0.932, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.3807509254362771, | |
| "grad_norm": 2.778456926345825, | |
| "learning_rate": 8.90162395476046e-05, | |
| "loss": 0.907, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.38286620835536755, | |
| "grad_norm": 2.811483383178711, | |
| "learning_rate": 8.875078257417295e-05, | |
| "loss": 0.8524, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.38498149127445797, | |
| "grad_norm": 2.951821804046631, | |
| "learning_rate": 8.848256189524662e-05, | |
| "loss": 0.9459, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 2.9781339168548584, | |
| "learning_rate": 8.821159664032223e-05, | |
| "loss": 0.9516, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.38921205711263884, | |
| "grad_norm": 2.985658645629883, | |
| "learning_rate": 8.793790613463955e-05, | |
| "loss": 0.9337, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.39132734003172925, | |
| "grad_norm": 2.818643808364868, | |
| "learning_rate": 8.766150989780318e-05, | |
| "loss": 0.8606, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.39344262295081966, | |
| "grad_norm": 3.2023520469665527, | |
| "learning_rate": 8.738242764239046e-05, | |
| "loss": 0.9403, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.3955579058699101, | |
| "grad_norm": 3.15983510017395, | |
| "learning_rate": 8.710067927254555e-05, | |
| "loss": 0.878, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.39767318878900054, | |
| "grad_norm": 3.0788826942443848, | |
| "learning_rate": 8.681628488255986e-05, | |
| "loss": 0.8531, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.39978847170809095, | |
| "grad_norm": 3.163588285446167, | |
| "learning_rate": 8.652926475543899e-05, | |
| "loss": 1.0054, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.40190375462718136, | |
| "grad_norm": 3.0600147247314453, | |
| "learning_rate": 8.6239639361456e-05, | |
| "loss": 0.9252, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.40401903754627183, | |
| "grad_norm": 3.1859021186828613, | |
| "learning_rate": 8.594742935669165e-05, | |
| "loss": 0.9387, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.40613432046536224, | |
| "grad_norm": 3.0455939769744873, | |
| "learning_rate": 8.565265558156101e-05, | |
| "loss": 0.8999, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.40824960338445265, | |
| "grad_norm": 3.108290672302246, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.81, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.4103648863035431, | |
| "grad_norm": 3.2528982162475586, | |
| "learning_rate": 8.505550099460265e-05, | |
| "loss": 0.8264, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.41248016922263353, | |
| "grad_norm": 3.38067889213562, | |
| "learning_rate": 8.475316277183509e-05, | |
| "loss": 0.9919, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.41459545214172394, | |
| "grad_norm": 3.193894147872925, | |
| "learning_rate": 8.444834595378434e-05, | |
| "loss": 0.9069, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.4167107350608144, | |
| "grad_norm": 3.862703323364258, | |
| "learning_rate": 8.414107227998329e-05, | |
| "loss": 0.8882, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.4188260179799048, | |
| "grad_norm": 3.4907665252685547, | |
| "learning_rate": 8.383136366518788e-05, | |
| "loss": 1.0051, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.42094130089899523, | |
| "grad_norm": 3.8930423259735107, | |
| "learning_rate": 8.351924219781393e-05, | |
| "loss": 0.8381, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.4230565838180857, | |
| "grad_norm": 4.245903491973877, | |
| "learning_rate": 8.320473013836196e-05, | |
| "loss": 0.9331, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4251718667371761, | |
| "grad_norm": 2.643822431564331, | |
| "learning_rate": 8.288784991782946e-05, | |
| "loss": 0.7513, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.4272871496562665, | |
| "grad_norm": 2.622617244720459, | |
| "learning_rate": 8.256862413611113e-05, | |
| "loss": 0.7931, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.42940243257535693, | |
| "grad_norm": 3.409309148788452, | |
| "learning_rate": 8.22470755603871e-05, | |
| "loss": 1.2241, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.4315177154944474, | |
| "grad_norm": 2.4329824447631836, | |
| "learning_rate": 8.192322712349917e-05, | |
| "loss": 0.8528, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.4336329984135378, | |
| "grad_norm": 2.328763484954834, | |
| "learning_rate": 8.15971019223152e-05, | |
| "loss": 0.8701, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.4357482813326282, | |
| "grad_norm": 2.2439918518066406, | |
| "learning_rate": 8.126872321608184e-05, | |
| "loss": 0.8036, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.4378635642517187, | |
| "grad_norm": 2.3202691078186035, | |
| "learning_rate": 8.093811442476573e-05, | |
| "loss": 0.8685, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.4399788471708091, | |
| "grad_norm": 2.3466012477874756, | |
| "learning_rate": 8.060529912738315e-05, | |
| "loss": 0.8369, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.4420941300898995, | |
| "grad_norm": 2.5325000286102295, | |
| "learning_rate": 8.027030106031836e-05, | |
| "loss": 0.943, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.44420941300899, | |
| "grad_norm": 2.6998066902160645, | |
| "learning_rate": 7.993314411563075e-05, | |
| "loss": 0.9273, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4463246959280804, | |
| "grad_norm": 2.5904581546783447, | |
| "learning_rate": 7.959385233935085e-05, | |
| "loss": 0.9509, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.4484399788471708, | |
| "grad_norm": 2.5315418243408203, | |
| "learning_rate": 7.925244992976538e-05, | |
| "loss": 0.8049, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.45055526176626126, | |
| "grad_norm": 2.661184310913086, | |
| "learning_rate": 7.890896123569136e-05, | |
| "loss": 0.9386, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.4526705446853517, | |
| "grad_norm": 2.444127321243286, | |
| "learning_rate": 7.856341075473962e-05, | |
| "loss": 0.8698, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.4547858276044421, | |
| "grad_norm": 2.5407636165618896, | |
| "learning_rate": 7.821582313156764e-05, | |
| "loss": 0.8877, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.45690111052353255, | |
| "grad_norm": 2.7174148559570312, | |
| "learning_rate": 7.786622315612183e-05, | |
| "loss": 0.8976, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.45901639344262296, | |
| "grad_norm": 2.5770790576934814, | |
| "learning_rate": 7.751463576186957e-05, | |
| "loss": 0.8609, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.46113167636171337, | |
| "grad_norm": 2.5155019760131836, | |
| "learning_rate": 7.716108602402094e-05, | |
| "loss": 0.8183, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.4632469592808038, | |
| "grad_norm": 2.812934637069702, | |
| "learning_rate": 7.680559915774034e-05, | |
| "loss": 0.9306, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.46536224219989425, | |
| "grad_norm": 2.5536584854125977, | |
| "learning_rate": 7.644820051634812e-05, | |
| "loss": 0.8586, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.46747752511898466, | |
| "grad_norm": 2.4447860717773438, | |
| "learning_rate": 7.608891558951249e-05, | |
| "loss": 0.8023, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.46959280803807507, | |
| "grad_norm": 2.5778310298919678, | |
| "learning_rate": 7.572777000143145e-05, | |
| "loss": 0.8771, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.47170809095716554, | |
| "grad_norm": 2.6907410621643066, | |
| "learning_rate": 7.536478950900538e-05, | |
| "loss": 0.8514, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.47382337387625595, | |
| "grad_norm": 2.682229995727539, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8711, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.47593865679534636, | |
| "grad_norm": 2.6666316986083984, | |
| "learning_rate": 7.463342749120014e-05, | |
| "loss": 0.8428, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.4780539397144368, | |
| "grad_norm": 2.8513665199279785, | |
| "learning_rate": 7.426509812655406e-05, | |
| "loss": 0.877, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.48016922263352724, | |
| "grad_norm": 2.9401919841766357, | |
| "learning_rate": 7.389503817530905e-05, | |
| "loss": 0.9199, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.48228450555261765, | |
| "grad_norm": 2.7450366020202637, | |
| "learning_rate": 7.35232740301378e-05, | |
| "loss": 0.8136, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.4843997884717081, | |
| "grad_norm": 2.990210771560669, | |
| "learning_rate": 7.314983220525604e-05, | |
| "loss": 0.9458, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.4865150713907985, | |
| "grad_norm": 2.915475606918335, | |
| "learning_rate": 7.27747393345317e-05, | |
| "loss": 0.9262, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.48863035430988894, | |
| "grad_norm": 2.913248062133789, | |
| "learning_rate": 7.239802216958523e-05, | |
| "loss": 0.8632, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.4907456372289794, | |
| "grad_norm": 3.139481544494629, | |
| "learning_rate": 7.201970757788172e-05, | |
| "loss": 0.9177, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.4928609201480698, | |
| "grad_norm": 2.9794747829437256, | |
| "learning_rate": 7.163982254081475e-05, | |
| "loss": 0.8903, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.4949762030671602, | |
| "grad_norm": 2.8736488819122314, | |
| "learning_rate": 7.125839415178204e-05, | |
| "loss": 0.8661, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.49709148598625064, | |
| "grad_norm": 3.0208191871643066, | |
| "learning_rate": 7.087544961425317e-05, | |
| "loss": 0.8658, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.4992067689053411, | |
| "grad_norm": 2.7812483310699463, | |
| "learning_rate": 7.049101623982937e-05, | |
| "loss": 0.8354, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.5013220518244316, | |
| "grad_norm": 3.3551738262176514, | |
| "learning_rate": 7.010512144629579e-05, | |
| "loss": 0.9178, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.5034373347435219, | |
| "grad_norm": 2.927945375442505, | |
| "learning_rate": 6.971779275566593e-05, | |
| "loss": 0.9225, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.5055526176626124, | |
| "grad_norm": 3.2569127082824707, | |
| "learning_rate": 6.93290577922188e-05, | |
| "loss": 0.9018, | |
| "step": 239 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 472, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 239, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.159932941697024e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |