| { | |
| "best_metric": 0.26948797702789307, | |
| "best_model_checkpoint": "./mixtral_ozon_yand_fulldata/checkpoint-2600", | |
| "epoch": 1.9794442329653599, | |
| "eval_steps": 40, | |
| "global_step": 2600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.999999999999999e-06, | |
| "loss": 0.3913, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.1999999999999999e-05, | |
| "loss": 0.2898, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.7999999999999997e-05, | |
| "loss": 0.4246, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.3999999999999997e-05, | |
| "loss": 0.3589, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.6418, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.5999999999999994e-05, | |
| "loss": 0.4162, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.5782, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.7999999999999994e-05, | |
| "loss": 0.5758, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 0.428, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.7684, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 6.599999999999999e-05, | |
| "loss": 0.3387, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 7.199999999999999e-05, | |
| "loss": 0.8253, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 7.8e-05, | |
| "loss": 0.4063, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.8454, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.7655, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.599999999999999e-05, | |
| "loss": 0.793, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.000102, | |
| "loss": 0.5692, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00010799999999999998, | |
| "loss": 0.307, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 0.7455, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.1189, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 0.4962174594402313, | |
| "eval_runtime": 9.345, | |
| "eval_samples_per_second": 3.317, | |
| "eval_steps_per_second": 0.428, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00012599999999999997, | |
| "loss": 0.7691, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00013199999999999998, | |
| "loss": 1.0324, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000138, | |
| "loss": 0.459, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00014399999999999998, | |
| "loss": 0.766, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00015, | |
| "loss": 0.6229, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00015299999999999998, | |
| "loss": 0.3599, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000159, | |
| "loss": 0.5854, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000165, | |
| "loss": 0.725, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00017099999999999998, | |
| "loss": 0.4273, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00017699999999999997, | |
| "loss": 0.5507, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00018299999999999998, | |
| "loss": 0.3801, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00018899999999999999, | |
| "loss": 0.2834, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.000195, | |
| "loss": 0.408, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.000201, | |
| "loss": 0.3378, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00020699999999999996, | |
| "loss": 0.5074, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00021299999999999997, | |
| "loss": 0.2696, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00021899999999999998, | |
| "loss": 0.2794, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000225, | |
| "loss": 0.5831, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00023099999999999998, | |
| "loss": 0.4975, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000237, | |
| "loss": 0.7105, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.4048958718776703, | |
| "eval_runtime": 9.3516, | |
| "eval_samples_per_second": 3.315, | |
| "eval_steps_per_second": 0.428, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000243, | |
| "loss": 0.405, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000249, | |
| "loss": 0.3169, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00025499999999999996, | |
| "loss": 0.7627, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000261, | |
| "loss": 0.6131, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000267, | |
| "loss": 0.5398, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00027299999999999997, | |
| "loss": 0.6164, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000279, | |
| "loss": 0.6252, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000285, | |
| "loss": 0.7338, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00029099999999999997, | |
| "loss": 0.4631, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00029699999999999996, | |
| "loss": 0.5412, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00029988123515439427, | |
| "loss": 0.7812, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00029964370546318287, | |
| "loss": 0.3077, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00029940617577197147, | |
| "loss": 0.2692, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00029916864608076006, | |
| "loss": 0.4492, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00029893111638954866, | |
| "loss": 0.4396, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029869358669833726, | |
| "loss": 0.5285, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029845605700712586, | |
| "loss": 0.3486, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029821852731591445, | |
| "loss": 0.3178, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029798099762470305, | |
| "loss": 0.3064, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029774346793349165, | |
| "loss": 0.3184, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.4015918970108032, | |
| "eval_runtime": 9.3622, | |
| "eval_samples_per_second": 3.311, | |
| "eval_steps_per_second": 0.427, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029750593824228025, | |
| "loss": 0.3421, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029726840855106884, | |
| "loss": 0.4612, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00029703087885985744, | |
| "loss": 0.545, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00029679334916864604, | |
| "loss": 0.6146, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002965558194774347, | |
| "loss": 0.622, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00029631828978622323, | |
| "loss": 0.4487, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00029608076009501183, | |
| "loss": 0.4074, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002958432304038005, | |
| "loss": 0.6431, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.000295605700712589, | |
| "loss": 0.7612, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002953681710213776, | |
| "loss": 0.3167, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002951306413301663, | |
| "loss": 0.615, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002948931116389548, | |
| "loss": 0.7035, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00029465558194774347, | |
| "loss": 0.5687, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00029441805225653207, | |
| "loss": 0.6208, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002941805225653206, | |
| "loss": 0.4184, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00029394299287410926, | |
| "loss": 0.3979, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00029370546318289786, | |
| "loss": 0.2571, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002934679334916864, | |
| "loss": 0.4573, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00029323040380047505, | |
| "loss": 0.4242, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00029299287410926365, | |
| "loss": 0.7929, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.3873758614063263, | |
| "eval_runtime": 9.3632, | |
| "eval_samples_per_second": 3.311, | |
| "eval_steps_per_second": 0.427, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002927553444180522, | |
| "loss": 0.2585, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00029251781472684085, | |
| "loss": 0.2083, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00029228028503562944, | |
| "loss": 0.351, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000292042755344418, | |
| "loss": 0.5127, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00029180522565320664, | |
| "loss": 0.4841, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00029156769596199524, | |
| "loss": 0.3963, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00029133016627078383, | |
| "loss": 0.7995, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00029109263657957243, | |
| "loss": 0.3502, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00029085510688836103, | |
| "loss": 0.4217, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002906175771971496, | |
| "loss": 0.3672, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002903800475059382, | |
| "loss": 1.1592, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002901425178147268, | |
| "loss": 0.6476, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002899049881235154, | |
| "loss": 0.5069, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.000289667458432304, | |
| "loss": 0.3885, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002894299287410926, | |
| "loss": 0.8418, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002891923990498812, | |
| "loss": 0.2927, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002889548693586698, | |
| "loss": 0.4557, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002887173396674584, | |
| "loss": 0.6756, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.000288479809976247, | |
| "loss": 0.682, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002882422802850356, | |
| "loss": 0.5531, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.36585813760757446, | |
| "eval_runtime": 9.3463, | |
| "eval_samples_per_second": 3.317, | |
| "eval_steps_per_second": 0.428, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002880047505938242, | |
| "loss": 0.2401, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002877672209026128, | |
| "loss": 0.2941, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002875296912114014, | |
| "loss": 0.6721, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00028729216152019, | |
| "loss": 0.311, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002870546318289786, | |
| "loss": 0.1646, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002868171021377672, | |
| "loss": 0.2189, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002865795724465558, | |
| "loss": 0.2905, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002863420427553444, | |
| "loss": 0.4144, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000286104513064133, | |
| "loss": 0.4271, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002858669833729216, | |
| "loss": 0.5791, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00028562945368171017, | |
| "loss": 0.3899, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00028539192399049877, | |
| "loss": 0.4753, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00028515439429928737, | |
| "loss": 0.4351, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00028491686460807597, | |
| "loss": 0.4096, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002846793349168646, | |
| "loss": 0.7996, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00028444180522565316, | |
| "loss": 0.6729, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00028420427553444176, | |
| "loss": 0.7239, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002839667458432304, | |
| "loss": 0.7276, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00028372921615201895, | |
| "loss": 0.4878, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00028349168646080755, | |
| "loss": 0.6066, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.350250780582428, | |
| "eval_runtime": 9.3481, | |
| "eval_samples_per_second": 3.316, | |
| "eval_steps_per_second": 0.428, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002832541567695962, | |
| "loss": 0.3477, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002830166270783848, | |
| "loss": 0.5446, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00028277909738717334, | |
| "loss": 0.6981, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.000282541567695962, | |
| "loss": 0.5214, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002823040380047506, | |
| "loss": 0.5459, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00028206650831353913, | |
| "loss": 0.2052, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002818289786223278, | |
| "loss": 0.5407, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002815914489311164, | |
| "loss": 0.3608, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.000281353919239905, | |
| "loss": 0.2969, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002811163895486936, | |
| "loss": 0.529, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002809976247030879, | |
| "loss": 0.5643, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002807600950118765, | |
| "loss": 0.3035, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00028052256532066507, | |
| "loss": 0.7444, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00028028503562945367, | |
| "loss": 0.4515, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028004750593824227, | |
| "loss": 0.4964, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00027980997624703086, | |
| "loss": 0.2412, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00027957244655581946, | |
| "loss": 0.3906, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00027933491686460806, | |
| "loss": 0.2199, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00027909738717339666, | |
| "loss": 0.7144, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00027885985748218525, | |
| "loss": 0.2723, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.3972644805908203, | |
| "eval_runtime": 9.3485, | |
| "eval_samples_per_second": 3.316, | |
| "eval_steps_per_second": 0.428, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00027862232779097385, | |
| "loss": 0.654, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027838479809976245, | |
| "loss": 0.428, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027814726840855105, | |
| "loss": 0.465, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027790973871733964, | |
| "loss": 0.5494, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027767220902612824, | |
| "loss": 0.4662, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027743467933491684, | |
| "loss": 0.4589, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027719714964370544, | |
| "loss": 0.504, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00027695961995249403, | |
| "loss": 0.6749, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00027672209026128263, | |
| "loss": 0.5869, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00027648456057007123, | |
| "loss": 0.6689, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002762470308788598, | |
| "loss": 0.2837, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002760095011876484, | |
| "loss": 0.4046, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000275771971496437, | |
| "loss": 0.17, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002755344418052256, | |
| "loss": 0.4964, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002752969121140142, | |
| "loss": 0.5627, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002750593824228028, | |
| "loss": 0.2281, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002748218527315914, | |
| "loss": 0.3021, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00027458432304038, | |
| "loss": 0.4209, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00027434679334916866, | |
| "loss": 0.2124, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002741092636579572, | |
| "loss": 0.141, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.38411885499954224, | |
| "eval_runtime": 9.3633, | |
| "eval_samples_per_second": 3.311, | |
| "eval_steps_per_second": 0.427, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002738717339667458, | |
| "loss": 0.8166, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00027363420427553445, | |
| "loss": 0.4706, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.000273396674584323, | |
| "loss": 0.1793, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002731591448931116, | |
| "loss": 0.342, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00027292161520190024, | |
| "loss": 0.6983, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002726840855106888, | |
| "loss": 0.3803, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002724465558194774, | |
| "loss": 0.4624, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00027220902612826604, | |
| "loss": 0.664, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002719714964370546, | |
| "loss": 0.2172, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002717339667458432, | |
| "loss": 0.8086, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00027149643705463183, | |
| "loss": 0.7088, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00027125890736342037, | |
| "loss": 0.5299, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.000271021377672209, | |
| "loss": 0.5036, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002707838479809976, | |
| "loss": 0.5713, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00027054631828978616, | |
| "loss": 0.7754, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002703087885985748, | |
| "loss": 0.1775, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002700712589073634, | |
| "loss": 0.2667, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00026983372921615196, | |
| "loss": 0.4825, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002695961995249406, | |
| "loss": 0.5809, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002693586698337292, | |
| "loss": 0.2108, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.3653150200843811, | |
| "eval_runtime": 9.3669, | |
| "eval_samples_per_second": 3.31, | |
| "eval_steps_per_second": 0.427, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002691211401425178, | |
| "loss": 0.3851, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002688836104513064, | |
| "loss": 0.6308, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.000268646080760095, | |
| "loss": 0.4483, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002684085510688836, | |
| "loss": 0.2517, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002681710213776722, | |
| "loss": 0.297, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002679334916864608, | |
| "loss": 0.4035, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002676959619952494, | |
| "loss": 0.3484, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000267458432304038, | |
| "loss": 0.3901, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002672209026128266, | |
| "loss": 0.4338, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002669833729216152, | |
| "loss": 0.1864, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002667458432304038, | |
| "loss": 0.3032, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002665083135391924, | |
| "loss": 0.4283, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00026627078384798097, | |
| "loss": 0.5854, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00026603325415676957, | |
| "loss": 0.4476, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00026579572446555817, | |
| "loss": 0.6709, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00026555819477434676, | |
| "loss": 0.8986, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00026532066508313536, | |
| "loss": 0.6288, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00026508313539192396, | |
| "loss": 0.6761, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00026484560570071256, | |
| "loss": 0.9205, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00026460807600950115, | |
| "loss": 0.8357, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.37132084369659424, | |
| "eval_runtime": 9.3788, | |
| "eval_samples_per_second": 3.305, | |
| "eval_steps_per_second": 0.426, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00026437054631828975, | |
| "loss": 0.3183, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00026413301662707835, | |
| "loss": 0.4029, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00026389548693586695, | |
| "loss": 0.2473, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00026365795724465554, | |
| "loss": 0.3392, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00026342042755344414, | |
| "loss": 0.152, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00026318289786223274, | |
| "loss": 0.7606, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002629453681710214, | |
| "loss": 0.3145, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00026270783847980993, | |
| "loss": 0.4427, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00026247030878859853, | |
| "loss": 0.3433, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002622327790973872, | |
| "loss": 0.3561, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002619952494061757, | |
| "loss": 0.1787, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002617577197149643, | |
| "loss": 0.4031, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.000261520190023753, | |
| "loss": 0.2517, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002612826603325415, | |
| "loss": 0.4073, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00026104513064133017, | |
| "loss": 0.285, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00026080760095011877, | |
| "loss": 0.7348, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002605700712589073, | |
| "loss": 0.3321, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00026033254156769596, | |
| "loss": 0.3248, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00026009501187648456, | |
| "loss": 0.3762, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002598574821852731, | |
| "loss": 0.4617, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.3326135277748108, | |
| "eval_runtime": 9.3635, | |
| "eval_samples_per_second": 3.311, | |
| "eval_steps_per_second": 0.427, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00025961995249406175, | |
| "loss": 0.5431, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00025938242280285035, | |
| "loss": 0.461, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002591448931116389, | |
| "loss": 0.7486, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00025890736342042755, | |
| "loss": 1.0537, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00025866983372921614, | |
| "loss": 0.3911, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002584323040380047, | |
| "loss": 0.2827, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00025819477434679334, | |
| "loss": 0.2125, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00025795724465558194, | |
| "loss": 0.5291, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00025771971496437053, | |
| "loss": 0.4086, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00025748218527315913, | |
| "loss": 0.3186, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00025724465558194773, | |
| "loss": 0.4514, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002570071258907363, | |
| "loss": 0.3062, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002567695961995249, | |
| "loss": 0.4006, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002565320665083135, | |
| "loss": 0.5599, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002562945368171021, | |
| "loss": 0.209, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002560570071258907, | |
| "loss": 0.4061, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002558194774346793, | |
| "loss": 0.509, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002555819477434679, | |
| "loss": 0.2212, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002553444180522565, | |
| "loss": 0.3223, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002551068883610451, | |
| "loss": 0.3705, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.3311932384967804, | |
| "eval_runtime": 9.3611, | |
| "eval_samples_per_second": 3.312, | |
| "eval_steps_per_second": 0.427, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002548693586698337, | |
| "loss": 0.3872, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002546318289786223, | |
| "loss": 0.357, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002543942992874109, | |
| "loss": 0.394, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002541567695961995, | |
| "loss": 0.6947, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002539192399049881, | |
| "loss": 0.587, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002536817102137767, | |
| "loss": 0.3654, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002534441805225653, | |
| "loss": 0.4124, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002532066508313539, | |
| "loss": 0.5718, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002529691211401425, | |
| "loss": 0.5408, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002527315914489311, | |
| "loss": 0.7847, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002524940617577197, | |
| "loss": 0.2047, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002522565320665083, | |
| "loss": 0.44, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00025201900237529687, | |
| "loss": 0.2529, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00025178147268408547, | |
| "loss": 0.5779, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00025154394299287407, | |
| "loss": 0.3368, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00025130641330166267, | |
| "loss": 0.7092, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002510688836104513, | |
| "loss": 0.2749, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00025083135391923986, | |
| "loss": 0.5612, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00025059382422802846, | |
| "loss": 0.2697, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002503562945368171, | |
| "loss": 0.3866, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.3422822952270508, | |
| "eval_runtime": 9.3706, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.427, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00025011876484560565, | |
| "loss": 0.1455, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00024988123515439425, | |
| "loss": 0.363, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002496437054631829, | |
| "loss": 0.3668, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002494061757719715, | |
| "loss": 0.1978, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00024916864608076004, | |
| "loss": 0.6822, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002489311163895487, | |
| "loss": 0.277, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002486935866983373, | |
| "loss": 0.578, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00024845605700712583, | |
| "loss": 0.335, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002482185273159145, | |
| "loss": 0.3037, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002479809976247031, | |
| "loss": 0.7765, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002477434679334917, | |
| "loss": 0.3561, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002475059382422803, | |
| "loss": 0.7907, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002472684085510689, | |
| "loss": 0.3645, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002470308788598575, | |
| "loss": 0.4742, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00024679334916864607, | |
| "loss": 0.4835, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00024655581947743467, | |
| "loss": 0.5613, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00024631828978622327, | |
| "loss": 0.1417, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00024608076009501186, | |
| "loss": 0.6417, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00024584323040380046, | |
| "loss": 0.0816, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00024560570071258906, | |
| "loss": 0.3542, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 0.3095850348472595, | |
| "eval_runtime": 9.3773, | |
| "eval_samples_per_second": 3.306, | |
| "eval_steps_per_second": 0.427, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00024536817102137766, | |
| "loss": 0.4251, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00024513064133016625, | |
| "loss": 0.1428, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00024489311163895485, | |
| "loss": 0.2823, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00024465558194774345, | |
| "loss": 0.1806, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00024441805225653204, | |
| "loss": 0.1927, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00024418052256532064, | |
| "loss": 0.5064, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00024394299287410924, | |
| "loss": 0.8591, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00024370546318289786, | |
| "loss": 0.2617, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00024346793349168643, | |
| "loss": 0.3761, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00024323040380047503, | |
| "loss": 0.4794, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00024299287410926366, | |
| "loss": 0.5079, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00024275534441805223, | |
| "loss": 0.5622, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00024251781472684082, | |
| "loss": 0.3593, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00024228028503562945, | |
| "loss": 0.5165, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00024204275534441802, | |
| "loss": 0.2907, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00024180522565320662, | |
| "loss": 0.6821, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00024156769596199524, | |
| "loss": 0.6338, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002413301662707838, | |
| "loss": 0.3202, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00024109263657957244, | |
| "loss": 0.4335, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00024085510688836103, | |
| "loss": 1.038, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.32087576389312744, | |
| "eval_runtime": 9.3801, | |
| "eval_samples_per_second": 3.305, | |
| "eval_steps_per_second": 0.426, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002406175771971496, | |
| "loss": 0.3078, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00024038004750593823, | |
| "loss": 0.1842, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00024014251781472683, | |
| "loss": 0.2668, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002399049881235154, | |
| "loss": 0.5238, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00023966745843230402, | |
| "loss": 0.1912, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00023942992874109262, | |
| "loss": 0.3954, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002391923990498812, | |
| "loss": 0.4588, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002389548693586698, | |
| "loss": 0.2253, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002387173396674584, | |
| "loss": 0.3087, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00023847980997624698, | |
| "loss": 0.3133, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002382422802850356, | |
| "loss": 0.2039, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002380047505938242, | |
| "loss": 0.3007, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00023776722090261283, | |
| "loss": 0.3728, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002375296912114014, | |
| "loss": 0.428, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00023729216152019, | |
| "loss": 0.4863, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00023705463182897862, | |
| "loss": 0.3753, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002368171021377672, | |
| "loss": 0.453, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002365795724465558, | |
| "loss": 0.607, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002363420427553444, | |
| "loss": 0.6307, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00023610451306413298, | |
| "loss": 0.2342, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.3386555314064026, | |
| "eval_runtime": 9.3562, | |
| "eval_samples_per_second": 3.313, | |
| "eval_steps_per_second": 0.428, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00023586698337292158, | |
| "loss": 0.57, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002356294536817102, | |
| "loss": 0.5011, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00023539192399049877, | |
| "loss": 0.3662, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00023515439429928737, | |
| "loss": 0.6828, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.000234916864608076, | |
| "loss": 0.8893, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002346793349168646, | |
| "loss": 0.2502, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002344418052256532, | |
| "loss": 0.2193, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002342042755344418, | |
| "loss": 0.2968, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00023396674584323039, | |
| "loss": 0.3268, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00023372921615201898, | |
| "loss": 0.2211, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00023349168646080758, | |
| "loss": 0.2749, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00023325415676959618, | |
| "loss": 0.1145, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00023301662707838478, | |
| "loss": 0.176, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00023277909738717337, | |
| "loss": 0.1624, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00023254156769596197, | |
| "loss": 0.3386, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00023230403800475057, | |
| "loss": 0.2456, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00023206650831353917, | |
| "loss": 0.3883, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00023182897862232776, | |
| "loss": 0.2532, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002315914489311164, | |
| "loss": 0.3974, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00023135391923990496, | |
| "loss": 0.2916, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.333130806684494, | |
| "eval_runtime": 9.3704, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.427, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00023111638954869358, | |
| "loss": 0.4512, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00023087885985748218, | |
| "loss": 0.4993, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00023064133016627075, | |
| "loss": 0.4243, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00023040380047505938, | |
| "loss": 0.6631, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00023016627078384797, | |
| "loss": 0.445, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00022992874109263654, | |
| "loss": 0.5938, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00022969121140142517, | |
| "loss": 0.2758, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00022945368171021376, | |
| "loss": 0.5372, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00022921615201900234, | |
| "loss": 0.5573, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00022897862232779096, | |
| "loss": 0.4405, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00022874109263657956, | |
| "loss": 0.3267, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00022850356294536813, | |
| "loss": 0.4658, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00022826603325415675, | |
| "loss": 0.2937, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00022802850356294535, | |
| "loss": 0.4125, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00022779097387173397, | |
| "loss": 0.6237, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00022755344418052254, | |
| "loss": 0.4166, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00022731591448931114, | |
| "loss": 0.1716, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00022707838479809977, | |
| "loss": 0.4588, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00022684085510688834, | |
| "loss": 0.3804, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00022660332541567693, | |
| "loss": 0.3955, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.30690163373947144, | |
| "eval_runtime": 9.3841, | |
| "eval_samples_per_second": 3.303, | |
| "eval_steps_per_second": 0.426, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00022636579572446556, | |
| "loss": 0.2965, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00022612826603325413, | |
| "loss": 0.3147, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00022589073634204273, | |
| "loss": 0.3258, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00022565320665083135, | |
| "loss": 0.4931, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00022541567695961992, | |
| "loss": 0.3053, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00022517814726840852, | |
| "loss": 0.3506, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00022494061757719714, | |
| "loss": 0.3847, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002247030878859857, | |
| "loss": 0.654, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00022446555819477434, | |
| "loss": 0.4389, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00022422802850356294, | |
| "loss": 0.5818, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002239904988123515, | |
| "loss": 0.2825, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00022375296912114013, | |
| "loss": 0.3545, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00022351543942992873, | |
| "loss": 0.5226, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002232779097387173, | |
| "loss": 0.3422, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00022304038004750592, | |
| "loss": 0.4571, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00022280285035629452, | |
| "loss": 0.3552, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002225653206650831, | |
| "loss": 0.3883, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00022232779097387172, | |
| "loss": 0.0943, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002220902612826603, | |
| "loss": 0.339, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00022185273159144888, | |
| "loss": 0.4682, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.30051201581954956, | |
| "eval_runtime": 9.37, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.427, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002216152019002375, | |
| "loss": 0.1816, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002213776722090261, | |
| "loss": 0.1316, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00022114014251781473, | |
| "loss": 0.3573, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002209026128266033, | |
| "loss": 0.2577, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002206650831353919, | |
| "loss": 0.3644, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00022042755344418052, | |
| "loss": 0.3935, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002201900237529691, | |
| "loss": 0.3146, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002199524940617577, | |
| "loss": 0.1429, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00021971496437054631, | |
| "loss": 0.5873, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00021947743467933488, | |
| "loss": 0.3515, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00021923990498812348, | |
| "loss": 0.2557, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002190023752969121, | |
| "loss": 0.2107, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00021876484560570068, | |
| "loss": 0.2708, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00021852731591448927, | |
| "loss": 0.6583, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002182897862232779, | |
| "loss": 0.4267, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002180522565320665, | |
| "loss": 0.3937, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002178147268408551, | |
| "loss": 0.5279, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002175771971496437, | |
| "loss": 0.3597, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002173396674584323, | |
| "loss": 0.551, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00021710213776722089, | |
| "loss": 0.5738, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.3106914162635803, | |
| "eval_runtime": 9.3568, | |
| "eval_samples_per_second": 3.313, | |
| "eval_steps_per_second": 0.427, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00021686460807600948, | |
| "loss": 0.3408, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00021662707838479808, | |
| "loss": 0.2379, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00021638954869358668, | |
| "loss": 0.3936, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00021615201900237528, | |
| "loss": 0.4368, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00021591448931116387, | |
| "loss": 0.4031, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00021567695961995247, | |
| "loss": 0.3129, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00021543942992874107, | |
| "loss": 0.3011, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00021520190023752967, | |
| "loss": 0.5397, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002149643705463183, | |
| "loss": 0.2948, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00021472684085510686, | |
| "loss": 0.3202, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00021448931116389548, | |
| "loss": 0.5377, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00021425178147268408, | |
| "loss": 0.313, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00021401425178147265, | |
| "loss": 0.2712, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00021377672209026128, | |
| "loss": 0.2576, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00021353919239904987, | |
| "loss": 0.2354, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00021330166270783844, | |
| "loss": 0.2094, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00021306413301662707, | |
| "loss": 0.2447, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00021282660332541567, | |
| "loss": 0.5329, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00021258907363420424, | |
| "loss": 0.7861, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00021235154394299286, | |
| "loss": 0.5189, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.3142649531364441, | |
| "eval_runtime": 9.3636, | |
| "eval_samples_per_second": 3.311, | |
| "eval_steps_per_second": 0.427, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00021211401425178146, | |
| "loss": 0.496, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00021187648456057003, | |
| "loss": 0.5717, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00021163895486935865, | |
| "loss": 0.6914, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00021140142517814725, | |
| "loss": 0.4288, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00021116389548693588, | |
| "loss": 0.4344, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00021092636579572445, | |
| "loss": 0.3406, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00021068883610451304, | |
| "loss": 0.4395, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00021045130641330167, | |
| "loss": 0.4019, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00021021377672209024, | |
| "loss": 0.4065, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00020997624703087884, | |
| "loss": 0.4056, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00020973871733966746, | |
| "loss": 0.293, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00020950118764845603, | |
| "loss": 0.178, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00020926365795724463, | |
| "loss": 0.3286, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00020902612826603325, | |
| "loss": 0.3743, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00020878859857482182, | |
| "loss": 0.1201, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00020855106888361042, | |
| "loss": 0.3745, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00020831353919239905, | |
| "loss": 0.1914, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00020807600950118762, | |
| "loss": 0.156, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00020783847980997624, | |
| "loss": 0.4407, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00020760095011876484, | |
| "loss": 0.2494, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.30005908012390137, | |
| "eval_runtime": 9.3677, | |
| "eval_samples_per_second": 3.309, | |
| "eval_steps_per_second": 0.427, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002073634204275534, | |
| "loss": 0.3569, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00020712589073634203, | |
| "loss": 0.5322, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00020688836104513063, | |
| "loss": 0.3475, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0002066508313539192, | |
| "loss": 0.7766, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00020641330166270782, | |
| "loss": 0.5736, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00020617577197149642, | |
| "loss": 0.7265, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.000205938242280285, | |
| "loss": 0.6645, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00020570071258907362, | |
| "loss": 0.5939, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00020546318289786221, | |
| "loss": 0.663, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00020522565320665078, | |
| "loss": 0.426, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002049881235154394, | |
| "loss": 0.5316, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.000204750593824228, | |
| "loss": 0.3482, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00020451306413301663, | |
| "loss": 0.2285, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002042755344418052, | |
| "loss": 0.3939, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002040380047505938, | |
| "loss": 0.2218, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00020380047505938242, | |
| "loss": 0.6687, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.000203562945368171, | |
| "loss": 0.3438, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002033254156769596, | |
| "loss": 0.4643, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00020308788598574822, | |
| "loss": 0.3205, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00020285035629453679, | |
| "loss": 0.2342, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.3056817352771759, | |
| "eval_runtime": 9.3743, | |
| "eval_samples_per_second": 3.307, | |
| "eval_steps_per_second": 0.427, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00020261282660332538, | |
| "loss": 0.6588, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.000202375296912114, | |
| "loss": 0.2558, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00020213776722090258, | |
| "loss": 0.3291, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00020190023752969118, | |
| "loss": 0.2376, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002016627078384798, | |
| "loss": 0.3169, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002014251781472684, | |
| "loss": 0.5664, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.000201187648456057, | |
| "loss": 0.5703, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002009501187648456, | |
| "loss": 0.3994, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002007125890736342, | |
| "loss": 0.4961, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002004750593824228, | |
| "loss": 0.2799, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00020023752969121139, | |
| "loss": 0.6838, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00019999999999999998, | |
| "loss": 0.7514, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00019976247030878858, | |
| "loss": 0.3226, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00019952494061757718, | |
| "loss": 0.4376, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00019928741092636577, | |
| "loss": 0.3865, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00019904988123515437, | |
| "loss": 0.2718, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00019881235154394297, | |
| "loss": 0.3613, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00019857482185273157, | |
| "loss": 0.1676, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0001983372921615202, | |
| "loss": 0.1592, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00019809976247030876, | |
| "loss": 0.1569, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.2912062406539917, | |
| "eval_runtime": 9.3645, | |
| "eval_samples_per_second": 3.31, | |
| "eval_steps_per_second": 0.427, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0001978622327790974, | |
| "loss": 0.2437, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00019762470308788598, | |
| "loss": 0.3692, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00019738717339667455, | |
| "loss": 0.4776, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00019714964370546318, | |
| "loss": 0.3758, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00019691211401425178, | |
| "loss": 0.3706, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00019667458432304035, | |
| "loss": 0.3859, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00019643705463182897, | |
| "loss": 0.3068, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00019619952494061757, | |
| "loss": 0.3434, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00019596199524940614, | |
| "loss": 0.251, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00019572446555819476, | |
| "loss": 0.3743, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00019548693586698336, | |
| "loss": 0.3823, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00019524940617577193, | |
| "loss": 0.5968, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00019501187648456056, | |
| "loss": 0.3111, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00019477434679334915, | |
| "loss": 0.4698, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00019453681710213778, | |
| "loss": 0.8493, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00019429928741092635, | |
| "loss": 0.3721, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00019406175771971495, | |
| "loss": 0.5048, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00019382422802850357, | |
| "loss": 0.8067, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00019358669833729214, | |
| "loss": 0.7082, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00019334916864608074, | |
| "loss": 0.3908, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.29726114869117737, | |
| "eval_runtime": 9.3689, | |
| "eval_samples_per_second": 3.309, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00019311163895486936, | |
| "loss": 0.1999, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00019287410926365793, | |
| "loss": 0.4173, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00019263657957244653, | |
| "loss": 0.4925, | |
| "step": 1006 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00019239904988123515, | |
| "loss": 0.3295, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00019216152019002372, | |
| "loss": 0.8868, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00019192399049881232, | |
| "loss": 0.2795, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00019168646080760095, | |
| "loss": 0.2334, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00019144893111638952, | |
| "loss": 0.3648, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00019121140142517814, | |
| "loss": 0.5019, | |
| "step": 1018 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00019097387173396674, | |
| "loss": 0.6776, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001907363420427553, | |
| "loss": 0.5213, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00019049881235154393, | |
| "loss": 0.2362, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00019026128266033253, | |
| "loss": 0.254, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001900237529691211, | |
| "loss": 0.3561, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00018978622327790973, | |
| "loss": 0.3274, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00018954869358669832, | |
| "loss": 0.5482, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001893111638954869, | |
| "loss": 0.1905, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00018907363420427552, | |
| "loss": 0.7008, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00018883610451306412, | |
| "loss": 0.4091, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001885985748218527, | |
| "loss": 0.299, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.3022250831127167, | |
| "eval_runtime": 9.3563, | |
| "eval_samples_per_second": 3.313, | |
| "eval_steps_per_second": 0.428, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001883610451306413, | |
| "loss": 0.377, | |
| "step": 1042 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001881235154394299, | |
| "loss": 0.4336, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00018788598574821853, | |
| "loss": 0.3129, | |
| "step": 1046 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001876484560570071, | |
| "loss": 0.2832, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001874109263657957, | |
| "loss": 0.4134, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00018717339667458433, | |
| "loss": 0.3931, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001869358669833729, | |
| "loss": 0.2382, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001866983372921615, | |
| "loss": 0.6188, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00018646080760095012, | |
| "loss": 0.291, | |
| "step": 1058 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0001862232779097387, | |
| "loss": 0.5257, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00018598574821852729, | |
| "loss": 0.2344, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0001857482185273159, | |
| "loss": 0.459, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00018551068883610448, | |
| "loss": 0.2123, | |
| "step": 1066 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00018527315914489308, | |
| "loss": 0.1802, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0001850356294536817, | |
| "loss": 0.2008, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001847980997624703, | |
| "loss": 0.4117, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001845605700712589, | |
| "loss": 0.3687, | |
| "step": 1074 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001843230403800475, | |
| "loss": 0.4176, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001840855106888361, | |
| "loss": 0.1763, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001838479809976247, | |
| "loss": 0.4687, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.28451159596443176, | |
| "eval_runtime": 9.3666, | |
| "eval_samples_per_second": 3.31, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001836104513064133, | |
| "loss": 0.3777, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00018337292161520188, | |
| "loss": 0.5257, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00018313539192399048, | |
| "loss": 0.309, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00018289786223277908, | |
| "loss": 0.3204, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00018266033254156768, | |
| "loss": 0.3176, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00018242280285035627, | |
| "loss": 0.4988, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00018218527315914487, | |
| "loss": 0.5506, | |
| "step": 1094 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00018194774346793347, | |
| "loss": 0.5344, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0001817102137767221, | |
| "loss": 0.291, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00018147268408551066, | |
| "loss": 0.7219, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0001812351543942993, | |
| "loss": 0.2022, | |
| "step": 1102 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00018099762470308789, | |
| "loss": 0.3979, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00018076009501187646, | |
| "loss": 0.2127, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00018052256532066508, | |
| "loss": 0.1794, | |
| "step": 1108 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00018028503562945368, | |
| "loss": 0.2382, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00018004750593824225, | |
| "loss": 0.1974, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00017980997624703087, | |
| "loss": 0.2626, | |
| "step": 1114 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00017957244655581947, | |
| "loss": 0.1322, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00017933491686460804, | |
| "loss": 0.4259, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00017909738717339667, | |
| "loss": 0.5042, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.28996601700782776, | |
| "eval_runtime": 9.3713, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00017885985748218526, | |
| "loss": 0.2776, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00017862232779097383, | |
| "loss": 0.3122, | |
| "step": 1124 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00017838479809976246, | |
| "loss": 0.3593, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00017814726840855106, | |
| "loss": 0.2119, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00017790973871733968, | |
| "loss": 0.3225, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00017767220902612825, | |
| "loss": 0.4566, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00017743467933491685, | |
| "loss": 0.2634, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00017719714964370547, | |
| "loss": 0.3555, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00017695961995249404, | |
| "loss": 0.6081, | |
| "step": 1138 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00017672209026128264, | |
| "loss": 0.6723, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00017648456057007126, | |
| "loss": 0.4368, | |
| "step": 1142 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00017624703087885983, | |
| "loss": 0.3456, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00017600950118764843, | |
| "loss": 0.5196, | |
| "step": 1146 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00017577197149643706, | |
| "loss": 0.6309, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00017553444180522563, | |
| "loss": 0.3567, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00017529691211401422, | |
| "loss": 0.1788, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00017505938242280285, | |
| "loss": 0.3107, | |
| "step": 1154 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00017482185273159142, | |
| "loss": 0.2521, | |
| "step": 1156 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00017458432304038004, | |
| "loss": 0.4581, | |
| "step": 1158 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00017434679334916864, | |
| "loss": 0.3965, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.29988202452659607, | |
| "eval_runtime": 9.3736, | |
| "eval_samples_per_second": 3.307, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0001741092636579572, | |
| "loss": 0.3428, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00017387173396674584, | |
| "loss": 0.201, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00017363420427553443, | |
| "loss": 0.0984, | |
| "step": 1166 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.000173396674584323, | |
| "loss": 0.2268, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00017315914489311163, | |
| "loss": 0.3022, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00017292161520190023, | |
| "loss": 0.1228, | |
| "step": 1172 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0001726840855106888, | |
| "loss": 0.3308, | |
| "step": 1174 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00017244655581947742, | |
| "loss": 0.2718, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00017220902612826602, | |
| "loss": 0.3271, | |
| "step": 1178 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0001719714964370546, | |
| "loss": 0.695, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0001717339667458432, | |
| "loss": 0.3261, | |
| "step": 1182 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0001714964370546318, | |
| "loss": 0.3856, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00017125890736342043, | |
| "loss": 0.6406, | |
| "step": 1186 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.000171021377672209, | |
| "loss": 0.4738, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0001707838479809976, | |
| "loss": 0.4359, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00017054631828978623, | |
| "loss": 0.47, | |
| "step": 1192 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0001703087885985748, | |
| "loss": 0.4494, | |
| "step": 1194 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0001700712589073634, | |
| "loss": 0.3126, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00016983372921615202, | |
| "loss": 0.6054, | |
| "step": 1198 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0001695961995249406, | |
| "loss": 0.5807, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 0.2884325683116913, | |
| "eval_runtime": 9.37, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0001693586698337292, | |
| "loss": 0.2636, | |
| "step": 1202 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0001691211401425178, | |
| "loss": 0.3178, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00016888361045130638, | |
| "loss": 0.2728, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00016864608076009498, | |
| "loss": 0.2114, | |
| "step": 1208 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0001684085510688836, | |
| "loss": 0.239, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0001681710213776722, | |
| "loss": 0.3943, | |
| "step": 1212 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0001679334916864608, | |
| "loss": 0.3986, | |
| "step": 1214 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0001676959619952494, | |
| "loss": 0.4496, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.000167458432304038, | |
| "loss": 0.212, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0001672209026128266, | |
| "loss": 0.3403, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0001669833729216152, | |
| "loss": 0.5408, | |
| "step": 1222 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00016674584323040379, | |
| "loss": 0.1845, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00016650831353919238, | |
| "loss": 0.7421, | |
| "step": 1226 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00016627078384798098, | |
| "loss": 0.5108, | |
| "step": 1228 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00016603325415676958, | |
| "loss": 0.2919, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00016579572446555818, | |
| "loss": 0.6641, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00016555819477434677, | |
| "loss": 0.3638, | |
| "step": 1234 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00016532066508313537, | |
| "loss": 0.4661, | |
| "step": 1236 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.000165083135391924, | |
| "loss": 0.2664, | |
| "step": 1238 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00016484560570071257, | |
| "loss": 0.7164, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.2925778031349182, | |
| "eval_runtime": 9.3647, | |
| "eval_samples_per_second": 3.31, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0001646080760095012, | |
| "loss": 0.6013, | |
| "step": 1242 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0001643705463182898, | |
| "loss": 0.3291, | |
| "step": 1244 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00016413301662707836, | |
| "loss": 0.4696, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00016389548693586698, | |
| "loss": 0.5757, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00016365795724465558, | |
| "loss": 0.44, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00016342042755344415, | |
| "loss": 0.1995, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00016318289786223277, | |
| "loss": 0.2627, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016294536817102137, | |
| "loss": 0.2906, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016270783847980994, | |
| "loss": 0.6191, | |
| "step": 1258 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016247030878859857, | |
| "loss": 0.1564, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016223277909738716, | |
| "loss": 0.2257, | |
| "step": 1262 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016199524940617573, | |
| "loss": 0.224, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016175771971496436, | |
| "loss": 0.2073, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016152019002375296, | |
| "loss": 0.4296, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016128266033254158, | |
| "loss": 0.2992, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016104513064133015, | |
| "loss": 0.5368, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016080760095011875, | |
| "loss": 0.395, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016057007125890737, | |
| "loss": 0.5972, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016033254156769594, | |
| "loss": 0.3517, | |
| "step": 1278 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016009501187648454, | |
| "loss": 0.6165, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.30172425508499146, | |
| "eval_runtime": 9.3735, | |
| "eval_samples_per_second": 3.307, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015985748218527317, | |
| "loss": 0.2574, | |
| "step": 1282 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015961995249406174, | |
| "loss": 0.5882, | |
| "step": 1284 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015938242280285033, | |
| "loss": 0.2955, | |
| "step": 1286 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015914489311163896, | |
| "loss": 0.573, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015890736342042753, | |
| "loss": 0.5312, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00015866983372921613, | |
| "loss": 0.5778, | |
| "step": 1292 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015843230403800475, | |
| "loss": 0.5417, | |
| "step": 1294 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015819477434679332, | |
| "loss": 0.542, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015795724465558195, | |
| "loss": 0.6474, | |
| "step": 1298 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015771971496437054, | |
| "loss": 0.6188, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0001574821852731591, | |
| "loss": 0.3035, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015724465558194774, | |
| "loss": 0.3204, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00015700712589073634, | |
| "loss": 0.1779, | |
| "step": 1306 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001567695961995249, | |
| "loss": 0.5388, | |
| "step": 1308 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00015653206650831353, | |
| "loss": 0.3138, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00015629453681710213, | |
| "loss": 0.2565, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001560570071258907, | |
| "loss": 0.2422, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00015581947743467932, | |
| "loss": 0.2166, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00015558194774346792, | |
| "loss": 0.6993, | |
| "step": 1318 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001553444180522565, | |
| "loss": 0.2133, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.29531198740005493, | |
| "eval_runtime": 9.3723, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00015510688836104511, | |
| "loss": 0.2226, | |
| "step": 1322 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0001548693586698337, | |
| "loss": 0.2377, | |
| "step": 1324 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00015463182897862234, | |
| "loss": 0.2588, | |
| "step": 1326 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0001543942992874109, | |
| "loss": 0.1465, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0001541567695961995, | |
| "loss": 0.1348, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00015391923990498813, | |
| "loss": 0.2277, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0001536817102137767, | |
| "loss": 0.2207, | |
| "step": 1334 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0001534441805225653, | |
| "loss": 0.1533, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00015320665083135392, | |
| "loss": 0.138, | |
| "step": 1338 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0001529691211401425, | |
| "loss": 0.304, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0001527315914489311, | |
| "loss": 0.1605, | |
| "step": 1342 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00015249406175771971, | |
| "loss": 0.1622, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00015225653206650828, | |
| "loss": 0.4186, | |
| "step": 1346 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00015201900237529688, | |
| "loss": 0.5146, | |
| "step": 1348 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001517814726840855, | |
| "loss": 0.2799, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001515439429928741, | |
| "loss": 0.2962, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001513064133016627, | |
| "loss": 0.4254, | |
| "step": 1354 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001510688836104513, | |
| "loss": 0.184, | |
| "step": 1356 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001508313539192399, | |
| "loss": 0.324, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0001505938242280285, | |
| "loss": 0.4349, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 0.30077916383743286, | |
| "eval_runtime": 9.3628, | |
| "eval_samples_per_second": 3.311, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0001503562945368171, | |
| "loss": 0.3595, | |
| "step": 1362 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0001501187648456057, | |
| "loss": 0.3216, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00014988123515439429, | |
| "loss": 0.2642, | |
| "step": 1366 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00014964370546318288, | |
| "loss": 0.2768, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00014940617577197148, | |
| "loss": 0.2836, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00014916864608076008, | |
| "loss": 0.271, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00014893111638954868, | |
| "loss": 0.1274, | |
| "step": 1374 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00014869358669833727, | |
| "loss": 0.2582, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00014845605700712587, | |
| "loss": 0.1205, | |
| "step": 1378 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00014821852731591447, | |
| "loss": 0.2666, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00014798099762470307, | |
| "loss": 0.3368, | |
| "step": 1382 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0001477434679334917, | |
| "loss": 0.2235, | |
| "step": 1384 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00014750593824228026, | |
| "loss": 0.174, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00014726840855106886, | |
| "loss": 0.2548, | |
| "step": 1388 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00014703087885985748, | |
| "loss": 0.1368, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00014679334916864608, | |
| "loss": 0.3339, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00014655581947743465, | |
| "loss": 0.2467, | |
| "step": 1394 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00014631828978622327, | |
| "loss": 0.545, | |
| "step": 1396 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00014608076009501187, | |
| "loss": 0.4737, | |
| "step": 1398 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00014584323040380044, | |
| "loss": 0.3211, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 0.298988401889801, | |
| "eval_runtime": 9.3754, | |
| "eval_samples_per_second": 3.307, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00014560570071258907, | |
| "loss": 0.4183, | |
| "step": 1402 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00014536817102137766, | |
| "loss": 0.3987, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00014513064133016626, | |
| "loss": 0.271, | |
| "step": 1406 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00014489311163895486, | |
| "loss": 0.5186, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00014465558194774346, | |
| "loss": 0.4565, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00014441805225653205, | |
| "loss": 0.587, | |
| "step": 1412 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014418052256532065, | |
| "loss": 0.2181, | |
| "step": 1414 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014394299287410925, | |
| "loss": 0.2768, | |
| "step": 1416 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014370546318289785, | |
| "loss": 0.206, | |
| "step": 1418 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014346793349168644, | |
| "loss": 0.2181, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014323040380047504, | |
| "loss": 0.3849, | |
| "step": 1422 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014299287410926364, | |
| "loss": 0.1969, | |
| "step": 1424 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00014275534441805224, | |
| "loss": 0.2128, | |
| "step": 1426 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00014251781472684083, | |
| "loss": 0.1358, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00014228028503562943, | |
| "loss": 0.13, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00014204275534441803, | |
| "loss": 0.1779, | |
| "step": 1432 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00014180522565320665, | |
| "loss": 0.3976, | |
| "step": 1434 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00014156769596199522, | |
| "loss": 0.2441, | |
| "step": 1436 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00014133016627078385, | |
| "loss": 0.2019, | |
| "step": 1438 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00014109263657957244, | |
| "loss": 0.3846, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 0.2891404330730438, | |
| "eval_runtime": 9.3736, | |
| "eval_samples_per_second": 3.307, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00014085510688836102, | |
| "loss": 0.1714, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00014061757719714964, | |
| "loss": 0.2879, | |
| "step": 1444 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00014038004750593824, | |
| "loss": 0.2013, | |
| "step": 1446 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00014014251781472683, | |
| "loss": 0.2848, | |
| "step": 1448 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00013990498812351543, | |
| "loss": 0.1802, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00013966745843230403, | |
| "loss": 0.3454, | |
| "step": 1452 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00013942992874109263, | |
| "loss": 0.3834, | |
| "step": 1454 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00013919239904988122, | |
| "loss": 0.1989, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00013895486935866982, | |
| "loss": 0.4012, | |
| "step": 1458 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00013871733966745842, | |
| "loss": 0.575, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00013847980997624702, | |
| "loss": 0.5694, | |
| "step": 1462 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00013824228028503561, | |
| "loss": 0.2037, | |
| "step": 1464 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0001380047505938242, | |
| "loss": 0.153, | |
| "step": 1466 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0001377672209026128, | |
| "loss": 0.2271, | |
| "step": 1468 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0001375296912114014, | |
| "loss": 0.0628, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00013729216152019, | |
| "loss": 0.2926, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0001370546318289786, | |
| "loss": 0.1305, | |
| "step": 1474 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00013681710213776723, | |
| "loss": 0.3799, | |
| "step": 1476 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001365795724465558, | |
| "loss": 0.2154, | |
| "step": 1478 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001363420427553444, | |
| "loss": 0.156, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 0.30829301476478577, | |
| "eval_runtime": 9.3804, | |
| "eval_samples_per_second": 3.305, | |
| "eval_steps_per_second": 0.426, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00013610451306413302, | |
| "loss": 0.1986, | |
| "step": 1482 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001358669833729216, | |
| "loss": 0.3165, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00013562945368171019, | |
| "loss": 0.1787, | |
| "step": 1486 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001353919239904988, | |
| "loss": 0.324, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001351543942992874, | |
| "loss": 0.5348, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00013491686460807598, | |
| "loss": 0.4912, | |
| "step": 1492 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001346793349168646, | |
| "loss": 0.2025, | |
| "step": 1494 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001344418052256532, | |
| "loss": 0.4557, | |
| "step": 1496 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001342042755344418, | |
| "loss": 0.1882, | |
| "step": 1498 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001339667458432304, | |
| "loss": 0.4147, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.000133729216152019, | |
| "loss": 0.1926, | |
| "step": 1502 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001334916864608076, | |
| "loss": 0.2459, | |
| "step": 1504 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001332541567695962, | |
| "loss": 0.2022, | |
| "step": 1506 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00013301662707838478, | |
| "loss": 0.3979, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00013277909738717338, | |
| "loss": 0.2447, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00013254156769596198, | |
| "loss": 0.4377, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00013230403800475058, | |
| "loss": 0.2919, | |
| "step": 1514 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00013206650831353917, | |
| "loss": 0.3803, | |
| "step": 1516 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00013182897862232777, | |
| "loss": 0.3226, | |
| "step": 1518 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00013159144893111637, | |
| "loss": 0.1986, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.29942193627357483, | |
| "eval_runtime": 9.3702, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00013135391923990497, | |
| "loss": 0.1756, | |
| "step": 1522 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001311163895486936, | |
| "loss": 0.1337, | |
| "step": 1524 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00013087885985748216, | |
| "loss": 0.255, | |
| "step": 1526 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00013064133016627076, | |
| "loss": 0.3432, | |
| "step": 1528 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00013040380047505938, | |
| "loss": 0.1389, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00013016627078384798, | |
| "loss": 0.5034, | |
| "step": 1532 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00012992874109263655, | |
| "loss": 0.2984, | |
| "step": 1534 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00012969121140142518, | |
| "loss": 0.2769, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00012945368171021377, | |
| "loss": 0.208, | |
| "step": 1538 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00012921615201900234, | |
| "loss": 0.1337, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00012897862232779097, | |
| "loss": 0.1577, | |
| "step": 1542 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00012874109263657957, | |
| "loss": 0.2292, | |
| "step": 1544 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00012850356294536816, | |
| "loss": 0.4786, | |
| "step": 1546 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00012826603325415676, | |
| "loss": 0.5353, | |
| "step": 1548 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00012802850356294536, | |
| "loss": 0.3776, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00012779097387173396, | |
| "loss": 0.4191, | |
| "step": 1552 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00012755344418052255, | |
| "loss": 0.4955, | |
| "step": 1554 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00012731591448931115, | |
| "loss": 0.2306, | |
| "step": 1556 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00012707838479809975, | |
| "loss": 0.2364, | |
| "step": 1558 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00012684085510688835, | |
| "loss": 0.5088, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.30880963802337646, | |
| "eval_runtime": 9.3477, | |
| "eval_samples_per_second": 3.316, | |
| "eval_steps_per_second": 0.428, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00012660332541567694, | |
| "loss": 0.3287, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00012636579572446554, | |
| "loss": 0.3194, | |
| "step": 1564 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00012612826603325414, | |
| "loss": 0.2959, | |
| "step": 1566 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00012589073634204274, | |
| "loss": 0.1207, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00012565320665083133, | |
| "loss": 0.1987, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00012541567695961993, | |
| "loss": 0.2112, | |
| "step": 1572 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00012517814726840855, | |
| "loss": 0.3108, | |
| "step": 1574 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00012494061757719712, | |
| "loss": 0.1942, | |
| "step": 1576 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00012470308788598575, | |
| "loss": 0.3274, | |
| "step": 1578 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00012446555819477435, | |
| "loss": 0.1127, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00012422802850356292, | |
| "loss": 0.1732, | |
| "step": 1582 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00012399049881235154, | |
| "loss": 0.0893, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00012375296912114014, | |
| "loss": 0.5852, | |
| "step": 1586 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00012351543942992874, | |
| "loss": 0.2248, | |
| "step": 1588 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00012327790973871733, | |
| "loss": 0.1555, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00012304038004750593, | |
| "loss": 0.3175, | |
| "step": 1592 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00012280285035629453, | |
| "loss": 0.4361, | |
| "step": 1594 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00012256532066508313, | |
| "loss": 0.3901, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00012232779097387172, | |
| "loss": 0.309, | |
| "step": 1598 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00012209026128266032, | |
| "loss": 0.5764, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 0.28751060366630554, | |
| "eval_runtime": 9.3587, | |
| "eval_samples_per_second": 3.312, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00012185273159144893, | |
| "loss": 0.2096, | |
| "step": 1602 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00012161520190023752, | |
| "loss": 0.3, | |
| "step": 1604 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00012137767220902611, | |
| "loss": 0.2637, | |
| "step": 1606 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00012114014251781472, | |
| "loss": 0.3272, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00012090261282660331, | |
| "loss": 0.3334, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001206650831353919, | |
| "loss": 0.3524, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00012042755344418052, | |
| "loss": 0.4394, | |
| "step": 1614 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00012019002375296911, | |
| "loss": 0.0791, | |
| "step": 1616 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001199524940617577, | |
| "loss": 0.2944, | |
| "step": 1618 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00011971496437054631, | |
| "loss": 0.117, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001194774346793349, | |
| "loss": 0.4517, | |
| "step": 1622 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00011923990498812349, | |
| "loss": 0.3192, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0001190023752969121, | |
| "loss": 0.0914, | |
| "step": 1626 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0001187648456057007, | |
| "loss": 0.2761, | |
| "step": 1628 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00011852731591448931, | |
| "loss": 0.2723, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0001182897862232779, | |
| "loss": 0.3125, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00011805225653206649, | |
| "loss": 0.1704, | |
| "step": 1634 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001178147268408551, | |
| "loss": 0.1787, | |
| "step": 1636 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00011757719714964369, | |
| "loss": 0.5133, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001173396674584323, | |
| "loss": 0.3073, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.28129419684410095, | |
| "eval_runtime": 9.3704, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001171021377672209, | |
| "loss": 0.1397, | |
| "step": 1642 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00011686460807600949, | |
| "loss": 0.2743, | |
| "step": 1644 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00011662707838479809, | |
| "loss": 0.2773, | |
| "step": 1646 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00011638954869358669, | |
| "loss": 0.3929, | |
| "step": 1648 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00011615201900237528, | |
| "loss": 0.3438, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00011591448931116388, | |
| "loss": 0.495, | |
| "step": 1652 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00011567695961995248, | |
| "loss": 0.255, | |
| "step": 1654 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00011543942992874109, | |
| "loss": 0.2498, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00011520190023752969, | |
| "loss": 0.2178, | |
| "step": 1658 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00011496437054631827, | |
| "loss": 0.624, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00011472684085510688, | |
| "loss": 0.429, | |
| "step": 1662 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00011448931116389548, | |
| "loss": 0.3015, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00011425178147268406, | |
| "loss": 0.3638, | |
| "step": 1666 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00011401425178147267, | |
| "loss": 0.2579, | |
| "step": 1668 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00011377672209026127, | |
| "loss": 0.425, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00011353919239904988, | |
| "loss": 0.2481, | |
| "step": 1672 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00011330166270783847, | |
| "loss": 0.2322, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00011306413301662706, | |
| "loss": 0.1958, | |
| "step": 1676 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00011282660332541568, | |
| "loss": 0.3868, | |
| "step": 1678 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00011258907363420426, | |
| "loss": 0.3634, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 0.2829703986644745, | |
| "eval_runtime": 9.368, | |
| "eval_samples_per_second": 3.309, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00011235154394299286, | |
| "loss": 0.1703, | |
| "step": 1682 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00011211401425178147, | |
| "loss": 0.2214, | |
| "step": 1684 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00011187648456057007, | |
| "loss": 0.3269, | |
| "step": 1686 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00011163895486935865, | |
| "loss": 0.1218, | |
| "step": 1688 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00011140142517814726, | |
| "loss": 0.3553, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00011116389548693586, | |
| "loss": 0.2318, | |
| "step": 1692 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00011092636579572444, | |
| "loss": 0.1631, | |
| "step": 1694 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00011068883610451305, | |
| "loss": 0.2334, | |
| "step": 1696 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00011045130641330165, | |
| "loss": 0.4449, | |
| "step": 1698 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00011021377672209026, | |
| "loss": 0.2483, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00010997624703087884, | |
| "loss": 0.3277, | |
| "step": 1702 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00010973871733966744, | |
| "loss": 0.3336, | |
| "step": 1704 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00010950118764845605, | |
| "loss": 0.4113, | |
| "step": 1706 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00010926365795724464, | |
| "loss": 0.2124, | |
| "step": 1708 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00010902612826603325, | |
| "loss": 0.3172, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00010878859857482185, | |
| "loss": 0.3622, | |
| "step": 1712 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00010855106888361044, | |
| "loss": 0.1893, | |
| "step": 1714 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00010831353919239904, | |
| "loss": 0.2008, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00010807600950118764, | |
| "loss": 0.0992, | |
| "step": 1718 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00010783847980997624, | |
| "loss": 0.154, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.29960963129997253, | |
| "eval_runtime": 9.359, | |
| "eval_samples_per_second": 3.312, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00010760095011876483, | |
| "loss": 0.0884, | |
| "step": 1722 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00010736342042755343, | |
| "loss": 0.2517, | |
| "step": 1724 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00010712589073634204, | |
| "loss": 0.2916, | |
| "step": 1726 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00010688836104513064, | |
| "loss": 0.3087, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00010665083135391922, | |
| "loss": 0.1531, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00010641330166270783, | |
| "loss": 0.3013, | |
| "step": 1732 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00010617577197149643, | |
| "loss": 0.1424, | |
| "step": 1734 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00010593824228028501, | |
| "loss": 0.3313, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00010570071258907363, | |
| "loss": 0.31, | |
| "step": 1738 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00010546318289786222, | |
| "loss": 0.4191, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00010522565320665083, | |
| "loss": 0.3121, | |
| "step": 1742 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00010498812351543942, | |
| "loss": 0.3626, | |
| "step": 1744 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00010475059382422802, | |
| "loss": 0.471, | |
| "step": 1746 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00010451306413301663, | |
| "loss": 0.3581, | |
| "step": 1748 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00010427553444180521, | |
| "loss": 0.5583, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00010403800475059381, | |
| "loss": 0.3143, | |
| "step": 1752 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00010380047505938242, | |
| "loss": 0.2945, | |
| "step": 1754 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00010356294536817102, | |
| "loss": 0.2709, | |
| "step": 1756 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0001033254156769596, | |
| "loss": 0.3516, | |
| "step": 1758 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00010308788598574821, | |
| "loss": 0.5142, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 0.2966551184654236, | |
| "eval_runtime": 9.367, | |
| "eval_samples_per_second": 3.309, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00010285035629453681, | |
| "loss": 0.6539, | |
| "step": 1762 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00010261282660332539, | |
| "loss": 0.2384, | |
| "step": 1764 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.000102375296912114, | |
| "loss": 0.1941, | |
| "step": 1766 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0001021377672209026, | |
| "loss": 0.2936, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00010190023752969121, | |
| "loss": 0.1306, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0001016627078384798, | |
| "loss": 0.2893, | |
| "step": 1772 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00010142517814726839, | |
| "loss": 0.4972, | |
| "step": 1774 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.000101187648456057, | |
| "loss": 0.1055, | |
| "step": 1776 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00010095011876484559, | |
| "loss": 0.1518, | |
| "step": 1778 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0001007125890736342, | |
| "loss": 0.2541, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0001004750593824228, | |
| "loss": 0.3058, | |
| "step": 1782 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0001002375296912114, | |
| "loss": 0.4288, | |
| "step": 1784 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 9.999999999999999e-05, | |
| "loss": 0.4042, | |
| "step": 1786 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 9.976247030878859e-05, | |
| "loss": 0.2071, | |
| "step": 1788 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 9.952494061757719e-05, | |
| "loss": 0.1791, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 9.928741092636578e-05, | |
| "loss": 0.1412, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.904988123515438e-05, | |
| "loss": 0.3325, | |
| "step": 1794 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.881235154394299e-05, | |
| "loss": 0.2778, | |
| "step": 1796 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.857482185273159e-05, | |
| "loss": 0.5972, | |
| "step": 1798 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.833729216152017e-05, | |
| "loss": 0.5167, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 0.2810644209384918, | |
| "eval_runtime": 9.3632, | |
| "eval_samples_per_second": 3.311, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.809976247030878e-05, | |
| "loss": 0.2728, | |
| "step": 1802 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.786223277909738e-05, | |
| "loss": 0.2504, | |
| "step": 1804 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.762470308788597e-05, | |
| "loss": 0.4784, | |
| "step": 1806 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 9.738717339667458e-05, | |
| "loss": 0.5608, | |
| "step": 1808 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 9.714964370546317e-05, | |
| "loss": 0.3195, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 9.691211401425179e-05, | |
| "loss": 0.2417, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 9.667458432304037e-05, | |
| "loss": 0.3684, | |
| "step": 1814 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 9.643705463182897e-05, | |
| "loss": 0.1482, | |
| "step": 1816 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 9.619952494061758e-05, | |
| "loss": 0.104, | |
| "step": 1818 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.596199524940616e-05, | |
| "loss": 0.4123, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.572446555819476e-05, | |
| "loss": 0.1742, | |
| "step": 1822 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.548693586698337e-05, | |
| "loss": 0.102, | |
| "step": 1824 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.524940617577197e-05, | |
| "loss": 0.1952, | |
| "step": 1826 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.501187648456055e-05, | |
| "loss": 0.355, | |
| "step": 1828 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.477434679334916e-05, | |
| "loss": 0.1664, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.453681710213776e-05, | |
| "loss": 0.2826, | |
| "step": 1832 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.429928741092634e-05, | |
| "loss": 0.1557, | |
| "step": 1834 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.406175771971495e-05, | |
| "loss": 0.0793, | |
| "step": 1836 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.382422802850355e-05, | |
| "loss": 0.5586, | |
| "step": 1838 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.358669833729216e-05, | |
| "loss": 0.1621, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.27923640608787537, | |
| "eval_runtime": 9.359, | |
| "eval_samples_per_second": 3.312, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.334916864608075e-05, | |
| "loss": 0.174, | |
| "step": 1842 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.311163895486934e-05, | |
| "loss": 0.1204, | |
| "step": 1844 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.287410926365795e-05, | |
| "loss": 0.43, | |
| "step": 1846 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.263657957244654e-05, | |
| "loss": 0.1443, | |
| "step": 1848 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.239904988123515e-05, | |
| "loss": 0.1289, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.216152019002375e-05, | |
| "loss": 0.1631, | |
| "step": 1852 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.192399049881234e-05, | |
| "loss": 0.1141, | |
| "step": 1854 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.168646080760094e-05, | |
| "loss": 0.3628, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.144893111638954e-05, | |
| "loss": 0.3337, | |
| "step": 1858 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.121140142517814e-05, | |
| "loss": 0.3215, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.097387173396673e-05, | |
| "loss": 0.7198, | |
| "step": 1862 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.073634204275533e-05, | |
| "loss": 0.3719, | |
| "step": 1864 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.049881235154394e-05, | |
| "loss": 0.1917, | |
| "step": 1866 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.026128266033254e-05, | |
| "loss": 0.1194, | |
| "step": 1868 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.002375296912112e-05, | |
| "loss": 0.3203, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.978622327790974e-05, | |
| "loss": 0.1243, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.954869358669833e-05, | |
| "loss": 0.2932, | |
| "step": 1874 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.931116389548692e-05, | |
| "loss": 0.196, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.907363420427553e-05, | |
| "loss": 0.3361, | |
| "step": 1878 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.883610451306412e-05, | |
| "loss": 0.095, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 0.2777572274208069, | |
| "eval_runtime": 9.3601, | |
| "eval_samples_per_second": 3.312, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.859857482185274e-05, | |
| "loss": 0.2712, | |
| "step": 1882 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.836104513064132e-05, | |
| "loss": 0.3259, | |
| "step": 1884 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.812351543942992e-05, | |
| "loss": 0.0914, | |
| "step": 1886 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.788598574821853e-05, | |
| "loss": 0.1682, | |
| "step": 1888 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.764845605700711e-05, | |
| "loss": 0.1419, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.741092636579571e-05, | |
| "loss": 0.374, | |
| "step": 1892 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.717339667458432e-05, | |
| "loss": 0.2816, | |
| "step": 1894 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.693586698337292e-05, | |
| "loss": 0.1357, | |
| "step": 1896 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.66983372921615e-05, | |
| "loss": 0.3469, | |
| "step": 1898 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.646080760095011e-05, | |
| "loss": 0.156, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.622327790973871e-05, | |
| "loss": 0.2251, | |
| "step": 1902 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.59857482185273e-05, | |
| "loss": 0.394, | |
| "step": 1904 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.57482185273159e-05, | |
| "loss": 0.2646, | |
| "step": 1906 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.55106888361045e-05, | |
| "loss": 0.3828, | |
| "step": 1908 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.527315914489311e-05, | |
| "loss": 0.2939, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.50356294536817e-05, | |
| "loss": 0.2697, | |
| "step": 1912 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.47980997624703e-05, | |
| "loss": 0.4667, | |
| "step": 1914 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.45605700712589e-05, | |
| "loss": 0.0942, | |
| "step": 1916 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.432304038004749e-05, | |
| "loss": 0.2499, | |
| "step": 1918 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.40855106888361e-05, | |
| "loss": 0.2036, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 0.28633174300193787, | |
| "eval_runtime": 9.3612, | |
| "eval_samples_per_second": 3.312, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.38479809976247e-05, | |
| "loss": 0.124, | |
| "step": 1922 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.36104513064133e-05, | |
| "loss": 0.1291, | |
| "step": 1924 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.337292161520189e-05, | |
| "loss": 0.1567, | |
| "step": 1926 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.313539192399049e-05, | |
| "loss": 0.2027, | |
| "step": 1928 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.289786223277909e-05, | |
| "loss": 0.302, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.266033254156769e-05, | |
| "loss": 0.1316, | |
| "step": 1932 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.242280285035628e-05, | |
| "loss": 0.4017, | |
| "step": 1934 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.21852731591449e-05, | |
| "loss": 0.1542, | |
| "step": 1936 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.194774346793349e-05, | |
| "loss": 0.2756, | |
| "step": 1938 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.171021377672208e-05, | |
| "loss": 0.4179, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.147268408551069e-05, | |
| "loss": 0.2002, | |
| "step": 1942 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.123515439429928e-05, | |
| "loss": 0.2008, | |
| "step": 1944 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.099762470308787e-05, | |
| "loss": 0.3566, | |
| "step": 1946 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.076009501187648e-05, | |
| "loss": 0.5271, | |
| "step": 1948 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.052256532066508e-05, | |
| "loss": 0.1332, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.028503562945369e-05, | |
| "loss": 0.2246, | |
| "step": 1952 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.004750593824227e-05, | |
| "loss": 0.2543, | |
| "step": 1954 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 7.980997624703087e-05, | |
| "loss": 0.2938, | |
| "step": 1956 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 7.957244655581948e-05, | |
| "loss": 0.5904, | |
| "step": 1958 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 7.933491686460806e-05, | |
| "loss": 0.3902, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 0.2950325906276703, | |
| "eval_runtime": 9.3616, | |
| "eval_samples_per_second": 3.311, | |
| "eval_steps_per_second": 0.427, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 7.909738717339666e-05, | |
| "loss": 0.2688, | |
| "step": 1962 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.885985748218527e-05, | |
| "loss": 0.4113, | |
| "step": 1964 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.862232779097387e-05, | |
| "loss": 0.1846, | |
| "step": 1966 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.838479809976245e-05, | |
| "loss": 0.2456, | |
| "step": 1968 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.814726840855106e-05, | |
| "loss": 0.1499, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.790973871733966e-05, | |
| "loss": 0.4278, | |
| "step": 1972 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.767220902612825e-05, | |
| "loss": 0.2225, | |
| "step": 1974 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.743467933491686e-05, | |
| "loss": 0.135, | |
| "step": 1976 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.719714964370545e-05, | |
| "loss": 0.1839, | |
| "step": 1978 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.695961995249406e-05, | |
| "loss": 0.1917, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.672209026128265e-05, | |
| "loss": 0.1356, | |
| "step": 1982 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.648456057007125e-05, | |
| "loss": 0.2198, | |
| "step": 1984 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.624703087885986e-05, | |
| "loss": 0.2097, | |
| "step": 1986 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.600950118764844e-05, | |
| "loss": 0.5525, | |
| "step": 1988 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.577197149643705e-05, | |
| "loss": 0.2272, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.553444180522565e-05, | |
| "loss": 0.0927, | |
| "step": 1992 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.529691211401425e-05, | |
| "loss": 0.4069, | |
| "step": 1994 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.505938242280284e-05, | |
| "loss": 0.1714, | |
| "step": 1996 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.482185273159144e-05, | |
| "loss": 0.0959, | |
| "step": 1998 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.458432304038004e-05, | |
| "loss": 0.2669, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 0.2871646583080292, | |
| "eval_runtime": 9.3732, | |
| "eval_samples_per_second": 3.307, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.434679334916864e-05, | |
| "loss": 0.3935, | |
| "step": 2002 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.410926365795723e-05, | |
| "loss": 0.5176, | |
| "step": 2004 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.387173396674584e-05, | |
| "loss": 0.4648, | |
| "step": 2006 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.363420427553443e-05, | |
| "loss": 0.3234, | |
| "step": 2008 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.339667458432304e-05, | |
| "loss": 0.3422, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.315914489311164e-05, | |
| "loss": 0.2731, | |
| "step": 2012 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.292161520190022e-05, | |
| "loss": 0.4215, | |
| "step": 2014 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.268408551068883e-05, | |
| "loss": 0.3272, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.244655581947743e-05, | |
| "loss": 0.2518, | |
| "step": 2018 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.220902612826603e-05, | |
| "loss": 0.2811, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.197149643705462e-05, | |
| "loss": 0.111, | |
| "step": 2022 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.173396674584322e-05, | |
| "loss": 0.2118, | |
| "step": 2024 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.149643705463182e-05, | |
| "loss": 0.34, | |
| "step": 2026 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.125890736342042e-05, | |
| "loss": 0.2277, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 7.102137767220901e-05, | |
| "loss": 0.158, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 7.078384798099761e-05, | |
| "loss": 0.143, | |
| "step": 2032 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 7.054631828978622e-05, | |
| "loss": 0.201, | |
| "step": 2034 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 7.030878859857482e-05, | |
| "loss": 0.3279, | |
| "step": 2036 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 7.007125890736342e-05, | |
| "loss": 0.4416, | |
| "step": 2038 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 6.983372921615201e-05, | |
| "loss": 0.177, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 0.2866095006465912, | |
| "eval_runtime": 9.359, | |
| "eval_samples_per_second": 3.312, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 6.959619952494061e-05, | |
| "loss": 0.2742, | |
| "step": 2042 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.935866983372921e-05, | |
| "loss": 0.2495, | |
| "step": 2044 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.912114014251781e-05, | |
| "loss": 0.1398, | |
| "step": 2046 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.88836104513064e-05, | |
| "loss": 0.1191, | |
| "step": 2048 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.8646080760095e-05, | |
| "loss": 0.1189, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.840855106888361e-05, | |
| "loss": 0.4908, | |
| "step": 2052 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.81710213776722e-05, | |
| "loss": 0.3248, | |
| "step": 2054 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.79334916864608e-05, | |
| "loss": 0.2646, | |
| "step": 2056 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.76959619952494e-05, | |
| "loss": 0.2602, | |
| "step": 2058 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.745843230403799e-05, | |
| "loss": 0.5139, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.72209026128266e-05, | |
| "loss": 0.2779, | |
| "step": 2062 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.69833729216152e-05, | |
| "loss": 0.3148, | |
| "step": 2064 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.67458432304038e-05, | |
| "loss": 0.135, | |
| "step": 2066 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.650831353919239e-05, | |
| "loss": 0.2449, | |
| "step": 2068 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 6.627078384798099e-05, | |
| "loss": 0.2559, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 6.603325415676959e-05, | |
| "loss": 0.5405, | |
| "step": 2072 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 6.579572446555818e-05, | |
| "loss": 0.2843, | |
| "step": 2074 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 6.55581947743468e-05, | |
| "loss": 0.2028, | |
| "step": 2076 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 6.532066508313538e-05, | |
| "loss": 0.1593, | |
| "step": 2078 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 6.508313539192399e-05, | |
| "loss": 0.1919, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 0.2877208888530731, | |
| "eval_runtime": 9.3725, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.484560570071259e-05, | |
| "loss": 0.2144, | |
| "step": 2082 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.460807600950117e-05, | |
| "loss": 0.1698, | |
| "step": 2084 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.437054631828978e-05, | |
| "loss": 0.2004, | |
| "step": 2086 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.413301662707838e-05, | |
| "loss": 0.2548, | |
| "step": 2088 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.389548693586698e-05, | |
| "loss": 0.1027, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.365795724465558e-05, | |
| "loss": 0.2526, | |
| "step": 2092 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.342042755344417e-05, | |
| "loss": 0.3702, | |
| "step": 2094 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.318289786223277e-05, | |
| "loss": 0.1358, | |
| "step": 2096 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.294536817102137e-05, | |
| "loss": 0.203, | |
| "step": 2098 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.270783847980996e-05, | |
| "loss": 0.2277, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.247030878859856e-05, | |
| "loss": 0.4521, | |
| "step": 2102 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.223277909738717e-05, | |
| "loss": 0.5379, | |
| "step": 2104 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.199524940617577e-05, | |
| "loss": 0.5, | |
| "step": 2106 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.175771971496437e-05, | |
| "loss": 0.4136, | |
| "step": 2108 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 6.152019002375297e-05, | |
| "loss": 0.3087, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 6.128266033254156e-05, | |
| "loss": 0.2025, | |
| "step": 2112 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 6.104513064133016e-05, | |
| "loss": 0.5468, | |
| "step": 2114 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 6.080760095011876e-05, | |
| "loss": 0.0856, | |
| "step": 2116 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 6.057007125890736e-05, | |
| "loss": 0.0566, | |
| "step": 2118 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 6.033254156769595e-05, | |
| "loss": 0.117, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 0.27925828099250793, | |
| "eval_runtime": 9.3682, | |
| "eval_samples_per_second": 3.309, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 6.009501187648456e-05, | |
| "loss": 0.1581, | |
| "step": 2122 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5.9857482185273155e-05, | |
| "loss": 0.2501, | |
| "step": 2124 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5.9619952494061745e-05, | |
| "loss": 0.267, | |
| "step": 2126 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5.938242280285035e-05, | |
| "loss": 0.1953, | |
| "step": 2128 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5.914489311163895e-05, | |
| "loss": 0.113, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5.890736342042755e-05, | |
| "loss": 0.3468, | |
| "step": 2132 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5.866983372921615e-05, | |
| "loss": 0.3671, | |
| "step": 2134 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 5.8432304038004746e-05, | |
| "loss": 0.213, | |
| "step": 2136 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 5.8194774346793343e-05, | |
| "loss": 0.3049, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 5.795724465558194e-05, | |
| "loss": 0.3587, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 5.7719714964370545e-05, | |
| "loss": 0.1607, | |
| "step": 2142 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 5.7482185273159136e-05, | |
| "loss": 0.3961, | |
| "step": 2144 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 5.724465558194774e-05, | |
| "loss": 0.5162, | |
| "step": 2146 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.700712589073634e-05, | |
| "loss": 0.2147, | |
| "step": 2148 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.676959619952494e-05, | |
| "loss": 0.2356, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.653206650831353e-05, | |
| "loss": 0.2201, | |
| "step": 2152 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.629453681710213e-05, | |
| "loss": 0.3852, | |
| "step": 2154 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.6057007125890734e-05, | |
| "loss": 0.3659, | |
| "step": 2156 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.5819477434679325e-05, | |
| "loss": 0.2305, | |
| "step": 2158 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.558194774346793e-05, | |
| "loss": 0.2608, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.27714648842811584, | |
| "eval_runtime": 9.3632, | |
| "eval_samples_per_second": 3.311, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5.5344418052256526e-05, | |
| "loss": 0.3119, | |
| "step": 2162 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5.510688836104513e-05, | |
| "loss": 0.4147, | |
| "step": 2164 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5.486935866983372e-05, | |
| "loss": 0.2113, | |
| "step": 2166 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5.463182897862232e-05, | |
| "loss": 0.1966, | |
| "step": 2168 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5.439429928741092e-05, | |
| "loss": 0.2277, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5.415676959619952e-05, | |
| "loss": 0.2326, | |
| "step": 2172 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 5.391923990498812e-05, | |
| "loss": 0.1252, | |
| "step": 2174 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 5.3681710213776715e-05, | |
| "loss": 0.1706, | |
| "step": 2176 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 5.344418052256532e-05, | |
| "loss": 0.175, | |
| "step": 2178 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 5.320665083135392e-05, | |
| "loss": 0.1525, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 5.296912114014251e-05, | |
| "loss": 0.2926, | |
| "step": 2182 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 5.273159144893111e-05, | |
| "loss": 0.3535, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 5.249406175771971e-05, | |
| "loss": 0.1871, | |
| "step": 2186 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.225653206650831e-05, | |
| "loss": 0.2173, | |
| "step": 2188 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.2019002375296904e-05, | |
| "loss": 0.1821, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.178147268408551e-05, | |
| "loss": 0.1527, | |
| "step": 2192 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.1543942992874106e-05, | |
| "loss": 0.3021, | |
| "step": 2194 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.1306413301662696e-05, | |
| "loss": 0.348, | |
| "step": 2196 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.10688836104513e-05, | |
| "loss": 0.2462, | |
| "step": 2198 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.08313539192399e-05, | |
| "loss": 0.2565, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.2779179811477661, | |
| "eval_runtime": 9.3678, | |
| "eval_samples_per_second": 3.309, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 5.05938242280285e-05, | |
| "loss": 0.3217, | |
| "step": 2202 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 5.03562945368171e-05, | |
| "loss": 0.2808, | |
| "step": 2204 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 5.01187648456057e-05, | |
| "loss": 0.3176, | |
| "step": 2206 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.9881235154394294e-05, | |
| "loss": 0.3842, | |
| "step": 2208 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.964370546318289e-05, | |
| "loss": 0.4804, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.9406175771971496e-05, | |
| "loss": 0.4944, | |
| "step": 2212 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.916864608076009e-05, | |
| "loss": 0.3637, | |
| "step": 2214 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.893111638954869e-05, | |
| "loss": 0.2561, | |
| "step": 2216 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.869358669833729e-05, | |
| "loss": 0.1181, | |
| "step": 2218 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.845605700712589e-05, | |
| "loss": 0.1691, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.821852731591448e-05, | |
| "loss": 0.2524, | |
| "step": 2222 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.798099762470308e-05, | |
| "loss": 0.1532, | |
| "step": 2224 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.7743467933491685e-05, | |
| "loss": 0.4069, | |
| "step": 2226 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.7505938242280275e-05, | |
| "loss": 0.2669, | |
| "step": 2228 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.726840855106888e-05, | |
| "loss": 0.1456, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.703087885985748e-05, | |
| "loss": 0.2315, | |
| "step": 2232 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.679334916864608e-05, | |
| "loss": 0.18, | |
| "step": 2234 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.655581947743467e-05, | |
| "loss": 0.1753, | |
| "step": 2236 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.631828978622327e-05, | |
| "loss": 0.2385, | |
| "step": 2238 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.6080760095011874e-05, | |
| "loss": 0.2439, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 0.27692317962646484, | |
| "eval_runtime": 9.3668, | |
| "eval_samples_per_second": 3.31, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.584323040380047e-05, | |
| "loss": 0.2969, | |
| "step": 2242 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.560570071258907e-05, | |
| "loss": 0.3012, | |
| "step": 2244 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.5368171021377666e-05, | |
| "loss": 0.227, | |
| "step": 2246 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.513064133016627e-05, | |
| "loss": 0.3316, | |
| "step": 2248 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.489311163895487e-05, | |
| "loss": 0.3104, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.465558194774346e-05, | |
| "loss": 0.2379, | |
| "step": 2252 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.441805225653206e-05, | |
| "loss": 0.3829, | |
| "step": 2254 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.418052256532066e-05, | |
| "loss": 0.3213, | |
| "step": 2256 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.3942992874109264e-05, | |
| "loss": 0.6011, | |
| "step": 2258 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.3705463182897855e-05, | |
| "loss": 0.6146, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.346793349168646e-05, | |
| "loss": 0.4858, | |
| "step": 2262 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.3230403800475056e-05, | |
| "loss": 0.3316, | |
| "step": 2264 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.299287410926365e-05, | |
| "loss": 0.2712, | |
| "step": 2266 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.275534441805225e-05, | |
| "loss": 0.3848, | |
| "step": 2268 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.251781472684085e-05, | |
| "loss": 0.3588, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.228028503562945e-05, | |
| "loss": 0.1915, | |
| "step": 2272 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.204275534441805e-05, | |
| "loss": 0.1383, | |
| "step": 2274 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.180522565320665e-05, | |
| "loss": 0.2695, | |
| "step": 2276 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.1567695961995245e-05, | |
| "loss": 0.1303, | |
| "step": 2278 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.133016627078384e-05, | |
| "loss": 0.1186, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 0.27118030190467834, | |
| "eval_runtime": 9.3658, | |
| "eval_samples_per_second": 3.31, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.109263657957245e-05, | |
| "loss": 0.2598, | |
| "step": 2282 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.085510688836104e-05, | |
| "loss": 0.4174, | |
| "step": 2284 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.061757719714964e-05, | |
| "loss": 0.1783, | |
| "step": 2286 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.038004750593824e-05, | |
| "loss": 0.3437, | |
| "step": 2288 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.0142517814726843e-05, | |
| "loss": 0.2497, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.9904988123515434e-05, | |
| "loss": 0.2498, | |
| "step": 2292 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.966745843230403e-05, | |
| "loss": 0.2084, | |
| "step": 2294 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.9429928741092636e-05, | |
| "loss": 0.365, | |
| "step": 2296 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.9192399049881226e-05, | |
| "loss": 0.5269, | |
| "step": 2298 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.895486935866983e-05, | |
| "loss": 0.2542, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.871733966745843e-05, | |
| "loss": 0.3138, | |
| "step": 2302 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.847980997624703e-05, | |
| "loss": 0.0877, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.824228028503562e-05, | |
| "loss": 0.595, | |
| "step": 2306 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.800475059382422e-05, | |
| "loss": 0.2971, | |
| "step": 2308 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.7767220902612825e-05, | |
| "loss": 0.3425, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.752969121140142e-05, | |
| "loss": 0.1848, | |
| "step": 2312 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.729216152019002e-05, | |
| "loss": 0.1213, | |
| "step": 2314 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.705463182897862e-05, | |
| "loss": 0.176, | |
| "step": 2316 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.6817102137767214e-05, | |
| "loss": 0.1598, | |
| "step": 2318 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.657957244655582e-05, | |
| "loss": 0.1153, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 0.28142210841178894, | |
| "eval_runtime": 9.3524, | |
| "eval_samples_per_second": 3.315, | |
| "eval_steps_per_second": 0.428, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.6342042755344416e-05, | |
| "loss": 0.1319, | |
| "step": 2322 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.6104513064133013e-05, | |
| "loss": 0.2766, | |
| "step": 2324 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.586698337292161e-05, | |
| "loss": 0.2458, | |
| "step": 2326 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.562945368171021e-05, | |
| "loss": 0.1604, | |
| "step": 2328 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.5391923990498806e-05, | |
| "loss": 0.1206, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.515439429928741e-05, | |
| "loss": 0.1132, | |
| "step": 2332 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.491686460807601e-05, | |
| "loss": 0.1886, | |
| "step": 2334 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.4679334916864605e-05, | |
| "loss": 0.3292, | |
| "step": 2336 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.44418052256532e-05, | |
| "loss": 0.2023, | |
| "step": 2338 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.4204275534441806e-05, | |
| "loss": 0.1748, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.39667458432304e-05, | |
| "loss": 0.4589, | |
| "step": 2342 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.3729216152018995e-05, | |
| "loss": 0.1825, | |
| "step": 2344 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.34916864608076e-05, | |
| "loss": 0.1707, | |
| "step": 2346 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.3254156769596196e-05, | |
| "loss": 0.1747, | |
| "step": 2348 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.3016627078384794e-05, | |
| "loss": 0.3958, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.27790973871734e-05, | |
| "loss": 0.3037, | |
| "step": 2352 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.2541567695961995e-05, | |
| "loss": 0.4159, | |
| "step": 2354 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.2304038004750586e-05, | |
| "loss": 0.2042, | |
| "step": 2356 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.206650831353919e-05, | |
| "loss": 0.3533, | |
| "step": 2358 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.182897862232779e-05, | |
| "loss": 0.5807, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.2814473509788513, | |
| "eval_runtime": 9.3639, | |
| "eval_samples_per_second": 3.311, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.1591448931116385e-05, | |
| "loss": 0.6157, | |
| "step": 2362 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.135391923990498e-05, | |
| "loss": 0.1465, | |
| "step": 2364 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.111638954869359e-05, | |
| "loss": 0.4005, | |
| "step": 2366 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.0878859857482184e-05, | |
| "loss": 0.3696, | |
| "step": 2368 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.064133016627078e-05, | |
| "loss": 0.2864, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.040380047505938e-05, | |
| "loss": 0.2612, | |
| "step": 2372 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.0166270783847976e-05, | |
| "loss": 0.2704, | |
| "step": 2374 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.9928741092636577e-05, | |
| "loss": 0.1519, | |
| "step": 2376 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.9691211401425175e-05, | |
| "loss": 0.2847, | |
| "step": 2378 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.9453681710213776e-05, | |
| "loss": 0.2993, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.9216152019002373e-05, | |
| "loss": 0.3466, | |
| "step": 2382 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.897862232779097e-05, | |
| "loss": 0.2256, | |
| "step": 2384 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.8741092636579568e-05, | |
| "loss": 0.3448, | |
| "step": 2386 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.850356294536817e-05, | |
| "loss": 0.2556, | |
| "step": 2388 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.8266033254156766e-05, | |
| "loss": 0.459, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.8028503562945367e-05, | |
| "loss": 0.3489, | |
| "step": 2392 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.7790973871733964e-05, | |
| "loss": 0.4236, | |
| "step": 2394 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.7553444180522565e-05, | |
| "loss": 0.3738, | |
| "step": 2396 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.731591448931116e-05, | |
| "loss": 0.5616, | |
| "step": 2398 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.707838479809976e-05, | |
| "loss": 0.2348, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 0.2760084867477417, | |
| "eval_runtime": 9.3699, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.6840855106888358e-05, | |
| "loss": 0.5928, | |
| "step": 2402 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.660332541567696e-05, | |
| "loss": 0.1919, | |
| "step": 2404 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.6365795724465556e-05, | |
| "loss": 0.2453, | |
| "step": 2406 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.6128266033254157e-05, | |
| "loss": 0.1858, | |
| "step": 2408 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.5890736342042754e-05, | |
| "loss": 0.3843, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.5653206650831348e-05, | |
| "loss": 0.3801, | |
| "step": 2412 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.541567695961995e-05, | |
| "loss": 0.1897, | |
| "step": 2414 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.517814726840855e-05, | |
| "loss": 0.2243, | |
| "step": 2416 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.4940617577197147e-05, | |
| "loss": 0.1292, | |
| "step": 2418 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.4703087885985748e-05, | |
| "loss": 0.135, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.4465558194774345e-05, | |
| "loss": 0.3375, | |
| "step": 2422 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.4228028503562946e-05, | |
| "loss": 0.2751, | |
| "step": 2424 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.399049881235154e-05, | |
| "loss": 0.3165, | |
| "step": 2426 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.3752969121140138e-05, | |
| "loss": 0.2338, | |
| "step": 2428 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.351543942992874e-05, | |
| "loss": 0.2244, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.3277909738717336e-05, | |
| "loss": 0.1548, | |
| "step": 2432 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.3040380047505937e-05, | |
| "loss": 0.1695, | |
| "step": 2434 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.2802850356294534e-05, | |
| "loss": 0.1612, | |
| "step": 2436 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.2565320665083135e-05, | |
| "loss": 0.3405, | |
| "step": 2438 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.232779097387173e-05, | |
| "loss": 0.0924, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 0.2725999653339386, | |
| "eval_runtime": 9.3677, | |
| "eval_samples_per_second": 3.309, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.209026128266033e-05, | |
| "loss": 0.2963, | |
| "step": 2442 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.1852731591448927e-05, | |
| "loss": 0.1525, | |
| "step": 2444 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.1615201900237528e-05, | |
| "loss": 0.4711, | |
| "step": 2446 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.1377672209026126e-05, | |
| "loss": 0.4293, | |
| "step": 2448 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.1140142517814726e-05, | |
| "loss": 0.2169, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0902612826603324e-05, | |
| "loss": 0.4243, | |
| "step": 2452 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.066508313539192e-05, | |
| "loss": 0.317, | |
| "step": 2454 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.042755344418052e-05, | |
| "loss": 0.4244, | |
| "step": 2456 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.019002375296912e-05, | |
| "loss": 0.1467, | |
| "step": 2458 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.9952494061757717e-05, | |
| "loss": 0.4868, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.9714964370546318e-05, | |
| "loss": 0.5826, | |
| "step": 2462 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.9477434679334915e-05, | |
| "loss": 0.187, | |
| "step": 2464 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.9239904988123516e-05, | |
| "loss": 0.0794, | |
| "step": 2466 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.900237529691211e-05, | |
| "loss": 0.1302, | |
| "step": 2468 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.876484560570071e-05, | |
| "loss": 0.4373, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.852731591448931e-05, | |
| "loss": 0.3002, | |
| "step": 2472 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.828978622327791e-05, | |
| "loss": 0.1335, | |
| "step": 2474 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.8052256532066507e-05, | |
| "loss": 0.1781, | |
| "step": 2476 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.7814726840855104e-05, | |
| "loss": 0.3901, | |
| "step": 2478 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.7577197149643705e-05, | |
| "loss": 0.1162, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 0.2703912854194641, | |
| "eval_runtime": 9.352, | |
| "eval_samples_per_second": 3.315, | |
| "eval_steps_per_second": 0.428, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.7339667458432302e-05, | |
| "loss": 0.5508, | |
| "step": 2482 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.7102137767220903e-05, | |
| "loss": 0.1435, | |
| "step": 2484 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.6864608076009497e-05, | |
| "loss": 0.25, | |
| "step": 2486 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.6627078384798098e-05, | |
| "loss": 0.1396, | |
| "step": 2488 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.63895486935867e-05, | |
| "loss": 0.2386, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.6152019002375293e-05, | |
| "loss": 0.1699, | |
| "step": 2492 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.5914489311163894e-05, | |
| "loss": 0.3928, | |
| "step": 2494 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.567695961995249e-05, | |
| "loss": 0.1304, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.5439429928741092e-05, | |
| "loss": 0.1347, | |
| "step": 2498 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.520190023752969e-05, | |
| "loss": 0.3371, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.4964370546318289e-05, | |
| "loss": 0.2277, | |
| "step": 2502 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.4845605700712587e-05, | |
| "loss": 0.1996, | |
| "step": 2504 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.4608076009501186e-05, | |
| "loss": 0.2997, | |
| "step": 2506 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.4370546318289784e-05, | |
| "loss": 0.4236, | |
| "step": 2508 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.4133016627078383e-05, | |
| "loss": 0.4184, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.3895486935866982e-05, | |
| "loss": 0.2087, | |
| "step": 2512 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.365795724465558e-05, | |
| "loss": 0.375, | |
| "step": 2514 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.3420427553444179e-05, | |
| "loss": 0.4326, | |
| "step": 2516 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.3182897862232778e-05, | |
| "loss": 0.2551, | |
| "step": 2518 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.2945368171021377e-05, | |
| "loss": 0.1352, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.2696640193462372, | |
| "eval_runtime": 9.3552, | |
| "eval_samples_per_second": 3.314, | |
| "eval_steps_per_second": 0.428, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.2707838479809974e-05, | |
| "loss": 0.4665, | |
| "step": 2522 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.2470308788598574e-05, | |
| "loss": 0.3718, | |
| "step": 2524 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.2232779097387173e-05, | |
| "loss": 0.2107, | |
| "step": 2526 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.199524940617577e-05, | |
| "loss": 0.2149, | |
| "step": 2528 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.175771971496437e-05, | |
| "loss": 0.0843, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.1520190023752968e-05, | |
| "loss": 0.277, | |
| "step": 2532 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.1282660332541568e-05, | |
| "loss": 0.2025, | |
| "step": 2534 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.1045130641330165e-05, | |
| "loss": 0.0943, | |
| "step": 2536 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.0807600950118764e-05, | |
| "loss": 0.365, | |
| "step": 2538 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.0570071258907363e-05, | |
| "loss": 0.3706, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.033254156769596e-05, | |
| "loss": 0.2405, | |
| "step": 2542 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.009501187648456e-05, | |
| "loss": 0.1997, | |
| "step": 2544 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 9.857482185273159e-06, | |
| "loss": 0.3591, | |
| "step": 2546 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 9.619952494061758e-06, | |
| "loss": 0.3283, | |
| "step": 2548 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 9.382422802850356e-06, | |
| "loss": 0.1642, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 9.144893111638955e-06, | |
| "loss": 0.1954, | |
| "step": 2552 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 8.907363420427552e-06, | |
| "loss": 0.1998, | |
| "step": 2554 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 8.669833729216151e-06, | |
| "loss": 0.3027, | |
| "step": 2556 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 8.432304038004749e-06, | |
| "loss": 0.1778, | |
| "step": 2558 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 8.19477434679335e-06, | |
| "loss": 0.3455, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 0.2705852687358856, | |
| "eval_runtime": 9.3719, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 7.957244655581947e-06, | |
| "loss": 0.3249, | |
| "step": 2562 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 7.719714964370546e-06, | |
| "loss": 0.2456, | |
| "step": 2564 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 7.482185273159144e-06, | |
| "loss": 0.0831, | |
| "step": 2566 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 7.244655581947743e-06, | |
| "loss": 0.2321, | |
| "step": 2568 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 7.007125890736342e-06, | |
| "loss": 0.124, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.76959619952494e-06, | |
| "loss": 0.2004, | |
| "step": 2572 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.532066508313539e-06, | |
| "loss": 0.2724, | |
| "step": 2574 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.2945368171021374e-06, | |
| "loss": 0.2477, | |
| "step": 2576 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.0570071258907366e-06, | |
| "loss": 0.1792, | |
| "step": 2578 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 5.819477434679334e-06, | |
| "loss": 0.3121, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 5.581947743467932e-06, | |
| "loss": 0.0487, | |
| "step": 2582 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 5.344418052256531e-06, | |
| "loss": 0.3694, | |
| "step": 2584 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 5.10688836104513e-06, | |
| "loss": 0.1692, | |
| "step": 2586 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.869358669833729e-06, | |
| "loss": 0.1156, | |
| "step": 2588 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.631828978622327e-06, | |
| "loss": 0.3615, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.394299287410926e-06, | |
| "loss": 0.2471, | |
| "step": 2592 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.1567695961995245e-06, | |
| "loss": 0.2129, | |
| "step": 2594 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 3.919239904988123e-06, | |
| "loss": 0.2738, | |
| "step": 2596 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 3.681710213776722e-06, | |
| "loss": 0.4506, | |
| "step": 2598 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 3.4441805225653207e-06, | |
| "loss": 0.2892, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.26948797702789307, | |
| "eval_runtime": 9.3784, | |
| "eval_samples_per_second": 3.305, | |
| "eval_steps_per_second": 0.427, | |
| "step": 2600 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 2626, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 40, | |
| "total_flos": 1.0137991299416064e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |