| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0713171383998217, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.036036036036036036, | |
| "grad_norm": 6.189637660980225, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 3.5287, | |
| "num_input_tokens_seen": 3200, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07207207207207207, | |
| "grad_norm": 5.866844177246094, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 3.4855, | |
| "num_input_tokens_seen": 6560, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 5.849005222320557, | |
| "learning_rate": 1e-05, | |
| "loss": 3.6108, | |
| "num_input_tokens_seen": 9856, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14414414414414414, | |
| "grad_norm": 7.444654941558838, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 3.418, | |
| "num_input_tokens_seen": 12752, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18018018018018017, | |
| "grad_norm": 5.2968339920043945, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 3.5055, | |
| "num_input_tokens_seen": 15824, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 6.087192058563232, | |
| "learning_rate": 2e-05, | |
| "loss": 3.4734, | |
| "num_input_tokens_seen": 18672, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25225225225225223, | |
| "grad_norm": 5.243087291717529, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 3.0335, | |
| "num_input_tokens_seen": 26016, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2882882882882883, | |
| "grad_norm": 5.207272052764893, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 3.5633, | |
| "num_input_tokens_seen": 30032, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32432432432432434, | |
| "grad_norm": 5.279658317565918, | |
| "learning_rate": 3e-05, | |
| "loss": 3.7508, | |
| "num_input_tokens_seen": 33504, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.36036036036036034, | |
| "grad_norm": 4.909541606903076, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.4502, | |
| "num_input_tokens_seen": 37472, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3963963963963964, | |
| "grad_norm": 5.139044284820557, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 2.9229, | |
| "num_input_tokens_seen": 45008, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 5.718777179718018, | |
| "learning_rate": 4e-05, | |
| "loss": 3.668, | |
| "num_input_tokens_seen": 48832, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.46846846846846846, | |
| "grad_norm": 5.036716938018799, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 3.2389, | |
| "num_input_tokens_seen": 51840, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5045045045045045, | |
| "grad_norm": 5.894410133361816, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 3.589, | |
| "num_input_tokens_seen": 54976, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 6.030157089233398, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7204, | |
| "num_input_tokens_seen": 58192, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5765765765765766, | |
| "grad_norm": 5.202926158905029, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 2.9049, | |
| "num_input_tokens_seen": 65872, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6126126126126126, | |
| "grad_norm": 6.379465103149414, | |
| "learning_rate": 5.666666666666667e-05, | |
| "loss": 3.6342, | |
| "num_input_tokens_seen": 69360, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6486486486486487, | |
| "grad_norm": 4.922969818115234, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4525, | |
| "num_input_tokens_seen": 72656, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6846846846846847, | |
| "grad_norm": 6.9363298416137695, | |
| "learning_rate": 6.333333333333333e-05, | |
| "loss": 3.4722, | |
| "num_input_tokens_seen": 76496, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "grad_norm": 5.329838275909424, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.2838, | |
| "num_input_tokens_seen": 79760, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "eval_loss": 2.9567394256591797, | |
| "eval_runtime": 0.3463, | |
| "eval_samples_per_second": 14.439, | |
| "eval_steps_per_second": 8.663, | |
| "num_input_tokens_seen": 79760, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7567567567567568, | |
| "grad_norm": 7.31512451171875, | |
| "learning_rate": 7e-05, | |
| "loss": 3.0849, | |
| "num_input_tokens_seen": 82880, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7927927927927928, | |
| "grad_norm": 5.24735164642334, | |
| "learning_rate": 7.333333333333333e-05, | |
| "loss": 3.0536, | |
| "num_input_tokens_seen": 86176, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8288288288288288, | |
| "grad_norm": 8.290057182312012, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 2.6354, | |
| "num_input_tokens_seen": 93136, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 6.639683246612549, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8682, | |
| "num_input_tokens_seen": 96800, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9009009009009009, | |
| "grad_norm": 6.359157562255859, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 3.0521, | |
| "num_input_tokens_seen": 100000, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9369369369369369, | |
| "grad_norm": 5.462643623352051, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 3.2956, | |
| "num_input_tokens_seen": 103504, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.972972972972973, | |
| "grad_norm": 5.68543815612793, | |
| "learning_rate": 9e-05, | |
| "loss": 3.2966, | |
| "num_input_tokens_seen": 106720, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.0144144144144145, | |
| "grad_norm": 6.407595634460449, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 3.6629, | |
| "num_input_tokens_seen": 110112, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0504504504504504, | |
| "grad_norm": 8.155672073364258, | |
| "learning_rate": 9.666666666666667e-05, | |
| "loss": 2.9811, | |
| "num_input_tokens_seen": 113184, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.0864864864864865, | |
| "grad_norm": 10.235915184020996, | |
| "learning_rate": 0.0001, | |
| "loss": 2.698, | |
| "num_input_tokens_seen": 116976, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1225225225225226, | |
| "grad_norm": 7.20429801940918, | |
| "learning_rate": 0.00010333333333333334, | |
| "loss": 2.5234, | |
| "num_input_tokens_seen": 120672, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.1585585585585585, | |
| "grad_norm": 7.340835094451904, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 2.7242, | |
| "num_input_tokens_seen": 123680, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.1945945945945946, | |
| "grad_norm": 8.580013275146484, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 2.8218, | |
| "num_input_tokens_seen": 126624, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.2306306306306307, | |
| "grad_norm": 0.891119658946991, | |
| "learning_rate": 0.00011333333333333334, | |
| "loss": 2.4674, | |
| "num_input_tokens_seen": 133728, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.2666666666666666, | |
| "grad_norm": 0.8570746779441833, | |
| "learning_rate": 0.00011666666666666668, | |
| "loss": 2.2086, | |
| "num_input_tokens_seen": 140880, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.3027027027027027, | |
| "grad_norm": 5.530377388000488, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4582, | |
| "num_input_tokens_seen": 148288, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3387387387387388, | |
| "grad_norm": 5.526784896850586, | |
| "learning_rate": 0.00012333333333333334, | |
| "loss": 2.9289, | |
| "num_input_tokens_seen": 151824, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.3747747747747747, | |
| "grad_norm": 9.305526733398438, | |
| "learning_rate": 0.00012666666666666666, | |
| "loss": 2.6308, | |
| "num_input_tokens_seen": 154896, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.4108108108108108, | |
| "grad_norm": 8.043120384216309, | |
| "learning_rate": 0.00013000000000000002, | |
| "loss": 2.8798, | |
| "num_input_tokens_seen": 158080, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.4468468468468467, | |
| "grad_norm": 7.124425411224365, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 2.9072, | |
| "num_input_tokens_seen": 161216, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4468468468468467, | |
| "eval_loss": 3.2079105377197266, | |
| "eval_runtime": 0.3, | |
| "eval_samples_per_second": 16.667, | |
| "eval_steps_per_second": 10.0, | |
| "num_input_tokens_seen": 161216, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4828828828828828, | |
| "grad_norm": 7.224998950958252, | |
| "learning_rate": 0.00013666666666666666, | |
| "loss": 2.8577, | |
| "num_input_tokens_seen": 164352, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.518918918918919, | |
| "grad_norm": 6.092015743255615, | |
| "learning_rate": 0.00014, | |
| "loss": 3.4773, | |
| "num_input_tokens_seen": 168416, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.554954954954955, | |
| "grad_norm": 0.6125243306159973, | |
| "learning_rate": 0.00014333333333333334, | |
| "loss": 2.2967, | |
| "num_input_tokens_seen": 176656, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.590990990990991, | |
| "grad_norm": 10.359404563903809, | |
| "learning_rate": 0.00014666666666666666, | |
| "loss": 2.9172, | |
| "num_input_tokens_seen": 179744, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.627027027027027, | |
| "grad_norm": 8.786321640014648, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.795, | |
| "num_input_tokens_seen": 182864, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.663063063063063, | |
| "grad_norm": 7.069016933441162, | |
| "learning_rate": 0.00015333333333333334, | |
| "loss": 2.8839, | |
| "num_input_tokens_seen": 185952, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.699099099099099, | |
| "grad_norm": 8.044764518737793, | |
| "learning_rate": 0.00015666666666666666, | |
| "loss": 2.9845, | |
| "num_input_tokens_seen": 189120, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.7351351351351352, | |
| "grad_norm": 4.376863956451416, | |
| "learning_rate": 0.00016, | |
| "loss": 2.5886, | |
| "num_input_tokens_seen": 193440, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.7711711711711713, | |
| "grad_norm": 7.085455417633057, | |
| "learning_rate": 0.00016333333333333334, | |
| "loss": 3.0422, | |
| "num_input_tokens_seen": 197248, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.8072072072072072, | |
| "grad_norm": 8.856867790222168, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 2.9034, | |
| "num_input_tokens_seen": 200096, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.8432432432432433, | |
| "grad_norm": 6.714722633361816, | |
| "learning_rate": 0.00017, | |
| "loss": 2.5464, | |
| "num_input_tokens_seen": 203792, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.8792792792792792, | |
| "grad_norm": 8.368040084838867, | |
| "learning_rate": 0.00017333333333333334, | |
| "loss": 3.1094, | |
| "num_input_tokens_seen": 206784, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.9153153153153153, | |
| "grad_norm": 7.750094413757324, | |
| "learning_rate": 0.00017666666666666666, | |
| "loss": 2.901, | |
| "num_input_tokens_seen": 210064, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.9513513513513514, | |
| "grad_norm": 7.384438991546631, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8172, | |
| "num_input_tokens_seen": 213520, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.9873873873873875, | |
| "grad_norm": 5.683988571166992, | |
| "learning_rate": 0.00018333333333333334, | |
| "loss": 2.8409, | |
| "num_input_tokens_seen": 216752, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.028828828828829, | |
| "grad_norm": 6.135600566864014, | |
| "learning_rate": 0.0001866666666666667, | |
| "loss": 2.6342, | |
| "num_input_tokens_seen": 220320, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.064864864864865, | |
| "grad_norm": 14.494550704956055, | |
| "learning_rate": 0.00019, | |
| "loss": 1.7648, | |
| "num_input_tokens_seen": 223808, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.1009009009009008, | |
| "grad_norm": 7.6210551261901855, | |
| "learning_rate": 0.00019333333333333333, | |
| "loss": 2.0011, | |
| "num_input_tokens_seen": 227280, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.136936936936937, | |
| "grad_norm": 6.052605628967285, | |
| "learning_rate": 0.00019666666666666666, | |
| "loss": 2.0263, | |
| "num_input_tokens_seen": 230656, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.172972972972973, | |
| "grad_norm": 9.172389030456543, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6316, | |
| "num_input_tokens_seen": 233776, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.172972972972973, | |
| "eval_loss": 3.5101757049560547, | |
| "eval_runtime": 0.2957, | |
| "eval_samples_per_second": 16.907, | |
| "eval_steps_per_second": 10.144, | |
| "num_input_tokens_seen": 233776, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.209009009009009, | |
| "grad_norm": 7.576519966125488, | |
| "learning_rate": 0.00019991889981715698, | |
| "loss": 2.0076, | |
| "num_input_tokens_seen": 237312, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.245045045045045, | |
| "grad_norm": 6.638524532318115, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 1.9773, | |
| "num_input_tokens_seen": 240736, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.281081081081081, | |
| "grad_norm": 4.5822906494140625, | |
| "learning_rate": 0.0001992708874098054, | |
| "loss": 1.6004, | |
| "num_input_tokens_seen": 248352, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.317117117117117, | |
| "grad_norm": 11.44710636138916, | |
| "learning_rate": 0.00019870502626379127, | |
| "loss": 2.0804, | |
| "num_input_tokens_seen": 252048, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.353153153153153, | |
| "grad_norm": 11.596573829650879, | |
| "learning_rate": 0.00019797906520422677, | |
| "loss": 1.8889, | |
| "num_input_tokens_seen": 255056, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.389189189189189, | |
| "grad_norm": 7.399219036102295, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 1.6757, | |
| "num_input_tokens_seen": 262768, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.4252252252252253, | |
| "grad_norm": 9.732112884521484, | |
| "learning_rate": 0.00019605181116313724, | |
| "loss": 1.8391, | |
| "num_input_tokens_seen": 265616, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.4612612612612614, | |
| "grad_norm": 11.036967277526855, | |
| "learning_rate": 0.00019485364419471454, | |
| "loss": 2.1077, | |
| "num_input_tokens_seen": 269040, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.4972972972972975, | |
| "grad_norm": 8.808915138244629, | |
| "learning_rate": 0.0001935016242685415, | |
| "loss": 1.7143, | |
| "num_input_tokens_seen": 272256, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.533333333333333, | |
| "grad_norm": 8.189955711364746, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 1.7009, | |
| "num_input_tokens_seen": 275312, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.5693693693693693, | |
| "grad_norm": 7.398507118225098, | |
| "learning_rate": 0.00019034504346103823, | |
| "loss": 2.174, | |
| "num_input_tokens_seen": 278928, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.6054054054054054, | |
| "grad_norm": 10.141551971435547, | |
| "learning_rate": 0.000188545602565321, | |
| "loss": 2.0016, | |
| "num_input_tokens_seen": 282256, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.6414414414414416, | |
| "grad_norm": 7.210516929626465, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.9766, | |
| "num_input_tokens_seen": 285616, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.6774774774774777, | |
| "grad_norm": 9.60509967803955, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 2.034, | |
| "num_input_tokens_seen": 292624, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.7135135135135133, | |
| "grad_norm": 7.727905750274658, | |
| "learning_rate": 0.00018229838658936564, | |
| "loss": 1.9747, | |
| "num_input_tokens_seen": 295760, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.7495495495495494, | |
| "grad_norm": 7.084625244140625, | |
| "learning_rate": 0.00017994427634035015, | |
| "loss": 2.2312, | |
| "num_input_tokens_seen": 298880, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.7855855855855856, | |
| "grad_norm": 8.565605163574219, | |
| "learning_rate": 0.00017746049618276545, | |
| "loss": 1.7228, | |
| "num_input_tokens_seen": 305968, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.8216216216216217, | |
| "grad_norm": 7.990584850311279, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 2.0828, | |
| "num_input_tokens_seen": 309680, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.857657657657658, | |
| "grad_norm": 8.152718544006348, | |
| "learning_rate": 0.00017212024473438147, | |
| "loss": 2.2638, | |
| "num_input_tokens_seen": 312752, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 2.8936936936936934, | |
| "grad_norm": 8.080291748046875, | |
| "learning_rate": 0.00016927243535095997, | |
| "loss": 2.1471, | |
| "num_input_tokens_seen": 316096, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.8936936936936934, | |
| "eval_loss": 3.6192080974578857, | |
| "eval_runtime": 0.2961, | |
| "eval_samples_per_second": 16.888, | |
| "eval_steps_per_second": 10.133, | |
| "num_input_tokens_seen": 316096, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02888344105192779, | |
| "grad_norm": 2.729156255722046, | |
| "learning_rate": 0.00019997110279082795, | |
| "loss": 2.2111, | |
| "num_input_tokens_seen": 328800, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.0292400267439269, | |
| "grad_norm": 1.5953912734985352, | |
| "learning_rate": 0.00019996828529806075, | |
| "loss": 1.7657, | |
| "num_input_tokens_seen": 342272, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.02959661243592601, | |
| "grad_norm": 1.2057961225509644, | |
| "learning_rate": 0.0001999653367874579, | |
| "loss": 1.9321, | |
| "num_input_tokens_seen": 354880, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.02995319812792512, | |
| "grad_norm": 1.0265964269638062, | |
| "learning_rate": 0.00019996225726288367, | |
| "loss": 1.7011, | |
| "num_input_tokens_seen": 369008, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.030309783819924226, | |
| "grad_norm": 1.1587436199188232, | |
| "learning_rate": 0.00019995904672837406, | |
| "loss": 1.8462, | |
| "num_input_tokens_seen": 382416, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.030666369511923332, | |
| "grad_norm": 1.5749984979629517, | |
| "learning_rate": 0.00019995570518813679, | |
| "loss": 1.6671, | |
| "num_input_tokens_seen": 394608, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.031022955203922443, | |
| "grad_norm": 0.9112032055854797, | |
| "learning_rate": 0.00019995223264655126, | |
| "loss": 1.6305, | |
| "num_input_tokens_seen": 408576, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.03137954089592155, | |
| "grad_norm": 1.300126075744629, | |
| "learning_rate": 0.00019994862910816856, | |
| "loss": 1.5954, | |
| "num_input_tokens_seen": 422848, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.03173612658792066, | |
| "grad_norm": 0.9108946323394775, | |
| "learning_rate": 0.00019994489457771146, | |
| "loss": 1.6211, | |
| "num_input_tokens_seen": 437920, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.03209271227991977, | |
| "grad_norm": 1.2991251945495605, | |
| "learning_rate": 0.00019994102906007447, | |
| "loss": 1.8802, | |
| "num_input_tokens_seen": 449264, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.032449297971918874, | |
| "grad_norm": 1.0694671869277954, | |
| "learning_rate": 0.0001999370325603236, | |
| "loss": 1.828, | |
| "num_input_tokens_seen": 461680, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.032805883663917984, | |
| "grad_norm": 0.929099440574646, | |
| "learning_rate": 0.00019993290508369673, | |
| "loss": 1.5744, | |
| "num_input_tokens_seen": 475520, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.033162469355917094, | |
| "grad_norm": 1.2470440864562988, | |
| "learning_rate": 0.00019992864663560329, | |
| "loss": 1.7386, | |
| "num_input_tokens_seen": 487968, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.033519055047916205, | |
| "grad_norm": 0.9236185550689697, | |
| "learning_rate": 0.00019992425722162435, | |
| "loss": 1.5627, | |
| "num_input_tokens_seen": 501696, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.03387564073991531, | |
| "grad_norm": 1.1745721101760864, | |
| "learning_rate": 0.00019991973684751267, | |
| "loss": 1.5464, | |
| "num_input_tokens_seen": 514864, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.03423222643191442, | |
| "grad_norm": 1.0948406457901, | |
| "learning_rate": 0.0001999150855191926, | |
| "loss": 1.5185, | |
| "num_input_tokens_seen": 526304, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.03458881212391353, | |
| "grad_norm": 0.8970179557800293, | |
| "learning_rate": 0.00019991030324276022, | |
| "loss": 1.7223, | |
| "num_input_tokens_seen": 537648, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.03494539781591264, | |
| "grad_norm": 1.3912155628204346, | |
| "learning_rate": 0.00019990539002448307, | |
| "loss": 1.5333, | |
| "num_input_tokens_seen": 550144, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.03530198350791174, | |
| "grad_norm": 1.0233279466629028, | |
| "learning_rate": 0.0001999003458708004, | |
| "loss": 1.695, | |
| "num_input_tokens_seen": 564336, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.03565856919991085, | |
| "grad_norm": 1.1323829889297485, | |
| "learning_rate": 0.00019989517078832308, | |
| "loss": 1.864, | |
| "num_input_tokens_seen": 578144, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03565856919991085, | |
| "eval_loss": 1.5353425741195679, | |
| "eval_runtime": 25.9763, | |
| "eval_samples_per_second": 17.323, | |
| "eval_steps_per_second": 8.662, | |
| "num_input_tokens_seen": 578144, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03601515489190996, | |
| "grad_norm": 1.0973526239395142, | |
| "learning_rate": 0.0001998898647838335, | |
| "loss": 1.5819, | |
| "num_input_tokens_seen": 589952, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.036371740583909073, | |
| "grad_norm": 1.1353367567062378, | |
| "learning_rate": 0.0001998844278642857, | |
| "loss": 1.6855, | |
| "num_input_tokens_seen": 604288, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.03672832627590818, | |
| "grad_norm": 0.9509443640708923, | |
| "learning_rate": 0.0001998788600368053, | |
| "loss": 1.6287, | |
| "num_input_tokens_seen": 617344, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.03708491196790729, | |
| "grad_norm": 1.1190470457077026, | |
| "learning_rate": 0.0001998731613086894, | |
| "loss": 1.5082, | |
| "num_input_tokens_seen": 630464, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.0374414976599064, | |
| "grad_norm": 0.9811726808547974, | |
| "learning_rate": 0.00019986733168740676, | |
| "loss": 1.6331, | |
| "num_input_tokens_seen": 640992, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.03779808335190551, | |
| "grad_norm": 0.9463362693786621, | |
| "learning_rate": 0.00019986137118059767, | |
| "loss": 1.7424, | |
| "num_input_tokens_seen": 652944, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.03815466904390461, | |
| "grad_norm": 0.8193320631980896, | |
| "learning_rate": 0.00019985527979607385, | |
| "loss": 1.6713, | |
| "num_input_tokens_seen": 667408, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.03851125473590372, | |
| "grad_norm": 0.7664808630943298, | |
| "learning_rate": 0.00019984905754181874, | |
| "loss": 1.5241, | |
| "num_input_tokens_seen": 681968, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.03886784042790283, | |
| "grad_norm": 0.7736773490905762, | |
| "learning_rate": 0.00019984270442598712, | |
| "loss": 1.6653, | |
| "num_input_tokens_seen": 695968, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.03922442611990194, | |
| "grad_norm": 0.8348143696784973, | |
| "learning_rate": 0.00019983622045690536, | |
| "loss": 1.6706, | |
| "num_input_tokens_seen": 709040, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.039581011811901046, | |
| "grad_norm": 0.938188374042511, | |
| "learning_rate": 0.00019982960564307129, | |
| "loss": 1.4911, | |
| "num_input_tokens_seen": 721712, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.039937597503900156, | |
| "grad_norm": 1.1161514520645142, | |
| "learning_rate": 0.0001998228599931543, | |
| "loss": 1.6092, | |
| "num_input_tokens_seen": 734896, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.040294183195899266, | |
| "grad_norm": 1.0454977750778198, | |
| "learning_rate": 0.00019981598351599515, | |
| "loss": 1.5464, | |
| "num_input_tokens_seen": 749472, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.04065076888789837, | |
| "grad_norm": 1.1589754819869995, | |
| "learning_rate": 0.00019980897622060614, | |
| "loss": 1.6342, | |
| "num_input_tokens_seen": 761968, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.04100735457989748, | |
| "grad_norm": 1.0694705247879028, | |
| "learning_rate": 0.00019980183811617094, | |
| "loss": 1.6302, | |
| "num_input_tokens_seen": 774112, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.04136394027189659, | |
| "grad_norm": 1.0234978199005127, | |
| "learning_rate": 0.00019979456921204479, | |
| "loss": 1.7415, | |
| "num_input_tokens_seen": 786016, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.0417205259638957, | |
| "grad_norm": 0.8734306693077087, | |
| "learning_rate": 0.00019978716951775418, | |
| "loss": 1.4202, | |
| "num_input_tokens_seen": 797520, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.042077111655894804, | |
| "grad_norm": 1.0587542057037354, | |
| "learning_rate": 0.0001997796390429972, | |
| "loss": 1.4963, | |
| "num_input_tokens_seen": 810448, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.042433697347893914, | |
| "grad_norm": 1.0301488637924194, | |
| "learning_rate": 0.00019977197779764313, | |
| "loss": 1.7623, | |
| "num_input_tokens_seen": 824176, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.042790283039893025, | |
| "grad_norm": 0.8244880437850952, | |
| "learning_rate": 0.00019976418579173286, | |
| "loss": 1.5259, | |
| "num_input_tokens_seen": 837264, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.042790283039893025, | |
| "eval_loss": 1.4980205297470093, | |
| "eval_runtime": 25.9775, | |
| "eval_samples_per_second": 17.323, | |
| "eval_steps_per_second": 8.661, | |
| "num_input_tokens_seen": 837264, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.043146868731892135, | |
| "grad_norm": 0.9113627076148987, | |
| "learning_rate": 0.0001997562630354785, | |
| "loss": 1.7852, | |
| "num_input_tokens_seen": 849456, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.04350345442389124, | |
| "grad_norm": 0.8031953573226929, | |
| "learning_rate": 0.0001997482095392636, | |
| "loss": 1.4472, | |
| "num_input_tokens_seen": 861488, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.04386004011589035, | |
| "grad_norm": 1.3095686435699463, | |
| "learning_rate": 0.00019974002531364293, | |
| "loss": 1.6599, | |
| "num_input_tokens_seen": 872416, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.04421662580788946, | |
| "grad_norm": 1.1288928985595703, | |
| "learning_rate": 0.0001997317103693428, | |
| "loss": 1.5452, | |
| "num_input_tokens_seen": 884592, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.04457321149988857, | |
| "grad_norm": 0.909373939037323, | |
| "learning_rate": 0.00019972326471726063, | |
| "loss": 1.5212, | |
| "num_input_tokens_seen": 897120, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.04492979719188767, | |
| "grad_norm": 1.1868454217910767, | |
| "learning_rate": 0.00019971468836846532, | |
| "loss": 1.5916, | |
| "num_input_tokens_seen": 907232, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.04528638288388678, | |
| "grad_norm": 0.9705728888511658, | |
| "learning_rate": 0.00019970598133419695, | |
| "loss": 1.5263, | |
| "num_input_tokens_seen": 920480, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.045642968575885894, | |
| "grad_norm": 1.021158218383789, | |
| "learning_rate": 0.0001996971436258669, | |
| "loss": 1.5248, | |
| "num_input_tokens_seen": 932960, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.045999554267885004, | |
| "grad_norm": 0.9590160846710205, | |
| "learning_rate": 0.0001996881752550578, | |
| "loss": 1.4684, | |
| "num_input_tokens_seen": 946832, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.04635613995988411, | |
| "grad_norm": 0.7721974849700928, | |
| "learning_rate": 0.00019967907623352361, | |
| "loss": 1.663, | |
| "num_input_tokens_seen": 960880, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.04671272565188322, | |
| "grad_norm": 0.913921058177948, | |
| "learning_rate": 0.0001996698465731894, | |
| "loss": 1.7776, | |
| "num_input_tokens_seen": 973312, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.04706931134388233, | |
| "grad_norm": 0.7938061356544495, | |
| "learning_rate": 0.00019966048628615148, | |
| "loss": 1.5013, | |
| "num_input_tokens_seen": 986944, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.04742589703588144, | |
| "grad_norm": 1.2008130550384521, | |
| "learning_rate": 0.00019965099538467746, | |
| "loss": 1.5296, | |
| "num_input_tokens_seen": 1001280, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.04778248272788054, | |
| "grad_norm": 0.9730687737464905, | |
| "learning_rate": 0.00019964137388120602, | |
| "loss": 1.7029, | |
| "num_input_tokens_seen": 1012784, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.04813906841987965, | |
| "grad_norm": 1.1330794095993042, | |
| "learning_rate": 0.00019963162178834705, | |
| "loss": 1.4998, | |
| "num_input_tokens_seen": 1024640, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.04849565411187876, | |
| "grad_norm": 0.9690409302711487, | |
| "learning_rate": 0.00019962173911888158, | |
| "loss": 1.4893, | |
| "num_input_tokens_seen": 1037392, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.04885223980387787, | |
| "grad_norm": 1.1701139211654663, | |
| "learning_rate": 0.00019961172588576175, | |
| "loss": 1.5194, | |
| "num_input_tokens_seen": 1049264, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.049208825495876976, | |
| "grad_norm": 0.9897874593734741, | |
| "learning_rate": 0.0001996015821021109, | |
| "loss": 1.4361, | |
| "num_input_tokens_seen": 1062144, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.049565411187876086, | |
| "grad_norm": 0.9895176887512207, | |
| "learning_rate": 0.00019959130778122338, | |
| "loss": 1.6835, | |
| "num_input_tokens_seen": 1074480, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.0499219968798752, | |
| "grad_norm": 0.7624967098236084, | |
| "learning_rate": 0.00019958090293656464, | |
| "loss": 1.6569, | |
| "num_input_tokens_seen": 1088624, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.0499219968798752, | |
| "eval_loss": 1.4771517515182495, | |
| "eval_runtime": 25.9347, | |
| "eval_samples_per_second": 17.351, | |
| "eval_steps_per_second": 8.676, | |
| "num_input_tokens_seen": 1088624, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.0502785825718743, | |
| "grad_norm": 1.0006903409957886, | |
| "learning_rate": 0.00019957036758177124, | |
| "loss": 1.763, | |
| "num_input_tokens_seen": 1099952, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.05063516826387341, | |
| "grad_norm": 0.8108828067779541, | |
| "learning_rate": 0.00019955970173065075, | |
| "loss": 1.4925, | |
| "num_input_tokens_seen": 1113952, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.05099175395587252, | |
| "grad_norm": 1.0443133115768433, | |
| "learning_rate": 0.00019954890539718173, | |
| "loss": 1.5073, | |
| "num_input_tokens_seen": 1129488, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.05134833964787163, | |
| "grad_norm": 0.6349768042564392, | |
| "learning_rate": 0.00019953797859551385, | |
| "loss": 1.825, | |
| "num_input_tokens_seen": 1145296, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.051704925339870735, | |
| "grad_norm": 1.1168112754821777, | |
| "learning_rate": 0.00019952692133996767, | |
| "loss": 1.5229, | |
| "num_input_tokens_seen": 1157936, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.052061511031869845, | |
| "grad_norm": 0.8870391249656677, | |
| "learning_rate": 0.00019951573364503474, | |
| "loss": 1.5875, | |
| "num_input_tokens_seen": 1171040, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.052418096723868955, | |
| "grad_norm": 1.017572283744812, | |
| "learning_rate": 0.00019950441552537768, | |
| "loss": 1.6827, | |
| "num_input_tokens_seen": 1185616, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.052774682415868066, | |
| "grad_norm": 0.7321210503578186, | |
| "learning_rate": 0.00019949296699582983, | |
| "loss": 1.633, | |
| "num_input_tokens_seen": 1197824, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.05313126810786717, | |
| "grad_norm": 0.8157454133033752, | |
| "learning_rate": 0.00019948138807139563, | |
| "loss": 1.6336, | |
| "num_input_tokens_seen": 1209120, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.05348785379986628, | |
| "grad_norm": 1.0458636283874512, | |
| "learning_rate": 0.00019946967876725036, | |
| "loss": 1.6223, | |
| "num_input_tokens_seen": 1220112, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.05384443949186539, | |
| "grad_norm": 1.1940375566482544, | |
| "learning_rate": 0.00019945783909874014, | |
| "loss": 1.7688, | |
| "num_input_tokens_seen": 1231328, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.0542010251838645, | |
| "grad_norm": 0.870665431022644, | |
| "learning_rate": 0.00019944586908138197, | |
| "loss": 1.7899, | |
| "num_input_tokens_seen": 1245488, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.0545576108758636, | |
| "grad_norm": 1.010379433631897, | |
| "learning_rate": 0.0001994337687308637, | |
| "loss": 1.5405, | |
| "num_input_tokens_seen": 1257792, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.054914196567862714, | |
| "grad_norm": 0.7964643239974976, | |
| "learning_rate": 0.00019942153806304394, | |
| "loss": 1.5962, | |
| "num_input_tokens_seen": 1271088, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.055270782259861824, | |
| "grad_norm": 0.8049175143241882, | |
| "learning_rate": 0.00019940917709395216, | |
| "loss": 1.4369, | |
| "num_input_tokens_seen": 1282912, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.055627367951860934, | |
| "grad_norm": 1.1336143016815186, | |
| "learning_rate": 0.00019939668583978857, | |
| "loss": 1.5273, | |
| "num_input_tokens_seen": 1295904, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.05598395364386004, | |
| "grad_norm": 1.0602260828018188, | |
| "learning_rate": 0.00019938406431692412, | |
| "loss": 1.6961, | |
| "num_input_tokens_seen": 1308816, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.05634053933585915, | |
| "grad_norm": 0.991144597530365, | |
| "learning_rate": 0.0001993713125419005, | |
| "loss": 1.6196, | |
| "num_input_tokens_seen": 1320768, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.05669712502785826, | |
| "grad_norm": 1.162597417831421, | |
| "learning_rate": 0.00019935843053143013, | |
| "loss": 1.5991, | |
| "num_input_tokens_seen": 1333520, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.05705371071985737, | |
| "grad_norm": 1.01413893699646, | |
| "learning_rate": 0.0001993454183023961, | |
| "loss": 1.6086, | |
| "num_input_tokens_seen": 1345120, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.05705371071985737, | |
| "eval_loss": 1.4568166732788086, | |
| "eval_runtime": 25.9764, | |
| "eval_samples_per_second": 17.323, | |
| "eval_steps_per_second": 8.662, | |
| "num_input_tokens_seen": 1345120, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.05741029641185647, | |
| "grad_norm": 1.002255916595459, | |
| "learning_rate": 0.00019933227587185214, | |
| "loss": 1.5361, | |
| "num_input_tokens_seen": 1357760, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.05776688210385558, | |
| "grad_norm": 0.9191799759864807, | |
| "learning_rate": 0.00019931900325702263, | |
| "loss": 1.4695, | |
| "num_input_tokens_seen": 1369728, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.05812346779585469, | |
| "grad_norm": 1.1915909051895142, | |
| "learning_rate": 0.00019930560047530264, | |
| "loss": 1.536, | |
| "num_input_tokens_seen": 1381664, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.0584800534878538, | |
| "grad_norm": 1.1932401657104492, | |
| "learning_rate": 0.00019929206754425768, | |
| "loss": 1.6324, | |
| "num_input_tokens_seen": 1397072, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.058836639179852906, | |
| "grad_norm": 0.7846195697784424, | |
| "learning_rate": 0.00019927840448162397, | |
| "loss": 1.5848, | |
| "num_input_tokens_seen": 1411456, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.05919322487185202, | |
| "grad_norm": 0.9281952381134033, | |
| "learning_rate": 0.0001992646113053083, | |
| "loss": 1.5532, | |
| "num_input_tokens_seen": 1423040, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.05954981056385113, | |
| "grad_norm": 0.8611142039299011, | |
| "learning_rate": 0.00019925068803338785, | |
| "loss": 1.4567, | |
| "num_input_tokens_seen": 1434832, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.05990639625585024, | |
| "grad_norm": 0.900896430015564, | |
| "learning_rate": 0.00019923663468411038, | |
| "loss": 1.423, | |
| "num_input_tokens_seen": 1449904, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.06026298194784934, | |
| "grad_norm": 0.7716097831726074, | |
| "learning_rate": 0.00019922245127589413, | |
| "loss": 1.6289, | |
| "num_input_tokens_seen": 1462224, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.06061956763984845, | |
| "grad_norm": 1.0148396492004395, | |
| "learning_rate": 0.00019920813782732785, | |
| "loss": 1.5684, | |
| "num_input_tokens_seen": 1473344, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.06097615333184756, | |
| "grad_norm": 1.283855676651001, | |
| "learning_rate": 0.0001991936943571706, | |
| "loss": 1.3161, | |
| "num_input_tokens_seen": 1487152, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.061332739023846665, | |
| "grad_norm": 0.8233208656311035, | |
| "learning_rate": 0.0001991791208843519, | |
| "loss": 1.526, | |
| "num_input_tokens_seen": 1500496, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.061689324715845775, | |
| "grad_norm": 1.0969665050506592, | |
| "learning_rate": 0.00019916441742797168, | |
| "loss": 1.5244, | |
| "num_input_tokens_seen": 1514480, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.062045910407844886, | |
| "grad_norm": 0.8461065292358398, | |
| "learning_rate": 0.0001991495840073002, | |
| "loss": 1.446, | |
| "num_input_tokens_seen": 1527920, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.062402496099843996, | |
| "grad_norm": 0.8559203147888184, | |
| "learning_rate": 0.00019913462064177805, | |
| "loss": 1.4903, | |
| "num_input_tokens_seen": 1540000, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.0627590817918431, | |
| "grad_norm": 0.9753026366233826, | |
| "learning_rate": 0.00019911952735101614, | |
| "loss": 1.5945, | |
| "num_input_tokens_seen": 1550800, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.06311566748384222, | |
| "grad_norm": 1.038980484008789, | |
| "learning_rate": 0.0001991043041547956, | |
| "loss": 1.7116, | |
| "num_input_tokens_seen": 1562272, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.06347225317584132, | |
| "grad_norm": 0.8071208000183105, | |
| "learning_rate": 0.00019908895107306792, | |
| "loss": 1.6224, | |
| "num_input_tokens_seen": 1574672, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.06382883886784042, | |
| "grad_norm": 0.9644535183906555, | |
| "learning_rate": 0.00019907346812595474, | |
| "loss": 1.4743, | |
| "num_input_tokens_seen": 1587840, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.06418542455983954, | |
| "grad_norm": 0.9939907193183899, | |
| "learning_rate": 0.00019905785533374788, | |
| "loss": 1.6472, | |
| "num_input_tokens_seen": 1600928, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.06418542455983954, | |
| "eval_loss": 1.4476536512374878, | |
| "eval_runtime": 25.9327, | |
| "eval_samples_per_second": 17.353, | |
| "eval_steps_per_second": 8.676, | |
| "num_input_tokens_seen": 1600928, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.06454201025183864, | |
| "grad_norm": 1.1221510171890259, | |
| "learning_rate": 0.0001990421127169094, | |
| "loss": 1.58, | |
| "num_input_tokens_seen": 1614560, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.06489859594383775, | |
| "grad_norm": 0.6738218665122986, | |
| "learning_rate": 0.0001990262402960715, | |
| "loss": 1.5166, | |
| "num_input_tokens_seen": 1628448, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.06525518163583686, | |
| "grad_norm": 1.1361334323883057, | |
| "learning_rate": 0.00019901023809203644, | |
| "loss": 1.3501, | |
| "num_input_tokens_seen": 1639888, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.06561176732783597, | |
| "grad_norm": 0.86082923412323, | |
| "learning_rate": 0.00019899410612577662, | |
| "loss": 1.6196, | |
| "num_input_tokens_seen": 1653776, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.06596835301983509, | |
| "grad_norm": 1.001594066619873, | |
| "learning_rate": 0.0001989778444184345, | |
| "loss": 1.7417, | |
| "num_input_tokens_seen": 1667536, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.06632493871183419, | |
| "grad_norm": 0.9237222671508789, | |
| "learning_rate": 0.00019896145299132262, | |
| "loss": 1.5764, | |
| "num_input_tokens_seen": 1678976, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.06668152440383329, | |
| "grad_norm": 1.0402158498764038, | |
| "learning_rate": 0.00019894493186592345, | |
| "loss": 1.5937, | |
| "num_input_tokens_seen": 1691424, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.06703811009583241, | |
| "grad_norm": 0.9966005086898804, | |
| "learning_rate": 0.00019892828106388946, | |
| "loss": 1.376, | |
| "num_input_tokens_seen": 1704144, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.06739469578783151, | |
| "grad_norm": 0.9723909497261047, | |
| "learning_rate": 0.00019891150060704312, | |
| "loss": 1.5858, | |
| "num_input_tokens_seen": 1716832, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.06775128147983062, | |
| "grad_norm": 0.849105715751648, | |
| "learning_rate": 0.00019889459051737677, | |
| "loss": 1.5743, | |
| "num_input_tokens_seen": 1729408, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.06810786717182973, | |
| "grad_norm": 0.718659520149231, | |
| "learning_rate": 0.0001988775508170527, | |
| "loss": 1.5805, | |
| "num_input_tokens_seen": 1741456, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.06846445286382884, | |
| "grad_norm": 1.210124135017395, | |
| "learning_rate": 0.00019886038152840306, | |
| "loss": 1.2253, | |
| "num_input_tokens_seen": 1752928, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.06882103855582795, | |
| "grad_norm": 0.8950662612915039, | |
| "learning_rate": 0.00019884308267392972, | |
| "loss": 1.5651, | |
| "num_input_tokens_seen": 1766736, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.06917762424782706, | |
| "grad_norm": 0.7714616060256958, | |
| "learning_rate": 0.00019882565427630454, | |
| "loss": 1.5761, | |
| "num_input_tokens_seen": 1778432, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.06953420993982616, | |
| "grad_norm": 0.9974557757377625, | |
| "learning_rate": 0.0001988080963583691, | |
| "loss": 1.5444, | |
| "num_input_tokens_seen": 1790368, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.06989079563182528, | |
| "grad_norm": 1.1878458261489868, | |
| "learning_rate": 0.0001987904089431346, | |
| "loss": 1.7706, | |
| "num_input_tokens_seen": 1802512, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.07024738132382438, | |
| "grad_norm": 0.9763291478157043, | |
| "learning_rate": 0.00019877259205378214, | |
| "loss": 1.4229, | |
| "num_input_tokens_seen": 1813488, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.07060396701582348, | |
| "grad_norm": 1.0481489896774292, | |
| "learning_rate": 0.00019875464571366243, | |
| "loss": 1.3622, | |
| "num_input_tokens_seen": 1826064, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.0709605527078226, | |
| "grad_norm": 0.9758256077766418, | |
| "learning_rate": 0.00019873656994629575, | |
| "loss": 1.3448, | |
| "num_input_tokens_seen": 1837856, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.0713171383998217, | |
| "grad_norm": 0.7545611262321472, | |
| "learning_rate": 0.0001987183647753722, | |
| "loss": 1.5894, | |
| "num_input_tokens_seen": 1850160, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0713171383998217, | |
| "eval_loss": 1.4465608596801758, | |
| "eval_runtime": 25.9554, | |
| "eval_samples_per_second": 17.337, | |
| "eval_steps_per_second": 8.669, | |
| "num_input_tokens_seen": 1850160, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 14021, | |
| "num_input_tokens_seen": 1850160, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.354467259154432e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |