| { | |
| "best_global_step": 5092, | |
| "best_metric": 6.146888256072998, | |
| "best_model_checkpoint": "saves/prefix-tuning/llama-3-8b-instruct/train_conala_1754652182/checkpoint-5092", | |
| "epoch": 10.0, | |
| "eval_steps": 268, | |
| "global_step": 5360, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009328358208955223, | |
| "grad_norm": 2.397639036178589, | |
| "learning_rate": 3.7313432835820895e-07, | |
| "loss": 13.2168, | |
| "num_input_tokens_seen": 1216, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018656716417910446, | |
| "grad_norm": 2.3020761013031006, | |
| "learning_rate": 8.395522388059702e-07, | |
| "loss": 13.33, | |
| "num_input_tokens_seen": 2528, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027985074626865673, | |
| "grad_norm": 1.7429076433181763, | |
| "learning_rate": 1.3059701492537314e-06, | |
| "loss": 13.2815, | |
| "num_input_tokens_seen": 4160, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03731343283582089, | |
| "grad_norm": 1.82960844039917, | |
| "learning_rate": 1.7723880597014925e-06, | |
| "loss": 13.1251, | |
| "num_input_tokens_seen": 5504, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04664179104477612, | |
| "grad_norm": 2.5426459312438965, | |
| "learning_rate": 2.238805970149254e-06, | |
| "loss": 13.0321, | |
| "num_input_tokens_seen": 6912, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.055970149253731345, | |
| "grad_norm": 1.7387545108795166, | |
| "learning_rate": 2.705223880597015e-06, | |
| "loss": 13.1437, | |
| "num_input_tokens_seen": 8544, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06529850746268656, | |
| "grad_norm": 2.2837631702423096, | |
| "learning_rate": 3.171641791044776e-06, | |
| "loss": 13.1011, | |
| "num_input_tokens_seen": 9696, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 1.9266175031661987, | |
| "learning_rate": 3.6380597014925376e-06, | |
| "loss": 13.3047, | |
| "num_input_tokens_seen": 10976, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08395522388059702, | |
| "grad_norm": 2.1445538997650146, | |
| "learning_rate": 4.1044776119402985e-06, | |
| "loss": 13.4022, | |
| "num_input_tokens_seen": 12320, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09328358208955224, | |
| "grad_norm": 1.645679235458374, | |
| "learning_rate": 4.57089552238806e-06, | |
| "loss": 13.1273, | |
| "num_input_tokens_seen": 13920, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10261194029850747, | |
| "grad_norm": 1.5380349159240723, | |
| "learning_rate": 5.037313432835821e-06, | |
| "loss": 12.9637, | |
| "num_input_tokens_seen": 15456, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.11194029850746269, | |
| "grad_norm": 1.5596805810928345, | |
| "learning_rate": 5.503731343283583e-06, | |
| "loss": 12.7974, | |
| "num_input_tokens_seen": 16864, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12126865671641791, | |
| "grad_norm": 1.4138047695159912, | |
| "learning_rate": 5.970149253731343e-06, | |
| "loss": 12.7056, | |
| "num_input_tokens_seen": 18336, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.13059701492537312, | |
| "grad_norm": 1.4869558811187744, | |
| "learning_rate": 6.436567164179105e-06, | |
| "loss": 13.0199, | |
| "num_input_tokens_seen": 19712, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13992537313432835, | |
| "grad_norm": 1.7431681156158447, | |
| "learning_rate": 6.902985074626867e-06, | |
| "loss": 12.9362, | |
| "num_input_tokens_seen": 21152, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 1.3312933444976807, | |
| "learning_rate": 7.369402985074628e-06, | |
| "loss": 12.9771, | |
| "num_input_tokens_seen": 22560, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.15858208955223882, | |
| "grad_norm": 1.39218270778656, | |
| "learning_rate": 7.835820895522389e-06, | |
| "loss": 12.8802, | |
| "num_input_tokens_seen": 23968, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.16791044776119404, | |
| "grad_norm": 1.9604254961013794, | |
| "learning_rate": 8.30223880597015e-06, | |
| "loss": 12.6029, | |
| "num_input_tokens_seen": 25600, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.17723880597014927, | |
| "grad_norm": 1.5197497606277466, | |
| "learning_rate": 8.768656716417911e-06, | |
| "loss": 12.9174, | |
| "num_input_tokens_seen": 26912, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1865671641791045, | |
| "grad_norm": 1.3315889835357666, | |
| "learning_rate": 9.235074626865672e-06, | |
| "loss": 12.9595, | |
| "num_input_tokens_seen": 28512, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1958955223880597, | |
| "grad_norm": 1.5090032815933228, | |
| "learning_rate": 9.701492537313434e-06, | |
| "loss": 12.563, | |
| "num_input_tokens_seen": 29888, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.20522388059701493, | |
| "grad_norm": 1.4965084791183472, | |
| "learning_rate": 1.0167910447761195e-05, | |
| "loss": 12.834, | |
| "num_input_tokens_seen": 31296, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.21455223880597016, | |
| "grad_norm": 1.4857761859893799, | |
| "learning_rate": 1.0634328358208955e-05, | |
| "loss": 12.7311, | |
| "num_input_tokens_seen": 32736, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 1.4428954124450684, | |
| "learning_rate": 1.1100746268656717e-05, | |
| "loss": 12.5369, | |
| "num_input_tokens_seen": 34240, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2332089552238806, | |
| "grad_norm": 1.5920934677124023, | |
| "learning_rate": 1.1567164179104478e-05, | |
| "loss": 12.1094, | |
| "num_input_tokens_seen": 35648, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.24253731343283583, | |
| "grad_norm": 1.3137093782424927, | |
| "learning_rate": 1.203358208955224e-05, | |
| "loss": 12.5198, | |
| "num_input_tokens_seen": 36992, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.251865671641791, | |
| "grad_norm": 1.3018798828125, | |
| "learning_rate": 1.25e-05, | |
| "loss": 12.3252, | |
| "num_input_tokens_seen": 38528, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.26119402985074625, | |
| "grad_norm": 1.5600255727767944, | |
| "learning_rate": 1.2966417910447761e-05, | |
| "loss": 12.3243, | |
| "num_input_tokens_seen": 39840, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.27052238805970147, | |
| "grad_norm": 1.358655333518982, | |
| "learning_rate": 1.3432835820895523e-05, | |
| "loss": 12.2945, | |
| "num_input_tokens_seen": 41216, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.2798507462686567, | |
| "grad_norm": 1.2274936437606812, | |
| "learning_rate": 1.3899253731343284e-05, | |
| "loss": 12.3962, | |
| "num_input_tokens_seen": 42624, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2891791044776119, | |
| "grad_norm": 1.313887596130371, | |
| "learning_rate": 1.4365671641791046e-05, | |
| "loss": 12.1956, | |
| "num_input_tokens_seen": 44192, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 1.0649096965789795, | |
| "learning_rate": 1.4832089552238807e-05, | |
| "loss": 12.2616, | |
| "num_input_tokens_seen": 45504, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.30783582089552236, | |
| "grad_norm": 1.6912094354629517, | |
| "learning_rate": 1.529850746268657e-05, | |
| "loss": 11.4618, | |
| "num_input_tokens_seen": 47360, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.31716417910447764, | |
| "grad_norm": 1.740127682685852, | |
| "learning_rate": 1.5764925373134328e-05, | |
| "loss": 12.2382, | |
| "num_input_tokens_seen": 48640, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.32649253731343286, | |
| "grad_norm": 1.4623463153839111, | |
| "learning_rate": 1.623134328358209e-05, | |
| "loss": 11.5946, | |
| "num_input_tokens_seen": 50016, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.3358208955223881, | |
| "grad_norm": 1.2018214464187622, | |
| "learning_rate": 1.6697761194029852e-05, | |
| "loss": 11.8057, | |
| "num_input_tokens_seen": 51296, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3451492537313433, | |
| "grad_norm": 1.5324360132217407, | |
| "learning_rate": 1.716417910447761e-05, | |
| "loss": 11.8073, | |
| "num_input_tokens_seen": 52576, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.35447761194029853, | |
| "grad_norm": 1.7239537239074707, | |
| "learning_rate": 1.7630597014925373e-05, | |
| "loss": 11.7853, | |
| "num_input_tokens_seen": 54080, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.36380597014925375, | |
| "grad_norm": 1.1210482120513916, | |
| "learning_rate": 1.8097014925373135e-05, | |
| "loss": 11.7581, | |
| "num_input_tokens_seen": 55392, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 1.2341680526733398, | |
| "learning_rate": 1.8563432835820898e-05, | |
| "loss": 11.6818, | |
| "num_input_tokens_seen": 56864, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3824626865671642, | |
| "grad_norm": 1.574833631515503, | |
| "learning_rate": 1.9029850746268656e-05, | |
| "loss": 11.4672, | |
| "num_input_tokens_seen": 58368, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.3917910447761194, | |
| "grad_norm": 1.1078836917877197, | |
| "learning_rate": 1.949626865671642e-05, | |
| "loss": 11.498, | |
| "num_input_tokens_seen": 59744, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.40111940298507465, | |
| "grad_norm": 1.2837330102920532, | |
| "learning_rate": 1.996268656716418e-05, | |
| "loss": 11.2536, | |
| "num_input_tokens_seen": 61152, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.41044776119402987, | |
| "grad_norm": 1.1495797634124756, | |
| "learning_rate": 2.042910447761194e-05, | |
| "loss": 11.4211, | |
| "num_input_tokens_seen": 62496, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4197761194029851, | |
| "grad_norm": 1.387069582939148, | |
| "learning_rate": 2.0895522388059702e-05, | |
| "loss": 11.8296, | |
| "num_input_tokens_seen": 63808, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.4291044776119403, | |
| "grad_norm": 1.3498380184173584, | |
| "learning_rate": 2.1361940298507464e-05, | |
| "loss": 11.4402, | |
| "num_input_tokens_seen": 65088, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.43843283582089554, | |
| "grad_norm": 1.2548513412475586, | |
| "learning_rate": 2.1828358208955223e-05, | |
| "loss": 11.4326, | |
| "num_input_tokens_seen": 66496, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 1.3348450660705566, | |
| "learning_rate": 2.2294776119402985e-05, | |
| "loss": 11.2131, | |
| "num_input_tokens_seen": 67872, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.457089552238806, | |
| "grad_norm": 1.1556657552719116, | |
| "learning_rate": 2.2761194029850747e-05, | |
| "loss": 11.4295, | |
| "num_input_tokens_seen": 69216, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.4664179104477612, | |
| "grad_norm": 1.211230754852295, | |
| "learning_rate": 2.3227611940298506e-05, | |
| "loss": 11.3182, | |
| "num_input_tokens_seen": 70816, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.47574626865671643, | |
| "grad_norm": 1.2439864873886108, | |
| "learning_rate": 2.369402985074627e-05, | |
| "loss": 10.9973, | |
| "num_input_tokens_seen": 72224, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.48507462686567165, | |
| "grad_norm": 1.1299711465835571, | |
| "learning_rate": 2.416044776119403e-05, | |
| "loss": 11.2015, | |
| "num_input_tokens_seen": 73600, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.4944029850746269, | |
| "grad_norm": 1.4416836500167847, | |
| "learning_rate": 2.4626865671641793e-05, | |
| "loss": 10.6497, | |
| "num_input_tokens_seen": 75168, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 10.7962064743042, | |
| "eval_runtime": 2.6008, | |
| "eval_samples_per_second": 91.509, | |
| "eval_steps_per_second": 23.069, | |
| "num_input_tokens_seen": 75936, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.503731343283582, | |
| "grad_norm": 1.0977672338485718, | |
| "learning_rate": 2.5093283582089555e-05, | |
| "loss": 10.7378, | |
| "num_input_tokens_seen": 76544, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5130597014925373, | |
| "grad_norm": 1.040235161781311, | |
| "learning_rate": 2.5559701492537314e-05, | |
| "loss": 11.0643, | |
| "num_input_tokens_seen": 78080, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 1.1158206462860107, | |
| "learning_rate": 2.6026119402985076e-05, | |
| "loss": 10.4075, | |
| "num_input_tokens_seen": 79520, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5317164179104478, | |
| "grad_norm": 1.2748277187347412, | |
| "learning_rate": 2.6492537313432835e-05, | |
| "loss": 10.5867, | |
| "num_input_tokens_seen": 80992, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.5410447761194029, | |
| "grad_norm": 1.146532416343689, | |
| "learning_rate": 2.69589552238806e-05, | |
| "loss": 10.5364, | |
| "num_input_tokens_seen": 82496, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5503731343283582, | |
| "grad_norm": 1.269221544265747, | |
| "learning_rate": 2.742537313432836e-05, | |
| "loss": 10.6677, | |
| "num_input_tokens_seen": 83712, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.5597014925373134, | |
| "grad_norm": 1.3155211210250854, | |
| "learning_rate": 2.789179104477612e-05, | |
| "loss": 10.2373, | |
| "num_input_tokens_seen": 85120, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5690298507462687, | |
| "grad_norm": 1.1165159940719604, | |
| "learning_rate": 2.835820895522388e-05, | |
| "loss": 10.891, | |
| "num_input_tokens_seen": 86560, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.5783582089552238, | |
| "grad_norm": 1.1585938930511475, | |
| "learning_rate": 2.8824626865671646e-05, | |
| "loss": 10.2735, | |
| "num_input_tokens_seen": 87936, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5876865671641791, | |
| "grad_norm": 1.1494544744491577, | |
| "learning_rate": 2.92910447761194e-05, | |
| "loss": 10.2151, | |
| "num_input_tokens_seen": 89312, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 1.143278956413269, | |
| "learning_rate": 2.9757462686567167e-05, | |
| "loss": 9.8693, | |
| "num_input_tokens_seen": 90560, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6063432835820896, | |
| "grad_norm": 1.1917845010757446, | |
| "learning_rate": 3.0223880597014926e-05, | |
| "loss": 10.2992, | |
| "num_input_tokens_seen": 91936, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.6156716417910447, | |
| "grad_norm": 1.1074010133743286, | |
| "learning_rate": 3.069029850746269e-05, | |
| "loss": 9.7121, | |
| "num_input_tokens_seen": 93344, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.9508233070373535, | |
| "learning_rate": 3.115671641791045e-05, | |
| "loss": 10.5188, | |
| "num_input_tokens_seen": 94560, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.6343283582089553, | |
| "grad_norm": 0.9387556910514832, | |
| "learning_rate": 3.162313432835821e-05, | |
| "loss": 10.3016, | |
| "num_input_tokens_seen": 96032, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6436567164179104, | |
| "grad_norm": 1.5737946033477783, | |
| "learning_rate": 3.208955223880597e-05, | |
| "loss": 9.9344, | |
| "num_input_tokens_seen": 97504, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.6529850746268657, | |
| "grad_norm": 1.1343944072723389, | |
| "learning_rate": 3.2555970149253733e-05, | |
| "loss": 9.9471, | |
| "num_input_tokens_seen": 98720, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6623134328358209, | |
| "grad_norm": 0.9977521896362305, | |
| "learning_rate": 3.302238805970149e-05, | |
| "loss": 9.4285, | |
| "num_input_tokens_seen": 100064, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 1.3763890266418457, | |
| "learning_rate": 3.348880597014926e-05, | |
| "loss": 9.6716, | |
| "num_input_tokens_seen": 101536, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6809701492537313, | |
| "grad_norm": 1.0821505784988403, | |
| "learning_rate": 3.395522388059701e-05, | |
| "loss": 9.6609, | |
| "num_input_tokens_seen": 103072, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.6902985074626866, | |
| "grad_norm": 1.1629343032836914, | |
| "learning_rate": 3.4421641791044776e-05, | |
| "loss": 9.6861, | |
| "num_input_tokens_seen": 104416, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6996268656716418, | |
| "grad_norm": 1.2199299335479736, | |
| "learning_rate": 3.488805970149254e-05, | |
| "loss": 9.5197, | |
| "num_input_tokens_seen": 105952, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.7089552238805971, | |
| "grad_norm": 1.0271679162979126, | |
| "learning_rate": 3.53544776119403e-05, | |
| "loss": 9.164, | |
| "num_input_tokens_seen": 107520, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7182835820895522, | |
| "grad_norm": 0.9137533903121948, | |
| "learning_rate": 3.582089552238806e-05, | |
| "loss": 9.4597, | |
| "num_input_tokens_seen": 109248, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.7276119402985075, | |
| "grad_norm": 0.8697826862335205, | |
| "learning_rate": 3.6287313432835824e-05, | |
| "loss": 10.0959, | |
| "num_input_tokens_seen": 110752, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7369402985074627, | |
| "grad_norm": 0.9557790160179138, | |
| "learning_rate": 3.675373134328358e-05, | |
| "loss": 9.446, | |
| "num_input_tokens_seen": 112320, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.9639798402786255, | |
| "learning_rate": 3.722014925373135e-05, | |
| "loss": 9.4224, | |
| "num_input_tokens_seen": 113792, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7555970149253731, | |
| "grad_norm": 1.075067400932312, | |
| "learning_rate": 3.7686567164179104e-05, | |
| "loss": 9.3109, | |
| "num_input_tokens_seen": 115328, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.7649253731343284, | |
| "grad_norm": 0.9383342266082764, | |
| "learning_rate": 3.8152985074626867e-05, | |
| "loss": 9.397, | |
| "num_input_tokens_seen": 116800, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.7742537313432836, | |
| "grad_norm": 0.9882476329803467, | |
| "learning_rate": 3.861940298507463e-05, | |
| "loss": 8.4697, | |
| "num_input_tokens_seen": 118592, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.7835820895522388, | |
| "grad_norm": 1.2925512790679932, | |
| "learning_rate": 3.908582089552239e-05, | |
| "loss": 9.0921, | |
| "num_input_tokens_seen": 119936, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.792910447761194, | |
| "grad_norm": 0.7949486970901489, | |
| "learning_rate": 3.9552238805970146e-05, | |
| "loss": 9.4084, | |
| "num_input_tokens_seen": 121280, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.8022388059701493, | |
| "grad_norm": 0.9894144535064697, | |
| "learning_rate": 4.0018656716417915e-05, | |
| "loss": 8.8077, | |
| "num_input_tokens_seen": 122944, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8115671641791045, | |
| "grad_norm": 1.03957998752594, | |
| "learning_rate": 4.048507462686567e-05, | |
| "loss": 9.3722, | |
| "num_input_tokens_seen": 124320, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.8208955223880597, | |
| "grad_norm": 0.9876894950866699, | |
| "learning_rate": 4.095149253731343e-05, | |
| "loss": 9.1341, | |
| "num_input_tokens_seen": 125888, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8302238805970149, | |
| "grad_norm": 1.0310249328613281, | |
| "learning_rate": 4.1417910447761195e-05, | |
| "loss": 9.4208, | |
| "num_input_tokens_seen": 127296, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.8395522388059702, | |
| "grad_norm": 1.0116007328033447, | |
| "learning_rate": 4.188432835820896e-05, | |
| "loss": 9.0534, | |
| "num_input_tokens_seen": 128512, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8488805970149254, | |
| "grad_norm": 1.0837348699569702, | |
| "learning_rate": 4.235074626865671e-05, | |
| "loss": 9.0785, | |
| "num_input_tokens_seen": 130048, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.8582089552238806, | |
| "grad_norm": 0.861038327217102, | |
| "learning_rate": 4.281716417910448e-05, | |
| "loss": 9.25, | |
| "num_input_tokens_seen": 131424, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.8675373134328358, | |
| "grad_norm": 0.7879683971405029, | |
| "learning_rate": 4.328358208955224e-05, | |
| "loss": 9.1648, | |
| "num_input_tokens_seen": 132704, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.8768656716417911, | |
| "grad_norm": 1.0319945812225342, | |
| "learning_rate": 4.375e-05, | |
| "loss": 9.5206, | |
| "num_input_tokens_seen": 134048, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.8861940298507462, | |
| "grad_norm": 0.9430369734764099, | |
| "learning_rate": 4.421641791044777e-05, | |
| "loss": 9.046, | |
| "num_input_tokens_seen": 135392, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 1.0650569200515747, | |
| "learning_rate": 4.4682835820895524e-05, | |
| "loss": 9.6769, | |
| "num_input_tokens_seen": 136832, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9048507462686567, | |
| "grad_norm": 0.9987925887107849, | |
| "learning_rate": 4.5149253731343286e-05, | |
| "loss": 9.2715, | |
| "num_input_tokens_seen": 138336, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.914179104477612, | |
| "grad_norm": 0.8934780359268188, | |
| "learning_rate": 4.561567164179105e-05, | |
| "loss": 8.908, | |
| "num_input_tokens_seen": 139840, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9235074626865671, | |
| "grad_norm": 0.9215578436851501, | |
| "learning_rate": 4.608208955223881e-05, | |
| "loss": 9.2125, | |
| "num_input_tokens_seen": 141344, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.9328358208955224, | |
| "grad_norm": 1.2112703323364258, | |
| "learning_rate": 4.6548507462686566e-05, | |
| "loss": 9.3081, | |
| "num_input_tokens_seen": 142848, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9421641791044776, | |
| "grad_norm": 0.8605320453643799, | |
| "learning_rate": 4.7014925373134335e-05, | |
| "loss": 9.1954, | |
| "num_input_tokens_seen": 144384, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.9514925373134329, | |
| "grad_norm": 0.7724307775497437, | |
| "learning_rate": 4.748134328358209e-05, | |
| "loss": 9.1012, | |
| "num_input_tokens_seen": 145760, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.960820895522388, | |
| "grad_norm": 0.7548246383666992, | |
| "learning_rate": 4.794776119402985e-05, | |
| "loss": 8.5388, | |
| "num_input_tokens_seen": 147168, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.9701492537313433, | |
| "grad_norm": 0.9139894247055054, | |
| "learning_rate": 4.8414179104477615e-05, | |
| "loss": 8.7257, | |
| "num_input_tokens_seen": 148480, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.9794776119402985, | |
| "grad_norm": 0.702167272567749, | |
| "learning_rate": 4.888059701492538e-05, | |
| "loss": 8.7671, | |
| "num_input_tokens_seen": 149920, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.9888059701492538, | |
| "grad_norm": 0.954757571220398, | |
| "learning_rate": 4.934701492537314e-05, | |
| "loss": 8.897, | |
| "num_input_tokens_seen": 151264, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.9981343283582089, | |
| "grad_norm": 0.7838152647018433, | |
| "learning_rate": 4.98134328358209e-05, | |
| "loss": 8.9279, | |
| "num_input_tokens_seen": 152608, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 8.663278579711914, | |
| "eval_runtime": 2.5663, | |
| "eval_samples_per_second": 92.74, | |
| "eval_steps_per_second": 23.38, | |
| "num_input_tokens_seen": 152672, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.007462686567164, | |
| "grad_norm": 0.9007129073143005, | |
| "learning_rate": 4.999995228691131e-05, | |
| "loss": 8.8564, | |
| "num_input_tokens_seen": 153760, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.0167910447761195, | |
| "grad_norm": 0.815585196018219, | |
| "learning_rate": 4.999966070758437e-05, | |
| "loss": 8.3945, | |
| "num_input_tokens_seen": 155104, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.0261194029850746, | |
| "grad_norm": 0.7844848036766052, | |
| "learning_rate": 4.999910405928983e-05, | |
| "loss": 8.5309, | |
| "num_input_tokens_seen": 156416, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.0354477611940298, | |
| "grad_norm": 0.8738976716995239, | |
| "learning_rate": 4.9998282347929784e-05, | |
| "loss": 9.1396, | |
| "num_input_tokens_seen": 157888, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.044776119402985, | |
| "grad_norm": 0.7945048213005066, | |
| "learning_rate": 4.999719558221674e-05, | |
| "loss": 8.6982, | |
| "num_input_tokens_seen": 159392, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.0541044776119404, | |
| "grad_norm": 0.9273176789283752, | |
| "learning_rate": 4.999584377367359e-05, | |
| "loss": 8.8241, | |
| "num_input_tokens_seen": 160864, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.0634328358208955, | |
| "grad_norm": 0.9342925548553467, | |
| "learning_rate": 4.9994226936633415e-05, | |
| "loss": 8.7151, | |
| "num_input_tokens_seen": 162240, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.0727611940298507, | |
| "grad_norm": 0.7982831001281738, | |
| "learning_rate": 4.999234508823938e-05, | |
| "loss": 8.3339, | |
| "num_input_tokens_seen": 163616, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.0820895522388059, | |
| "grad_norm": 0.9416908621788025, | |
| "learning_rate": 4.999019824844455e-05, | |
| "loss": 8.4545, | |
| "num_input_tokens_seen": 165152, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.0914179104477613, | |
| "grad_norm": 0.8664380311965942, | |
| "learning_rate": 4.998778644001165e-05, | |
| "loss": 8.2728, | |
| "num_input_tokens_seen": 166560, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.1007462686567164, | |
| "grad_norm": 0.8122774958610535, | |
| "learning_rate": 4.9985109688512854e-05, | |
| "loss": 8.3721, | |
| "num_input_tokens_seen": 167904, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.1100746268656716, | |
| "grad_norm": 0.7695725560188293, | |
| "learning_rate": 4.998216802232949e-05, | |
| "loss": 8.427, | |
| "num_input_tokens_seen": 169280, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.1194029850746268, | |
| "grad_norm": 1.0179617404937744, | |
| "learning_rate": 4.9978961472651774e-05, | |
| "loss": 8.3741, | |
| "num_input_tokens_seen": 170656, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.1287313432835822, | |
| "grad_norm": 0.8880394101142883, | |
| "learning_rate": 4.997549007347842e-05, | |
| "loss": 7.8491, | |
| "num_input_tokens_seen": 172352, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.1380597014925373, | |
| "grad_norm": 0.8841779232025146, | |
| "learning_rate": 4.9971753861616354e-05, | |
| "loss": 8.19, | |
| "num_input_tokens_seen": 173888, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.1473880597014925, | |
| "grad_norm": 0.9059610962867737, | |
| "learning_rate": 4.9967752876680254e-05, | |
| "loss": 8.3163, | |
| "num_input_tokens_seen": 175040, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.1567164179104479, | |
| "grad_norm": 0.7437261939048767, | |
| "learning_rate": 4.996348716109217e-05, | |
| "loss": 8.0931, | |
| "num_input_tokens_seen": 176480, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.166044776119403, | |
| "grad_norm": 0.9212306141853333, | |
| "learning_rate": 4.9958956760081085e-05, | |
| "loss": 8.4488, | |
| "num_input_tokens_seen": 177952, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.1753731343283582, | |
| "grad_norm": 0.942762017250061, | |
| "learning_rate": 4.995416172168239e-05, | |
| "loss": 8.8229, | |
| "num_input_tokens_seen": 179552, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.1847014925373134, | |
| "grad_norm": 0.7891209125518799, | |
| "learning_rate": 4.994910209673741e-05, | |
| "loss": 8.6877, | |
| "num_input_tokens_seen": 181120, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "grad_norm": 0.7660623788833618, | |
| "learning_rate": 4.9943777938892855e-05, | |
| "loss": 8.4657, | |
| "num_input_tokens_seen": 182560, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.203358208955224, | |
| "grad_norm": 0.8372623920440674, | |
| "learning_rate": 4.993818930460026e-05, | |
| "loss": 8.4572, | |
| "num_input_tokens_seen": 184064, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.212686567164179, | |
| "grad_norm": 0.950301468372345, | |
| "learning_rate": 4.9932336253115354e-05, | |
| "loss": 8.3868, | |
| "num_input_tokens_seen": 185600, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.2220149253731343, | |
| "grad_norm": 0.7954419851303101, | |
| "learning_rate": 4.9926218846497486e-05, | |
| "loss": 8.0466, | |
| "num_input_tokens_seen": 186848, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.2313432835820897, | |
| "grad_norm": 0.8403342366218567, | |
| "learning_rate": 4.991983714960892e-05, | |
| "loss": 8.3877, | |
| "num_input_tokens_seen": 188224, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.2406716417910448, | |
| "grad_norm": 0.6610814332962036, | |
| "learning_rate": 4.9913191230114156e-05, | |
| "loss": 8.5721, | |
| "num_input_tokens_seen": 189696, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.8098878860473633, | |
| "learning_rate": 4.990628115847924e-05, | |
| "loss": 8.2866, | |
| "num_input_tokens_seen": 191360, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.2593283582089552, | |
| "grad_norm": 0.9260333180427551, | |
| "learning_rate": 4.9899107007971004e-05, | |
| "loss": 8.2224, | |
| "num_input_tokens_seen": 192800, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.2686567164179103, | |
| "grad_norm": 0.8632802367210388, | |
| "learning_rate": 4.989166885465624e-05, | |
| "loss": 7.8275, | |
| "num_input_tokens_seen": 194208, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.2779850746268657, | |
| "grad_norm": 0.8590320944786072, | |
| "learning_rate": 4.988396677740097e-05, | |
| "loss": 8.2978, | |
| "num_input_tokens_seen": 195552, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.287313432835821, | |
| "grad_norm": 0.9525817632675171, | |
| "learning_rate": 4.9876000857869583e-05, | |
| "loss": 7.9729, | |
| "num_input_tokens_seen": 196832, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.296641791044776, | |
| "grad_norm": 0.9368866682052612, | |
| "learning_rate": 4.986777118052393e-05, | |
| "loss": 7.5958, | |
| "num_input_tokens_seen": 198112, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.3059701492537314, | |
| "grad_norm": 0.8002532124519348, | |
| "learning_rate": 4.9859277832622494e-05, | |
| "loss": 7.7611, | |
| "num_input_tokens_seen": 199680, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.3152985074626866, | |
| "grad_norm": 0.7887699007987976, | |
| "learning_rate": 4.98505209042194e-05, | |
| "loss": 7.8067, | |
| "num_input_tokens_seen": 200960, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.3246268656716418, | |
| "grad_norm": 1.2881039381027222, | |
| "learning_rate": 4.9841500488163526e-05, | |
| "loss": 7.676, | |
| "num_input_tokens_seen": 202368, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.333955223880597, | |
| "grad_norm": 0.7441263794898987, | |
| "learning_rate": 4.983221668009744e-05, | |
| "loss": 8.1728, | |
| "num_input_tokens_seen": 203744, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.3432835820895521, | |
| "grad_norm": 0.8960073590278625, | |
| "learning_rate": 4.982266957845648e-05, | |
| "loss": 7.9879, | |
| "num_input_tokens_seen": 205056, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.3526119402985075, | |
| "grad_norm": 0.8797266483306885, | |
| "learning_rate": 4.981285928446762e-05, | |
| "loss": 7.8765, | |
| "num_input_tokens_seen": 206432, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.3619402985074627, | |
| "grad_norm": 1.006440281867981, | |
| "learning_rate": 4.9802785902148455e-05, | |
| "loss": 7.9381, | |
| "num_input_tokens_seen": 207712, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.3712686567164178, | |
| "grad_norm": 0.8682586550712585, | |
| "learning_rate": 4.979244953830608e-05, | |
| "loss": 7.9643, | |
| "num_input_tokens_seen": 208992, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.3805970149253732, | |
| "grad_norm": 0.9311002492904663, | |
| "learning_rate": 4.9781850302535945e-05, | |
| "loss": 7.8442, | |
| "num_input_tokens_seen": 210400, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.3899253731343284, | |
| "grad_norm": 0.7790952920913696, | |
| "learning_rate": 4.9770988307220736e-05, | |
| "loss": 7.8334, | |
| "num_input_tokens_seen": 211936, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 1.3992537313432836, | |
| "grad_norm": 0.8371986746788025, | |
| "learning_rate": 4.97598636675291e-05, | |
| "loss": 7.5606, | |
| "num_input_tokens_seen": 213376, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.4085820895522387, | |
| "grad_norm": 0.8788151741027832, | |
| "learning_rate": 4.974847650141453e-05, | |
| "loss": 7.6396, | |
| "num_input_tokens_seen": 214784, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 1.417910447761194, | |
| "grad_norm": 0.8070874810218811, | |
| "learning_rate": 4.973682692961403e-05, | |
| "loss": 7.4207, | |
| "num_input_tokens_seen": 216224, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.4272388059701493, | |
| "grad_norm": 0.8868241310119629, | |
| "learning_rate": 4.972491507564688e-05, | |
| "loss": 8.1997, | |
| "num_input_tokens_seen": 217600, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 1.4365671641791045, | |
| "grad_norm": 0.9156266450881958, | |
| "learning_rate": 4.971274106581331e-05, | |
| "loss": 7.9907, | |
| "num_input_tokens_seen": 219040, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.4458955223880596, | |
| "grad_norm": 1.1338731050491333, | |
| "learning_rate": 4.970030502919315e-05, | |
| "loss": 8.4593, | |
| "num_input_tokens_seen": 220480, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.455223880597015, | |
| "grad_norm": 0.9340184926986694, | |
| "learning_rate": 4.9687607097644495e-05, | |
| "loss": 7.1874, | |
| "num_input_tokens_seen": 222208, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.4645522388059702, | |
| "grad_norm": 0.8250755667686462, | |
| "learning_rate": 4.967464740580227e-05, | |
| "loss": 7.7768, | |
| "num_input_tokens_seen": 223648, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 1.4738805970149254, | |
| "grad_norm": 0.7392362952232361, | |
| "learning_rate": 4.9661426091076834e-05, | |
| "loss": 7.8255, | |
| "num_input_tokens_seen": 225152, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.4832089552238805, | |
| "grad_norm": 0.965112030506134, | |
| "learning_rate": 4.9647943293652486e-05, | |
| "loss": 7.9542, | |
| "num_input_tokens_seen": 226528, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 1.4925373134328357, | |
| "grad_norm": 1.136421799659729, | |
| "learning_rate": 4.963419915648603e-05, | |
| "loss": 7.7268, | |
| "num_input_tokens_seen": 228000, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 7.69692325592041, | |
| "eval_runtime": 2.5555, | |
| "eval_samples_per_second": 93.132, | |
| "eval_steps_per_second": 23.479, | |
| "num_input_tokens_seen": 229344, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 1.501865671641791, | |
| "grad_norm": 0.750250518321991, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 7.6279, | |
| "num_input_tokens_seen": 229600, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 1.5111940298507462, | |
| "grad_norm": 1.0556617975234985, | |
| "learning_rate": 4.960592744860717e-05, | |
| "loss": 7.3638, | |
| "num_input_tokens_seen": 230912, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.5205223880597014, | |
| "grad_norm": 0.8755062818527222, | |
| "learning_rate": 4.9591400177656935e-05, | |
| "loss": 7.3002, | |
| "num_input_tokens_seen": 232256, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 1.5298507462686568, | |
| "grad_norm": 0.8359950184822083, | |
| "learning_rate": 4.957661216648573e-05, | |
| "loss": 7.7275, | |
| "num_input_tokens_seen": 233728, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.539179104477612, | |
| "grad_norm": 0.8320292830467224, | |
| "learning_rate": 4.95615635718894e-05, | |
| "loss": 7.736, | |
| "num_input_tokens_seen": 235072, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.5485074626865671, | |
| "grad_norm": 0.7479209899902344, | |
| "learning_rate": 4.954625455342674e-05, | |
| "loss": 7.2555, | |
| "num_input_tokens_seen": 236512, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.5578358208955225, | |
| "grad_norm": 0.8577715158462524, | |
| "learning_rate": 4.953068527341777e-05, | |
| "loss": 7.5543, | |
| "num_input_tokens_seen": 237952, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 1.5671641791044775, | |
| "grad_norm": 0.9075712561607361, | |
| "learning_rate": 4.9514855896942046e-05, | |
| "loss": 8.1271, | |
| "num_input_tokens_seen": 239328, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.5764925373134329, | |
| "grad_norm": 0.7837645411491394, | |
| "learning_rate": 4.949876659183692e-05, | |
| "loss": 7.4141, | |
| "num_input_tokens_seen": 240736, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 1.585820895522388, | |
| "grad_norm": 0.6916003227233887, | |
| "learning_rate": 4.948241752869571e-05, | |
| "loss": 7.4536, | |
| "num_input_tokens_seen": 241984, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.5951492537313432, | |
| "grad_norm": 1.0420584678649902, | |
| "learning_rate": 4.946580888086595e-05, | |
| "loss": 7.8676, | |
| "num_input_tokens_seen": 243296, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 1.6044776119402986, | |
| "grad_norm": 1.0447683334350586, | |
| "learning_rate": 4.9448940824447515e-05, | |
| "loss": 6.9482, | |
| "num_input_tokens_seen": 244960, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.6138059701492538, | |
| "grad_norm": 1.0610510110855103, | |
| "learning_rate": 4.943181353829076e-05, | |
| "loss": 7.5292, | |
| "num_input_tokens_seen": 246304, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 1.623134328358209, | |
| "grad_norm": 1.1125695705413818, | |
| "learning_rate": 4.941442720399464e-05, | |
| "loss": 7.6678, | |
| "num_input_tokens_seen": 247680, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.6324626865671643, | |
| "grad_norm": 0.8901277184486389, | |
| "learning_rate": 4.939678200590475e-05, | |
| "loss": 7.4366, | |
| "num_input_tokens_seen": 249152, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.6417910447761193, | |
| "grad_norm": 0.808103621006012, | |
| "learning_rate": 4.937887813111142e-05, | |
| "loss": 7.3552, | |
| "num_input_tokens_seen": 250496, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.6511194029850746, | |
| "grad_norm": 0.8424286842346191, | |
| "learning_rate": 4.936071576944769e-05, | |
| "loss": 7.7847, | |
| "num_input_tokens_seen": 251872, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 1.6604477611940298, | |
| "grad_norm": 0.9387964606285095, | |
| "learning_rate": 4.93422951134873e-05, | |
| "loss": 7.0814, | |
| "num_input_tokens_seen": 253440, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.669776119402985, | |
| "grad_norm": 1.0396795272827148, | |
| "learning_rate": 4.932361635854268e-05, | |
| "loss": 6.8777, | |
| "num_input_tokens_seen": 254720, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 1.6791044776119404, | |
| "grad_norm": 1.2299745082855225, | |
| "learning_rate": 4.9304679702662854e-05, | |
| "loss": 7.3267, | |
| "num_input_tokens_seen": 256320, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.6884328358208955, | |
| "grad_norm": 0.9200482964515686, | |
| "learning_rate": 4.9285485346631334e-05, | |
| "loss": 7.6562, | |
| "num_input_tokens_seen": 257600, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 1.6977611940298507, | |
| "grad_norm": 1.0085023641586304, | |
| "learning_rate": 4.9266033493964e-05, | |
| "loss": 7.3446, | |
| "num_input_tokens_seen": 259008, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.707089552238806, | |
| "grad_norm": 0.8369162678718567, | |
| "learning_rate": 4.924632435090696e-05, | |
| "loss": 7.2013, | |
| "num_input_tokens_seen": 260448, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 1.716417910447761, | |
| "grad_norm": 0.8195828199386597, | |
| "learning_rate": 4.922635812643434e-05, | |
| "loss": 7.7115, | |
| "num_input_tokens_seen": 261888, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.7257462686567164, | |
| "grad_norm": 1.132403016090393, | |
| "learning_rate": 4.920613503224608e-05, | |
| "loss": 7.2164, | |
| "num_input_tokens_seen": 263328, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.7350746268656716, | |
| "grad_norm": 1.0942069292068481, | |
| "learning_rate": 4.9185655282765655e-05, | |
| "loss": 7.544, | |
| "num_input_tokens_seen": 264832, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.7444029850746268, | |
| "grad_norm": 1.027674913406372, | |
| "learning_rate": 4.916491909513787e-05, | |
| "loss": 6.8825, | |
| "num_input_tokens_seen": 266368, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 1.7537313432835822, | |
| "grad_norm": 0.6552566885948181, | |
| "learning_rate": 4.914392668922651e-05, | |
| "loss": 7.6216, | |
| "num_input_tokens_seen": 267904, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.7630597014925373, | |
| "grad_norm": 1.247434377670288, | |
| "learning_rate": 4.912267828761199e-05, | |
| "loss": 7.3775, | |
| "num_input_tokens_seen": 269504, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 1.7723880597014925, | |
| "grad_norm": 0.7790011167526245, | |
| "learning_rate": 4.910117411558906e-05, | |
| "loss": 6.7441, | |
| "num_input_tokens_seen": 270912, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.7817164179104479, | |
| "grad_norm": 0.8391587138175964, | |
| "learning_rate": 4.907941440116436e-05, | |
| "loss": 7.2112, | |
| "num_input_tokens_seen": 272384, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 1.7910447761194028, | |
| "grad_norm": 0.8718048930168152, | |
| "learning_rate": 4.905739937505401e-05, | |
| "loss": 7.2948, | |
| "num_input_tokens_seen": 273760, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.8003731343283582, | |
| "grad_norm": 1.0466101169586182, | |
| "learning_rate": 4.9035129270681196e-05, | |
| "loss": 7.2113, | |
| "num_input_tokens_seen": 275424, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 1.8097014925373134, | |
| "grad_norm": 0.7440748810768127, | |
| "learning_rate": 4.901260432417367e-05, | |
| "loss": 7.6151, | |
| "num_input_tokens_seen": 276832, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.8190298507462686, | |
| "grad_norm": 0.6578248143196106, | |
| "learning_rate": 4.8989824774361236e-05, | |
| "loss": 7.7834, | |
| "num_input_tokens_seen": 278336, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.828358208955224, | |
| "grad_norm": 0.6893697381019592, | |
| "learning_rate": 4.896679086277325e-05, | |
| "loss": 7.1615, | |
| "num_input_tokens_seen": 279712, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.837686567164179, | |
| "grad_norm": 0.7361366748809814, | |
| "learning_rate": 4.8943502833636026e-05, | |
| "loss": 7.066, | |
| "num_input_tokens_seen": 281152, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 1.8470149253731343, | |
| "grad_norm": 0.9279003739356995, | |
| "learning_rate": 4.891996093387028e-05, | |
| "loss": 7.5003, | |
| "num_input_tokens_seen": 282560, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.8563432835820897, | |
| "grad_norm": 0.9073846340179443, | |
| "learning_rate": 4.889616541308847e-05, | |
| "loss": 6.7303, | |
| "num_input_tokens_seen": 283968, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 1.8656716417910446, | |
| "grad_norm": 0.8598644137382507, | |
| "learning_rate": 4.8872116523592196e-05, | |
| "loss": 6.7719, | |
| "num_input_tokens_seen": 285440, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 0.86404949426651, | |
| "learning_rate": 4.8847814520369475e-05, | |
| "loss": 6.4091, | |
| "num_input_tokens_seen": 286944, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 1.8843283582089554, | |
| "grad_norm": 0.9933352470397949, | |
| "learning_rate": 4.8823259661092104e-05, | |
| "loss": 7.0659, | |
| "num_input_tokens_seen": 288320, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.8936567164179103, | |
| "grad_norm": 0.8071138262748718, | |
| "learning_rate": 4.879845220611284e-05, | |
| "loss": 6.9223, | |
| "num_input_tokens_seen": 289568, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 1.9029850746268657, | |
| "grad_norm": 0.8464536666870117, | |
| "learning_rate": 4.877339241846273e-05, | |
| "loss": 7.5876, | |
| "num_input_tokens_seen": 290976, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.912313432835821, | |
| "grad_norm": 0.6788743734359741, | |
| "learning_rate": 4.874808056384825e-05, | |
| "loss": 7.4811, | |
| "num_input_tokens_seen": 292576, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.921641791044776, | |
| "grad_norm": 0.9995241165161133, | |
| "learning_rate": 4.872251691064854e-05, | |
| "loss": 7.0982, | |
| "num_input_tokens_seen": 293952, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.9309701492537314, | |
| "grad_norm": 0.9767850637435913, | |
| "learning_rate": 4.869670172991252e-05, | |
| "loss": 7.4047, | |
| "num_input_tokens_seen": 295488, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 1.9402985074626866, | |
| "grad_norm": 0.8503986597061157, | |
| "learning_rate": 4.8670635295356035e-05, | |
| "loss": 7.268, | |
| "num_input_tokens_seen": 296768, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.9496268656716418, | |
| "grad_norm": 0.7711080312728882, | |
| "learning_rate": 4.8644317883358956e-05, | |
| "loss": 6.7933, | |
| "num_input_tokens_seen": 298240, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 1.9589552238805972, | |
| "grad_norm": 1.1063729524612427, | |
| "learning_rate": 4.861774977296223e-05, | |
| "loss": 7.4257, | |
| "num_input_tokens_seen": 299712, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.9682835820895521, | |
| "grad_norm": 0.8842138051986694, | |
| "learning_rate": 4.8590931245864954e-05, | |
| "loss": 7.252, | |
| "num_input_tokens_seen": 300864, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 1.9776119402985075, | |
| "grad_norm": 0.9442459940910339, | |
| "learning_rate": 4.856386258642135e-05, | |
| "loss": 6.9777, | |
| "num_input_tokens_seen": 302336, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.9869402985074627, | |
| "grad_norm": 0.7461578845977783, | |
| "learning_rate": 4.8536544081637787e-05, | |
| "loss": 7.1512, | |
| "num_input_tokens_seen": 303584, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 1.9962686567164178, | |
| "grad_norm": 0.7680010795593262, | |
| "learning_rate": 4.8508976021169705e-05, | |
| "loss": 7.3138, | |
| "num_input_tokens_seen": 304960, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 7.15101957321167, | |
| "eval_runtime": 2.5606, | |
| "eval_samples_per_second": 92.947, | |
| "eval_steps_per_second": 23.432, | |
| "num_input_tokens_seen": 305288, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 2.0055970149253732, | |
| "grad_norm": 1.187349557876587, | |
| "learning_rate": 4.8481158697318564e-05, | |
| "loss": 7.529, | |
| "num_input_tokens_seen": 306152, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.014925373134328, | |
| "grad_norm": 0.7942609190940857, | |
| "learning_rate": 4.845309240502874e-05, | |
| "loss": 7.797, | |
| "num_input_tokens_seen": 307464, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.0242537313432836, | |
| "grad_norm": 0.8442389369010925, | |
| "learning_rate": 4.8424777441884405e-05, | |
| "loss": 7.5253, | |
| "num_input_tokens_seen": 308968, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 2.033582089552239, | |
| "grad_norm": 0.8311645984649658, | |
| "learning_rate": 4.839621410810634e-05, | |
| "loss": 7.4095, | |
| "num_input_tokens_seen": 310440, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.042910447761194, | |
| "grad_norm": 1.0612478256225586, | |
| "learning_rate": 4.8367402706548805e-05, | |
| "loss": 7.2855, | |
| "num_input_tokens_seen": 312008, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 2.0522388059701493, | |
| "grad_norm": 0.8402652740478516, | |
| "learning_rate": 4.8338343542696275e-05, | |
| "loss": 7.0683, | |
| "num_input_tokens_seen": 313416, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.0615671641791047, | |
| "grad_norm": 0.8630161285400391, | |
| "learning_rate": 4.830903692466024e-05, | |
| "loss": 6.9105, | |
| "num_input_tokens_seen": 314728, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 2.0708955223880596, | |
| "grad_norm": 1.113158106803894, | |
| "learning_rate": 4.82794831631759e-05, | |
| "loss": 7.605, | |
| "num_input_tokens_seen": 316072, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.080223880597015, | |
| "grad_norm": 1.022423267364502, | |
| "learning_rate": 4.8249682571598945e-05, | |
| "loss": 7.245, | |
| "num_input_tokens_seen": 317384, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 2.08955223880597, | |
| "grad_norm": 0.726763129234314, | |
| "learning_rate": 4.821963546590211e-05, | |
| "loss": 7.04, | |
| "num_input_tokens_seen": 318696, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.0988805970149254, | |
| "grad_norm": 0.8199240565299988, | |
| "learning_rate": 4.8189342164671944e-05, | |
| "loss": 6.7811, | |
| "num_input_tokens_seen": 320008, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.1082089552238807, | |
| "grad_norm": 0.939614474773407, | |
| "learning_rate": 4.815880298910537e-05, | |
| "loss": 7.008, | |
| "num_input_tokens_seen": 321480, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.1175373134328357, | |
| "grad_norm": 0.7770618200302124, | |
| "learning_rate": 4.8128018263006305e-05, | |
| "loss": 6.7962, | |
| "num_input_tokens_seen": 323016, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 2.126865671641791, | |
| "grad_norm": 0.771385133266449, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 7.0804, | |
| "num_input_tokens_seen": 324456, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.1361940298507465, | |
| "grad_norm": 0.9445033669471741, | |
| "learning_rate": 4.806571346744053e-05, | |
| "loss": 7.6275, | |
| "num_input_tokens_seen": 326120, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 2.1455223880597014, | |
| "grad_norm": 0.985575258731842, | |
| "learning_rate": 4.803419405858553e-05, | |
| "loss": 7.8758, | |
| "num_input_tokens_seen": 327624, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.154850746268657, | |
| "grad_norm": 0.9831741452217102, | |
| "learning_rate": 4.8002430420414356e-05, | |
| "loss": 6.8095, | |
| "num_input_tokens_seen": 329160, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 2.1641791044776117, | |
| "grad_norm": 0.890044093132019, | |
| "learning_rate": 4.79704228897138e-05, | |
| "loss": 7.3275, | |
| "num_input_tokens_seen": 330472, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.173507462686567, | |
| "grad_norm": 0.9993547201156616, | |
| "learning_rate": 4.79381718058566e-05, | |
| "loss": 7.1853, | |
| "num_input_tokens_seen": 332008, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 2.1828358208955225, | |
| "grad_norm": 0.8203708529472351, | |
| "learning_rate": 4.790567751079783e-05, | |
| "loss": 6.2736, | |
| "num_input_tokens_seen": 333384, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.1921641791044775, | |
| "grad_norm": 0.9586541056632996, | |
| "learning_rate": 4.787294034907135e-05, | |
| "loss": 7.0594, | |
| "num_input_tokens_seen": 334696, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.201492537313433, | |
| "grad_norm": 1.0974242687225342, | |
| "learning_rate": 4.78399606677861e-05, | |
| "loss": 7.1676, | |
| "num_input_tokens_seen": 336232, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.2108208955223883, | |
| "grad_norm": 0.7506399750709534, | |
| "learning_rate": 4.780673881662242e-05, | |
| "loss": 7.1117, | |
| "num_input_tokens_seen": 337512, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 2.220149253731343, | |
| "grad_norm": 0.8450372815132141, | |
| "learning_rate": 4.777327514782837e-05, | |
| "loss": 6.5368, | |
| "num_input_tokens_seen": 339080, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.2294776119402986, | |
| "grad_norm": 0.9724050760269165, | |
| "learning_rate": 4.773957001621597e-05, | |
| "loss": 6.9429, | |
| "num_input_tokens_seen": 340456, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 2.2388059701492535, | |
| "grad_norm": 0.9393750429153442, | |
| "learning_rate": 4.7705623779157435e-05, | |
| "loss": 6.9668, | |
| "num_input_tokens_seen": 341864, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.248134328358209, | |
| "grad_norm": 0.7946945428848267, | |
| "learning_rate": 4.7671436796581426e-05, | |
| "loss": 6.8569, | |
| "num_input_tokens_seen": 343240, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 2.2574626865671643, | |
| "grad_norm": 1.11447012424469, | |
| "learning_rate": 4.7637009430969194e-05, | |
| "loss": 6.3704, | |
| "num_input_tokens_seen": 344808, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.2667910447761193, | |
| "grad_norm": 0.8194858431816101, | |
| "learning_rate": 4.760234204735072e-05, | |
| "loss": 6.6781, | |
| "num_input_tokens_seen": 346152, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 2.2761194029850746, | |
| "grad_norm": 1.1508831977844238, | |
| "learning_rate": 4.756743501330091e-05, | |
| "loss": 7.1345, | |
| "num_input_tokens_seen": 347528, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.28544776119403, | |
| "grad_norm": 1.1286933422088623, | |
| "learning_rate": 4.753228869893566e-05, | |
| "loss": 7.5046, | |
| "num_input_tokens_seen": 348776, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.294776119402985, | |
| "grad_norm": 0.8779248595237732, | |
| "learning_rate": 4.7496903476907885e-05, | |
| "loss": 6.8257, | |
| "num_input_tokens_seen": 350088, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.3041044776119404, | |
| "grad_norm": 0.7894880175590515, | |
| "learning_rate": 4.746127972240367e-05, | |
| "loss": 7.0531, | |
| "num_input_tokens_seen": 351528, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 2.3134328358208958, | |
| "grad_norm": 0.8634639382362366, | |
| "learning_rate": 4.742541781313822e-05, | |
| "loss": 6.8511, | |
| "num_input_tokens_seen": 352840, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.3227611940298507, | |
| "grad_norm": 1.0780106782913208, | |
| "learning_rate": 4.738931812935186e-05, | |
| "loss": 6.6784, | |
| "num_input_tokens_seen": 354152, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 2.332089552238806, | |
| "grad_norm": 0.8303219676017761, | |
| "learning_rate": 4.735298105380601e-05, | |
| "loss": 6.7425, | |
| "num_input_tokens_seen": 355496, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.341417910447761, | |
| "grad_norm": 0.9376876354217529, | |
| "learning_rate": 4.7316406971779145e-05, | |
| "loss": 7.2814, | |
| "num_input_tokens_seen": 357096, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 2.3507462686567164, | |
| "grad_norm": 0.904336154460907, | |
| "learning_rate": 4.7279596271062716e-05, | |
| "loss": 6.8146, | |
| "num_input_tokens_seen": 358312, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.360074626865672, | |
| "grad_norm": 0.8111023902893066, | |
| "learning_rate": 4.724254934195697e-05, | |
| "loss": 7.5862, | |
| "num_input_tokens_seen": 359752, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 2.3694029850746268, | |
| "grad_norm": 0.9991461634635925, | |
| "learning_rate": 4.720526657726691e-05, | |
| "loss": 6.7293, | |
| "num_input_tokens_seen": 361128, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.378731343283582, | |
| "grad_norm": 1.074427604675293, | |
| "learning_rate": 4.716774837229804e-05, | |
| "loss": 7.019, | |
| "num_input_tokens_seen": 362600, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.388059701492537, | |
| "grad_norm": 0.906004786491394, | |
| "learning_rate": 4.712999512485225e-05, | |
| "loss": 6.5359, | |
| "num_input_tokens_seen": 364072, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.3973880597014925, | |
| "grad_norm": 1.3794955015182495, | |
| "learning_rate": 4.709200723522353e-05, | |
| "loss": 6.6359, | |
| "num_input_tokens_seen": 365576, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 2.406716417910448, | |
| "grad_norm": 0.9847550988197327, | |
| "learning_rate": 4.7053785106193793e-05, | |
| "loss": 7.2102, | |
| "num_input_tokens_seen": 367208, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.416044776119403, | |
| "grad_norm": 0.8597169518470764, | |
| "learning_rate": 4.701532914302853e-05, | |
| "loss": 7.1793, | |
| "num_input_tokens_seen": 368680, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 2.425373134328358, | |
| "grad_norm": 1.2162729501724243, | |
| "learning_rate": 4.697663975347258e-05, | |
| "loss": 7.2568, | |
| "num_input_tokens_seen": 370408, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.4347014925373136, | |
| "grad_norm": 0.7937232255935669, | |
| "learning_rate": 4.693771734774578e-05, | |
| "loss": 6.9625, | |
| "num_input_tokens_seen": 371784, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 2.4440298507462686, | |
| "grad_norm": 0.8241081237792969, | |
| "learning_rate": 4.6898562338538606e-05, | |
| "loss": 6.4715, | |
| "num_input_tokens_seen": 373256, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.453358208955224, | |
| "grad_norm": 0.7692975997924805, | |
| "learning_rate": 4.6859175141007796e-05, | |
| "loss": 6.8562, | |
| "num_input_tokens_seen": 374760, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 2.4626865671641793, | |
| "grad_norm": 0.9061848521232605, | |
| "learning_rate": 4.6819556172771974e-05, | |
| "loss": 6.7238, | |
| "num_input_tokens_seen": 376360, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.4720149253731343, | |
| "grad_norm": 0.9060867428779602, | |
| "learning_rate": 4.6779705853907205e-05, | |
| "loss": 6.3232, | |
| "num_input_tokens_seen": 377960, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.4813432835820897, | |
| "grad_norm": 0.9075210690498352, | |
| "learning_rate": 4.673962460694254e-05, | |
| "loss": 6.797, | |
| "num_input_tokens_seen": 379208, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.4906716417910446, | |
| "grad_norm": 0.7569303512573242, | |
| "learning_rate": 4.669931285685553e-05, | |
| "loss": 6.7893, | |
| "num_input_tokens_seen": 380744, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.9851577877998352, | |
| "learning_rate": 4.6658771031067734e-05, | |
| "loss": 6.8308, | |
| "num_input_tokens_seen": 382120, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 6.847332954406738, | |
| "eval_runtime": 2.5729, | |
| "eval_samples_per_second": 92.502, | |
| "eval_steps_per_second": 23.32, | |
| "num_input_tokens_seen": 382120, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.5093283582089554, | |
| "grad_norm": 0.8297715187072754, | |
| "learning_rate": 4.6617999559440187e-05, | |
| "loss": 6.9646, | |
| "num_input_tokens_seen": 383400, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 2.5186567164179103, | |
| "grad_norm": 0.8038099408149719, | |
| "learning_rate": 4.657699887426884e-05, | |
| "loss": 6.5551, | |
| "num_input_tokens_seen": 384680, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.5279850746268657, | |
| "grad_norm": 0.7128905653953552, | |
| "learning_rate": 4.653576941027995e-05, | |
| "loss": 6.7656, | |
| "num_input_tokens_seen": 385992, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 2.5373134328358207, | |
| "grad_norm": 0.7808387279510498, | |
| "learning_rate": 4.649431160462552e-05, | |
| "loss": 6.3868, | |
| "num_input_tokens_seen": 387368, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.546641791044776, | |
| "grad_norm": 0.8519075512886047, | |
| "learning_rate": 4.645262589687861e-05, | |
| "loss": 6.2019, | |
| "num_input_tokens_seen": 388776, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 2.5559701492537314, | |
| "grad_norm": 0.7525355815887451, | |
| "learning_rate": 4.6410712729028734e-05, | |
| "loss": 6.7456, | |
| "num_input_tokens_seen": 390440, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.5652985074626864, | |
| "grad_norm": 1.2101694345474243, | |
| "learning_rate": 4.636857254547712e-05, | |
| "loss": 6.3728, | |
| "num_input_tokens_seen": 391720, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 2.574626865671642, | |
| "grad_norm": 0.7277738451957703, | |
| "learning_rate": 4.632620579303203e-05, | |
| "loss": 6.7978, | |
| "num_input_tokens_seen": 393032, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.583955223880597, | |
| "grad_norm": 0.7772236466407776, | |
| "learning_rate": 4.628361292090403e-05, | |
| "loss": 6.2146, | |
| "num_input_tokens_seen": 394312, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 2.593283582089552, | |
| "grad_norm": 0.8174942135810852, | |
| "learning_rate": 4.624079438070117e-05, | |
| "loss": 6.4358, | |
| "num_input_tokens_seen": 395656, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.6026119402985075, | |
| "grad_norm": 1.1736090183258057, | |
| "learning_rate": 4.6197750626424277e-05, | |
| "loss": 6.744, | |
| "num_input_tokens_seen": 397288, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 2.611940298507463, | |
| "grad_norm": 1.0777864456176758, | |
| "learning_rate": 4.615448211446208e-05, | |
| "loss": 6.8124, | |
| "num_input_tokens_seen": 398600, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.621268656716418, | |
| "grad_norm": 0.7666352391242981, | |
| "learning_rate": 4.6110989303586396e-05, | |
| "loss": 6.621, | |
| "num_input_tokens_seen": 400168, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 2.6305970149253732, | |
| "grad_norm": 0.8335666656494141, | |
| "learning_rate": 4.606727265494727e-05, | |
| "loss": 7.0945, | |
| "num_input_tokens_seen": 401544, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.6399253731343286, | |
| "grad_norm": 0.8491174578666687, | |
| "learning_rate": 4.602333263206806e-05, | |
| "loss": 6.5069, | |
| "num_input_tokens_seen": 402984, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 2.6492537313432836, | |
| "grad_norm": 0.7431519031524658, | |
| "learning_rate": 4.597916970084056e-05, | |
| "loss": 7.1347, | |
| "num_input_tokens_seen": 404328, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.658582089552239, | |
| "grad_norm": 0.7434252500534058, | |
| "learning_rate": 4.593478432952002e-05, | |
| "loss": 6.0565, | |
| "num_input_tokens_seen": 405608, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 2.667910447761194, | |
| "grad_norm": 1.122470498085022, | |
| "learning_rate": 4.5890176988720205e-05, | |
| "loss": 6.3487, | |
| "num_input_tokens_seen": 407208, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.6772388059701493, | |
| "grad_norm": 1.0308672189712524, | |
| "learning_rate": 4.584534815140842e-05, | |
| "loss": 6.8202, | |
| "num_input_tokens_seen": 408776, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 2.6865671641791042, | |
| "grad_norm": 0.9447910785675049, | |
| "learning_rate": 4.5800298292900446e-05, | |
| "loss": 6.1282, | |
| "num_input_tokens_seen": 410120, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.6958955223880596, | |
| "grad_norm": 0.8939276933670044, | |
| "learning_rate": 4.575502789085555e-05, | |
| "loss": 6.467, | |
| "num_input_tokens_seen": 411624, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 2.705223880597015, | |
| "grad_norm": 0.6873200535774231, | |
| "learning_rate": 4.57095374252714e-05, | |
| "loss": 6.3529, | |
| "num_input_tokens_seen": 413096, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.71455223880597, | |
| "grad_norm": 0.9514541625976562, | |
| "learning_rate": 4.5663827378478975e-05, | |
| "loss": 6.9861, | |
| "num_input_tokens_seen": 414472, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 2.7238805970149254, | |
| "grad_norm": 0.9086441397666931, | |
| "learning_rate": 4.561789823513743e-05, | |
| "loss": 7.2706, | |
| "num_input_tokens_seen": 416072, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.7332089552238807, | |
| "grad_norm": 1.111498475074768, | |
| "learning_rate": 4.5571750482229016e-05, | |
| "loss": 6.7473, | |
| "num_input_tokens_seen": 417640, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 2.7425373134328357, | |
| "grad_norm": 0.8762888312339783, | |
| "learning_rate": 4.552538460905386e-05, | |
| "loss": 6.9012, | |
| "num_input_tokens_seen": 419048, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.751865671641791, | |
| "grad_norm": 0.9860914945602417, | |
| "learning_rate": 4.54788011072248e-05, | |
| "loss": 6.3489, | |
| "num_input_tokens_seen": 420520, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 2.7611940298507465, | |
| "grad_norm": 0.8717337846755981, | |
| "learning_rate": 4.543200047066216e-05, | |
| "loss": 6.5353, | |
| "num_input_tokens_seen": 421960, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.7705223880597014, | |
| "grad_norm": 1.1262425184249878, | |
| "learning_rate": 4.538498319558854e-05, | |
| "loss": 6.489, | |
| "num_input_tokens_seen": 423304, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 2.779850746268657, | |
| "grad_norm": 0.874546468257904, | |
| "learning_rate": 4.5337749780523526e-05, | |
| "loss": 6.8703, | |
| "num_input_tokens_seen": 424552, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.789179104477612, | |
| "grad_norm": 0.9099519848823547, | |
| "learning_rate": 4.5290300726278415e-05, | |
| "loss": 6.516, | |
| "num_input_tokens_seen": 425896, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 2.798507462686567, | |
| "grad_norm": 0.9403135776519775, | |
| "learning_rate": 4.5242636535950913e-05, | |
| "loss": 6.2462, | |
| "num_input_tokens_seen": 427208, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.8078358208955225, | |
| "grad_norm": 0.8429607152938843, | |
| "learning_rate": 4.519475771491978e-05, | |
| "loss": 6.361, | |
| "num_input_tokens_seen": 428392, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 2.8171641791044775, | |
| "grad_norm": 0.7554488182067871, | |
| "learning_rate": 4.5146664770839495e-05, | |
| "loss": 7.0662, | |
| "num_input_tokens_seen": 429928, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 2.826492537313433, | |
| "grad_norm": 1.2687819004058838, | |
| "learning_rate": 4.5098358213634876e-05, | |
| "loss": 7.1708, | |
| "num_input_tokens_seen": 431464, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 2.835820895522388, | |
| "grad_norm": 0.717535138130188, | |
| "learning_rate": 4.504983855549562e-05, | |
| "loss": 6.8913, | |
| "num_input_tokens_seen": 432968, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.845149253731343, | |
| "grad_norm": 0.7901401519775391, | |
| "learning_rate": 4.5001106310870946e-05, | |
| "loss": 7.1544, | |
| "num_input_tokens_seen": 434472, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 2.8544776119402986, | |
| "grad_norm": 0.6806740760803223, | |
| "learning_rate": 4.49521619964641e-05, | |
| "loss": 6.3892, | |
| "num_input_tokens_seen": 435944, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 2.8638059701492535, | |
| "grad_norm": 0.8405523896217346, | |
| "learning_rate": 4.4903006131226874e-05, | |
| "loss": 6.9862, | |
| "num_input_tokens_seen": 437608, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 2.873134328358209, | |
| "grad_norm": 1.3679183721542358, | |
| "learning_rate": 4.485363923635413e-05, | |
| "loss": 7.2509, | |
| "num_input_tokens_seen": 439176, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 2.8824626865671643, | |
| "grad_norm": 1.0259038209915161, | |
| "learning_rate": 4.480406183527823e-05, | |
| "loss": 6.3681, | |
| "num_input_tokens_seen": 440520, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 2.8917910447761193, | |
| "grad_norm": 1.1281458139419556, | |
| "learning_rate": 4.475427445366355e-05, | |
| "loss": 6.1798, | |
| "num_input_tokens_seen": 441896, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.9011194029850746, | |
| "grad_norm": 1.0936812162399292, | |
| "learning_rate": 4.4704277619400834e-05, | |
| "loss": 7.0098, | |
| "num_input_tokens_seen": 443176, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 2.91044776119403, | |
| "grad_norm": 1.082368016242981, | |
| "learning_rate": 4.4654071862601654e-05, | |
| "loss": 6.9893, | |
| "num_input_tokens_seen": 444680, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.919776119402985, | |
| "grad_norm": 0.6438327431678772, | |
| "learning_rate": 4.460365771559275e-05, | |
| "loss": 6.3998, | |
| "num_input_tokens_seen": 446024, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 2.9291044776119404, | |
| "grad_norm": 0.8255813121795654, | |
| "learning_rate": 4.455303571291042e-05, | |
| "loss": 6.3063, | |
| "num_input_tokens_seen": 447656, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 2.9384328358208958, | |
| "grad_norm": 1.045172095298767, | |
| "learning_rate": 4.4502206391294824e-05, | |
| "loss": 6.7395, | |
| "num_input_tokens_seen": 448904, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 2.9477611940298507, | |
| "grad_norm": 0.7798609137535095, | |
| "learning_rate": 4.445117028968431e-05, | |
| "loss": 6.6092, | |
| "num_input_tokens_seen": 450216, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 2.957089552238806, | |
| "grad_norm": 0.7614557147026062, | |
| "learning_rate": 4.439992794920969e-05, | |
| "loss": 6.4942, | |
| "num_input_tokens_seen": 451592, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 2.966417910447761, | |
| "grad_norm": 0.9290444254875183, | |
| "learning_rate": 4.434847991318851e-05, | |
| "loss": 6.6325, | |
| "num_input_tokens_seen": 453032, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.9757462686567164, | |
| "grad_norm": 1.4096976518630981, | |
| "learning_rate": 4.4296826727119296e-05, | |
| "loss": 6.5674, | |
| "num_input_tokens_seen": 454408, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 2.9850746268656714, | |
| "grad_norm": 1.2403829097747803, | |
| "learning_rate": 4.424496893867573e-05, | |
| "loss": 6.6931, | |
| "num_input_tokens_seen": 455912, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.9944029850746268, | |
| "grad_norm": 0.8583068251609802, | |
| "learning_rate": 4.419290709770091e-05, | |
| "loss": 6.5213, | |
| "num_input_tokens_seen": 457256, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6.66015625, | |
| "eval_runtime": 2.5649, | |
| "eval_samples_per_second": 92.791, | |
| "eval_steps_per_second": 23.393, | |
| "num_input_tokens_seen": 457952, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 3.003731343283582, | |
| "grad_norm": 0.8232004642486572, | |
| "learning_rate": 4.414064175620146e-05, | |
| "loss": 6.3029, | |
| "num_input_tokens_seen": 458464, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 3.013059701492537, | |
| "grad_norm": 0.8364391922950745, | |
| "learning_rate": 4.408817346834169e-05, | |
| "loss": 7.0312, | |
| "num_input_tokens_seen": 459872, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 3.0223880597014925, | |
| "grad_norm": 0.6609486937522888, | |
| "learning_rate": 4.4035502790437764e-05, | |
| "loss": 6.9781, | |
| "num_input_tokens_seen": 461408, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 3.031716417910448, | |
| "grad_norm": 0.9955732226371765, | |
| "learning_rate": 4.398263028095175e-05, | |
| "loss": 6.7744, | |
| "num_input_tokens_seen": 462624, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 3.041044776119403, | |
| "grad_norm": 0.7589630484580994, | |
| "learning_rate": 4.392955650048571e-05, | |
| "loss": 6.8695, | |
| "num_input_tokens_seen": 464096, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 3.050373134328358, | |
| "grad_norm": 0.6912356019020081, | |
| "learning_rate": 4.387628201177577e-05, | |
| "loss": 6.6582, | |
| "num_input_tokens_seen": 465408, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 3.0597014925373136, | |
| "grad_norm": 0.7805551290512085, | |
| "learning_rate": 4.382280737968614e-05, | |
| "loss": 6.7798, | |
| "num_input_tokens_seen": 466880, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 3.0690298507462686, | |
| "grad_norm": 1.0802308320999146, | |
| "learning_rate": 4.3769133171203144e-05, | |
| "loss": 6.5449, | |
| "num_input_tokens_seen": 468416, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 3.078358208955224, | |
| "grad_norm": 1.6585947275161743, | |
| "learning_rate": 4.371525995542918e-05, | |
| "loss": 6.5721, | |
| "num_input_tokens_seen": 469952, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.0876865671641793, | |
| "grad_norm": 0.9884666204452515, | |
| "learning_rate": 4.366118830357672e-05, | |
| "loss": 6.1842, | |
| "num_input_tokens_seen": 471264, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 3.0970149253731343, | |
| "grad_norm": 0.9238292574882507, | |
| "learning_rate": 4.3606918788962205e-05, | |
| "loss": 6.5954, | |
| "num_input_tokens_seen": 472640, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 3.1063432835820897, | |
| "grad_norm": 0.9086124897003174, | |
| "learning_rate": 4.355245198700003e-05, | |
| "loss": 6.67, | |
| "num_input_tokens_seen": 473984, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 3.1156716417910446, | |
| "grad_norm": 0.8775209784507751, | |
| "learning_rate": 4.3497788475196376e-05, | |
| "loss": 6.7531, | |
| "num_input_tokens_seen": 475488, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 3.125, | |
| "grad_norm": 0.7578677535057068, | |
| "learning_rate": 4.3442928833143145e-05, | |
| "loss": 6.8457, | |
| "num_input_tokens_seen": 476864, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 3.1343283582089554, | |
| "grad_norm": 0.8706665635108948, | |
| "learning_rate": 4.338787364251177e-05, | |
| "loss": 6.157, | |
| "num_input_tokens_seen": 478272, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 3.1436567164179103, | |
| "grad_norm": 1.0108400583267212, | |
| "learning_rate": 4.3332623487047084e-05, | |
| "loss": 6.3999, | |
| "num_input_tokens_seen": 479648, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 3.1529850746268657, | |
| "grad_norm": 0.9112622737884521, | |
| "learning_rate": 4.32771789525611e-05, | |
| "loss": 6.34, | |
| "num_input_tokens_seen": 481152, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 3.1623134328358207, | |
| "grad_norm": 1.284745216369629, | |
| "learning_rate": 4.3221540626926824e-05, | |
| "loss": 6.6815, | |
| "num_input_tokens_seen": 482624, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 3.171641791044776, | |
| "grad_norm": 1.4875261783599854, | |
| "learning_rate": 4.3165709100071986e-05, | |
| "loss": 7.0455, | |
| "num_input_tokens_seen": 484032, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.1809701492537314, | |
| "grad_norm": 1.0912647247314453, | |
| "learning_rate": 4.310968496397284e-05, | |
| "loss": 6.2077, | |
| "num_input_tokens_seen": 485440, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 3.1902985074626864, | |
| "grad_norm": 0.8089683651924133, | |
| "learning_rate": 4.305346881264785e-05, | |
| "loss": 6.4335, | |
| "num_input_tokens_seen": 486848, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 3.199626865671642, | |
| "grad_norm": 1.3359805345535278, | |
| "learning_rate": 4.299706124215138e-05, | |
| "loss": 6.2969, | |
| "num_input_tokens_seen": 488192, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 3.208955223880597, | |
| "grad_norm": 0.9441768527030945, | |
| "learning_rate": 4.294046285056742e-05, | |
| "loss": 6.4261, | |
| "num_input_tokens_seen": 489696, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 3.218283582089552, | |
| "grad_norm": 0.896895706653595, | |
| "learning_rate": 4.288367423800319e-05, | |
| "loss": 6.3899, | |
| "num_input_tokens_seen": 491008, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 3.2276119402985075, | |
| "grad_norm": 0.8911027312278748, | |
| "learning_rate": 4.2826696006582825e-05, | |
| "loss": 7.1036, | |
| "num_input_tokens_seen": 492576, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 3.236940298507463, | |
| "grad_norm": 0.9505497813224792, | |
| "learning_rate": 4.276952876044096e-05, | |
| "loss": 6.8823, | |
| "num_input_tokens_seen": 493824, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 3.246268656716418, | |
| "grad_norm": 0.990657389163971, | |
| "learning_rate": 4.2712173105716346e-05, | |
| "loss": 7.2438, | |
| "num_input_tokens_seen": 495200, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 3.2555970149253732, | |
| "grad_norm": 1.1892321109771729, | |
| "learning_rate": 4.265462965054539e-05, | |
| "loss": 6.7313, | |
| "num_input_tokens_seen": 496576, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 3.264925373134328, | |
| "grad_norm": 0.933014452457428, | |
| "learning_rate": 4.259689900505576e-05, | |
| "loss": 6.3991, | |
| "num_input_tokens_seen": 498112, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 3.2742537313432836, | |
| "grad_norm": 0.952068567276001, | |
| "learning_rate": 4.253898178135985e-05, | |
| "loss": 6.7519, | |
| "num_input_tokens_seen": 499552, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 3.283582089552239, | |
| "grad_norm": 1.079302430152893, | |
| "learning_rate": 4.2480878593548344e-05, | |
| "loss": 6.9308, | |
| "num_input_tokens_seen": 500960, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 3.292910447761194, | |
| "grad_norm": 0.9718023538589478, | |
| "learning_rate": 4.24225900576837e-05, | |
| "loss": 6.0125, | |
| "num_input_tokens_seen": 502208, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 3.3022388059701493, | |
| "grad_norm": 1.0265660285949707, | |
| "learning_rate": 4.236411679179357e-05, | |
| "loss": 5.9982, | |
| "num_input_tokens_seen": 503808, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 3.3115671641791042, | |
| "grad_norm": 0.8161365389823914, | |
| "learning_rate": 4.230545941586431e-05, | |
| "loss": 6.1401, | |
| "num_input_tokens_seen": 505248, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 3.3208955223880596, | |
| "grad_norm": 1.3264844417572021, | |
| "learning_rate": 4.224661855183435e-05, | |
| "loss": 6.5042, | |
| "num_input_tokens_seen": 507072, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 3.330223880597015, | |
| "grad_norm": 1.0835908651351929, | |
| "learning_rate": 4.218759482358765e-05, | |
| "loss": 7.3425, | |
| "num_input_tokens_seen": 508576, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 3.33955223880597, | |
| "grad_norm": 0.7933202385902405, | |
| "learning_rate": 4.212838885694705e-05, | |
| "loss": 6.2476, | |
| "num_input_tokens_seen": 509824, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 3.3488805970149254, | |
| "grad_norm": 1.0839298963546753, | |
| "learning_rate": 4.206900127966764e-05, | |
| "loss": 5.6183, | |
| "num_input_tokens_seen": 511392, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 3.3582089552238807, | |
| "grad_norm": 0.8385881781578064, | |
| "learning_rate": 4.200943272143013e-05, | |
| "loss": 6.7416, | |
| "num_input_tokens_seen": 512672, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.3675373134328357, | |
| "grad_norm": 0.9048122763633728, | |
| "learning_rate": 4.194968381383414e-05, | |
| "loss": 6.9277, | |
| "num_input_tokens_seen": 514144, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 3.376865671641791, | |
| "grad_norm": 1.0432989597320557, | |
| "learning_rate": 4.188975519039151e-05, | |
| "loss": 6.4683, | |
| "num_input_tokens_seen": 515584, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 3.3861940298507465, | |
| "grad_norm": 0.865658164024353, | |
| "learning_rate": 4.1829647486519596e-05, | |
| "loss": 6.5091, | |
| "num_input_tokens_seen": 516928, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 3.3955223880597014, | |
| "grad_norm": 0.9050042033195496, | |
| "learning_rate": 4.176936133953454e-05, | |
| "loss": 6.495, | |
| "num_input_tokens_seen": 518432, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 3.404850746268657, | |
| "grad_norm": 0.9352641105651855, | |
| "learning_rate": 4.170889738864448e-05, | |
| "loss": 6.0773, | |
| "num_input_tokens_seen": 519904, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 3.4141791044776117, | |
| "grad_norm": 0.7213832139968872, | |
| "learning_rate": 4.16482562749428e-05, | |
| "loss": 6.6777, | |
| "num_input_tokens_seen": 521472, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 3.423507462686567, | |
| "grad_norm": 0.8704091906547546, | |
| "learning_rate": 4.158743864140131e-05, | |
| "loss": 6.1763, | |
| "num_input_tokens_seen": 522848, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 3.4328358208955225, | |
| "grad_norm": 0.974309504032135, | |
| "learning_rate": 4.152644513286348e-05, | |
| "loss": 6.407, | |
| "num_input_tokens_seen": 524160, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 3.4421641791044775, | |
| "grad_norm": 0.8126544952392578, | |
| "learning_rate": 4.146527639603751e-05, | |
| "loss": 6.5662, | |
| "num_input_tokens_seen": 525504, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 3.451492537313433, | |
| "grad_norm": 0.9578900337219238, | |
| "learning_rate": 4.1403933079489585e-05, | |
| "loss": 6.1601, | |
| "num_input_tokens_seen": 526816, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 3.4608208955223883, | |
| "grad_norm": 0.8764714598655701, | |
| "learning_rate": 4.1342415833636904e-05, | |
| "loss": 6.4124, | |
| "num_input_tokens_seen": 528224, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 3.470149253731343, | |
| "grad_norm": 0.932793140411377, | |
| "learning_rate": 4.128072531074084e-05, | |
| "loss": 5.9867, | |
| "num_input_tokens_seen": 529504, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 3.4794776119402986, | |
| "grad_norm": 0.901010274887085, | |
| "learning_rate": 4.121886216489998e-05, | |
| "loss": 6.4769, | |
| "num_input_tokens_seen": 531072, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 3.4888059701492535, | |
| "grad_norm": 0.9698062539100647, | |
| "learning_rate": 4.115682705204326e-05, | |
| "loss": 6.6296, | |
| "num_input_tokens_seen": 532832, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 3.498134328358209, | |
| "grad_norm": 0.8078415393829346, | |
| "learning_rate": 4.109462062992293e-05, | |
| "loss": 6.1458, | |
| "num_input_tokens_seen": 534272, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_loss": 6.530898094177246, | |
| "eval_runtime": 2.5637, | |
| "eval_samples_per_second": 92.836, | |
| "eval_steps_per_second": 23.404, | |
| "num_input_tokens_seen": 534688, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 3.5074626865671643, | |
| "grad_norm": 0.8010856509208679, | |
| "learning_rate": 4.103224355810761e-05, | |
| "loss": 6.7196, | |
| "num_input_tokens_seen": 535872, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 3.5167910447761193, | |
| "grad_norm": 0.829319953918457, | |
| "learning_rate": 4.096969649797534e-05, | |
| "loss": 6.6623, | |
| "num_input_tokens_seen": 537376, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 3.5261194029850746, | |
| "grad_norm": 0.7482777237892151, | |
| "learning_rate": 4.0906980112706494e-05, | |
| "loss": 5.9926, | |
| "num_input_tokens_seen": 538880, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 3.53544776119403, | |
| "grad_norm": 0.9391413331031799, | |
| "learning_rate": 4.08440950672768e-05, | |
| "loss": 6.4891, | |
| "num_input_tokens_seen": 540512, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 3.544776119402985, | |
| "grad_norm": 0.8121633529663086, | |
| "learning_rate": 4.078104202845027e-05, | |
| "loss": 6.9897, | |
| "num_input_tokens_seen": 541920, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.5541044776119404, | |
| "grad_norm": 0.9392657279968262, | |
| "learning_rate": 4.071782166477213e-05, | |
| "loss": 6.0652, | |
| "num_input_tokens_seen": 543328, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 3.5634328358208958, | |
| "grad_norm": 1.008346438407898, | |
| "learning_rate": 4.065443464656174e-05, | |
| "loss": 6.3105, | |
| "num_input_tokens_seen": 544800, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 3.5727611940298507, | |
| "grad_norm": 0.8515278100967407, | |
| "learning_rate": 4.0590881645905475e-05, | |
| "loss": 6.2764, | |
| "num_input_tokens_seen": 546208, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 3.582089552238806, | |
| "grad_norm": 0.9222008585929871, | |
| "learning_rate": 4.052716333664963e-05, | |
| "loss": 6.4578, | |
| "num_input_tokens_seen": 547616, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 3.591417910447761, | |
| "grad_norm": 0.8278989791870117, | |
| "learning_rate": 4.046328039439321e-05, | |
| "loss": 6.3317, | |
| "num_input_tokens_seen": 549088, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 3.6007462686567164, | |
| "grad_norm": 1.0889692306518555, | |
| "learning_rate": 4.039923349648084e-05, | |
| "loss": 6.5272, | |
| "num_input_tokens_seen": 550464, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 3.6100746268656714, | |
| "grad_norm": 1.164398193359375, | |
| "learning_rate": 4.0335023321995545e-05, | |
| "loss": 5.8427, | |
| "num_input_tokens_seen": 552032, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 3.6194029850746268, | |
| "grad_norm": 0.9753542542457581, | |
| "learning_rate": 4.0270650551751546e-05, | |
| "loss": 6.3749, | |
| "num_input_tokens_seen": 553344, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 3.628731343283582, | |
| "grad_norm": 0.9358706474304199, | |
| "learning_rate": 4.020611586828705e-05, | |
| "loss": 6.5775, | |
| "num_input_tokens_seen": 554592, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 3.638059701492537, | |
| "grad_norm": 0.9618571400642395, | |
| "learning_rate": 4.0141419955857044e-05, | |
| "loss": 6.7602, | |
| "num_input_tokens_seen": 556064, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.6473880597014925, | |
| "grad_norm": 1.795710802078247, | |
| "learning_rate": 4.007656350042595e-05, | |
| "loss": 5.6166, | |
| "num_input_tokens_seen": 557536, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 3.656716417910448, | |
| "grad_norm": 0.8476569056510925, | |
| "learning_rate": 4.001154718966048e-05, | |
| "loss": 6.717, | |
| "num_input_tokens_seen": 558976, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 3.666044776119403, | |
| "grad_norm": 0.6623837947845459, | |
| "learning_rate": 3.994637171292223e-05, | |
| "loss": 5.7437, | |
| "num_input_tokens_seen": 560192, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 3.675373134328358, | |
| "grad_norm": 1.039686679840088, | |
| "learning_rate": 3.988103776126042e-05, | |
| "loss": 6.5671, | |
| "num_input_tokens_seen": 561472, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 3.6847014925373136, | |
| "grad_norm": 1.1107091903686523, | |
| "learning_rate": 3.9815546027404603e-05, | |
| "loss": 6.267, | |
| "num_input_tokens_seen": 562912, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 3.6940298507462686, | |
| "grad_norm": 1.070863962173462, | |
| "learning_rate": 3.974989720575724e-05, | |
| "loss": 6.494, | |
| "num_input_tokens_seen": 564288, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 3.703358208955224, | |
| "grad_norm": 0.8570924401283264, | |
| "learning_rate": 3.9684091992386393e-05, | |
| "loss": 6.3349, | |
| "num_input_tokens_seen": 565664, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 3.7126865671641793, | |
| "grad_norm": 0.6981739401817322, | |
| "learning_rate": 3.961813108501833e-05, | |
| "loss": 6.595, | |
| "num_input_tokens_seen": 567040, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 3.7220149253731343, | |
| "grad_norm": 1.0859757661819458, | |
| "learning_rate": 3.9552015183030136e-05, | |
| "loss": 6.1501, | |
| "num_input_tokens_seen": 568320, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 3.7313432835820897, | |
| "grad_norm": 0.8336313962936401, | |
| "learning_rate": 3.9485744987442266e-05, | |
| "loss": 6.5023, | |
| "num_input_tokens_seen": 569696, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.7406716417910446, | |
| "grad_norm": 0.8433949947357178, | |
| "learning_rate": 3.9419321200911155e-05, | |
| "loss": 6.8004, | |
| "num_input_tokens_seen": 571296, | |
| "step": 2005 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "grad_norm": 0.7963794469833374, | |
| "learning_rate": 3.9352744527721754e-05, | |
| "loss": 6.9846, | |
| "num_input_tokens_seen": 572768, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 3.7593283582089554, | |
| "grad_norm": 0.9318357110023499, | |
| "learning_rate": 3.928601567378003e-05, | |
| "loss": 6.1147, | |
| "num_input_tokens_seen": 574080, | |
| "step": 2015 | |
| }, | |
| { | |
| "epoch": 3.7686567164179103, | |
| "grad_norm": 1.0676405429840088, | |
| "learning_rate": 3.921913534660552e-05, | |
| "loss": 6.2397, | |
| "num_input_tokens_seen": 575456, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 3.7779850746268657, | |
| "grad_norm": 1.0161662101745605, | |
| "learning_rate": 3.915210425532383e-05, | |
| "loss": 6.8914, | |
| "num_input_tokens_seen": 576864, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 3.7873134328358207, | |
| "grad_norm": 0.6612462997436523, | |
| "learning_rate": 3.908492311065909e-05, | |
| "loss": 6.6493, | |
| "num_input_tokens_seen": 578304, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 3.796641791044776, | |
| "grad_norm": 1.3637316226959229, | |
| "learning_rate": 3.901759262492643e-05, | |
| "loss": 6.654, | |
| "num_input_tokens_seen": 579744, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 3.8059701492537314, | |
| "grad_norm": 1.0594669580459595, | |
| "learning_rate": 3.895011351202443e-05, | |
| "loss": 6.6757, | |
| "num_input_tokens_seen": 581088, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 3.8152985074626864, | |
| "grad_norm": 1.081887125968933, | |
| "learning_rate": 3.888248648742756e-05, | |
| "loss": 6.9096, | |
| "num_input_tokens_seen": 582560, | |
| "step": 2045 | |
| }, | |
| { | |
| "epoch": 3.824626865671642, | |
| "grad_norm": 0.8722996115684509, | |
| "learning_rate": 3.881471226817858e-05, | |
| "loss": 6.2226, | |
| "num_input_tokens_seen": 584000, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 3.833955223880597, | |
| "grad_norm": 0.9458469152450562, | |
| "learning_rate": 3.874679157288092e-05, | |
| "loss": 6.2206, | |
| "num_input_tokens_seen": 585248, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 3.843283582089552, | |
| "grad_norm": 1.1535446643829346, | |
| "learning_rate": 3.86787251216911e-05, | |
| "loss": 6.6818, | |
| "num_input_tokens_seen": 586720, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 3.8526119402985075, | |
| "grad_norm": 0.9748989343643188, | |
| "learning_rate": 3.8610513636311073e-05, | |
| "loss": 6.701, | |
| "num_input_tokens_seen": 588352, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 3.861940298507463, | |
| "grad_norm": 0.9816749095916748, | |
| "learning_rate": 3.854215783998058e-05, | |
| "loss": 6.5315, | |
| "num_input_tokens_seen": 589632, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 3.871268656716418, | |
| "grad_norm": 0.9961613416671753, | |
| "learning_rate": 3.8473658457469466e-05, | |
| "loss": 5.8164, | |
| "num_input_tokens_seen": 591072, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 3.8805970149253732, | |
| "grad_norm": 1.265100121498108, | |
| "learning_rate": 3.840501621507003e-05, | |
| "loss": 6.5248, | |
| "num_input_tokens_seen": 592544, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 3.8899253731343286, | |
| "grad_norm": 1.816586971282959, | |
| "learning_rate": 3.833623184058926e-05, | |
| "loss": 6.2466, | |
| "num_input_tokens_seen": 594112, | |
| "step": 2085 | |
| }, | |
| { | |
| "epoch": 3.8992537313432836, | |
| "grad_norm": 0.9094443321228027, | |
| "learning_rate": 3.826730606334119e-05, | |
| "loss": 6.3241, | |
| "num_input_tokens_seen": 595744, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 3.908582089552239, | |
| "grad_norm": 0.8418962359428406, | |
| "learning_rate": 3.819823961413912e-05, | |
| "loss": 6.4945, | |
| "num_input_tokens_seen": 597184, | |
| "step": 2095 | |
| }, | |
| { | |
| "epoch": 3.917910447761194, | |
| "grad_norm": 0.9625788331031799, | |
| "learning_rate": 3.812903322528789e-05, | |
| "loss": 6.8721, | |
| "num_input_tokens_seen": 598816, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.9272388059701493, | |
| "grad_norm": 0.8912540078163147, | |
| "learning_rate": 3.805968763057609e-05, | |
| "loss": 6.3736, | |
| "num_input_tokens_seen": 600192, | |
| "step": 2105 | |
| }, | |
| { | |
| "epoch": 3.9365671641791042, | |
| "grad_norm": 0.8132984638214111, | |
| "learning_rate": 3.7990203565268314e-05, | |
| "loss": 6.1833, | |
| "num_input_tokens_seen": 601472, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 3.9458955223880596, | |
| "grad_norm": 0.8152676224708557, | |
| "learning_rate": 3.792058176609734e-05, | |
| "loss": 6.2474, | |
| "num_input_tokens_seen": 602880, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 3.955223880597015, | |
| "grad_norm": 0.8810433745384216, | |
| "learning_rate": 3.785082297125631e-05, | |
| "loss": 6.5263, | |
| "num_input_tokens_seen": 604416, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 3.96455223880597, | |
| "grad_norm": 0.938319742679596, | |
| "learning_rate": 3.7780927920390964e-05, | |
| "loss": 6.5571, | |
| "num_input_tokens_seen": 605696, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 3.9738805970149254, | |
| "grad_norm": 0.8142312169075012, | |
| "learning_rate": 3.771089735459168e-05, | |
| "loss": 6.8228, | |
| "num_input_tokens_seen": 607040, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 3.9832089552238807, | |
| "grad_norm": 0.8673137426376343, | |
| "learning_rate": 3.7640732016385745e-05, | |
| "loss": 6.2469, | |
| "num_input_tokens_seen": 608608, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 3.9925373134328357, | |
| "grad_norm": 1.0599561929702759, | |
| "learning_rate": 3.757043264972941e-05, | |
| "loss": 6.4748, | |
| "num_input_tokens_seen": 609984, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 6.432187080383301, | |
| "eval_runtime": 2.5729, | |
| "eval_samples_per_second": 92.502, | |
| "eval_steps_per_second": 23.32, | |
| "num_input_tokens_seen": 610944, | |
| "step": 2144 | |
| }, | |
| { | |
| "epoch": 4.001865671641791, | |
| "grad_norm": 1.2047561407089233, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 5.8664, | |
| "num_input_tokens_seen": 611200, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 4.0111940298507465, | |
| "grad_norm": 1.7999390363693237, | |
| "learning_rate": 3.742943481398805e-05, | |
| "loss": 6.1699, | |
| "num_input_tokens_seen": 612512, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 4.020522388059701, | |
| "grad_norm": 0.8161091804504395, | |
| "learning_rate": 3.7358737839889356e-05, | |
| "loss": 6.1006, | |
| "num_input_tokens_seen": 613920, | |
| "step": 2155 | |
| }, | |
| { | |
| "epoch": 4.029850746268656, | |
| "grad_norm": 0.9980080723762512, | |
| "learning_rate": 3.728790982729705e-05, | |
| "loss": 6.1764, | |
| "num_input_tokens_seen": 615264, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 4.039179104477612, | |
| "grad_norm": 1.3915200233459473, | |
| "learning_rate": 3.721695152719364e-05, | |
| "loss": 6.2364, | |
| "num_input_tokens_seen": 616576, | |
| "step": 2165 | |
| }, | |
| { | |
| "epoch": 4.048507462686567, | |
| "grad_norm": 1.388858437538147, | |
| "learning_rate": 3.7145863691943076e-05, | |
| "loss": 6.1802, | |
| "num_input_tokens_seen": 617984, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 4.057835820895522, | |
| "grad_norm": 1.662692904472351, | |
| "learning_rate": 3.707464707528275e-05, | |
| "loss": 6.2227, | |
| "num_input_tokens_seen": 619520, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 4.067164179104478, | |
| "grad_norm": 1.0371544361114502, | |
| "learning_rate": 3.700330243231552e-05, | |
| "loss": 6.4914, | |
| "num_input_tokens_seen": 620864, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 4.076492537313433, | |
| "grad_norm": 0.7505616545677185, | |
| "learning_rate": 3.6931830519501685e-05, | |
| "loss": 6.3576, | |
| "num_input_tokens_seen": 622272, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 4.085820895522388, | |
| "grad_norm": 0.9928741455078125, | |
| "learning_rate": 3.686023209465096e-05, | |
| "loss": 5.6246, | |
| "num_input_tokens_seen": 623840, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 4.095149253731344, | |
| "grad_norm": 0.8647277355194092, | |
| "learning_rate": 3.678850791691448e-05, | |
| "loss": 6.6165, | |
| "num_input_tokens_seen": 625216, | |
| "step": 2195 | |
| }, | |
| { | |
| "epoch": 4.104477611940299, | |
| "grad_norm": 0.8217287063598633, | |
| "learning_rate": 3.671665874677673e-05, | |
| "loss": 6.4202, | |
| "num_input_tokens_seen": 626592, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.1138059701492535, | |
| "grad_norm": 0.7509205937385559, | |
| "learning_rate": 3.664468534604745e-05, | |
| "loss": 6.526, | |
| "num_input_tokens_seen": 627968, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 4.123134328358209, | |
| "grad_norm": 0.741330623626709, | |
| "learning_rate": 3.65725884778536e-05, | |
| "loss": 6.0054, | |
| "num_input_tokens_seen": 629248, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 4.132462686567164, | |
| "grad_norm": 1.515855312347412, | |
| "learning_rate": 3.650036890663124e-05, | |
| "loss": 5.8631, | |
| "num_input_tokens_seen": 631040, | |
| "step": 2215 | |
| }, | |
| { | |
| "epoch": 4.141791044776119, | |
| "grad_norm": 1.0722737312316895, | |
| "learning_rate": 3.642802739811747e-05, | |
| "loss": 6.5582, | |
| "num_input_tokens_seen": 632320, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 4.151119402985074, | |
| "grad_norm": 0.9516023397445679, | |
| "learning_rate": 3.635556471934224e-05, | |
| "loss": 6.6937, | |
| "num_input_tokens_seen": 633792, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 4.16044776119403, | |
| "grad_norm": 1.0214040279388428, | |
| "learning_rate": 3.628298163862029e-05, | |
| "loss": 6.5748, | |
| "num_input_tokens_seen": 635328, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 4.169776119402985, | |
| "grad_norm": 0.7492480874061584, | |
| "learning_rate": 3.621027892554295e-05, | |
| "loss": 6.0516, | |
| "num_input_tokens_seen": 636864, | |
| "step": 2235 | |
| }, | |
| { | |
| "epoch": 4.17910447761194, | |
| "grad_norm": 0.7994016408920288, | |
| "learning_rate": 3.613745735096999e-05, | |
| "loss": 5.9094, | |
| "num_input_tokens_seen": 638112, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 4.188432835820896, | |
| "grad_norm": 1.0601117610931396, | |
| "learning_rate": 3.606451768702151e-05, | |
| "loss": 6.2744, | |
| "num_input_tokens_seen": 639456, | |
| "step": 2245 | |
| }, | |
| { | |
| "epoch": 4.197761194029851, | |
| "grad_norm": 1.167376160621643, | |
| "learning_rate": 3.599146070706964e-05, | |
| "loss": 6.1296, | |
| "num_input_tokens_seen": 640736, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 4.207089552238806, | |
| "grad_norm": 1.1699732542037964, | |
| "learning_rate": 3.5918287185730414e-05, | |
| "loss": 6.0515, | |
| "num_input_tokens_seen": 642208, | |
| "step": 2255 | |
| }, | |
| { | |
| "epoch": 4.2164179104477615, | |
| "grad_norm": 0.7409828901290894, | |
| "learning_rate": 3.5844997898855566e-05, | |
| "loss": 6.505, | |
| "num_input_tokens_seen": 643616, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 4.225746268656716, | |
| "grad_norm": 0.8586326241493225, | |
| "learning_rate": 3.5771593623524265e-05, | |
| "loss": 6.9843, | |
| "num_input_tokens_seen": 645024, | |
| "step": 2265 | |
| }, | |
| { | |
| "epoch": 4.235074626865671, | |
| "grad_norm": 0.9609360694885254, | |
| "learning_rate": 3.569807513803488e-05, | |
| "loss": 6.3727, | |
| "num_input_tokens_seen": 646464, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 4.244402985074627, | |
| "grad_norm": 1.165371060371399, | |
| "learning_rate": 3.5624443221896776e-05, | |
| "loss": 6.8002, | |
| "num_input_tokens_seen": 647968, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 4.253731343283582, | |
| "grad_norm": 0.8617619872093201, | |
| "learning_rate": 3.555069865582197e-05, | |
| "loss": 6.6819, | |
| "num_input_tokens_seen": 649312, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 4.263059701492537, | |
| "grad_norm": 1.4539963006973267, | |
| "learning_rate": 3.547684222171692e-05, | |
| "loss": 6.133, | |
| "num_input_tokens_seen": 650656, | |
| "step": 2285 | |
| }, | |
| { | |
| "epoch": 4.272388059701493, | |
| "grad_norm": 1.0110911130905151, | |
| "learning_rate": 3.54028747026742e-05, | |
| "loss": 6.7494, | |
| "num_input_tokens_seen": 652032, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 4.281716417910448, | |
| "grad_norm": 0.9399405121803284, | |
| "learning_rate": 3.532879688296421e-05, | |
| "loss": 7.0372, | |
| "num_input_tokens_seen": 653504, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 4.291044776119403, | |
| "grad_norm": 0.9495043754577637, | |
| "learning_rate": 3.5254609548026865e-05, | |
| "loss": 6.6207, | |
| "num_input_tokens_seen": 654912, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 4.300373134328359, | |
| "grad_norm": 1.0825306177139282, | |
| "learning_rate": 3.518031348446324e-05, | |
| "loss": 7.1731, | |
| "num_input_tokens_seen": 656256, | |
| "step": 2305 | |
| }, | |
| { | |
| "epoch": 4.309701492537314, | |
| "grad_norm": 1.040719747543335, | |
| "learning_rate": 3.5105909480027276e-05, | |
| "loss": 6.5055, | |
| "num_input_tokens_seen": 657792, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 4.3190298507462686, | |
| "grad_norm": 1.0200971364974976, | |
| "learning_rate": 3.5031398323617366e-05, | |
| "loss": 5.8665, | |
| "num_input_tokens_seen": 659264, | |
| "step": 2315 | |
| }, | |
| { | |
| "epoch": 4.3283582089552235, | |
| "grad_norm": 0.7819699048995972, | |
| "learning_rate": 3.4956780805268066e-05, | |
| "loss": 6.0873, | |
| "num_input_tokens_seen": 660640, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 4.337686567164179, | |
| "grad_norm": 0.7906717658042908, | |
| "learning_rate": 3.4882057716141635e-05, | |
| "loss": 6.3679, | |
| "num_input_tokens_seen": 662016, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 4.347014925373134, | |
| "grad_norm": 1.0831886529922485, | |
| "learning_rate": 3.480722984851972e-05, | |
| "loss": 6.804, | |
| "num_input_tokens_seen": 663392, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 4.356343283582089, | |
| "grad_norm": 0.8662129044532776, | |
| "learning_rate": 3.473229799579492e-05, | |
| "loss": 5.9175, | |
| "num_input_tokens_seen": 664928, | |
| "step": 2335 | |
| }, | |
| { | |
| "epoch": 4.365671641791045, | |
| "grad_norm": 0.9845402240753174, | |
| "learning_rate": 3.465726295246236e-05, | |
| "loss": 6.4613, | |
| "num_input_tokens_seen": 666176, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 4.375, | |
| "grad_norm": 1.0584032535552979, | |
| "learning_rate": 3.45821255141113e-05, | |
| "loss": 6.4258, | |
| "num_input_tokens_seen": 667552, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 4.384328358208955, | |
| "grad_norm": 0.9324563145637512, | |
| "learning_rate": 3.450688647741668e-05, | |
| "loss": 6.3671, | |
| "num_input_tokens_seen": 669056, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 4.393656716417911, | |
| "grad_norm": 1.1247103214263916, | |
| "learning_rate": 3.443154664013067e-05, | |
| "loss": 6.2882, | |
| "num_input_tokens_seen": 670592, | |
| "step": 2355 | |
| }, | |
| { | |
| "epoch": 4.402985074626866, | |
| "grad_norm": 1.0601203441619873, | |
| "learning_rate": 3.4356106801074245e-05, | |
| "loss": 6.6846, | |
| "num_input_tokens_seen": 672096, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 4.412313432835821, | |
| "grad_norm": 0.8400149941444397, | |
| "learning_rate": 3.4280567760128656e-05, | |
| "loss": 7.0621, | |
| "num_input_tokens_seen": 673568, | |
| "step": 2365 | |
| }, | |
| { | |
| "epoch": 4.4216417910447765, | |
| "grad_norm": 0.9119383692741394, | |
| "learning_rate": 3.4204930318227016e-05, | |
| "loss": 6.1608, | |
| "num_input_tokens_seen": 674976, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 4.4309701492537314, | |
| "grad_norm": 0.757416844367981, | |
| "learning_rate": 3.4129195277345724e-05, | |
| "loss": 6.4338, | |
| "num_input_tokens_seen": 676288, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 4.440298507462686, | |
| "grad_norm": 0.832974374294281, | |
| "learning_rate": 3.405336344049607e-05, | |
| "loss": 6.3068, | |
| "num_input_tokens_seen": 677888, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 4.449626865671641, | |
| "grad_norm": 0.9011245965957642, | |
| "learning_rate": 3.397743561171562e-05, | |
| "loss": 6.3268, | |
| "num_input_tokens_seen": 679328, | |
| "step": 2385 | |
| }, | |
| { | |
| "epoch": 4.458955223880597, | |
| "grad_norm": 0.8695389032363892, | |
| "learning_rate": 3.390141259605975e-05, | |
| "loss": 6.2514, | |
| "num_input_tokens_seen": 680736, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 4.468283582089552, | |
| "grad_norm": 0.9919965267181396, | |
| "learning_rate": 3.3825295199593084e-05, | |
| "loss": 6.6166, | |
| "num_input_tokens_seen": 682304, | |
| "step": 2395 | |
| }, | |
| { | |
| "epoch": 4.477611940298507, | |
| "grad_norm": 0.8801030516624451, | |
| "learning_rate": 3.3749084229380976e-05, | |
| "loss": 6.3584, | |
| "num_input_tokens_seen": 683936, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 4.486940298507463, | |
| "grad_norm": 0.7869558930397034, | |
| "learning_rate": 3.367278049348093e-05, | |
| "loss": 6.4258, | |
| "num_input_tokens_seen": 685312, | |
| "step": 2405 | |
| }, | |
| { | |
| "epoch": 4.496268656716418, | |
| "grad_norm": 0.9862135648727417, | |
| "learning_rate": 3.3596384800934e-05, | |
| "loss": 6.0796, | |
| "num_input_tokens_seen": 686752, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_loss": 6.357021808624268, | |
| "eval_runtime": 2.6104, | |
| "eval_samples_per_second": 91.173, | |
| "eval_steps_per_second": 22.985, | |
| "num_input_tokens_seen": 687328, | |
| "step": 2412 | |
| }, | |
| { | |
| "epoch": 4.505597014925373, | |
| "grad_norm": 0.9362825751304626, | |
| "learning_rate": 3.351989796175628e-05, | |
| "loss": 6.05, | |
| "num_input_tokens_seen": 688096, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 4.514925373134329, | |
| "grad_norm": 0.739857017993927, | |
| "learning_rate": 3.3443320786930275e-05, | |
| "loss": 6.0463, | |
| "num_input_tokens_seen": 689664, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 4.524253731343284, | |
| "grad_norm": 1.0322692394256592, | |
| "learning_rate": 3.3366654088396326e-05, | |
| "loss": 5.9086, | |
| "num_input_tokens_seen": 690912, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 4.5335820895522385, | |
| "grad_norm": 1.1899574995040894, | |
| "learning_rate": 3.328989867904396e-05, | |
| "loss": 5.9177, | |
| "num_input_tokens_seen": 692320, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 4.542910447761194, | |
| "grad_norm": 1.1681069135665894, | |
| "learning_rate": 3.3213055372703305e-05, | |
| "loss": 5.967, | |
| "num_input_tokens_seen": 693568, | |
| "step": 2435 | |
| }, | |
| { | |
| "epoch": 4.552238805970149, | |
| "grad_norm": 1.2067676782608032, | |
| "learning_rate": 3.313612498413646e-05, | |
| "loss": 6.7199, | |
| "num_input_tokens_seen": 695168, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 4.561567164179104, | |
| "grad_norm": 1.3214055299758911, | |
| "learning_rate": 3.305910832902884e-05, | |
| "loss": 5.6648, | |
| "num_input_tokens_seen": 696384, | |
| "step": 2445 | |
| }, | |
| { | |
| "epoch": 4.57089552238806, | |
| "grad_norm": 1.1338502168655396, | |
| "learning_rate": 3.298200622398054e-05, | |
| "loss": 6.0214, | |
| "num_input_tokens_seen": 697792, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 4.580223880597015, | |
| "grad_norm": 0.6251217722892761, | |
| "learning_rate": 3.290481948649767e-05, | |
| "loss": 6.3854, | |
| "num_input_tokens_seen": 699232, | |
| "step": 2455 | |
| }, | |
| { | |
| "epoch": 4.58955223880597, | |
| "grad_norm": 0.813247561454773, | |
| "learning_rate": 3.282754893498369e-05, | |
| "loss": 5.8858, | |
| "num_input_tokens_seen": 700704, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 4.598880597014926, | |
| "grad_norm": 1.029220461845398, | |
| "learning_rate": 3.275019538873071e-05, | |
| "loss": 6.2053, | |
| "num_input_tokens_seen": 702016, | |
| "step": 2465 | |
| }, | |
| { | |
| "epoch": 4.608208955223881, | |
| "grad_norm": 0.759621262550354, | |
| "learning_rate": 3.267275966791088e-05, | |
| "loss": 6.2383, | |
| "num_input_tokens_seen": 703456, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 4.617537313432836, | |
| "grad_norm": 0.9053934216499329, | |
| "learning_rate": 3.259524259356759e-05, | |
| "loss": 6.4459, | |
| "num_input_tokens_seen": 704896, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 4.6268656716417915, | |
| "grad_norm": 1.1944023370742798, | |
| "learning_rate": 3.251764498760683e-05, | |
| "loss": 6.5718, | |
| "num_input_tokens_seen": 706272, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 4.6361940298507465, | |
| "grad_norm": 0.8400816321372986, | |
| "learning_rate": 3.243996767278846e-05, | |
| "loss": 6.808, | |
| "num_input_tokens_seen": 707744, | |
| "step": 2485 | |
| }, | |
| { | |
| "epoch": 4.645522388059701, | |
| "grad_norm": 0.7267037630081177, | |
| "learning_rate": 3.2362211472717484e-05, | |
| "loss": 6.5115, | |
| "num_input_tokens_seen": 709120, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 4.654850746268656, | |
| "grad_norm": 0.8602089881896973, | |
| "learning_rate": 3.228437721183531e-05, | |
| "loss": 5.607, | |
| "num_input_tokens_seen": 710592, | |
| "step": 2495 | |
| }, | |
| { | |
| "epoch": 4.664179104477612, | |
| "grad_norm": 1.8790227174758911, | |
| "learning_rate": 3.220646571541105e-05, | |
| "loss": 6.2247, | |
| "num_input_tokens_seen": 712000, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.673507462686567, | |
| "grad_norm": 0.8083376884460449, | |
| "learning_rate": 3.2128477809532684e-05, | |
| "loss": 6.4959, | |
| "num_input_tokens_seen": 713408, | |
| "step": 2505 | |
| }, | |
| { | |
| "epoch": 4.682835820895522, | |
| "grad_norm": 1.41470205783844, | |
| "learning_rate": 3.2050414321098385e-05, | |
| "loss": 6.466, | |
| "num_input_tokens_seen": 714688, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 4.692164179104478, | |
| "grad_norm": 1.3266335725784302, | |
| "learning_rate": 3.197227607780774e-05, | |
| "loss": 6.6022, | |
| "num_input_tokens_seen": 716128, | |
| "step": 2515 | |
| }, | |
| { | |
| "epoch": 4.701492537313433, | |
| "grad_norm": 1.03994619846344, | |
| "learning_rate": 3.1894063908152916e-05, | |
| "loss": 6.836, | |
| "num_input_tokens_seen": 717632, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 4.710820895522388, | |
| "grad_norm": 0.8564523458480835, | |
| "learning_rate": 3.181577864140992e-05, | |
| "loss": 5.9339, | |
| "num_input_tokens_seen": 719264, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 4.720149253731344, | |
| "grad_norm": 1.0640394687652588, | |
| "learning_rate": 3.173742110762984e-05, | |
| "loss": 5.8009, | |
| "num_input_tokens_seen": 720832, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 4.729477611940299, | |
| "grad_norm": 1.125375509262085, | |
| "learning_rate": 3.165899213762995e-05, | |
| "loss": 6.2572, | |
| "num_input_tokens_seen": 722240, | |
| "step": 2535 | |
| }, | |
| { | |
| "epoch": 4.7388059701492535, | |
| "grad_norm": 0.8316742181777954, | |
| "learning_rate": 3.158049256298499e-05, | |
| "loss": 6.5728, | |
| "num_input_tokens_seen": 723552, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 4.7481343283582085, | |
| "grad_norm": 1.1118327379226685, | |
| "learning_rate": 3.15019232160183e-05, | |
| "loss": 6.0845, | |
| "num_input_tokens_seen": 724864, | |
| "step": 2545 | |
| }, | |
| { | |
| "epoch": 4.757462686567164, | |
| "grad_norm": 0.9741475582122803, | |
| "learning_rate": 3.142328492979301e-05, | |
| "loss": 5.9881, | |
| "num_input_tokens_seen": 726176, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 4.766791044776119, | |
| "grad_norm": 1.0174107551574707, | |
| "learning_rate": 3.134457853810322e-05, | |
| "loss": 6.3026, | |
| "num_input_tokens_seen": 727680, | |
| "step": 2555 | |
| }, | |
| { | |
| "epoch": 4.776119402985074, | |
| "grad_norm": 1.0384331941604614, | |
| "learning_rate": 3.126580487546513e-05, | |
| "loss": 6.149, | |
| "num_input_tokens_seen": 729024, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 4.78544776119403, | |
| "grad_norm": 1.1076503992080688, | |
| "learning_rate": 3.1186964777108215e-05, | |
| "loss": 6.2203, | |
| "num_input_tokens_seen": 730304, | |
| "step": 2565 | |
| }, | |
| { | |
| "epoch": 4.794776119402985, | |
| "grad_norm": 1.3865909576416016, | |
| "learning_rate": 3.110805907896637e-05, | |
| "loss": 6.4271, | |
| "num_input_tokens_seen": 731776, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 4.80410447761194, | |
| "grad_norm": 0.8223596811294556, | |
| "learning_rate": 3.1029088617669e-05, | |
| "loss": 5.6447, | |
| "num_input_tokens_seen": 733152, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 4.813432835820896, | |
| "grad_norm": 1.155343770980835, | |
| "learning_rate": 3.0950054230532235e-05, | |
| "loss": 6.4536, | |
| "num_input_tokens_seen": 734432, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 4.822761194029851, | |
| "grad_norm": 0.7214459180831909, | |
| "learning_rate": 3.0870956755549976e-05, | |
| "loss": 6.2467, | |
| "num_input_tokens_seen": 735808, | |
| "step": 2585 | |
| }, | |
| { | |
| "epoch": 4.832089552238806, | |
| "grad_norm": 0.909172773361206, | |
| "learning_rate": 3.079179703138505e-05, | |
| "loss": 6.329, | |
| "num_input_tokens_seen": 737088, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 4.8414179104477615, | |
| "grad_norm": 1.0502411127090454, | |
| "learning_rate": 3.0712575897360304e-05, | |
| "loss": 6.1552, | |
| "num_input_tokens_seen": 738528, | |
| "step": 2595 | |
| }, | |
| { | |
| "epoch": 4.850746268656716, | |
| "grad_norm": 0.9423935413360596, | |
| "learning_rate": 3.0633294193449695e-05, | |
| "loss": 6.5962, | |
| "num_input_tokens_seen": 740128, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.860074626865671, | |
| "grad_norm": 1.2888314723968506, | |
| "learning_rate": 3.0553952760269426e-05, | |
| "loss": 5.7478, | |
| "num_input_tokens_seen": 741760, | |
| "step": 2605 | |
| }, | |
| { | |
| "epoch": 4.869402985074627, | |
| "grad_norm": 1.1500736474990845, | |
| "learning_rate": 3.0474552439068978e-05, | |
| "loss": 6.2444, | |
| "num_input_tokens_seen": 743136, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 4.878731343283582, | |
| "grad_norm": 0.6845166683197021, | |
| "learning_rate": 3.039509407172222e-05, | |
| "loss": 5.913, | |
| "num_input_tokens_seen": 744384, | |
| "step": 2615 | |
| }, | |
| { | |
| "epoch": 4.888059701492537, | |
| "grad_norm": 0.81601881980896, | |
| "learning_rate": 3.0315578500718476e-05, | |
| "loss": 6.4635, | |
| "num_input_tokens_seen": 745888, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 4.897388059701493, | |
| "grad_norm": 0.9223809838294983, | |
| "learning_rate": 3.0236006569153617e-05, | |
| "loss": 6.0929, | |
| "num_input_tokens_seen": 747360, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 4.906716417910448, | |
| "grad_norm": 1.111869215965271, | |
| "learning_rate": 3.0156379120721068e-05, | |
| "loss": 6.0556, | |
| "num_input_tokens_seen": 748576, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 4.916044776119403, | |
| "grad_norm": 0.8643698692321777, | |
| "learning_rate": 3.0076696999702913e-05, | |
| "loss": 5.938, | |
| "num_input_tokens_seen": 749792, | |
| "step": 2635 | |
| }, | |
| { | |
| "epoch": 4.925373134328359, | |
| "grad_norm": 0.9772742390632629, | |
| "learning_rate": 2.9996961050960932e-05, | |
| "loss": 6.3418, | |
| "num_input_tokens_seen": 751200, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 4.934701492537314, | |
| "grad_norm": 0.933300793170929, | |
| "learning_rate": 2.9917172119927606e-05, | |
| "loss": 5.9282, | |
| "num_input_tokens_seen": 752608, | |
| "step": 2645 | |
| }, | |
| { | |
| "epoch": 4.9440298507462686, | |
| "grad_norm": 0.9566914439201355, | |
| "learning_rate": 2.9837331052597224e-05, | |
| "loss": 6.3392, | |
| "num_input_tokens_seen": 754144, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 4.9533582089552235, | |
| "grad_norm": 0.7642708420753479, | |
| "learning_rate": 2.9757438695516816e-05, | |
| "loss": 6.6677, | |
| "num_input_tokens_seen": 755584, | |
| "step": 2655 | |
| }, | |
| { | |
| "epoch": 4.962686567164179, | |
| "grad_norm": 0.9811196327209473, | |
| "learning_rate": 2.9677495895777286e-05, | |
| "loss": 5.873, | |
| "num_input_tokens_seen": 757152, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 4.972014925373134, | |
| "grad_norm": 1.0901542901992798, | |
| "learning_rate": 2.9597503501004343e-05, | |
| "loss": 6.7788, | |
| "num_input_tokens_seen": 758528, | |
| "step": 2665 | |
| }, | |
| { | |
| "epoch": 4.981343283582089, | |
| "grad_norm": 0.857291042804718, | |
| "learning_rate": 2.9517462359349553e-05, | |
| "loss": 6.1211, | |
| "num_input_tokens_seen": 759904, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 4.990671641791045, | |
| "grad_norm": 1.4602748155593872, | |
| "learning_rate": 2.943737331948136e-05, | |
| "loss": 6.3025, | |
| "num_input_tokens_seen": 761344, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 2.9824469089508057, | |
| "learning_rate": 2.9357237230576045e-05, | |
| "loss": 6.3133, | |
| "num_input_tokens_seen": 762440, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 6.3077392578125, | |
| "eval_runtime": 2.5799, | |
| "eval_samples_per_second": 92.252, | |
| "eval_steps_per_second": 23.257, | |
| "num_input_tokens_seen": 762440, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 5.009328358208955, | |
| "grad_norm": 0.9206458330154419, | |
| "learning_rate": 2.927705494230875e-05, | |
| "loss": 6.1517, | |
| "num_input_tokens_seen": 763656, | |
| "step": 2685 | |
| }, | |
| { | |
| "epoch": 5.018656716417911, | |
| "grad_norm": 1.3123348951339722, | |
| "learning_rate": 2.9196827304844483e-05, | |
| "loss": 6.0177, | |
| "num_input_tokens_seen": 764968, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 5.027985074626866, | |
| "grad_norm": 0.9847822785377502, | |
| "learning_rate": 2.911655516882905e-05, | |
| "loss": 6.0259, | |
| "num_input_tokens_seen": 766440, | |
| "step": 2695 | |
| }, | |
| { | |
| "epoch": 5.037313432835821, | |
| "grad_norm": 0.9711946845054626, | |
| "learning_rate": 2.9036239385380098e-05, | |
| "loss": 5.963, | |
| "num_input_tokens_seen": 767784, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 5.0466417910447765, | |
| "grad_norm": 1.0825556516647339, | |
| "learning_rate": 2.8955880806078068e-05, | |
| "loss": 5.9648, | |
| "num_input_tokens_seen": 769128, | |
| "step": 2705 | |
| }, | |
| { | |
| "epoch": 5.0559701492537314, | |
| "grad_norm": 0.8246394395828247, | |
| "learning_rate": 2.8875480282957133e-05, | |
| "loss": 5.6471, | |
| "num_input_tokens_seen": 770536, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 5.065298507462686, | |
| "grad_norm": 1.33425772190094, | |
| "learning_rate": 2.8795038668496222e-05, | |
| "loss": 6.2019, | |
| "num_input_tokens_seen": 772040, | |
| "step": 2715 | |
| }, | |
| { | |
| "epoch": 5.074626865671641, | |
| "grad_norm": 1.1973999738693237, | |
| "learning_rate": 2.8714556815609926e-05, | |
| "loss": 6.6323, | |
| "num_input_tokens_seen": 773480, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 5.083955223880597, | |
| "grad_norm": 0.9225637912750244, | |
| "learning_rate": 2.8634035577639505e-05, | |
| "loss": 5.851, | |
| "num_input_tokens_seen": 774888, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 5.093283582089552, | |
| "grad_norm": 0.9178676009178162, | |
| "learning_rate": 2.8553475808343798e-05, | |
| "loss": 5.7735, | |
| "num_input_tokens_seen": 776296, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 5.102611940298507, | |
| "grad_norm": 0.7278265953063965, | |
| "learning_rate": 2.847287836189019e-05, | |
| "loss": 5.9805, | |
| "num_input_tokens_seen": 777928, | |
| "step": 2735 | |
| }, | |
| { | |
| "epoch": 5.111940298507463, | |
| "grad_norm": 0.7470238208770752, | |
| "learning_rate": 2.839224409284556e-05, | |
| "loss": 6.4475, | |
| "num_input_tokens_seen": 779304, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 5.121268656716418, | |
| "grad_norm": 1.0595344305038452, | |
| "learning_rate": 2.83115738561672e-05, | |
| "loss": 6.3653, | |
| "num_input_tokens_seen": 780456, | |
| "step": 2745 | |
| }, | |
| { | |
| "epoch": 5.130597014925373, | |
| "grad_norm": 1.1577999591827393, | |
| "learning_rate": 2.8230868507193785e-05, | |
| "loss": 6.3319, | |
| "num_input_tokens_seen": 781800, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 5.139925373134329, | |
| "grad_norm": 0.9985320568084717, | |
| "learning_rate": 2.8150128901636262e-05, | |
| "loss": 5.9545, | |
| "num_input_tokens_seen": 783176, | |
| "step": 2755 | |
| }, | |
| { | |
| "epoch": 5.149253731343284, | |
| "grad_norm": 0.9474596977233887, | |
| "learning_rate": 2.8069355895568805e-05, | |
| "loss": 6.5791, | |
| "num_input_tokens_seen": 784488, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 5.1585820895522385, | |
| "grad_norm": 0.9749534130096436, | |
| "learning_rate": 2.7988550345419733e-05, | |
| "loss": 6.686, | |
| "num_input_tokens_seen": 785928, | |
| "step": 2765 | |
| }, | |
| { | |
| "epoch": 5.167910447761194, | |
| "grad_norm": 1.2434371709823608, | |
| "learning_rate": 2.790771310796243e-05, | |
| "loss": 6.7563, | |
| "num_input_tokens_seen": 787368, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 5.177238805970149, | |
| "grad_norm": 1.0295319557189941, | |
| "learning_rate": 2.7826845040306238e-05, | |
| "loss": 6.4211, | |
| "num_input_tokens_seen": 788744, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 5.186567164179104, | |
| "grad_norm": 0.8541420102119446, | |
| "learning_rate": 2.7745946999887406e-05, | |
| "loss": 6.3064, | |
| "num_input_tokens_seen": 790216, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 5.19589552238806, | |
| "grad_norm": 0.8907437920570374, | |
| "learning_rate": 2.766501984445999e-05, | |
| "loss": 6.3934, | |
| "num_input_tokens_seen": 791656, | |
| "step": 2785 | |
| }, | |
| { | |
| "epoch": 5.205223880597015, | |
| "grad_norm": 1.6039609909057617, | |
| "learning_rate": 2.7584064432086716e-05, | |
| "loss": 6.2562, | |
| "num_input_tokens_seen": 793288, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 5.21455223880597, | |
| "grad_norm": 0.9367539882659912, | |
| "learning_rate": 2.750308162112995e-05, | |
| "loss": 6.7897, | |
| "num_input_tokens_seen": 794984, | |
| "step": 2795 | |
| }, | |
| { | |
| "epoch": 5.223880597014926, | |
| "grad_norm": 1.0441266298294067, | |
| "learning_rate": 2.7422072270242548e-05, | |
| "loss": 5.7294, | |
| "num_input_tokens_seen": 796328, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 5.233208955223881, | |
| "grad_norm": 0.9566605091094971, | |
| "learning_rate": 2.7341037238358774e-05, | |
| "loss": 6.2595, | |
| "num_input_tokens_seen": 797704, | |
| "step": 2805 | |
| }, | |
| { | |
| "epoch": 5.242537313432836, | |
| "grad_norm": 1.0519027709960938, | |
| "learning_rate": 2.7259977384685163e-05, | |
| "loss": 5.8314, | |
| "num_input_tokens_seen": 798984, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 5.251865671641791, | |
| "grad_norm": 0.8249859809875488, | |
| "learning_rate": 2.717889356869146e-05, | |
| "loss": 6.2151, | |
| "num_input_tokens_seen": 800392, | |
| "step": 2815 | |
| }, | |
| { | |
| "epoch": 5.2611940298507465, | |
| "grad_norm": 1.0564582347869873, | |
| "learning_rate": 2.7097786650101458e-05, | |
| "loss": 6.1419, | |
| "num_input_tokens_seen": 801832, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 5.270522388059701, | |
| "grad_norm": 0.9412636756896973, | |
| "learning_rate": 2.7016657488883928e-05, | |
| "loss": 5.7732, | |
| "num_input_tokens_seen": 803272, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 5.279850746268656, | |
| "grad_norm": 1.0432401895523071, | |
| "learning_rate": 2.693550694524346e-05, | |
| "loss": 6.5791, | |
| "num_input_tokens_seen": 804872, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 5.289179104477612, | |
| "grad_norm": 0.9447091221809387, | |
| "learning_rate": 2.685433587961136e-05, | |
| "loss": 6.0309, | |
| "num_input_tokens_seen": 806312, | |
| "step": 2835 | |
| }, | |
| { | |
| "epoch": 5.298507462686567, | |
| "grad_norm": 0.9110550284385681, | |
| "learning_rate": 2.6773145152636536e-05, | |
| "loss": 6.2054, | |
| "num_input_tokens_seen": 807944, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 5.307835820895522, | |
| "grad_norm": 1.236222743988037, | |
| "learning_rate": 2.6691935625176357e-05, | |
| "loss": 6.9317, | |
| "num_input_tokens_seen": 809320, | |
| "step": 2845 | |
| }, | |
| { | |
| "epoch": 5.317164179104478, | |
| "grad_norm": 0.905897855758667, | |
| "learning_rate": 2.6610708158287535e-05, | |
| "loss": 6.0374, | |
| "num_input_tokens_seen": 810952, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 5.326492537313433, | |
| "grad_norm": 0.9211243987083435, | |
| "learning_rate": 2.6529463613216986e-05, | |
| "loss": 6.5508, | |
| "num_input_tokens_seen": 812264, | |
| "step": 2855 | |
| }, | |
| { | |
| "epoch": 5.335820895522388, | |
| "grad_norm": 0.9618635177612305, | |
| "learning_rate": 2.644820285139271e-05, | |
| "loss": 6.2744, | |
| "num_input_tokens_seen": 813704, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 5.345149253731344, | |
| "grad_norm": 1.0738120079040527, | |
| "learning_rate": 2.636692673441465e-05, | |
| "loss": 6.2007, | |
| "num_input_tokens_seen": 815272, | |
| "step": 2865 | |
| }, | |
| { | |
| "epoch": 5.354477611940299, | |
| "grad_norm": 1.4284543991088867, | |
| "learning_rate": 2.628563612404556e-05, | |
| "loss": 6.3687, | |
| "num_input_tokens_seen": 816904, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 5.3638059701492535, | |
| "grad_norm": 1.0768283605575562, | |
| "learning_rate": 2.6204331882201864e-05, | |
| "loss": 6.2943, | |
| "num_input_tokens_seen": 818440, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 5.373134328358209, | |
| "grad_norm": 1.4978874921798706, | |
| "learning_rate": 2.6123014870944517e-05, | |
| "loss": 6.4227, | |
| "num_input_tokens_seen": 819752, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 5.382462686567164, | |
| "grad_norm": 1.1821980476379395, | |
| "learning_rate": 2.6041685952469875e-05, | |
| "loss": 6.314, | |
| "num_input_tokens_seen": 820936, | |
| "step": 2885 | |
| }, | |
| { | |
| "epoch": 5.391791044776119, | |
| "grad_norm": 0.9584994316101074, | |
| "learning_rate": 2.596034598910053e-05, | |
| "loss": 6.1103, | |
| "num_input_tokens_seen": 822408, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 5.401119402985074, | |
| "grad_norm": 0.8577700257301331, | |
| "learning_rate": 2.5878995843276204e-05, | |
| "loss": 5.8164, | |
| "num_input_tokens_seen": 823784, | |
| "step": 2895 | |
| }, | |
| { | |
| "epoch": 5.41044776119403, | |
| "grad_norm": 1.4151724576950073, | |
| "learning_rate": 2.5797636377544564e-05, | |
| "loss": 5.6906, | |
| "num_input_tokens_seen": 825064, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 5.419776119402985, | |
| "grad_norm": 1.025488018989563, | |
| "learning_rate": 2.5716268454552095e-05, | |
| "loss": 6.471, | |
| "num_input_tokens_seen": 826600, | |
| "step": 2905 | |
| }, | |
| { | |
| "epoch": 5.42910447761194, | |
| "grad_norm": 0.9173970222473145, | |
| "learning_rate": 2.563489293703496e-05, | |
| "loss": 6.076, | |
| "num_input_tokens_seen": 828104, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 5.438432835820896, | |
| "grad_norm": 0.8691163063049316, | |
| "learning_rate": 2.5553510687809855e-05, | |
| "loss": 5.8456, | |
| "num_input_tokens_seen": 829640, | |
| "step": 2915 | |
| }, | |
| { | |
| "epoch": 5.447761194029851, | |
| "grad_norm": 0.8215888738632202, | |
| "learning_rate": 2.547212256976484e-05, | |
| "loss": 6.5653, | |
| "num_input_tokens_seen": 831112, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 5.457089552238806, | |
| "grad_norm": 1.082973837852478, | |
| "learning_rate": 2.5390729445850198e-05, | |
| "loss": 6.372, | |
| "num_input_tokens_seen": 832744, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 5.4664179104477615, | |
| "grad_norm": 1.278608798980713, | |
| "learning_rate": 2.53093321790693e-05, | |
| "loss": 6.6638, | |
| "num_input_tokens_seen": 834248, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 5.475746268656716, | |
| "grad_norm": 0.8474575281143188, | |
| "learning_rate": 2.5227931632469437e-05, | |
| "loss": 6.0771, | |
| "num_input_tokens_seen": 835752, | |
| "step": 2935 | |
| }, | |
| { | |
| "epoch": 5.485074626865671, | |
| "grad_norm": 1.7495900392532349, | |
| "learning_rate": 2.5146528669132664e-05, | |
| "loss": 6.0065, | |
| "num_input_tokens_seen": 837064, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 5.494402985074627, | |
| "grad_norm": 1.3310050964355469, | |
| "learning_rate": 2.506512415216669e-05, | |
| "loss": 5.5232, | |
| "num_input_tokens_seen": 838440, | |
| "step": 2945 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "eval_loss": 6.261446952819824, | |
| "eval_runtime": 2.5744, | |
| "eval_samples_per_second": 92.449, | |
| "eval_steps_per_second": 23.307, | |
| "num_input_tokens_seen": 839656, | |
| "step": 2948 | |
| }, | |
| { | |
| "epoch": 5.503731343283582, | |
| "grad_norm": 0.8216014504432678, | |
| "learning_rate": 2.4983718944695672e-05, | |
| "loss": 6.3547, | |
| "num_input_tokens_seen": 840232, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 5.513059701492537, | |
| "grad_norm": 0.9752035737037659, | |
| "learning_rate": 2.49023139098511e-05, | |
| "loss": 6.0888, | |
| "num_input_tokens_seen": 841576, | |
| "step": 2955 | |
| }, | |
| { | |
| "epoch": 5.522388059701493, | |
| "grad_norm": 0.9398236274719238, | |
| "learning_rate": 2.4820909910762628e-05, | |
| "loss": 6.4842, | |
| "num_input_tokens_seen": 842984, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 5.531716417910448, | |
| "grad_norm": 0.8302134871482849, | |
| "learning_rate": 2.473950781054893e-05, | |
| "loss": 6.1522, | |
| "num_input_tokens_seen": 844232, | |
| "step": 2965 | |
| }, | |
| { | |
| "epoch": 5.541044776119403, | |
| "grad_norm": 1.1869540214538574, | |
| "learning_rate": 2.4658108472308545e-05, | |
| "loss": 6.2037, | |
| "num_input_tokens_seen": 845576, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 5.550373134328359, | |
| "grad_norm": 0.7356037497520447, | |
| "learning_rate": 2.4576712759110728e-05, | |
| "loss": 5.5291, | |
| "num_input_tokens_seen": 846984, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 5.559701492537314, | |
| "grad_norm": 0.9556671380996704, | |
| "learning_rate": 2.4495321533986297e-05, | |
| "loss": 6.5366, | |
| "num_input_tokens_seen": 848328, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 5.5690298507462686, | |
| "grad_norm": 0.7378389239311218, | |
| "learning_rate": 2.441393565991849e-05, | |
| "loss": 5.6366, | |
| "num_input_tokens_seen": 849800, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 5.5783582089552235, | |
| "grad_norm": 0.8746010065078735, | |
| "learning_rate": 2.43325559998338e-05, | |
| "loss": 6.0048, | |
| "num_input_tokens_seen": 851176, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 5.587686567164179, | |
| "grad_norm": 0.8357123732566833, | |
| "learning_rate": 2.425118341659284e-05, | |
| "loss": 6.3708, | |
| "num_input_tokens_seen": 852776, | |
| "step": 2995 | |
| }, | |
| { | |
| "epoch": 5.597014925373134, | |
| "grad_norm": 1.832527995109558, | |
| "learning_rate": 2.416981877298118e-05, | |
| "loss": 6.4106, | |
| "num_input_tokens_seen": 854184, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.606343283582089, | |
| "grad_norm": 0.8620015978813171, | |
| "learning_rate": 2.4088462931700214e-05, | |
| "loss": 6.1106, | |
| "num_input_tokens_seen": 855496, | |
| "step": 3005 | |
| }, | |
| { | |
| "epoch": 5.615671641791045, | |
| "grad_norm": 0.9503886103630066, | |
| "learning_rate": 2.4007116755357995e-05, | |
| "loss": 6.4924, | |
| "num_input_tokens_seen": 856840, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 5.625, | |
| "grad_norm": 0.9680227041244507, | |
| "learning_rate": 2.392578110646012e-05, | |
| "loss": 6.0096, | |
| "num_input_tokens_seen": 858184, | |
| "step": 3015 | |
| }, | |
| { | |
| "epoch": 5.634328358208955, | |
| "grad_norm": 1.2329450845718384, | |
| "learning_rate": 2.384445684740055e-05, | |
| "loss": 6.6961, | |
| "num_input_tokens_seen": 859624, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 5.643656716417911, | |
| "grad_norm": 0.8868666887283325, | |
| "learning_rate": 2.376314484045248e-05, | |
| "loss": 6.0794, | |
| "num_input_tokens_seen": 860968, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 5.652985074626866, | |
| "grad_norm": 1.3599214553833008, | |
| "learning_rate": 2.3681845947759206e-05, | |
| "loss": 6.0095, | |
| "num_input_tokens_seen": 862472, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 5.662313432835821, | |
| "grad_norm": 1.0626275539398193, | |
| "learning_rate": 2.3600561031324958e-05, | |
| "loss": 6.6307, | |
| "num_input_tokens_seen": 863880, | |
| "step": 3035 | |
| }, | |
| { | |
| "epoch": 5.6716417910447765, | |
| "grad_norm": 1.0481562614440918, | |
| "learning_rate": 2.3519290953005784e-05, | |
| "loss": 6.6959, | |
| "num_input_tokens_seen": 865288, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 5.6809701492537314, | |
| "grad_norm": 0.7444071173667908, | |
| "learning_rate": 2.3438036574500432e-05, | |
| "loss": 6.4052, | |
| "num_input_tokens_seen": 866824, | |
| "step": 3045 | |
| }, | |
| { | |
| "epoch": 5.690298507462686, | |
| "grad_norm": 0.9876862168312073, | |
| "learning_rate": 2.3356798757341155e-05, | |
| "loss": 6.1437, | |
| "num_input_tokens_seen": 868104, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 5.699626865671641, | |
| "grad_norm": 0.8382055759429932, | |
| "learning_rate": 2.327557836288461e-05, | |
| "loss": 6.6104, | |
| "num_input_tokens_seen": 869512, | |
| "step": 3055 | |
| }, | |
| { | |
| "epoch": 5.708955223880597, | |
| "grad_norm": 1.4601103067398071, | |
| "learning_rate": 2.3194376252302723e-05, | |
| "loss": 6.2532, | |
| "num_input_tokens_seen": 871048, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 5.718283582089552, | |
| "grad_norm": 0.9206922054290771, | |
| "learning_rate": 2.311319328657358e-05, | |
| "loss": 6.4148, | |
| "num_input_tokens_seen": 872424, | |
| "step": 3065 | |
| }, | |
| { | |
| "epoch": 5.727611940298507, | |
| "grad_norm": 0.9345753788948059, | |
| "learning_rate": 2.3032030326472235e-05, | |
| "loss": 6.8183, | |
| "num_input_tokens_seen": 873992, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 5.736940298507463, | |
| "grad_norm": 0.7898691296577454, | |
| "learning_rate": 2.2950888232561672e-05, | |
| "loss": 6.1796, | |
| "num_input_tokens_seen": 875368, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 5.746268656716418, | |
| "grad_norm": 0.8319314122200012, | |
| "learning_rate": 2.2869767865183612e-05, | |
| "loss": 6.403, | |
| "num_input_tokens_seen": 876808, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 5.755597014925373, | |
| "grad_norm": 0.9827578663825989, | |
| "learning_rate": 2.2788670084449394e-05, | |
| "loss": 6.5861, | |
| "num_input_tokens_seen": 878152, | |
| "step": 3085 | |
| }, | |
| { | |
| "epoch": 5.764925373134329, | |
| "grad_norm": 0.8735271692276001, | |
| "learning_rate": 2.2707595750230894e-05, | |
| "loss": 6.1444, | |
| "num_input_tokens_seen": 879496, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 5.774253731343284, | |
| "grad_norm": 1.0752406120300293, | |
| "learning_rate": 2.2626545722151384e-05, | |
| "loss": 5.9159, | |
| "num_input_tokens_seen": 880904, | |
| "step": 3095 | |
| }, | |
| { | |
| "epoch": 5.7835820895522385, | |
| "grad_norm": 0.8324728012084961, | |
| "learning_rate": 2.254552085957641e-05, | |
| "loss": 6.0135, | |
| "num_input_tokens_seen": 882152, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 5.792910447761194, | |
| "grad_norm": 0.7936992049217224, | |
| "learning_rate": 2.246452202160471e-05, | |
| "loss": 6.0739, | |
| "num_input_tokens_seen": 883400, | |
| "step": 3105 | |
| }, | |
| { | |
| "epoch": 5.802238805970149, | |
| "grad_norm": 1.1770528554916382, | |
| "learning_rate": 2.2383550067059063e-05, | |
| "loss": 5.5673, | |
| "num_input_tokens_seen": 884968, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 5.811567164179104, | |
| "grad_norm": 1.0411667823791504, | |
| "learning_rate": 2.2302605854477228e-05, | |
| "loss": 5.7823, | |
| "num_input_tokens_seen": 886312, | |
| "step": 3115 | |
| }, | |
| { | |
| "epoch": 5.82089552238806, | |
| "grad_norm": 0.8854592442512512, | |
| "learning_rate": 2.22216902421028e-05, | |
| "loss": 5.9224, | |
| "num_input_tokens_seen": 887752, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 5.830223880597015, | |
| "grad_norm": 1.2184094190597534, | |
| "learning_rate": 2.2140804087876132e-05, | |
| "loss": 6.0152, | |
| "num_input_tokens_seen": 889096, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 5.83955223880597, | |
| "grad_norm": 0.7486042976379395, | |
| "learning_rate": 2.2059948249425243e-05, | |
| "loss": 5.6847, | |
| "num_input_tokens_seen": 890408, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 5.848880597014926, | |
| "grad_norm": 1.8652020692825317, | |
| "learning_rate": 2.197912358405672e-05, | |
| "loss": 6.2443, | |
| "num_input_tokens_seen": 892072, | |
| "step": 3135 | |
| }, | |
| { | |
| "epoch": 5.858208955223881, | |
| "grad_norm": 1.3339096307754517, | |
| "learning_rate": 2.189833094874661e-05, | |
| "loss": 6.5642, | |
| "num_input_tokens_seen": 893608, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 5.867537313432836, | |
| "grad_norm": 1.1163021326065063, | |
| "learning_rate": 2.1817571200131358e-05, | |
| "loss": 6.7222, | |
| "num_input_tokens_seen": 894920, | |
| "step": 3145 | |
| }, | |
| { | |
| "epoch": 5.8768656716417915, | |
| "grad_norm": 0.9783477187156677, | |
| "learning_rate": 2.173684519449872e-05, | |
| "loss": 5.7076, | |
| "num_input_tokens_seen": 896328, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 5.8861940298507465, | |
| "grad_norm": 0.866126298904419, | |
| "learning_rate": 2.1656153787778645e-05, | |
| "loss": 5.7822, | |
| "num_input_tokens_seen": 897896, | |
| "step": 3155 | |
| }, | |
| { | |
| "epoch": 5.895522388059701, | |
| "grad_norm": 1.021458387374878, | |
| "learning_rate": 2.157549783553429e-05, | |
| "loss": 5.8496, | |
| "num_input_tokens_seen": 899272, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 5.904850746268656, | |
| "grad_norm": 1.3909484148025513, | |
| "learning_rate": 2.1494878192952855e-05, | |
| "loss": 6.2368, | |
| "num_input_tokens_seen": 900584, | |
| "step": 3165 | |
| }, | |
| { | |
| "epoch": 5.914179104477612, | |
| "grad_norm": 1.4661751985549927, | |
| "learning_rate": 2.141429571483655e-05, | |
| "loss": 6.3732, | |
| "num_input_tokens_seen": 901992, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 5.923507462686567, | |
| "grad_norm": 0.9526384472846985, | |
| "learning_rate": 2.1333751255593552e-05, | |
| "loss": 5.8465, | |
| "num_input_tokens_seen": 903304, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 5.932835820895522, | |
| "grad_norm": 1.0814648866653442, | |
| "learning_rate": 2.1253245669228905e-05, | |
| "loss": 6.3578, | |
| "num_input_tokens_seen": 904712, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 5.942164179104478, | |
| "grad_norm": 1.4046601057052612, | |
| "learning_rate": 2.1172779809335496e-05, | |
| "loss": 5.9194, | |
| "num_input_tokens_seen": 906120, | |
| "step": 3185 | |
| }, | |
| { | |
| "epoch": 5.951492537313433, | |
| "grad_norm": 1.1524070501327515, | |
| "learning_rate": 2.109235452908502e-05, | |
| "loss": 5.8607, | |
| "num_input_tokens_seen": 907464, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 5.960820895522388, | |
| "grad_norm": 1.2335410118103027, | |
| "learning_rate": 2.101197068121888e-05, | |
| "loss": 6.1528, | |
| "num_input_tokens_seen": 909000, | |
| "step": 3195 | |
| }, | |
| { | |
| "epoch": 5.970149253731344, | |
| "grad_norm": 1.086081624031067, | |
| "learning_rate": 2.0931629118039185e-05, | |
| "loss": 5.9187, | |
| "num_input_tokens_seen": 910280, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.979477611940299, | |
| "grad_norm": 0.856933057308197, | |
| "learning_rate": 2.0851330691399713e-05, | |
| "loss": 6.3052, | |
| "num_input_tokens_seen": 911816, | |
| "step": 3205 | |
| }, | |
| { | |
| "epoch": 5.9888059701492535, | |
| "grad_norm": 1.1056967973709106, | |
| "learning_rate": 2.0771076252696846e-05, | |
| "loss": 6.3172, | |
| "num_input_tokens_seen": 913320, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 5.9981343283582085, | |
| "grad_norm": 1.0022315979003906, | |
| "learning_rate": 2.0690866652860584e-05, | |
| "loss": 5.3684, | |
| "num_input_tokens_seen": 914856, | |
| "step": 3215 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 6.22491979598999, | |
| "eval_runtime": 2.5607, | |
| "eval_samples_per_second": 92.944, | |
| "eval_steps_per_second": 23.431, | |
| "num_input_tokens_seen": 914920, | |
| "step": 3216 | |
| }, | |
| { | |
| "epoch": 6.007462686567164, | |
| "grad_norm": 0.7969170808792114, | |
| "learning_rate": 2.0610702742345517e-05, | |
| "loss": 5.8152, | |
| "num_input_tokens_seen": 916136, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 6.016791044776119, | |
| "grad_norm": 0.7614337205886841, | |
| "learning_rate": 2.053058537112177e-05, | |
| "loss": 5.1948, | |
| "num_input_tokens_seen": 917544, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 6.026119402985074, | |
| "grad_norm": 1.372154951095581, | |
| "learning_rate": 2.0450515388666022e-05, | |
| "loss": 6.3608, | |
| "num_input_tokens_seen": 919080, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 6.03544776119403, | |
| "grad_norm": 0.9270302653312683, | |
| "learning_rate": 2.0370493643952507e-05, | |
| "loss": 5.5958, | |
| "num_input_tokens_seen": 920840, | |
| "step": 3235 | |
| }, | |
| { | |
| "epoch": 6.044776119402985, | |
| "grad_norm": 0.8929545283317566, | |
| "learning_rate": 2.0290520985443985e-05, | |
| "loss": 6.1229, | |
| "num_input_tokens_seen": 922248, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 6.05410447761194, | |
| "grad_norm": 1.2521339654922485, | |
| "learning_rate": 2.0210598261082765e-05, | |
| "loss": 6.1346, | |
| "num_input_tokens_seen": 923912, | |
| "step": 3245 | |
| }, | |
| { | |
| "epoch": 6.063432835820896, | |
| "grad_norm": 1.2209833860397339, | |
| "learning_rate": 2.013072631828171e-05, | |
| "loss": 6.4707, | |
| "num_input_tokens_seen": 925352, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 6.072761194029851, | |
| "grad_norm": 1.4623795747756958, | |
| "learning_rate": 2.005090600391526e-05, | |
| "loss": 6.3204, | |
| "num_input_tokens_seen": 926856, | |
| "step": 3255 | |
| }, | |
| { | |
| "epoch": 6.082089552238806, | |
| "grad_norm": 0.8794171214103699, | |
| "learning_rate": 1.9971138164310422e-05, | |
| "loss": 6.3356, | |
| "num_input_tokens_seen": 928168, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 6.0914179104477615, | |
| "grad_norm": 1.1788820028305054, | |
| "learning_rate": 1.9891423645237834e-05, | |
| "loss": 6.8347, | |
| "num_input_tokens_seen": 929544, | |
| "step": 3265 | |
| }, | |
| { | |
| "epoch": 6.100746268656716, | |
| "grad_norm": 1.3938360214233398, | |
| "learning_rate": 1.9811763291902774e-05, | |
| "loss": 6.2436, | |
| "num_input_tokens_seen": 930792, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 6.110074626865671, | |
| "grad_norm": 0.8921086192131042, | |
| "learning_rate": 1.9732157948936204e-05, | |
| "loss": 5.7265, | |
| "num_input_tokens_seen": 932072, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 6.119402985074627, | |
| "grad_norm": 0.8545194864273071, | |
| "learning_rate": 1.9652608460385843e-05, | |
| "loss": 6.2326, | |
| "num_input_tokens_seen": 933384, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 6.128731343283582, | |
| "grad_norm": 1.0797127485275269, | |
| "learning_rate": 1.957311566970716e-05, | |
| "loss": 6.2225, | |
| "num_input_tokens_seen": 934888, | |
| "step": 3285 | |
| }, | |
| { | |
| "epoch": 6.138059701492537, | |
| "grad_norm": 1.106021761894226, | |
| "learning_rate": 1.949368041975447e-05, | |
| "loss": 6.1285, | |
| "num_input_tokens_seen": 936328, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 6.147388059701493, | |
| "grad_norm": 0.8624814748764038, | |
| "learning_rate": 1.9414303552771997e-05, | |
| "loss": 6.3063, | |
| "num_input_tokens_seen": 937864, | |
| "step": 3295 | |
| }, | |
| { | |
| "epoch": 6.156716417910448, | |
| "grad_norm": 1.471142053604126, | |
| "learning_rate": 1.9334985910384923e-05, | |
| "loss": 6.1906, | |
| "num_input_tokens_seen": 939464, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 6.166044776119403, | |
| "grad_norm": 1.175945520401001, | |
| "learning_rate": 1.9255728333590475e-05, | |
| "loss": 6.5144, | |
| "num_input_tokens_seen": 940968, | |
| "step": 3305 | |
| }, | |
| { | |
| "epoch": 6.175373134328359, | |
| "grad_norm": 0.952471137046814, | |
| "learning_rate": 1.9176531662749044e-05, | |
| "loss": 6.1677, | |
| "num_input_tokens_seen": 942152, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 6.184701492537314, | |
| "grad_norm": 1.2104790210723877, | |
| "learning_rate": 1.9097396737575206e-05, | |
| "loss": 6.4936, | |
| "num_input_tokens_seen": 943720, | |
| "step": 3315 | |
| }, | |
| { | |
| "epoch": 6.1940298507462686, | |
| "grad_norm": 1.4254320859909058, | |
| "learning_rate": 1.9018324397128866e-05, | |
| "loss": 6.0559, | |
| "num_input_tokens_seen": 944904, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 6.2033582089552235, | |
| "grad_norm": 0.7728973031044006, | |
| "learning_rate": 1.893931547980635e-05, | |
| "loss": 6.0315, | |
| "num_input_tokens_seen": 946344, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 6.212686567164179, | |
| "grad_norm": 0.9435825347900391, | |
| "learning_rate": 1.8860370823331513e-05, | |
| "loss": 6.5622, | |
| "num_input_tokens_seen": 947816, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 6.222014925373134, | |
| "grad_norm": 0.9837219715118408, | |
| "learning_rate": 1.878149126474685e-05, | |
| "loss": 5.7034, | |
| "num_input_tokens_seen": 949320, | |
| "step": 3335 | |
| }, | |
| { | |
| "epoch": 6.231343283582089, | |
| "grad_norm": 1.5329033136367798, | |
| "learning_rate": 1.870267764040465e-05, | |
| "loss": 6.2352, | |
| "num_input_tokens_seen": 950664, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 6.240671641791045, | |
| "grad_norm": 1.1350693702697754, | |
| "learning_rate": 1.8623930785958092e-05, | |
| "loss": 6.1331, | |
| "num_input_tokens_seen": 952328, | |
| "step": 3345 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "grad_norm": 0.8554601073265076, | |
| "learning_rate": 1.8545251536352402e-05, | |
| "loss": 6.0583, | |
| "num_input_tokens_seen": 953736, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 6.259328358208955, | |
| "grad_norm": 0.8496954441070557, | |
| "learning_rate": 1.8466640725816e-05, | |
| "loss": 6.2618, | |
| "num_input_tokens_seen": 955272, | |
| "step": 3355 | |
| }, | |
| { | |
| "epoch": 6.268656716417911, | |
| "grad_norm": 0.9268368482589722, | |
| "learning_rate": 1.838809918785166e-05, | |
| "loss": 5.9719, | |
| "num_input_tokens_seen": 956808, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 6.277985074626866, | |
| "grad_norm": 0.9561167359352112, | |
| "learning_rate": 1.8309627755227643e-05, | |
| "loss": 6.1851, | |
| "num_input_tokens_seen": 958152, | |
| "step": 3365 | |
| }, | |
| { | |
| "epoch": 6.287313432835821, | |
| "grad_norm": 1.1899299621582031, | |
| "learning_rate": 1.8231227259968926e-05, | |
| "loss": 5.8786, | |
| "num_input_tokens_seen": 959560, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 6.2966417910447765, | |
| "grad_norm": 0.8815051913261414, | |
| "learning_rate": 1.8152898533348317e-05, | |
| "loss": 5.6246, | |
| "num_input_tokens_seen": 960776, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 6.3059701492537314, | |
| "grad_norm": 0.8512840270996094, | |
| "learning_rate": 1.8074642405877673e-05, | |
| "loss": 6.6206, | |
| "num_input_tokens_seen": 962280, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 6.315298507462686, | |
| "grad_norm": 0.921742856502533, | |
| "learning_rate": 1.799645970729909e-05, | |
| "loss": 6.4849, | |
| "num_input_tokens_seen": 963752, | |
| "step": 3385 | |
| }, | |
| { | |
| "epoch": 6.324626865671641, | |
| "grad_norm": 0.8544665575027466, | |
| "learning_rate": 1.7918351266576112e-05, | |
| "loss": 6.4516, | |
| "num_input_tokens_seen": 965096, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 6.333955223880597, | |
| "grad_norm": 1.2899925708770752, | |
| "learning_rate": 1.784031791188492e-05, | |
| "loss": 5.5782, | |
| "num_input_tokens_seen": 966600, | |
| "step": 3395 | |
| }, | |
| { | |
| "epoch": 6.343283582089552, | |
| "grad_norm": 1.0962835550308228, | |
| "learning_rate": 1.776236047060558e-05, | |
| "loss": 5.7395, | |
| "num_input_tokens_seen": 967976, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 6.352611940298507, | |
| "grad_norm": 1.2898722887039185, | |
| "learning_rate": 1.768447976931326e-05, | |
| "loss": 5.9395, | |
| "num_input_tokens_seen": 969256, | |
| "step": 3405 | |
| }, | |
| { | |
| "epoch": 6.361940298507463, | |
| "grad_norm": 1.0590548515319824, | |
| "learning_rate": 1.760667663376943e-05, | |
| "loss": 6.3237, | |
| "num_input_tokens_seen": 970696, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 6.371268656716418, | |
| "grad_norm": 0.8787952661514282, | |
| "learning_rate": 1.7528951888913177e-05, | |
| "loss": 6.1189, | |
| "num_input_tokens_seen": 972072, | |
| "step": 3415 | |
| }, | |
| { | |
| "epoch": 6.380597014925373, | |
| "grad_norm": 0.7947739958763123, | |
| "learning_rate": 1.7451306358852386e-05, | |
| "loss": 5.9715, | |
| "num_input_tokens_seen": 973736, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 6.389925373134329, | |
| "grad_norm": 1.0734895467758179, | |
| "learning_rate": 1.737374086685504e-05, | |
| "loss": 6.1186, | |
| "num_input_tokens_seen": 975144, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 6.399253731343284, | |
| "grad_norm": 1.097859501838684, | |
| "learning_rate": 1.729625623534053e-05, | |
| "loss": 6.0654, | |
| "num_input_tokens_seen": 976712, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 6.4085820895522385, | |
| "grad_norm": 1.554700255393982, | |
| "learning_rate": 1.721885328587083e-05, | |
| "loss": 6.1522, | |
| "num_input_tokens_seen": 978088, | |
| "step": 3435 | |
| }, | |
| { | |
| "epoch": 6.417910447761194, | |
| "grad_norm": 0.9875174164772034, | |
| "learning_rate": 1.714153283914189e-05, | |
| "loss": 6.0852, | |
| "num_input_tokens_seen": 979560, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 6.427238805970149, | |
| "grad_norm": 0.9719420671463013, | |
| "learning_rate": 1.706429571497486e-05, | |
| "loss": 6.0977, | |
| "num_input_tokens_seen": 981000, | |
| "step": 3445 | |
| }, | |
| { | |
| "epoch": 6.436567164179104, | |
| "grad_norm": 0.8326826691627502, | |
| "learning_rate": 1.698714273230746e-05, | |
| "loss": 5.745, | |
| "num_input_tokens_seen": 982568, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 6.44589552238806, | |
| "grad_norm": 1.0362448692321777, | |
| "learning_rate": 1.6910074709185235e-05, | |
| "loss": 6.1179, | |
| "num_input_tokens_seen": 984040, | |
| "step": 3455 | |
| }, | |
| { | |
| "epoch": 6.455223880597015, | |
| "grad_norm": 0.8656745553016663, | |
| "learning_rate": 1.6833092462752942e-05, | |
| "loss": 6.3443, | |
| "num_input_tokens_seen": 985384, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 6.46455223880597, | |
| "grad_norm": 1.0124107599258423, | |
| "learning_rate": 1.6756196809245838e-05, | |
| "loss": 5.5857, | |
| "num_input_tokens_seen": 986696, | |
| "step": 3465 | |
| }, | |
| { | |
| "epoch": 6.473880597014926, | |
| "grad_norm": 1.2300325632095337, | |
| "learning_rate": 1.667938856398105e-05, | |
| "loss": 6.0145, | |
| "num_input_tokens_seen": 988136, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 6.483208955223881, | |
| "grad_norm": 0.8901059031486511, | |
| "learning_rate": 1.6602668541348916e-05, | |
| "loss": 6.17, | |
| "num_input_tokens_seen": 989608, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 6.492537313432836, | |
| "grad_norm": 1.087119221687317, | |
| "learning_rate": 1.6526037554804367e-05, | |
| "loss": 5.9655, | |
| "num_input_tokens_seen": 990984, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "eval_loss": 6.200956344604492, | |
| "eval_runtime": 2.5707, | |
| "eval_samples_per_second": 92.583, | |
| "eval_steps_per_second": 23.34, | |
| "num_input_tokens_seen": 992104, | |
| "step": 3484 | |
| }, | |
| { | |
| "epoch": 6.5018656716417915, | |
| "grad_norm": 0.9768283367156982, | |
| "learning_rate": 1.6449496416858284e-05, | |
| "loss": 5.4054, | |
| "num_input_tokens_seen": 992360, | |
| "step": 3485 | |
| }, | |
| { | |
| "epoch": 6.5111940298507465, | |
| "grad_norm": 1.3688615560531616, | |
| "learning_rate": 1.637304593906891e-05, | |
| "loss": 6.5438, | |
| "num_input_tokens_seen": 993864, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 6.520522388059701, | |
| "grad_norm": 1.3379185199737549, | |
| "learning_rate": 1.6296686932033203e-05, | |
| "loss": 5.9384, | |
| "num_input_tokens_seen": 995176, | |
| "step": 3495 | |
| }, | |
| { | |
| "epoch": 6.529850746268656, | |
| "grad_norm": 1.1199098825454712, | |
| "learning_rate": 1.6220420205378282e-05, | |
| "loss": 5.8669, | |
| "num_input_tokens_seen": 996680, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.539179104477612, | |
| "grad_norm": 1.5652060508728027, | |
| "learning_rate": 1.614424656775283e-05, | |
| "loss": 6.4108, | |
| "num_input_tokens_seen": 998024, | |
| "step": 3505 | |
| }, | |
| { | |
| "epoch": 6.548507462686567, | |
| "grad_norm": 1.527854561805725, | |
| "learning_rate": 1.6068166826818492e-05, | |
| "loss": 6.0936, | |
| "num_input_tokens_seen": 999432, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 6.557835820895522, | |
| "grad_norm": 0.8947622776031494, | |
| "learning_rate": 1.5992181789241353e-05, | |
| "loss": 6.0611, | |
| "num_input_tokens_seen": 1000712, | |
| "step": 3515 | |
| }, | |
| { | |
| "epoch": 6.567164179104478, | |
| "grad_norm": 1.3037960529327393, | |
| "learning_rate": 1.591629226068338e-05, | |
| "loss": 6.1056, | |
| "num_input_tokens_seen": 1002056, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 6.576492537313433, | |
| "grad_norm": 0.9004983305931091, | |
| "learning_rate": 1.5840499045793843e-05, | |
| "loss": 5.8667, | |
| "num_input_tokens_seen": 1003464, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 6.585820895522388, | |
| "grad_norm": 1.1855685710906982, | |
| "learning_rate": 1.5764802948200825e-05, | |
| "loss": 5.888, | |
| "num_input_tokens_seen": 1004808, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 6.595149253731344, | |
| "grad_norm": 1.1696436405181885, | |
| "learning_rate": 1.5689204770502666e-05, | |
| "loss": 6.055, | |
| "num_input_tokens_seen": 1006120, | |
| "step": 3535 | |
| }, | |
| { | |
| "epoch": 6.604477611940299, | |
| "grad_norm": 1.2286403179168701, | |
| "learning_rate": 1.5613705314259492e-05, | |
| "loss": 6.5947, | |
| "num_input_tokens_seen": 1007624, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 6.6138059701492535, | |
| "grad_norm": 1.881672739982605, | |
| "learning_rate": 1.553830537998466e-05, | |
| "loss": 6.248, | |
| "num_input_tokens_seen": 1009000, | |
| "step": 3545 | |
| }, | |
| { | |
| "epoch": 6.6231343283582085, | |
| "grad_norm": 0.7775828838348389, | |
| "learning_rate": 1.5463005767136356e-05, | |
| "loss": 6.6569, | |
| "num_input_tokens_seen": 1010376, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 6.632462686567164, | |
| "grad_norm": 1.0550016164779663, | |
| "learning_rate": 1.5387807274109038e-05, | |
| "loss": 6.4636, | |
| "num_input_tokens_seen": 1011816, | |
| "step": 3555 | |
| }, | |
| { | |
| "epoch": 6.641791044776119, | |
| "grad_norm": 1.0155189037322998, | |
| "learning_rate": 1.531271069822499e-05, | |
| "loss": 6.2983, | |
| "num_input_tokens_seen": 1013416, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 6.651119402985074, | |
| "grad_norm": 1.406023621559143, | |
| "learning_rate": 1.5237716835725906e-05, | |
| "loss": 5.957, | |
| "num_input_tokens_seen": 1014728, | |
| "step": 3565 | |
| }, | |
| { | |
| "epoch": 6.66044776119403, | |
| "grad_norm": 1.1783486604690552, | |
| "learning_rate": 1.5162826481764398e-05, | |
| "loss": 5.8537, | |
| "num_input_tokens_seen": 1016136, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 6.669776119402985, | |
| "grad_norm": 1.0167632102966309, | |
| "learning_rate": 1.5088040430395589e-05, | |
| "loss": 6.2042, | |
| "num_input_tokens_seen": 1017416, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 6.67910447761194, | |
| "grad_norm": 0.9302517175674438, | |
| "learning_rate": 1.5013359474568712e-05, | |
| "loss": 6.421, | |
| "num_input_tokens_seen": 1019048, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 6.688432835820896, | |
| "grad_norm": 0.9630568027496338, | |
| "learning_rate": 1.493878440611866e-05, | |
| "loss": 6.5384, | |
| "num_input_tokens_seen": 1020552, | |
| "step": 3585 | |
| }, | |
| { | |
| "epoch": 6.697761194029851, | |
| "grad_norm": 0.8778367042541504, | |
| "learning_rate": 1.4864316015757623e-05, | |
| "loss": 6.6356, | |
| "num_input_tokens_seen": 1021896, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 6.707089552238806, | |
| "grad_norm": 1.3292162418365479, | |
| "learning_rate": 1.478995509306669e-05, | |
| "loss": 6.4283, | |
| "num_input_tokens_seen": 1023240, | |
| "step": 3595 | |
| }, | |
| { | |
| "epoch": 6.7164179104477615, | |
| "grad_norm": 0.8208860158920288, | |
| "learning_rate": 1.4715702426487482e-05, | |
| "loss": 5.6127, | |
| "num_input_tokens_seen": 1024712, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 6.725746268656716, | |
| "grad_norm": 0.9894682765007019, | |
| "learning_rate": 1.4641558803313781e-05, | |
| "loss": 6.131, | |
| "num_input_tokens_seen": 1026216, | |
| "step": 3605 | |
| }, | |
| { | |
| "epoch": 6.735074626865671, | |
| "grad_norm": 0.9610740542411804, | |
| "learning_rate": 1.4567525009683219e-05, | |
| "loss": 6.1017, | |
| "num_input_tokens_seen": 1027592, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 6.744402985074627, | |
| "grad_norm": 0.9337359070777893, | |
| "learning_rate": 1.4493601830568887e-05, | |
| "loss": 5.7326, | |
| "num_input_tokens_seen": 1029064, | |
| "step": 3615 | |
| }, | |
| { | |
| "epoch": 6.753731343283582, | |
| "grad_norm": 1.0650213956832886, | |
| "learning_rate": 1.4419790049771068e-05, | |
| "loss": 6.5532, | |
| "num_input_tokens_seen": 1030632, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 6.763059701492537, | |
| "grad_norm": 0.9499257802963257, | |
| "learning_rate": 1.434609044990886e-05, | |
| "loss": 6.0863, | |
| "num_input_tokens_seen": 1032072, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 6.772388059701493, | |
| "grad_norm": 1.07285475730896, | |
| "learning_rate": 1.4272503812411974e-05, | |
| "loss": 6.4396, | |
| "num_input_tokens_seen": 1033480, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 6.781716417910448, | |
| "grad_norm": 1.11931574344635, | |
| "learning_rate": 1.4199030917512329e-05, | |
| "loss": 6.4214, | |
| "num_input_tokens_seen": 1034792, | |
| "step": 3635 | |
| }, | |
| { | |
| "epoch": 6.791044776119403, | |
| "grad_norm": 0.9230740070343018, | |
| "learning_rate": 1.412567254423589e-05, | |
| "loss": 6.6049, | |
| "num_input_tokens_seen": 1036200, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 6.800373134328359, | |
| "grad_norm": 0.8019490242004395, | |
| "learning_rate": 1.4052429470394352e-05, | |
| "loss": 6.6506, | |
| "num_input_tokens_seen": 1037608, | |
| "step": 3645 | |
| }, | |
| { | |
| "epoch": 6.809701492537314, | |
| "grad_norm": 1.2723616361618042, | |
| "learning_rate": 1.3979302472576868e-05, | |
| "loss": 6.4012, | |
| "num_input_tokens_seen": 1038952, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 6.8190298507462686, | |
| "grad_norm": 1.2407257556915283, | |
| "learning_rate": 1.3906292326141904e-05, | |
| "loss": 6.1017, | |
| "num_input_tokens_seen": 1040584, | |
| "step": 3655 | |
| }, | |
| { | |
| "epoch": 6.8283582089552235, | |
| "grad_norm": 1.383824348449707, | |
| "learning_rate": 1.3833399805208904e-05, | |
| "loss": 6.2408, | |
| "num_input_tokens_seen": 1041960, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 6.837686567164179, | |
| "grad_norm": 0.9098367691040039, | |
| "learning_rate": 1.376062568265018e-05, | |
| "loss": 5.5561, | |
| "num_input_tokens_seen": 1043336, | |
| "step": 3665 | |
| }, | |
| { | |
| "epoch": 6.847014925373134, | |
| "grad_norm": 1.3620972633361816, | |
| "learning_rate": 1.3687970730082678e-05, | |
| "loss": 6.2007, | |
| "num_input_tokens_seen": 1044712, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 6.856343283582089, | |
| "grad_norm": 1.1604808568954468, | |
| "learning_rate": 1.361543571785976e-05, | |
| "loss": 5.9179, | |
| "num_input_tokens_seen": 1046120, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 6.865671641791045, | |
| "grad_norm": 1.0559042692184448, | |
| "learning_rate": 1.3543021415063117e-05, | |
| "loss": 6.482, | |
| "num_input_tokens_seen": 1047592, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 6.875, | |
| "grad_norm": 1.0173639059066772, | |
| "learning_rate": 1.347072858949453e-05, | |
| "loss": 5.4138, | |
| "num_input_tokens_seen": 1048936, | |
| "step": 3685 | |
| }, | |
| { | |
| "epoch": 6.884328358208955, | |
| "grad_norm": 1.1889828443527222, | |
| "learning_rate": 1.3398558007667806e-05, | |
| "loss": 6.5698, | |
| "num_input_tokens_seen": 1050376, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 6.893656716417911, | |
| "grad_norm": 0.8617175221443176, | |
| "learning_rate": 1.3326510434800566e-05, | |
| "loss": 5.5196, | |
| "num_input_tokens_seen": 1051816, | |
| "step": 3695 | |
| }, | |
| { | |
| "epoch": 6.902985074626866, | |
| "grad_norm": 1.0169047117233276, | |
| "learning_rate": 1.3254586634806249e-05, | |
| "loss": 5.9008, | |
| "num_input_tokens_seen": 1053128, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 6.912313432835821, | |
| "grad_norm": 0.8695893287658691, | |
| "learning_rate": 1.3182787370285865e-05, | |
| "loss": 6.6612, | |
| "num_input_tokens_seen": 1054440, | |
| "step": 3705 | |
| }, | |
| { | |
| "epoch": 6.9216417910447765, | |
| "grad_norm": 1.0931859016418457, | |
| "learning_rate": 1.3111113402520053e-05, | |
| "loss": 5.8695, | |
| "num_input_tokens_seen": 1055816, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 6.9309701492537314, | |
| "grad_norm": 1.1550060510635376, | |
| "learning_rate": 1.3039565491460882e-05, | |
| "loss": 6.0544, | |
| "num_input_tokens_seen": 1057288, | |
| "step": 3715 | |
| }, | |
| { | |
| "epoch": 6.940298507462686, | |
| "grad_norm": 0.9765520691871643, | |
| "learning_rate": 1.2968144395723914e-05, | |
| "loss": 5.9799, | |
| "num_input_tokens_seen": 1058888, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 6.949626865671641, | |
| "grad_norm": 0.8144245147705078, | |
| "learning_rate": 1.289685087258004e-05, | |
| "loss": 6.2505, | |
| "num_input_tokens_seen": 1060296, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 6.958955223880597, | |
| "grad_norm": 1.0203068256378174, | |
| "learning_rate": 1.2825685677947563e-05, | |
| "loss": 5.6764, | |
| "num_input_tokens_seen": 1061640, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 6.968283582089552, | |
| "grad_norm": 0.7647175192832947, | |
| "learning_rate": 1.2754649566384114e-05, | |
| "loss": 5.4387, | |
| "num_input_tokens_seen": 1062888, | |
| "step": 3735 | |
| }, | |
| { | |
| "epoch": 6.977611940298507, | |
| "grad_norm": 1.0274134874343872, | |
| "learning_rate": 1.2683743291078649e-05, | |
| "loss": 6.3835, | |
| "num_input_tokens_seen": 1064328, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 6.986940298507463, | |
| "grad_norm": 1.1975784301757812, | |
| "learning_rate": 1.2612967603843512e-05, | |
| "loss": 5.9752, | |
| "num_input_tokens_seen": 1065928, | |
| "step": 3745 | |
| }, | |
| { | |
| "epoch": 6.996268656716418, | |
| "grad_norm": 1.264822006225586, | |
| "learning_rate": 1.2542323255106408e-05, | |
| "loss": 6.3153, | |
| "num_input_tokens_seen": 1067176, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 6.178179740905762, | |
| "eval_runtime": 2.5573, | |
| "eval_samples_per_second": 93.066, | |
| "eval_steps_per_second": 23.462, | |
| "num_input_tokens_seen": 1067520, | |
| "step": 3752 | |
| }, | |
| { | |
| "epoch": 7.005597014925373, | |
| "grad_norm": 1.1028817892074585, | |
| "learning_rate": 1.24718109939025e-05, | |
| "loss": 5.9444, | |
| "num_input_tokens_seen": 1068192, | |
| "step": 3755 | |
| }, | |
| { | |
| "epoch": 7.014925373134329, | |
| "grad_norm": 1.2641462087631226, | |
| "learning_rate": 1.2401431567866425e-05, | |
| "loss": 6.1903, | |
| "num_input_tokens_seen": 1069600, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 7.024253731343284, | |
| "grad_norm": 1.0974889993667603, | |
| "learning_rate": 1.233118572322437e-05, | |
| "loss": 5.4235, | |
| "num_input_tokens_seen": 1070880, | |
| "step": 3765 | |
| }, | |
| { | |
| "epoch": 7.0335820895522385, | |
| "grad_norm": 1.554669737815857, | |
| "learning_rate": 1.22610742047862e-05, | |
| "loss": 5.953, | |
| "num_input_tokens_seen": 1072416, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 7.042910447761194, | |
| "grad_norm": 0.6584553718566895, | |
| "learning_rate": 1.21910977559375e-05, | |
| "loss": 6.5618, | |
| "num_input_tokens_seen": 1073824, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 7.052238805970149, | |
| "grad_norm": 0.9760370254516602, | |
| "learning_rate": 1.212125711863176e-05, | |
| "loss": 6.1063, | |
| "num_input_tokens_seen": 1074976, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 7.061567164179104, | |
| "grad_norm": 1.1033216714859009, | |
| "learning_rate": 1.2051553033382425e-05, | |
| "loss": 5.7972, | |
| "num_input_tokens_seen": 1076416, | |
| "step": 3785 | |
| }, | |
| { | |
| "epoch": 7.07089552238806, | |
| "grad_norm": 0.870838463306427, | |
| "learning_rate": 1.1981986239255164e-05, | |
| "loss": 5.831, | |
| "num_input_tokens_seen": 1077920, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 7.080223880597015, | |
| "grad_norm": 1.359560251235962, | |
| "learning_rate": 1.1912557473859895e-05, | |
| "loss": 5.5865, | |
| "num_input_tokens_seen": 1079776, | |
| "step": 3795 | |
| }, | |
| { | |
| "epoch": 7.08955223880597, | |
| "grad_norm": 1.0016227960586548, | |
| "learning_rate": 1.1843267473343048e-05, | |
| "loss": 6.3899, | |
| "num_input_tokens_seen": 1081088, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 7.098880597014926, | |
| "grad_norm": 0.9860274791717529, | |
| "learning_rate": 1.177411697237977e-05, | |
| "loss": 6.194, | |
| "num_input_tokens_seen": 1082624, | |
| "step": 3805 | |
| }, | |
| { | |
| "epoch": 7.108208955223881, | |
| "grad_norm": 1.2353649139404297, | |
| "learning_rate": 1.1705106704166069e-05, | |
| "loss": 6.7915, | |
| "num_input_tokens_seen": 1084000, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 7.117537313432836, | |
| "grad_norm": 1.4799851179122925, | |
| "learning_rate": 1.1636237400411107e-05, | |
| "loss": 6.0824, | |
| "num_input_tokens_seen": 1085504, | |
| "step": 3815 | |
| }, | |
| { | |
| "epoch": 7.126865671641791, | |
| "grad_norm": 0.9429288506507874, | |
| "learning_rate": 1.1567509791329401e-05, | |
| "loss": 6.0044, | |
| "num_input_tokens_seen": 1086848, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 7.1361940298507465, | |
| "grad_norm": 0.852864682674408, | |
| "learning_rate": 1.1498924605633111e-05, | |
| "loss": 6.3117, | |
| "num_input_tokens_seen": 1088160, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 7.145522388059701, | |
| "grad_norm": 0.648108720779419, | |
| "learning_rate": 1.1430482570524253e-05, | |
| "loss": 6.0298, | |
| "num_input_tokens_seen": 1089568, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 7.154850746268656, | |
| "grad_norm": 1.1080104112625122, | |
| "learning_rate": 1.136218441168709e-05, | |
| "loss": 5.9721, | |
| "num_input_tokens_seen": 1090752, | |
| "step": 3835 | |
| }, | |
| { | |
| "epoch": 7.164179104477612, | |
| "grad_norm": 1.0027233362197876, | |
| "learning_rate": 1.1294030853280321e-05, | |
| "loss": 5.8658, | |
| "num_input_tokens_seen": 1092128, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 7.173507462686567, | |
| "grad_norm": 0.8183642029762268, | |
| "learning_rate": 1.12260226179295e-05, | |
| "loss": 6.0109, | |
| "num_input_tokens_seen": 1093376, | |
| "step": 3845 | |
| }, | |
| { | |
| "epoch": 7.182835820895522, | |
| "grad_norm": 0.9977642893791199, | |
| "learning_rate": 1.115816042671933e-05, | |
| "loss": 5.887, | |
| "num_input_tokens_seen": 1094848, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 7.192164179104478, | |
| "grad_norm": 0.822098970413208, | |
| "learning_rate": 1.1090444999186e-05, | |
| "loss": 6.0866, | |
| "num_input_tokens_seen": 1096352, | |
| "step": 3855 | |
| }, | |
| { | |
| "epoch": 7.201492537313433, | |
| "grad_norm": 0.9472689032554626, | |
| "learning_rate": 1.102287705330961e-05, | |
| "loss": 6.0945, | |
| "num_input_tokens_seen": 1097824, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 7.210820895522388, | |
| "grad_norm": 1.789987325668335, | |
| "learning_rate": 1.095545730550649e-05, | |
| "loss": 6.4308, | |
| "num_input_tokens_seen": 1099136, | |
| "step": 3865 | |
| }, | |
| { | |
| "epoch": 7.220149253731344, | |
| "grad_norm": 1.0045933723449707, | |
| "learning_rate": 1.0888186470621675e-05, | |
| "loss": 5.7004, | |
| "num_input_tokens_seen": 1100512, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 7.229477611940299, | |
| "grad_norm": 0.8498923182487488, | |
| "learning_rate": 1.0821065261921262e-05, | |
| "loss": 6.2317, | |
| "num_input_tokens_seen": 1101856, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 7.2388059701492535, | |
| "grad_norm": 1.022011637687683, | |
| "learning_rate": 1.0754094391084896e-05, | |
| "loss": 5.8558, | |
| "num_input_tokens_seen": 1103264, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 7.248134328358209, | |
| "grad_norm": 1.511824369430542, | |
| "learning_rate": 1.0687274568198208e-05, | |
| "loss": 6.0049, | |
| "num_input_tokens_seen": 1104736, | |
| "step": 3885 | |
| }, | |
| { | |
| "epoch": 7.257462686567164, | |
| "grad_norm": 0.6900339722633362, | |
| "learning_rate": 1.0620606501745251e-05, | |
| "loss": 5.9316, | |
| "num_input_tokens_seen": 1106336, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 7.266791044776119, | |
| "grad_norm": 0.9342882037162781, | |
| "learning_rate": 1.0554090898601062e-05, | |
| "loss": 5.6941, | |
| "num_input_tokens_seen": 1107808, | |
| "step": 3895 | |
| }, | |
| { | |
| "epoch": 7.276119402985074, | |
| "grad_norm": 1.010172724723816, | |
| "learning_rate": 1.0487728464024086e-05, | |
| "loss": 6.6189, | |
| "num_input_tokens_seen": 1109184, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 7.28544776119403, | |
| "grad_norm": 1.0880299806594849, | |
| "learning_rate": 1.0421519901648758e-05, | |
| "loss": 6.732, | |
| "num_input_tokens_seen": 1110720, | |
| "step": 3905 | |
| }, | |
| { | |
| "epoch": 7.294776119402985, | |
| "grad_norm": 0.8344075679779053, | |
| "learning_rate": 1.0355465913478019e-05, | |
| "loss": 5.4294, | |
| "num_input_tokens_seen": 1112096, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 7.30410447761194, | |
| "grad_norm": 1.2708202600479126, | |
| "learning_rate": 1.0289567199875878e-05, | |
| "loss": 5.931, | |
| "num_input_tokens_seen": 1113408, | |
| "step": 3915 | |
| }, | |
| { | |
| "epoch": 7.313432835820896, | |
| "grad_norm": 1.0959720611572266, | |
| "learning_rate": 1.0223824459559971e-05, | |
| "loss": 6.1846, | |
| "num_input_tokens_seen": 1114784, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 7.322761194029851, | |
| "grad_norm": 0.9723264575004578, | |
| "learning_rate": 1.0158238389594164e-05, | |
| "loss": 6.5178, | |
| "num_input_tokens_seen": 1116416, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 7.332089552238806, | |
| "grad_norm": 0.9236953258514404, | |
| "learning_rate": 1.009280968538118e-05, | |
| "loss": 6.2234, | |
| "num_input_tokens_seen": 1117824, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 7.3414179104477615, | |
| "grad_norm": 0.9102874398231506, | |
| "learning_rate": 1.0027539040655173e-05, | |
| "loss": 6.1671, | |
| "num_input_tokens_seen": 1119136, | |
| "step": 3935 | |
| }, | |
| { | |
| "epoch": 7.350746268656716, | |
| "grad_norm": 0.9816330671310425, | |
| "learning_rate": 9.962427147474474e-06, | |
| "loss": 5.7908, | |
| "num_input_tokens_seen": 1120480, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 7.360074626865671, | |
| "grad_norm": 1.5242828130722046, | |
| "learning_rate": 9.89747469621411e-06, | |
| "loss": 6.0781, | |
| "num_input_tokens_seen": 1121856, | |
| "step": 3945 | |
| }, | |
| { | |
| "epoch": 7.369402985074627, | |
| "grad_norm": 0.7413934469223022, | |
| "learning_rate": 9.832682375558614e-06, | |
| "loss": 6.1132, | |
| "num_input_tokens_seen": 1123136, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 7.378731343283582, | |
| "grad_norm": 1.189329981803894, | |
| "learning_rate": 9.768050872494638e-06, | |
| "loss": 6.3012, | |
| "num_input_tokens_seen": 1124480, | |
| "step": 3955 | |
| }, | |
| { | |
| "epoch": 7.388059701492537, | |
| "grad_norm": 1.1660680770874023, | |
| "learning_rate": 9.70358087230373e-06, | |
| "loss": 6.2296, | |
| "num_input_tokens_seen": 1125856, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 7.397388059701493, | |
| "grad_norm": 1.0313493013381958, | |
| "learning_rate": 9.639273058555004e-06, | |
| "loss": 6.0967, | |
| "num_input_tokens_seen": 1127264, | |
| "step": 3965 | |
| }, | |
| { | |
| "epoch": 7.406716417910448, | |
| "grad_norm": 0.940030038356781, | |
| "learning_rate": 9.575128113097952e-06, | |
| "loss": 6.4853, | |
| "num_input_tokens_seen": 1128640, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 7.416044776119403, | |
| "grad_norm": 1.000184416770935, | |
| "learning_rate": 9.5111467160552e-06, | |
| "loss": 6.4158, | |
| "num_input_tokens_seen": 1129984, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 7.425373134328359, | |
| "grad_norm": 1.014087200164795, | |
| "learning_rate": 9.447329545815246e-06, | |
| "loss": 6.0877, | |
| "num_input_tokens_seen": 1131552, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 7.434701492537314, | |
| "grad_norm": 0.9893119931221008, | |
| "learning_rate": 9.383677279025347e-06, | |
| "loss": 6.1683, | |
| "num_input_tokens_seen": 1132928, | |
| "step": 3985 | |
| }, | |
| { | |
| "epoch": 7.4440298507462686, | |
| "grad_norm": 0.9065735936164856, | |
| "learning_rate": 9.320190590584273e-06, | |
| "loss": 5.8752, | |
| "num_input_tokens_seen": 1134336, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 7.4533582089552235, | |
| "grad_norm": 1.1620935201644897, | |
| "learning_rate": 9.256870153635208e-06, | |
| "loss": 5.8536, | |
| "num_input_tokens_seen": 1135840, | |
| "step": 3995 | |
| }, | |
| { | |
| "epoch": 7.462686567164179, | |
| "grad_norm": 1.189558506011963, | |
| "learning_rate": 9.193716639558587e-06, | |
| "loss": 5.8271, | |
| "num_input_tokens_seen": 1137216, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 7.472014925373134, | |
| "grad_norm": 0.7589160799980164, | |
| "learning_rate": 9.130730717964948e-06, | |
| "loss": 6.065, | |
| "num_input_tokens_seen": 1138528, | |
| "step": 4005 | |
| }, | |
| { | |
| "epoch": 7.481343283582089, | |
| "grad_norm": 0.9153366088867188, | |
| "learning_rate": 9.067913056687899e-06, | |
| "loss": 6.6618, | |
| "num_input_tokens_seen": 1139872, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 7.490671641791045, | |
| "grad_norm": 0.8106452822685242, | |
| "learning_rate": 9.005264321776974e-06, | |
| "loss": 6.6422, | |
| "num_input_tokens_seen": 1141408, | |
| "step": 4015 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 1.1609067916870117, | |
| "learning_rate": 8.942785177490617e-06, | |
| "loss": 6.4198, | |
| "num_input_tokens_seen": 1142912, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "eval_loss": 6.164480686187744, | |
| "eval_runtime": 2.5752, | |
| "eval_samples_per_second": 92.42, | |
| "eval_steps_per_second": 23.299, | |
| "num_input_tokens_seen": 1142912, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 7.509328358208955, | |
| "grad_norm": 0.8688708543777466, | |
| "learning_rate": 8.880476286289091e-06, | |
| "loss": 5.6221, | |
| "num_input_tokens_seen": 1144256, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 7.518656716417911, | |
| "grad_norm": 1.0034016370773315, | |
| "learning_rate": 8.818338308827529e-06, | |
| "loss": 5.5548, | |
| "num_input_tokens_seen": 1145568, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 7.527985074626866, | |
| "grad_norm": 1.006486415863037, | |
| "learning_rate": 8.75637190394884e-06, | |
| "loss": 6.2794, | |
| "num_input_tokens_seen": 1147008, | |
| "step": 4035 | |
| }, | |
| { | |
| "epoch": 7.537313432835821, | |
| "grad_norm": 1.4222718477249146, | |
| "learning_rate": 8.69457772867677e-06, | |
| "loss": 5.8641, | |
| "num_input_tokens_seen": 1148416, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 7.5466417910447765, | |
| "grad_norm": 1.0556979179382324, | |
| "learning_rate": 8.632956438208961e-06, | |
| "loss": 6.2364, | |
| "num_input_tokens_seen": 1149888, | |
| "step": 4045 | |
| }, | |
| { | |
| "epoch": 7.5559701492537314, | |
| "grad_norm": 0.9346198439598083, | |
| "learning_rate": 8.571508685909931e-06, | |
| "loss": 5.519, | |
| "num_input_tokens_seen": 1151360, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 7.565298507462686, | |
| "grad_norm": 0.9846770763397217, | |
| "learning_rate": 8.510235123304227e-06, | |
| "loss": 6.4117, | |
| "num_input_tokens_seen": 1152800, | |
| "step": 4055 | |
| }, | |
| { | |
| "epoch": 7.574626865671641, | |
| "grad_norm": 1.1656240224838257, | |
| "learning_rate": 8.449136400069464e-06, | |
| "loss": 5.8707, | |
| "num_input_tokens_seen": 1154272, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 7.583955223880597, | |
| "grad_norm": 0.8148749470710754, | |
| "learning_rate": 8.38821316402946e-06, | |
| "loss": 6.2107, | |
| "num_input_tokens_seen": 1155584, | |
| "step": 4065 | |
| }, | |
| { | |
| "epoch": 7.593283582089552, | |
| "grad_norm": 1.024634838104248, | |
| "learning_rate": 8.327466061147337e-06, | |
| "loss": 6.3887, | |
| "num_input_tokens_seen": 1157152, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 7.602611940298507, | |
| "grad_norm": 1.0860704183578491, | |
| "learning_rate": 8.266895735518729e-06, | |
| "loss": 6.1544, | |
| "num_input_tokens_seen": 1158432, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 7.611940298507463, | |
| "grad_norm": 0.8634097576141357, | |
| "learning_rate": 8.20650282936488e-06, | |
| "loss": 5.8934, | |
| "num_input_tokens_seen": 1160032, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 7.621268656716418, | |
| "grad_norm": 0.920130729675293, | |
| "learning_rate": 8.146287983025903e-06, | |
| "loss": 5.6975, | |
| "num_input_tokens_seen": 1161536, | |
| "step": 4085 | |
| }, | |
| { | |
| "epoch": 7.630597014925373, | |
| "grad_norm": 0.8016346096992493, | |
| "learning_rate": 8.086251834953953e-06, | |
| "loss": 6.0205, | |
| "num_input_tokens_seen": 1163072, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 7.639925373134329, | |
| "grad_norm": 1.0282458066940308, | |
| "learning_rate": 8.02639502170645e-06, | |
| "loss": 6.2374, | |
| "num_input_tokens_seen": 1164384, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 7.649253731343284, | |
| "grad_norm": 1.0683046579360962, | |
| "learning_rate": 7.966718177939366e-06, | |
| "loss": 6.2528, | |
| "num_input_tokens_seen": 1165728, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 7.6585820895522385, | |
| "grad_norm": 0.9176127314567566, | |
| "learning_rate": 7.907221936400453e-06, | |
| "loss": 6.3124, | |
| "num_input_tokens_seen": 1167264, | |
| "step": 4105 | |
| }, | |
| { | |
| "epoch": 7.667910447761194, | |
| "grad_norm": 0.9905545115470886, | |
| "learning_rate": 7.847906927922574e-06, | |
| "loss": 6.0519, | |
| "num_input_tokens_seen": 1168800, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 7.677238805970149, | |
| "grad_norm": 0.8021838665008545, | |
| "learning_rate": 7.788773781416974e-06, | |
| "loss": 6.3352, | |
| "num_input_tokens_seen": 1170240, | |
| "step": 4115 | |
| }, | |
| { | |
| "epoch": 7.686567164179104, | |
| "grad_norm": 0.7918004393577576, | |
| "learning_rate": 7.729823123866656e-06, | |
| "loss": 5.5979, | |
| "num_input_tokens_seen": 1171936, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 7.69589552238806, | |
| "grad_norm": 0.8650549650192261, | |
| "learning_rate": 7.671055580319706e-06, | |
| "loss": 6.1621, | |
| "num_input_tokens_seen": 1173216, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 7.705223880597015, | |
| "grad_norm": 0.8319261074066162, | |
| "learning_rate": 7.612471773882651e-06, | |
| "loss": 6.2407, | |
| "num_input_tokens_seen": 1174496, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 7.71455223880597, | |
| "grad_norm": 0.9002445340156555, | |
| "learning_rate": 7.554072325713896e-06, | |
| "loss": 5.7773, | |
| "num_input_tokens_seen": 1176032, | |
| "step": 4135 | |
| }, | |
| { | |
| "epoch": 7.723880597014926, | |
| "grad_norm": 1.0894677639007568, | |
| "learning_rate": 7.495857855017091e-06, | |
| "loss": 5.7109, | |
| "num_input_tokens_seen": 1177472, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 7.733208955223881, | |
| "grad_norm": 1.1029695272445679, | |
| "learning_rate": 7.437828979034606e-06, | |
| "loss": 6.2057, | |
| "num_input_tokens_seen": 1178976, | |
| "step": 4145 | |
| }, | |
| { | |
| "epoch": 7.742537313432836, | |
| "grad_norm": 1.071293592453003, | |
| "learning_rate": 7.379986313040959e-06, | |
| "loss": 5.5216, | |
| "num_input_tokens_seen": 1180448, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 7.7518656716417915, | |
| "grad_norm": 1.099521517753601, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 5.5106, | |
| "num_input_tokens_seen": 1181888, | |
| "step": 4155 | |
| }, | |
| { | |
| "epoch": 7.7611940298507465, | |
| "grad_norm": 0.865702748298645, | |
| "learning_rate": 7.264862062239947e-06, | |
| "loss": 6.0824, | |
| "num_input_tokens_seen": 1183456, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 7.770522388059701, | |
| "grad_norm": 0.7887092232704163, | |
| "learning_rate": 7.2075816980837814e-06, | |
| "loss": 6.2111, | |
| "num_input_tokens_seen": 1184800, | |
| "step": 4165 | |
| }, | |
| { | |
| "epoch": 7.779850746268656, | |
| "grad_norm": 0.8101704120635986, | |
| "learning_rate": 7.150489985205952e-06, | |
| "loss": 6.2457, | |
| "num_input_tokens_seen": 1186304, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 7.789179104477612, | |
| "grad_norm": 0.7540645003318787, | |
| "learning_rate": 7.093587528944326e-06, | |
| "loss": 6.3101, | |
| "num_input_tokens_seen": 1187744, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 7.798507462686567, | |
| "grad_norm": 0.9706438183784485, | |
| "learning_rate": 7.036874932630117e-06, | |
| "loss": 6.1509, | |
| "num_input_tokens_seen": 1189376, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 7.807835820895522, | |
| "grad_norm": 1.1090978384017944, | |
| "learning_rate": 6.980352797581438e-06, | |
| "loss": 6.6927, | |
| "num_input_tokens_seen": 1190912, | |
| "step": 4185 | |
| }, | |
| { | |
| "epoch": 7.817164179104478, | |
| "grad_norm": 1.0484838485717773, | |
| "learning_rate": 6.924021723097004e-06, | |
| "loss": 5.8994, | |
| "num_input_tokens_seen": 1192416, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 7.826492537313433, | |
| "grad_norm": 0.9052582383155823, | |
| "learning_rate": 6.867882306449694e-06, | |
| "loss": 5.8114, | |
| "num_input_tokens_seen": 1193792, | |
| "step": 4195 | |
| }, | |
| { | |
| "epoch": 7.835820895522388, | |
| "grad_norm": 1.4265191555023193, | |
| "learning_rate": 6.8119351428802796e-06, | |
| "loss": 6.5992, | |
| "num_input_tokens_seen": 1195200, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 7.845149253731344, | |
| "grad_norm": 1.106819987297058, | |
| "learning_rate": 6.756180825591099e-06, | |
| "loss": 6.0213, | |
| "num_input_tokens_seen": 1196672, | |
| "step": 4205 | |
| }, | |
| { | |
| "epoch": 7.854477611940299, | |
| "grad_norm": 1.4743338823318481, | |
| "learning_rate": 6.700619945739728e-06, | |
| "loss": 6.4122, | |
| "num_input_tokens_seen": 1198336, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 7.8638059701492535, | |
| "grad_norm": 1.3929013013839722, | |
| "learning_rate": 6.645253092432785e-06, | |
| "loss": 5.9713, | |
| "num_input_tokens_seen": 1199712, | |
| "step": 4215 | |
| }, | |
| { | |
| "epoch": 7.8731343283582085, | |
| "grad_norm": 0.950134813785553, | |
| "learning_rate": 6.590080852719602e-06, | |
| "loss": 6.1534, | |
| "num_input_tokens_seen": 1201088, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 7.882462686567164, | |
| "grad_norm": 0.9204327464103699, | |
| "learning_rate": 6.535103811586085e-06, | |
| "loss": 5.9652, | |
| "num_input_tokens_seen": 1202432, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 7.891791044776119, | |
| "grad_norm": 0.8025768399238586, | |
| "learning_rate": 6.480322551948426e-06, | |
| "loss": 6.0424, | |
| "num_input_tokens_seen": 1203872, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 7.901119402985074, | |
| "grad_norm": 0.7892027497291565, | |
| "learning_rate": 6.425737654646993e-06, | |
| "loss": 6.0421, | |
| "num_input_tokens_seen": 1205312, | |
| "step": 4235 | |
| }, | |
| { | |
| "epoch": 7.91044776119403, | |
| "grad_norm": 1.194388747215271, | |
| "learning_rate": 6.371349698440149e-06, | |
| "loss": 6.4943, | |
| "num_input_tokens_seen": 1206688, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 7.919776119402985, | |
| "grad_norm": 1.1354224681854248, | |
| "learning_rate": 6.317159259998073e-06, | |
| "loss": 5.6156, | |
| "num_input_tokens_seen": 1208064, | |
| "step": 4245 | |
| }, | |
| { | |
| "epoch": 7.92910447761194, | |
| "grad_norm": 0.8459598422050476, | |
| "learning_rate": 6.2631669138967285e-06, | |
| "loss": 5.9599, | |
| "num_input_tokens_seen": 1209600, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 7.938432835820896, | |
| "grad_norm": 0.8911008834838867, | |
| "learning_rate": 6.209373232611682e-06, | |
| "loss": 6.229, | |
| "num_input_tokens_seen": 1210976, | |
| "step": 4255 | |
| }, | |
| { | |
| "epoch": 7.947761194029851, | |
| "grad_norm": 0.9538748264312744, | |
| "learning_rate": 6.155778786512109e-06, | |
| "loss": 6.2099, | |
| "num_input_tokens_seen": 1212416, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 7.957089552238806, | |
| "grad_norm": 1.5598032474517822, | |
| "learning_rate": 6.102384143854698e-06, | |
| "loss": 5.8344, | |
| "num_input_tokens_seen": 1213920, | |
| "step": 4265 | |
| }, | |
| { | |
| "epoch": 7.9664179104477615, | |
| "grad_norm": 1.2082208395004272, | |
| "learning_rate": 6.049189870777652e-06, | |
| "loss": 5.5065, | |
| "num_input_tokens_seen": 1215360, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 7.975746268656716, | |
| "grad_norm": 1.2141947746276855, | |
| "learning_rate": 5.996196531294657e-06, | |
| "loss": 6.3202, | |
| "num_input_tokens_seen": 1216736, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 7.985074626865671, | |
| "grad_norm": 0.8237694501876831, | |
| "learning_rate": 5.943404687288939e-06, | |
| "loss": 6.4767, | |
| "num_input_tokens_seen": 1218240, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 7.994402985074627, | |
| "grad_norm": 0.9265881776809692, | |
| "learning_rate": 5.890814898507277e-06, | |
| "loss": 5.8816, | |
| "num_input_tokens_seen": 1219488, | |
| "step": 4285 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 6.157891273498535, | |
| "eval_runtime": 2.5717, | |
| "eval_samples_per_second": 92.544, | |
| "eval_steps_per_second": 23.33, | |
| "num_input_tokens_seen": 1220200, | |
| "step": 4288 | |
| }, | |
| { | |
| "epoch": 8.003731343283581, | |
| "grad_norm": 0.8366351127624512, | |
| "learning_rate": 5.838427722554057e-06, | |
| "loss": 5.6459, | |
| "num_input_tokens_seen": 1220808, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 8.013059701492537, | |
| "grad_norm": 0.8628629446029663, | |
| "learning_rate": 5.786243714885442e-06, | |
| "loss": 5.8122, | |
| "num_input_tokens_seen": 1222280, | |
| "step": 4295 | |
| }, | |
| { | |
| "epoch": 8.022388059701493, | |
| "grad_norm": 1.2532949447631836, | |
| "learning_rate": 5.734263428803352e-06, | |
| "loss": 6.4911, | |
| "num_input_tokens_seen": 1223688, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 8.031716417910447, | |
| "grad_norm": 0.8800325989723206, | |
| "learning_rate": 5.6824874154497194e-06, | |
| "loss": 6.5237, | |
| "num_input_tokens_seen": 1225352, | |
| "step": 4305 | |
| }, | |
| { | |
| "epoch": 8.041044776119403, | |
| "grad_norm": 0.8613767623901367, | |
| "learning_rate": 5.63091622380055e-06, | |
| "loss": 5.625, | |
| "num_input_tokens_seen": 1226824, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 8.050373134328359, | |
| "grad_norm": 0.9300804734230042, | |
| "learning_rate": 5.5795504006601855e-06, | |
| "loss": 6.3955, | |
| "num_input_tokens_seen": 1228232, | |
| "step": 4315 | |
| }, | |
| { | |
| "epoch": 8.059701492537313, | |
| "grad_norm": 1.2023978233337402, | |
| "learning_rate": 5.528390490655428e-06, | |
| "loss": 5.3909, | |
| "num_input_tokens_seen": 1229672, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 8.069029850746269, | |
| "grad_norm": 1.2321088314056396, | |
| "learning_rate": 5.477437036229833e-06, | |
| "loss": 6.1, | |
| "num_input_tokens_seen": 1230920, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 8.078358208955224, | |
| "grad_norm": 0.8637142777442932, | |
| "learning_rate": 5.426690577637913e-06, | |
| "loss": 5.7076, | |
| "num_input_tokens_seen": 1232232, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 8.087686567164178, | |
| "grad_norm": 1.6133989095687866, | |
| "learning_rate": 5.37615165293942e-06, | |
| "loss": 6.0606, | |
| "num_input_tokens_seen": 1233640, | |
| "step": 4335 | |
| }, | |
| { | |
| "epoch": 8.097014925373134, | |
| "grad_norm": 0.8489130735397339, | |
| "learning_rate": 5.325820797993661e-06, | |
| "loss": 6.2203, | |
| "num_input_tokens_seen": 1235048, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 8.10634328358209, | |
| "grad_norm": 1.3658015727996826, | |
| "learning_rate": 5.275698546453775e-06, | |
| "loss": 6.419, | |
| "num_input_tokens_seen": 1236552, | |
| "step": 4345 | |
| }, | |
| { | |
| "epoch": 8.115671641791044, | |
| "grad_norm": 1.2736412286758423, | |
| "learning_rate": 5.225785429761124e-06, | |
| "loss": 5.5199, | |
| "num_input_tokens_seen": 1237896, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 8.125, | |
| "grad_norm": 0.9222644567489624, | |
| "learning_rate": 5.176081977139621e-06, | |
| "loss": 6.2647, | |
| "num_input_tokens_seen": 1239112, | |
| "step": 4355 | |
| }, | |
| { | |
| "epoch": 8.134328358208956, | |
| "grad_norm": 1.5764142274856567, | |
| "learning_rate": 5.12658871559013e-06, | |
| "loss": 5.9782, | |
| "num_input_tokens_seen": 1240744, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 8.14365671641791, | |
| "grad_norm": 0.8553769588470459, | |
| "learning_rate": 5.077306169884888e-06, | |
| "loss": 6.3084, | |
| "num_input_tokens_seen": 1242152, | |
| "step": 4365 | |
| }, | |
| { | |
| "epoch": 8.152985074626866, | |
| "grad_norm": 0.8614527583122253, | |
| "learning_rate": 5.0282348625619175e-06, | |
| "loss": 6.4504, | |
| "num_input_tokens_seen": 1243496, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 8.162313432835822, | |
| "grad_norm": 1.009321928024292, | |
| "learning_rate": 4.979375313919526e-06, | |
| "loss": 6.322, | |
| "num_input_tokens_seen": 1245064, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 8.171641791044776, | |
| "grad_norm": 0.8585836887359619, | |
| "learning_rate": 4.930728042010724e-06, | |
| "loss": 5.6682, | |
| "num_input_tokens_seen": 1246408, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 8.180970149253731, | |
| "grad_norm": 1.0325151681900024, | |
| "learning_rate": 4.882293562637827e-06, | |
| "loss": 5.9767, | |
| "num_input_tokens_seen": 1247784, | |
| "step": 4385 | |
| }, | |
| { | |
| "epoch": 8.190298507462687, | |
| "grad_norm": 1.085978627204895, | |
| "learning_rate": 4.834072389346883e-06, | |
| "loss": 5.9875, | |
| "num_input_tokens_seen": 1249192, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 8.199626865671641, | |
| "grad_norm": 1.1030997037887573, | |
| "learning_rate": 4.78606503342231e-06, | |
| "loss": 6.2637, | |
| "num_input_tokens_seen": 1250664, | |
| "step": 4395 | |
| }, | |
| { | |
| "epoch": 8.208955223880597, | |
| "grad_norm": 1.4077669382095337, | |
| "learning_rate": 4.738272003881417e-06, | |
| "loss": 5.9832, | |
| "num_input_tokens_seen": 1252072, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 8.218283582089553, | |
| "grad_norm": 1.0058317184448242, | |
| "learning_rate": 4.690693807469035e-06, | |
| "loss": 5.776, | |
| "num_input_tokens_seen": 1253416, | |
| "step": 4405 | |
| }, | |
| { | |
| "epoch": 8.227611940298507, | |
| "grad_norm": 1.0817641019821167, | |
| "learning_rate": 4.643330948652155e-06, | |
| "loss": 5.8053, | |
| "num_input_tokens_seen": 1254728, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 8.236940298507463, | |
| "grad_norm": 0.8724300265312195, | |
| "learning_rate": 4.596183929614559e-06, | |
| "loss": 6.3171, | |
| "num_input_tokens_seen": 1255976, | |
| "step": 4415 | |
| }, | |
| { | |
| "epoch": 8.246268656716419, | |
| "grad_norm": 0.9982905983924866, | |
| "learning_rate": 4.549253250251498e-06, | |
| "loss": 6.0461, | |
| "num_input_tokens_seen": 1257288, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 8.255597014925373, | |
| "grad_norm": 0.7670168280601501, | |
| "learning_rate": 4.502539408164386e-06, | |
| "loss": 6.5616, | |
| "num_input_tokens_seen": 1258664, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 8.264925373134329, | |
| "grad_norm": 0.8246083855628967, | |
| "learning_rate": 4.4560428986555516e-06, | |
| "loss": 5.9998, | |
| "num_input_tokens_seen": 1260104, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 8.274253731343283, | |
| "grad_norm": 1.3330838680267334, | |
| "learning_rate": 4.409764214722945e-06, | |
| "loss": 6.1062, | |
| "num_input_tokens_seen": 1261448, | |
| "step": 4435 | |
| }, | |
| { | |
| "epoch": 8.283582089552239, | |
| "grad_norm": 1.0275695323944092, | |
| "learning_rate": 4.363703847054948e-06, | |
| "loss": 5.5596, | |
| "num_input_tokens_seen": 1263048, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 8.292910447761194, | |
| "grad_norm": 1.0857993364334106, | |
| "learning_rate": 4.317862284025165e-06, | |
| "loss": 6.4068, | |
| "num_input_tokens_seen": 1264360, | |
| "step": 4445 | |
| }, | |
| { | |
| "epoch": 8.302238805970148, | |
| "grad_norm": 1.1808459758758545, | |
| "learning_rate": 4.272240011687206e-06, | |
| "loss": 6.4016, | |
| "num_input_tokens_seen": 1265640, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 8.311567164179104, | |
| "grad_norm": 1.1197727918624878, | |
| "learning_rate": 4.226837513769596e-06, | |
| "loss": 6.5845, | |
| "num_input_tokens_seen": 1267016, | |
| "step": 4455 | |
| }, | |
| { | |
| "epoch": 8.32089552238806, | |
| "grad_norm": 0.9971846342086792, | |
| "learning_rate": 4.181655271670587e-06, | |
| "loss": 5.9948, | |
| "num_input_tokens_seen": 1268744, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 8.330223880597014, | |
| "grad_norm": 0.9493358731269836, | |
| "learning_rate": 4.1366937644531e-06, | |
| "loss": 6.4208, | |
| "num_input_tokens_seen": 1270120, | |
| "step": 4465 | |
| }, | |
| { | |
| "epoch": 8.33955223880597, | |
| "grad_norm": 0.9574012756347656, | |
| "learning_rate": 4.091953468839607e-06, | |
| "loss": 6.3729, | |
| "num_input_tokens_seen": 1271656, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 8.348880597014926, | |
| "grad_norm": 1.045838713645935, | |
| "learning_rate": 4.047434859207114e-06, | |
| "loss": 6.1454, | |
| "num_input_tokens_seen": 1273128, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 8.35820895522388, | |
| "grad_norm": 1.3099522590637207, | |
| "learning_rate": 4.003138407582102e-06, | |
| "loss": 5.9514, | |
| "num_input_tokens_seen": 1274632, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 8.367537313432836, | |
| "grad_norm": 1.0678362846374512, | |
| "learning_rate": 3.959064583635527e-06, | |
| "loss": 6.3528, | |
| "num_input_tokens_seen": 1275848, | |
| "step": 4485 | |
| }, | |
| { | |
| "epoch": 8.376865671641792, | |
| "grad_norm": 1.178047776222229, | |
| "learning_rate": 3.9152138546778625e-06, | |
| "loss": 6.2285, | |
| "num_input_tokens_seen": 1277224, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 8.386194029850746, | |
| "grad_norm": 0.9788335561752319, | |
| "learning_rate": 3.871586685654102e-06, | |
| "loss": 5.8961, | |
| "num_input_tokens_seen": 1278504, | |
| "step": 4495 | |
| }, | |
| { | |
| "epoch": 8.395522388059701, | |
| "grad_norm": 1.1402276754379272, | |
| "learning_rate": 3.82818353913888e-06, | |
| "loss": 6.0349, | |
| "num_input_tokens_seen": 1279784, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 8.404850746268657, | |
| "grad_norm": 1.023734211921692, | |
| "learning_rate": 3.785004875331527e-06, | |
| "loss": 5.5966, | |
| "num_input_tokens_seen": 1281256, | |
| "step": 4505 | |
| }, | |
| { | |
| "epoch": 8.414179104477611, | |
| "grad_norm": 0.8168004155158997, | |
| "learning_rate": 3.742051152051221e-06, | |
| "loss": 6.1516, | |
| "num_input_tokens_seen": 1282792, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 8.423507462686567, | |
| "grad_norm": 1.1997103691101074, | |
| "learning_rate": 3.6993228247320877e-06, | |
| "loss": 6.2826, | |
| "num_input_tokens_seen": 1284232, | |
| "step": 4515 | |
| }, | |
| { | |
| "epoch": 8.432835820895523, | |
| "grad_norm": 1.003173828125, | |
| "learning_rate": 3.6568203464184383e-06, | |
| "loss": 5.8751, | |
| "num_input_tokens_seen": 1285448, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 8.442164179104477, | |
| "grad_norm": 0.8415361046791077, | |
| "learning_rate": 3.614544167759901e-06, | |
| "loss": 6.5124, | |
| "num_input_tokens_seen": 1286824, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 8.451492537313433, | |
| "grad_norm": 0.8698881268501282, | |
| "learning_rate": 3.5724947370066708e-06, | |
| "loss": 5.7768, | |
| "num_input_tokens_seen": 1288136, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 8.460820895522389, | |
| "grad_norm": 1.024012804031372, | |
| "learning_rate": 3.5306725000047918e-06, | |
| "loss": 5.7891, | |
| "num_input_tokens_seen": 1289512, | |
| "step": 4535 | |
| }, | |
| { | |
| "epoch": 8.470149253731343, | |
| "grad_norm": 0.7139818072319031, | |
| "learning_rate": 3.4890779001913452e-06, | |
| "loss": 5.6005, | |
| "num_input_tokens_seen": 1291144, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 8.479477611940299, | |
| "grad_norm": 1.1193733215332031, | |
| "learning_rate": 3.4477113785898407e-06, | |
| "loss": 6.3989, | |
| "num_input_tokens_seen": 1292680, | |
| "step": 4545 | |
| }, | |
| { | |
| "epoch": 8.488805970149254, | |
| "grad_norm": 1.2999134063720703, | |
| "learning_rate": 3.4065733738054606e-06, | |
| "loss": 5.6335, | |
| "num_input_tokens_seen": 1294056, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 8.498134328358208, | |
| "grad_norm": 0.9450815320014954, | |
| "learning_rate": 3.3656643220204785e-06, | |
| "loss": 5.8843, | |
| "num_input_tokens_seen": 1295400, | |
| "step": 4555 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "eval_loss": 6.15064001083374, | |
| "eval_runtime": 2.5665, | |
| "eval_samples_per_second": 92.733, | |
| "eval_steps_per_second": 23.378, | |
| "num_input_tokens_seen": 1295720, | |
| "step": 4556 | |
| }, | |
| { | |
| "epoch": 8.507462686567164, | |
| "grad_norm": 1.6086044311523438, | |
| "learning_rate": 3.3249846569895744e-06, | |
| "loss": 6.3928, | |
| "num_input_tokens_seen": 1296872, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 8.51679104477612, | |
| "grad_norm": 1.048813819885254, | |
| "learning_rate": 3.284534810035278e-06, | |
| "loss": 6.5311, | |
| "num_input_tokens_seen": 1298408, | |
| "step": 4565 | |
| }, | |
| { | |
| "epoch": 8.526119402985074, | |
| "grad_norm": 0.9637424349784851, | |
| "learning_rate": 3.2443152100433832e-06, | |
| "loss": 6.1849, | |
| "num_input_tokens_seen": 1299848, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 8.53544776119403, | |
| "grad_norm": 0.8295625448226929, | |
| "learning_rate": 3.204326283458381e-06, | |
| "loss": 6.3188, | |
| "num_input_tokens_seen": 1301224, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 8.544776119402986, | |
| "grad_norm": 0.9644291400909424, | |
| "learning_rate": 3.1645684542789765e-06, | |
| "loss": 6.3155, | |
| "num_input_tokens_seen": 1302856, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 8.55410447761194, | |
| "grad_norm": 1.141606330871582, | |
| "learning_rate": 3.12504214405355e-06, | |
| "loss": 6.0966, | |
| "num_input_tokens_seen": 1304168, | |
| "step": 4585 | |
| }, | |
| { | |
| "epoch": 8.563432835820896, | |
| "grad_norm": 0.9591335654258728, | |
| "learning_rate": 3.0857477718757187e-06, | |
| "loss": 6.1417, | |
| "num_input_tokens_seen": 1305704, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 8.572761194029852, | |
| "grad_norm": 0.8181482553482056, | |
| "learning_rate": 3.0466857543798966e-06, | |
| "loss": 6.2247, | |
| "num_input_tokens_seen": 1307080, | |
| "step": 4595 | |
| }, | |
| { | |
| "epoch": 8.582089552238806, | |
| "grad_norm": 1.2230607271194458, | |
| "learning_rate": 3.007856505736836e-06, | |
| "loss": 5.7227, | |
| "num_input_tokens_seen": 1308296, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 8.591417910447761, | |
| "grad_norm": 1.019697904586792, | |
| "learning_rate": 2.969260437649293e-06, | |
| "loss": 5.766, | |
| "num_input_tokens_seen": 1309832, | |
| "step": 4605 | |
| }, | |
| { | |
| "epoch": 8.600746268656717, | |
| "grad_norm": 0.9698091745376587, | |
| "learning_rate": 2.9308979593476004e-06, | |
| "loss": 6.0528, | |
| "num_input_tokens_seen": 1311368, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 8.610074626865671, | |
| "grad_norm": 0.9309684038162231, | |
| "learning_rate": 2.892769477585397e-06, | |
| "loss": 5.7876, | |
| "num_input_tokens_seen": 1312680, | |
| "step": 4615 | |
| }, | |
| { | |
| "epoch": 8.619402985074627, | |
| "grad_norm": 0.9794005155563354, | |
| "learning_rate": 2.8548753966352426e-06, | |
| "loss": 6.2917, | |
| "num_input_tokens_seen": 1314152, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 8.628731343283581, | |
| "grad_norm": 0.7938780188560486, | |
| "learning_rate": 2.8172161182844075e-06, | |
| "loss": 5.7763, | |
| "num_input_tokens_seen": 1315496, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 8.638059701492537, | |
| "grad_norm": 0.950524091720581, | |
| "learning_rate": 2.779792041830537e-06, | |
| "loss": 5.471, | |
| "num_input_tokens_seen": 1317192, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 8.647388059701493, | |
| "grad_norm": 0.9595046639442444, | |
| "learning_rate": 2.742603564077478e-06, | |
| "loss": 5.8353, | |
| "num_input_tokens_seen": 1318632, | |
| "step": 4635 | |
| }, | |
| { | |
| "epoch": 8.656716417910447, | |
| "grad_norm": 1.0390723943710327, | |
| "learning_rate": 2.7056510793310314e-06, | |
| "loss": 6.0485, | |
| "num_input_tokens_seen": 1320232, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 8.666044776119403, | |
| "grad_norm": 0.920795738697052, | |
| "learning_rate": 2.6689349793947994e-06, | |
| "loss": 5.7388, | |
| "num_input_tokens_seen": 1321768, | |
| "step": 4645 | |
| }, | |
| { | |
| "epoch": 8.675373134328359, | |
| "grad_norm": 1.3264048099517822, | |
| "learning_rate": 2.6324556535660045e-06, | |
| "loss": 5.8221, | |
| "num_input_tokens_seen": 1323272, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 8.684701492537313, | |
| "grad_norm": 0.9962963461875916, | |
| "learning_rate": 2.5962134886313936e-06, | |
| "loss": 5.7343, | |
| "num_input_tokens_seen": 1324680, | |
| "step": 4655 | |
| }, | |
| { | |
| "epoch": 8.694029850746269, | |
| "grad_norm": 1.2119454145431519, | |
| "learning_rate": 2.5602088688631148e-06, | |
| "loss": 6.0207, | |
| "num_input_tokens_seen": 1325992, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 8.703358208955224, | |
| "grad_norm": 0.932567298412323, | |
| "learning_rate": 2.5244421760146355e-06, | |
| "loss": 6.0659, | |
| "num_input_tokens_seen": 1327400, | |
| "step": 4665 | |
| }, | |
| { | |
| "epoch": 8.712686567164178, | |
| "grad_norm": 0.7066296935081482, | |
| "learning_rate": 2.488913789316724e-06, | |
| "loss": 6.1124, | |
| "num_input_tokens_seen": 1328744, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 8.722014925373134, | |
| "grad_norm": 1.1219143867492676, | |
| "learning_rate": 2.4536240854733967e-06, | |
| "loss": 6.0934, | |
| "num_input_tokens_seen": 1330280, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 8.73134328358209, | |
| "grad_norm": 0.9601245522499084, | |
| "learning_rate": 2.4185734386579506e-06, | |
| "loss": 5.9329, | |
| "num_input_tokens_seen": 1331784, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 8.740671641791044, | |
| "grad_norm": 1.71365487575531, | |
| "learning_rate": 2.383762220508984e-06, | |
| "loss": 5.8547, | |
| "num_input_tokens_seen": 1333128, | |
| "step": 4685 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "grad_norm": 1.145279049873352, | |
| "learning_rate": 2.349190800126444e-06, | |
| "loss": 6.4847, | |
| "num_input_tokens_seen": 1334696, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 8.759328358208956, | |
| "grad_norm": 0.9766605496406555, | |
| "learning_rate": 2.3148595440677405e-06, | |
| "loss": 6.6503, | |
| "num_input_tokens_seen": 1336264, | |
| "step": 4695 | |
| }, | |
| { | |
| "epoch": 8.76865671641791, | |
| "grad_norm": 1.177186369895935, | |
| "learning_rate": 2.280768816343834e-06, | |
| "loss": 6.4588, | |
| "num_input_tokens_seen": 1337608, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 8.777985074626866, | |
| "grad_norm": 0.8967664837837219, | |
| "learning_rate": 2.246918978415394e-06, | |
| "loss": 6.0364, | |
| "num_input_tokens_seen": 1339144, | |
| "step": 4705 | |
| }, | |
| { | |
| "epoch": 8.787313432835822, | |
| "grad_norm": 1.3448737859725952, | |
| "learning_rate": 2.2133103891889438e-06, | |
| "loss": 5.9358, | |
| "num_input_tokens_seen": 1340488, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 8.796641791044776, | |
| "grad_norm": 0.7832242846488953, | |
| "learning_rate": 2.1799434050131018e-06, | |
| "loss": 6.1433, | |
| "num_input_tokens_seen": 1341960, | |
| "step": 4715 | |
| }, | |
| { | |
| "epoch": 8.805970149253731, | |
| "grad_norm": 1.2268966436386108, | |
| "learning_rate": 2.1468183796747365e-06, | |
| "loss": 6.5289, | |
| "num_input_tokens_seen": 1343624, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 8.815298507462687, | |
| "grad_norm": 1.034939169883728, | |
| "learning_rate": 2.1139356643952666e-06, | |
| "loss": 6.0176, | |
| "num_input_tokens_seen": 1344936, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 8.824626865671641, | |
| "grad_norm": 0.9292502999305725, | |
| "learning_rate": 2.0812956078269275e-06, | |
| "loss": 6.1572, | |
| "num_input_tokens_seen": 1346408, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 8.833955223880597, | |
| "grad_norm": 0.8195312023162842, | |
| "learning_rate": 2.0488985560490477e-06, | |
| "loss": 5.8598, | |
| "num_input_tokens_seen": 1347784, | |
| "step": 4735 | |
| }, | |
| { | |
| "epoch": 8.843283582089553, | |
| "grad_norm": 1.0142407417297363, | |
| "learning_rate": 2.01674485256442e-06, | |
| "loss": 5.6125, | |
| "num_input_tokens_seen": 1349128, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 8.852611940298507, | |
| "grad_norm": 1.0794872045516968, | |
| "learning_rate": 1.9848348382956293e-06, | |
| "loss": 5.9085, | |
| "num_input_tokens_seen": 1350312, | |
| "step": 4745 | |
| }, | |
| { | |
| "epoch": 8.861940298507463, | |
| "grad_norm": 0.8347100615501404, | |
| "learning_rate": 1.953168851581452e-06, | |
| "loss": 5.7896, | |
| "num_input_tokens_seen": 1351784, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 8.871268656716419, | |
| "grad_norm": 1.2306413650512695, | |
| "learning_rate": 1.921747228173254e-06, | |
| "loss": 5.599, | |
| "num_input_tokens_seen": 1353416, | |
| "step": 4755 | |
| }, | |
| { | |
| "epoch": 8.880597014925373, | |
| "grad_norm": 1.1434723138809204, | |
| "learning_rate": 1.8905703012314563e-06, | |
| "loss": 5.8288, | |
| "num_input_tokens_seen": 1354760, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 8.889925373134329, | |
| "grad_norm": 1.0781902074813843, | |
| "learning_rate": 1.8596384013219725e-06, | |
| "loss": 5.6458, | |
| "num_input_tokens_seen": 1355976, | |
| "step": 4765 | |
| }, | |
| { | |
| "epoch": 8.899253731343283, | |
| "grad_norm": 0.9892986416816711, | |
| "learning_rate": 1.8289518564127223e-06, | |
| "loss": 6.052, | |
| "num_input_tokens_seen": 1357416, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 8.908582089552239, | |
| "grad_norm": 0.967785656452179, | |
| "learning_rate": 1.7985109918701643e-06, | |
| "loss": 6.4766, | |
| "num_input_tokens_seen": 1359080, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 8.917910447761194, | |
| "grad_norm": 1.0148444175720215, | |
| "learning_rate": 1.7683161304558076e-06, | |
| "loss": 5.9509, | |
| "num_input_tokens_seen": 1360552, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 8.927238805970148, | |
| "grad_norm": 0.8816660642623901, | |
| "learning_rate": 1.738367592322837e-06, | |
| "loss": 6.3764, | |
| "num_input_tokens_seen": 1361960, | |
| "step": 4785 | |
| }, | |
| { | |
| "epoch": 8.936567164179104, | |
| "grad_norm": 0.917543351650238, | |
| "learning_rate": 1.708665695012676e-06, | |
| "loss": 6.3492, | |
| "num_input_tokens_seen": 1363368, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 8.94589552238806, | |
| "grad_norm": 1.017173409461975, | |
| "learning_rate": 1.6792107534516571e-06, | |
| "loss": 6.0071, | |
| "num_input_tokens_seen": 1364840, | |
| "step": 4795 | |
| }, | |
| { | |
| "epoch": 8.955223880597014, | |
| "grad_norm": 0.7504062056541443, | |
| "learning_rate": 1.6500030799476513e-06, | |
| "loss": 6.1538, | |
| "num_input_tokens_seen": 1366152, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 8.96455223880597, | |
| "grad_norm": 0.9764262437820435, | |
| "learning_rate": 1.621042984186777e-06, | |
| "loss": 6.033, | |
| "num_input_tokens_seen": 1367528, | |
| "step": 4805 | |
| }, | |
| { | |
| "epoch": 8.973880597014926, | |
| "grad_norm": 1.0792709589004517, | |
| "learning_rate": 1.5923307732301136e-06, | |
| "loss": 6.1146, | |
| "num_input_tokens_seen": 1368968, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 8.98320895522388, | |
| "grad_norm": 1.239707112312317, | |
| "learning_rate": 1.5638667515104288e-06, | |
| "loss": 6.0489, | |
| "num_input_tokens_seen": 1370248, | |
| "step": 4815 | |
| }, | |
| { | |
| "epoch": 8.992537313432836, | |
| "grad_norm": 1.1049518585205078, | |
| "learning_rate": 1.5356512208289846e-06, | |
| "loss": 6.5707, | |
| "num_input_tokens_seen": 1371496, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 6.147698879241943, | |
| "eval_runtime": 2.574, | |
| "eval_samples_per_second": 92.464, | |
| "eval_steps_per_second": 23.31, | |
| "num_input_tokens_seen": 1372560, | |
| "step": 4824 | |
| }, | |
| { | |
| "epoch": 9.001865671641792, | |
| "grad_norm": 0.8798587918281555, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 6.0195, | |
| "num_input_tokens_seen": 1372784, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 9.011194029850746, | |
| "grad_norm": 1.037070631980896, | |
| "learning_rate": 1.4799668266089834e-06, | |
| "loss": 6.2133, | |
| "num_input_tokens_seen": 1374160, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 9.020522388059701, | |
| "grad_norm": 0.8667246103286743, | |
| "learning_rate": 1.452498553486642e-06, | |
| "loss": 6.3108, | |
| "num_input_tokens_seen": 1375472, | |
| "step": 4835 | |
| }, | |
| { | |
| "epoch": 9.029850746268657, | |
| "grad_norm": 0.9855802059173584, | |
| "learning_rate": 1.4252799522286892e-06, | |
| "loss": 6.0475, | |
| "num_input_tokens_seen": 1376976, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 9.039179104477611, | |
| "grad_norm": 1.0825735330581665, | |
| "learning_rate": 1.398311311431308e-06, | |
| "loss": 6.0916, | |
| "num_input_tokens_seen": 1378256, | |
| "step": 4845 | |
| }, | |
| { | |
| "epoch": 9.048507462686567, | |
| "grad_norm": 1.3935683965682983, | |
| "learning_rate": 1.3715929170403623e-06, | |
| "loss": 5.8887, | |
| "num_input_tokens_seen": 1379856, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 9.057835820895523, | |
| "grad_norm": 1.2672241926193237, | |
| "learning_rate": 1.3451250523483976e-06, | |
| "loss": 5.3402, | |
| "num_input_tokens_seen": 1381584, | |
| "step": 4855 | |
| }, | |
| { | |
| "epoch": 9.067164179104477, | |
| "grad_norm": 0.802736759185791, | |
| "learning_rate": 1.3189079979915864e-06, | |
| "loss": 6.4677, | |
| "num_input_tokens_seen": 1382896, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 9.076492537313433, | |
| "grad_norm": 1.5916028022766113, | |
| "learning_rate": 1.2929420319468255e-06, | |
| "loss": 6.3469, | |
| "num_input_tokens_seen": 1384240, | |
| "step": 4865 | |
| }, | |
| { | |
| "epoch": 9.085820895522389, | |
| "grad_norm": 0.8873980641365051, | |
| "learning_rate": 1.2672274295287057e-06, | |
| "loss": 6.7847, | |
| "num_input_tokens_seen": 1385808, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 9.095149253731343, | |
| "grad_norm": 0.9541593790054321, | |
| "learning_rate": 1.2417644633866632e-06, | |
| "loss": 6.7933, | |
| "num_input_tokens_seen": 1387312, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 9.104477611940299, | |
| "grad_norm": 1.1291139125823975, | |
| "learning_rate": 1.2165534035020409e-06, | |
| "loss": 5.9755, | |
| "num_input_tokens_seen": 1388688, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 9.113805970149254, | |
| "grad_norm": 1.0748240947723389, | |
| "learning_rate": 1.1915945171852572e-06, | |
| "loss": 5.6617, | |
| "num_input_tokens_seen": 1390000, | |
| "step": 4885 | |
| }, | |
| { | |
| "epoch": 9.123134328358208, | |
| "grad_norm": 1.4428189992904663, | |
| "learning_rate": 1.1668880690729467e-06, | |
| "loss": 6.112, | |
| "num_input_tokens_seen": 1391408, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 9.132462686567164, | |
| "grad_norm": 0.6945452690124512, | |
| "learning_rate": 1.142434321125177e-06, | |
| "loss": 5.8184, | |
| "num_input_tokens_seen": 1392848, | |
| "step": 4895 | |
| }, | |
| { | |
| "epoch": 9.14179104477612, | |
| "grad_norm": 0.9029362201690674, | |
| "learning_rate": 1.1182335326226533e-06, | |
| "loss": 6.4218, | |
| "num_input_tokens_seen": 1394320, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 9.151119402985074, | |
| "grad_norm": 1.8606007099151611, | |
| "learning_rate": 1.0942859601639794e-06, | |
| "loss": 6.3468, | |
| "num_input_tokens_seen": 1395504, | |
| "step": 4905 | |
| }, | |
| { | |
| "epoch": 9.16044776119403, | |
| "grad_norm": 0.9317994117736816, | |
| "learning_rate": 1.0705918576629364e-06, | |
| "loss": 6.2776, | |
| "num_input_tokens_seen": 1396880, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 9.169776119402986, | |
| "grad_norm": 1.2369999885559082, | |
| "learning_rate": 1.0471514763457814e-06, | |
| "loss": 6.0301, | |
| "num_input_tokens_seen": 1398064, | |
| "step": 4915 | |
| }, | |
| { | |
| "epoch": 9.17910447761194, | |
| "grad_norm": 0.8084278106689453, | |
| "learning_rate": 1.023965064748597e-06, | |
| "loss": 5.9416, | |
| "num_input_tokens_seen": 1399504, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 9.188432835820896, | |
| "grad_norm": 1.182437539100647, | |
| "learning_rate": 1.0010328687146464e-06, | |
| "loss": 5.931, | |
| "num_input_tokens_seen": 1400848, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 9.197761194029852, | |
| "grad_norm": 1.0093863010406494, | |
| "learning_rate": 9.783551313917699e-07, | |
| "loss": 5.2613, | |
| "num_input_tokens_seen": 1402128, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 9.207089552238806, | |
| "grad_norm": 0.9161207675933838, | |
| "learning_rate": 9.559320932298111e-07, | |
| "loss": 5.9859, | |
| "num_input_tokens_seen": 1403632, | |
| "step": 4935 | |
| }, | |
| { | |
| "epoch": 9.216417910447761, | |
| "grad_norm": 1.0224767923355103, | |
| "learning_rate": 9.337639919780539e-07, | |
| "loss": 5.9936, | |
| "num_input_tokens_seen": 1405072, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 9.225746268656717, | |
| "grad_norm": 1.0474905967712402, | |
| "learning_rate": 9.118510626827198e-07, | |
| "loss": 6.1751, | |
| "num_input_tokens_seen": 1406480, | |
| "step": 4945 | |
| }, | |
| { | |
| "epoch": 9.235074626865671, | |
| "grad_norm": 1.0553940534591675, | |
| "learning_rate": 8.901935376844611e-07, | |
| "loss": 5.7156, | |
| "num_input_tokens_seen": 1407792, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 9.244402985074627, | |
| "grad_norm": 0.8949416279792786, | |
| "learning_rate": 8.687916466159157e-07, | |
| "loss": 5.8181, | |
| "num_input_tokens_seen": 1409072, | |
| "step": 4955 | |
| }, | |
| { | |
| "epoch": 9.253731343283581, | |
| "grad_norm": 0.8155070543289185, | |
| "learning_rate": 8.476456163992397e-07, | |
| "loss": 5.9283, | |
| "num_input_tokens_seen": 1410576, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 9.263059701492537, | |
| "grad_norm": 1.0416960716247559, | |
| "learning_rate": 8.267556712437341e-07, | |
| "loss": 5.9073, | |
| "num_input_tokens_seen": 1411856, | |
| "step": 4965 | |
| }, | |
| { | |
| "epoch": 9.272388059701493, | |
| "grad_norm": 0.9014449715614319, | |
| "learning_rate": 8.061220326434582e-07, | |
| "loss": 5.8621, | |
| "num_input_tokens_seen": 1413200, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 9.281716417910447, | |
| "grad_norm": 1.2011274099349976, | |
| "learning_rate": 7.857449193748645e-07, | |
| "loss": 5.8104, | |
| "num_input_tokens_seen": 1414576, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 9.291044776119403, | |
| "grad_norm": 2.0178565979003906, | |
| "learning_rate": 7.656245474945034e-07, | |
| "loss": 5.529, | |
| "num_input_tokens_seen": 1415952, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 9.300373134328359, | |
| "grad_norm": 1.1331008672714233, | |
| "learning_rate": 7.457611303367196e-07, | |
| "loss": 5.9731, | |
| "num_input_tokens_seen": 1417136, | |
| "step": 4985 | |
| }, | |
| { | |
| "epoch": 9.309701492537313, | |
| "grad_norm": 0.9494741559028625, | |
| "learning_rate": 7.261548785113925e-07, | |
| "loss": 5.6118, | |
| "num_input_tokens_seen": 1418736, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 9.319029850746269, | |
| "grad_norm": 1.4031850099563599, | |
| "learning_rate": 7.068059999016969e-07, | |
| "loss": 5.792, | |
| "num_input_tokens_seen": 1420144, | |
| "step": 4995 | |
| }, | |
| { | |
| "epoch": 9.328358208955224, | |
| "grad_norm": 0.8044705986976624, | |
| "learning_rate": 6.877146996619122e-07, | |
| "loss": 6.6212, | |
| "num_input_tokens_seen": 1421552, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 9.337686567164178, | |
| "grad_norm": 1.113943099975586, | |
| "learning_rate": 6.688811802152279e-07, | |
| "loss": 6.3556, | |
| "num_input_tokens_seen": 1423024, | |
| "step": 5005 | |
| }, | |
| { | |
| "epoch": 9.347014925373134, | |
| "grad_norm": 1.2765414714813232, | |
| "learning_rate": 6.503056412516223e-07, | |
| "loss": 6.0487, | |
| "num_input_tokens_seen": 1424208, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 9.35634328358209, | |
| "grad_norm": 1.190150260925293, | |
| "learning_rate": 6.31988279725726e-07, | |
| "loss": 6.3627, | |
| "num_input_tokens_seen": 1425648, | |
| "step": 5015 | |
| }, | |
| { | |
| "epoch": 9.365671641791044, | |
| "grad_norm": 0.84220290184021, | |
| "learning_rate": 6.139292898547366e-07, | |
| "loss": 5.7354, | |
| "num_input_tokens_seen": 1426896, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 9.375, | |
| "grad_norm": 0.8413920998573303, | |
| "learning_rate": 5.961288631163687e-07, | |
| "loss": 6.1586, | |
| "num_input_tokens_seen": 1428336, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 9.384328358208956, | |
| "grad_norm": 0.9460731148719788, | |
| "learning_rate": 5.785871882468069e-07, | |
| "loss": 5.803, | |
| "num_input_tokens_seen": 1429712, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 9.39365671641791, | |
| "grad_norm": 0.9440296292304993, | |
| "learning_rate": 5.613044512387283e-07, | |
| "loss": 6.0366, | |
| "num_input_tokens_seen": 1430928, | |
| "step": 5035 | |
| }, | |
| { | |
| "epoch": 9.402985074626866, | |
| "grad_norm": 0.8335430026054382, | |
| "learning_rate": 5.442808353393059e-07, | |
| "loss": 5.5562, | |
| "num_input_tokens_seen": 1432272, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 9.412313432835822, | |
| "grad_norm": 0.730353593826294, | |
| "learning_rate": 5.275165210482824e-07, | |
| "loss": 6.158, | |
| "num_input_tokens_seen": 1433616, | |
| "step": 5045 | |
| }, | |
| { | |
| "epoch": 9.421641791044776, | |
| "grad_norm": 0.9387096762657166, | |
| "learning_rate": 5.110116861160502e-07, | |
| "loss": 6.1654, | |
| "num_input_tokens_seen": 1435216, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 9.430970149253731, | |
| "grad_norm": 1.0278619527816772, | |
| "learning_rate": 4.947665055417605e-07, | |
| "loss": 5.7938, | |
| "num_input_tokens_seen": 1436432, | |
| "step": 5055 | |
| }, | |
| { | |
| "epoch": 9.440298507462687, | |
| "grad_norm": 1.4740822315216064, | |
| "learning_rate": 4.787811515714919e-07, | |
| "loss": 6.2575, | |
| "num_input_tokens_seen": 1437808, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 9.449626865671641, | |
| "grad_norm": 0.9518821835517883, | |
| "learning_rate": 4.6305579369638475e-07, | |
| "loss": 6.0175, | |
| "num_input_tokens_seen": 1439152, | |
| "step": 5065 | |
| }, | |
| { | |
| "epoch": 9.458955223880597, | |
| "grad_norm": 1.1227983236312866, | |
| "learning_rate": 4.4759059865088494e-07, | |
| "loss": 6.5007, | |
| "num_input_tokens_seen": 1440752, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 9.468283582089553, | |
| "grad_norm": 1.028881311416626, | |
| "learning_rate": 4.323857304109419e-07, | |
| "loss": 6.0571, | |
| "num_input_tokens_seen": 1442128, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 9.477611940298507, | |
| "grad_norm": 1.279516577720642, | |
| "learning_rate": 4.1744135019230193e-07, | |
| "loss": 6.5857, | |
| "num_input_tokens_seen": 1443728, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 9.486940298507463, | |
| "grad_norm": 1.1105010509490967, | |
| "learning_rate": 4.0275761644876787e-07, | |
| "loss": 5.8465, | |
| "num_input_tokens_seen": 1445136, | |
| "step": 5085 | |
| }, | |
| { | |
| "epoch": 9.496268656716419, | |
| "grad_norm": 1.081645131111145, | |
| "learning_rate": 3.883346848705338e-07, | |
| "loss": 5.8709, | |
| "num_input_tokens_seen": 1446736, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "eval_loss": 6.146888256072998, | |
| "eval_runtime": 2.5949, | |
| "eval_samples_per_second": 91.719, | |
| "eval_steps_per_second": 23.122, | |
| "num_input_tokens_seen": 1447376, | |
| "step": 5092 | |
| }, | |
| { | |
| "epoch": 9.505597014925373, | |
| "grad_norm": 1.1067471504211426, | |
| "learning_rate": 3.741727083825475e-07, | |
| "loss": 6.6405, | |
| "num_input_tokens_seen": 1448112, | |
| "step": 5095 | |
| }, | |
| { | |
| "epoch": 9.514925373134329, | |
| "grad_norm": 1.1662929058074951, | |
| "learning_rate": 3.6027183714285595e-07, | |
| "loss": 5.934, | |
| "num_input_tokens_seen": 1449744, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 9.524253731343283, | |
| "grad_norm": 1.2254843711853027, | |
| "learning_rate": 3.4663221854105423e-07, | |
| "loss": 5.9534, | |
| "num_input_tokens_seen": 1451024, | |
| "step": 5105 | |
| }, | |
| { | |
| "epoch": 9.533582089552239, | |
| "grad_norm": 0.9283788204193115, | |
| "learning_rate": 3.332539971966836e-07, | |
| "loss": 5.6455, | |
| "num_input_tokens_seen": 1452304, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 9.542910447761194, | |
| "grad_norm": 1.5924255847930908, | |
| "learning_rate": 3.201373149577247e-07, | |
| "loss": 6.4375, | |
| "num_input_tokens_seen": 1453968, | |
| "step": 5115 | |
| }, | |
| { | |
| "epoch": 9.552238805970148, | |
| "grad_norm": 0.9197564125061035, | |
| "learning_rate": 3.0728231089907634e-07, | |
| "loss": 5.8376, | |
| "num_input_tokens_seen": 1455376, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 9.561567164179104, | |
| "grad_norm": 0.9308797717094421, | |
| "learning_rate": 2.946891213211012e-07, | |
| "loss": 5.6522, | |
| "num_input_tokens_seen": 1456816, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 9.57089552238806, | |
| "grad_norm": 1.0564948320388794, | |
| "learning_rate": 2.823578797481574e-07, | |
| "loss": 6.4457, | |
| "num_input_tokens_seen": 1458320, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 9.580223880597014, | |
| "grad_norm": 1.0667122602462769, | |
| "learning_rate": 2.7028871692720003e-07, | |
| "loss": 5.3658, | |
| "num_input_tokens_seen": 1459632, | |
| "step": 5135 | |
| }, | |
| { | |
| "epoch": 9.58955223880597, | |
| "grad_norm": 1.2637442350387573, | |
| "learning_rate": 2.5848176082639007e-07, | |
| "loss": 5.9502, | |
| "num_input_tokens_seen": 1461008, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 9.598880597014926, | |
| "grad_norm": 1.1092824935913086, | |
| "learning_rate": 2.4693713663372644e-07, | |
| "loss": 6.4102, | |
| "num_input_tokens_seen": 1462224, | |
| "step": 5145 | |
| }, | |
| { | |
| "epoch": 9.60820895522388, | |
| "grad_norm": 0.8753446936607361, | |
| "learning_rate": 2.3565496675574118e-07, | |
| "loss": 6.4049, | |
| "num_input_tokens_seen": 1463664, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 9.617537313432836, | |
| "grad_norm": 0.7987043261528015, | |
| "learning_rate": 2.246353708161758e-07, | |
| "loss": 6.2554, | |
| "num_input_tokens_seen": 1465168, | |
| "step": 5155 | |
| }, | |
| { | |
| "epoch": 9.626865671641792, | |
| "grad_norm": 1.2305909395217896, | |
| "learning_rate": 2.1387846565474045e-07, | |
| "loss": 5.9242, | |
| "num_input_tokens_seen": 1466544, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 9.636194029850746, | |
| "grad_norm": 1.0777299404144287, | |
| "learning_rate": 2.0338436532584827e-07, | |
| "loss": 5.4619, | |
| "num_input_tokens_seen": 1468176, | |
| "step": 5165 | |
| }, | |
| { | |
| "epoch": 9.645522388059701, | |
| "grad_norm": 1.0288116931915283, | |
| "learning_rate": 1.9315318109742465e-07, | |
| "loss": 6.3981, | |
| "num_input_tokens_seen": 1469680, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 9.654850746268657, | |
| "grad_norm": 0.9100699424743652, | |
| "learning_rate": 1.831850214497194e-07, | |
| "loss": 6.2368, | |
| "num_input_tokens_seen": 1471024, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 9.664179104477611, | |
| "grad_norm": 1.372232437133789, | |
| "learning_rate": 1.7347999207415478e-07, | |
| "loss": 6.3969, | |
| "num_input_tokens_seen": 1472464, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 9.673507462686567, | |
| "grad_norm": 1.0139808654785156, | |
| "learning_rate": 1.6403819587221814e-07, | |
| "loss": 5.6938, | |
| "num_input_tokens_seen": 1473904, | |
| "step": 5185 | |
| }, | |
| { | |
| "epoch": 9.682835820895523, | |
| "grad_norm": 0.8533895015716553, | |
| "learning_rate": 1.5485973295434885e-07, | |
| "loss": 6.3233, | |
| "num_input_tokens_seen": 1475408, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 9.692164179104477, | |
| "grad_norm": 0.8795657157897949, | |
| "learning_rate": 1.4594470063890308e-07, | |
| "loss": 6.5344, | |
| "num_input_tokens_seen": 1476784, | |
| "step": 5195 | |
| }, | |
| { | |
| "epoch": 9.701492537313433, | |
| "grad_norm": 0.93294757604599, | |
| "learning_rate": 1.3729319345109348e-07, | |
| "loss": 5.6072, | |
| "num_input_tokens_seen": 1478160, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 9.710820895522389, | |
| "grad_norm": 1.0522263050079346, | |
| "learning_rate": 1.2890530312200945e-07, | |
| "loss": 6.325, | |
| "num_input_tokens_seen": 1479600, | |
| "step": 5205 | |
| }, | |
| { | |
| "epoch": 9.720149253731343, | |
| "grad_norm": 1.0035853385925293, | |
| "learning_rate": 1.207811185876373e-07, | |
| "loss": 6.7264, | |
| "num_input_tokens_seen": 1480944, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 9.729477611940299, | |
| "grad_norm": 1.7949774265289307, | |
| "learning_rate": 1.1292072598791114e-07, | |
| "loss": 6.4153, | |
| "num_input_tokens_seen": 1482448, | |
| "step": 5215 | |
| }, | |
| { | |
| "epoch": 9.738805970149254, | |
| "grad_norm": 0.935214638710022, | |
| "learning_rate": 1.0532420866581072e-07, | |
| "loss": 6.253, | |
| "num_input_tokens_seen": 1483920, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 9.748134328358208, | |
| "grad_norm": 0.9638765454292297, | |
| "learning_rate": 9.799164716646769e-08, | |
| "loss": 6.2562, | |
| "num_input_tokens_seen": 1485232, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 9.757462686567164, | |
| "grad_norm": 1.0886130332946777, | |
| "learning_rate": 9.092311923632191e-08, | |
| "loss": 5.9339, | |
| "num_input_tokens_seen": 1486640, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 9.76679104477612, | |
| "grad_norm": 0.7271848320960999, | |
| "learning_rate": 8.411869982228038e-08, | |
| "loss": 5.9634, | |
| "num_input_tokens_seen": 1488080, | |
| "step": 5235 | |
| }, | |
| { | |
| "epoch": 9.776119402985074, | |
| "grad_norm": 0.9579696655273438, | |
| "learning_rate": 7.757846107094291e-08, | |
| "loss": 6.3032, | |
| "num_input_tokens_seen": 1489456, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 9.78544776119403, | |
| "grad_norm": 1.0699812173843384, | |
| "learning_rate": 7.130247232782216e-08, | |
| "loss": 5.7682, | |
| "num_input_tokens_seen": 1491024, | |
| "step": 5245 | |
| }, | |
| { | |
| "epoch": 9.794776119402986, | |
| "grad_norm": 0.9073269367218018, | |
| "learning_rate": 6.529080013661648e-08, | |
| "loss": 5.2717, | |
| "num_input_tokens_seen": 1492432, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 9.80410447761194, | |
| "grad_norm": 0.9515265226364136, | |
| "learning_rate": 5.954350823850208e-08, | |
| "loss": 6.1187, | |
| "num_input_tokens_seen": 1494064, | |
| "step": 5255 | |
| }, | |
| { | |
| "epoch": 9.813432835820896, | |
| "grad_norm": 1.1247105598449707, | |
| "learning_rate": 5.4060657571453064e-08, | |
| "loss": 5.6411, | |
| "num_input_tokens_seen": 1495536, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 9.822761194029852, | |
| "grad_norm": 0.8148595690727234, | |
| "learning_rate": 4.884230626960307e-08, | |
| "loss": 5.9149, | |
| "num_input_tokens_seen": 1496848, | |
| "step": 5265 | |
| }, | |
| { | |
| "epoch": 9.832089552238806, | |
| "grad_norm": 1.1116526126861572, | |
| "learning_rate": 4.388850966261793e-08, | |
| "loss": 6.223, | |
| "num_input_tokens_seen": 1498352, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 9.841417910447761, | |
| "grad_norm": 0.9703407883644104, | |
| "learning_rate": 3.919932027512674e-08, | |
| "loss": 6.0281, | |
| "num_input_tokens_seen": 1499824, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 9.850746268656717, | |
| "grad_norm": 0.8704729080200195, | |
| "learning_rate": 3.477478782614452e-08, | |
| "loss": 6.8476, | |
| "num_input_tokens_seen": 1501328, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 9.860074626865671, | |
| "grad_norm": 0.8876141905784607, | |
| "learning_rate": 3.061495922855873e-08, | |
| "loss": 6.3168, | |
| "num_input_tokens_seen": 1502640, | |
| "step": 5285 | |
| }, | |
| { | |
| "epoch": 9.869402985074627, | |
| "grad_norm": 1.123094081878662, | |
| "learning_rate": 2.67198785886269e-08, | |
| "loss": 6.3805, | |
| "num_input_tokens_seen": 1504144, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 9.878731343283581, | |
| "grad_norm": 0.7880057096481323, | |
| "learning_rate": 2.3089587205507578e-08, | |
| "loss": 6.0447, | |
| "num_input_tokens_seen": 1505584, | |
| "step": 5295 | |
| }, | |
| { | |
| "epoch": 9.888059701492537, | |
| "grad_norm": 0.9500113129615784, | |
| "learning_rate": 1.972412357083009e-08, | |
| "loss": 5.8787, | |
| "num_input_tokens_seen": 1507184, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 9.897388059701493, | |
| "grad_norm": 1.19023597240448, | |
| "learning_rate": 1.662352336827544e-08, | |
| "loss": 5.76, | |
| "num_input_tokens_seen": 1508656, | |
| "step": 5305 | |
| }, | |
| { | |
| "epoch": 9.906716417910447, | |
| "grad_norm": 0.9171772003173828, | |
| "learning_rate": 1.3787819473207176e-08, | |
| "loss": 5.9212, | |
| "num_input_tokens_seen": 1510192, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 9.916044776119403, | |
| "grad_norm": 0.9838932156562805, | |
| "learning_rate": 1.1217041952313323e-08, | |
| "loss": 6.5124, | |
| "num_input_tokens_seen": 1511632, | |
| "step": 5315 | |
| }, | |
| { | |
| "epoch": 9.925373134328359, | |
| "grad_norm": 0.962877631187439, | |
| "learning_rate": 8.91121806330386e-09, | |
| "loss": 6.0284, | |
| "num_input_tokens_seen": 1513008, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 9.934701492537313, | |
| "grad_norm": 1.5715117454528809, | |
| "learning_rate": 6.870372254602631e-09, | |
| "loss": 6.1722, | |
| "num_input_tokens_seen": 1514416, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 9.944029850746269, | |
| "grad_norm": 1.0709813833236694, | |
| "learning_rate": 5.09452616509476e-09, | |
| "loss": 6.1963, | |
| "num_input_tokens_seen": 1515856, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 9.953358208955224, | |
| "grad_norm": 1.1252517700195312, | |
| "learning_rate": 3.58369862391017e-09, | |
| "loss": 5.8672, | |
| "num_input_tokens_seen": 1517328, | |
| "step": 5335 | |
| }, | |
| { | |
| "epoch": 9.962686567164178, | |
| "grad_norm": 0.7628347873687744, | |
| "learning_rate": 2.3379056502015327e-09, | |
| "loss": 5.6686, | |
| "num_input_tokens_seen": 1518800, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 9.972014925373134, | |
| "grad_norm": 1.0351388454437256, | |
| "learning_rate": 1.357160452988837e-09, | |
| "loss": 5.7095, | |
| "num_input_tokens_seen": 1520208, | |
| "step": 5345 | |
| }, | |
| { | |
| "epoch": 9.98134328358209, | |
| "grad_norm": 0.9517416954040527, | |
| "learning_rate": 6.414734310233872e-10, | |
| "loss": 6.2756, | |
| "num_input_tokens_seen": 1521616, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 9.990671641791044, | |
| "grad_norm": 0.9882842898368835, | |
| "learning_rate": 1.9085217266290312e-10, | |
| "loss": 6.6308, | |
| "num_input_tokens_seen": 1522992, | |
| "step": 5355 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 2.53108549118042, | |
| "learning_rate": 5.3014557993558144e-12, | |
| "loss": 5.5584, | |
| "num_input_tokens_seen": 1524216, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 6.148874282836914, | |
| "eval_runtime": 2.5779, | |
| "eval_samples_per_second": 92.322, | |
| "eval_steps_per_second": 23.274, | |
| "num_input_tokens_seen": 1524216, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "num_input_tokens_seen": 1524216, | |
| "step": 5360, | |
| "total_flos": 6.863475758314291e+16, | |
| "train_loss": 6.878011975003712, | |
| "train_runtime": 559.4489, | |
| "train_samples_per_second": 38.27, | |
| "train_steps_per_second": 9.581 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 5360, | |
| "num_input_tokens_seen": 1524216, | |
| "num_train_epochs": 10, | |
| "save_steps": 268, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.863475758314291e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |