| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023593252329833666, | |
| "eval_steps": 200, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011796626164916834, | |
| "grad_norm": 93.0, | |
| "learning_rate": 1.8912529550827425e-07, | |
| "loss": 7.9641, | |
| "num_input_tokens_seen": 1179648, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002359325232983367, | |
| "grad_norm": 95.0, | |
| "learning_rate": 3.782505910165485e-07, | |
| "loss": 7.9866, | |
| "num_input_tokens_seen": 2359296, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000353898784947505, | |
| "grad_norm": 97.5, | |
| "learning_rate": 5.673758865248227e-07, | |
| "loss": 7.983, | |
| "num_input_tokens_seen": 3538944, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004718650465966734, | |
| "grad_norm": 92.0, | |
| "learning_rate": 7.56501182033097e-07, | |
| "loss": 7.9018, | |
| "num_input_tokens_seen": 4718592, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005898313082458417, | |
| "grad_norm": 102.5, | |
| "learning_rate": 9.456264775413712e-07, | |
| "loss": 8.0784, | |
| "num_input_tokens_seen": 5898240, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00070779756989501, | |
| "grad_norm": 95.0, | |
| "learning_rate": 1.1347517730496454e-06, | |
| "loss": 7.9578, | |
| "num_input_tokens_seen": 7077888, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008257638315441783, | |
| "grad_norm": 93.5, | |
| "learning_rate": 1.3238770685579196e-06, | |
| "loss": 7.975, | |
| "num_input_tokens_seen": 8257536, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009437300931933467, | |
| "grad_norm": 85.0, | |
| "learning_rate": 1.513002364066194e-06, | |
| "loss": 7.8405, | |
| "num_input_tokens_seen": 9437184, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001061696354842515, | |
| "grad_norm": 83.0, | |
| "learning_rate": 1.7021276595744682e-06, | |
| "loss": 7.841, | |
| "num_input_tokens_seen": 10616832, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011796626164916834, | |
| "grad_norm": 82.5, | |
| "learning_rate": 1.8912529550827423e-06, | |
| "loss": 7.9491, | |
| "num_input_tokens_seen": 11796480, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012976288781408518, | |
| "grad_norm": 68.0, | |
| "learning_rate": 2.0803782505910165e-06, | |
| "loss": 7.5612, | |
| "num_input_tokens_seen": 12976128, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00141559513979002, | |
| "grad_norm": 66.5, | |
| "learning_rate": 2.269503546099291e-06, | |
| "loss": 7.5808, | |
| "num_input_tokens_seen": 14155776, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0015335614014391884, | |
| "grad_norm": 57.5, | |
| "learning_rate": 2.4586288416075653e-06, | |
| "loss": 7.4494, | |
| "num_input_tokens_seen": 15335424, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0016515276630883566, | |
| "grad_norm": 51.25, | |
| "learning_rate": 2.6477541371158392e-06, | |
| "loss": 7.4606, | |
| "num_input_tokens_seen": 16515072, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.001769493924737525, | |
| "grad_norm": 42.75, | |
| "learning_rate": 2.836879432624114e-06, | |
| "loss": 7.2804, | |
| "num_input_tokens_seen": 17694720, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0018874601863866935, | |
| "grad_norm": 38.0, | |
| "learning_rate": 3.026004728132388e-06, | |
| "loss": 7.2173, | |
| "num_input_tokens_seen": 18874368, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0020054264480358617, | |
| "grad_norm": 33.75, | |
| "learning_rate": 3.2151300236406624e-06, | |
| "loss": 7.0934, | |
| "num_input_tokens_seen": 20054016, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00212339270968503, | |
| "grad_norm": 30.5, | |
| "learning_rate": 3.4042553191489363e-06, | |
| "loss": 7.1284, | |
| "num_input_tokens_seen": 21233664, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0022413589713341986, | |
| "grad_norm": 26.5, | |
| "learning_rate": 3.5933806146572107e-06, | |
| "loss": 6.932, | |
| "num_input_tokens_seen": 22413312, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0023593252329833668, | |
| "grad_norm": 23.875, | |
| "learning_rate": 3.7825059101654847e-06, | |
| "loss": 6.9163, | |
| "num_input_tokens_seen": 23592960, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002477291494632535, | |
| "grad_norm": 21.625, | |
| "learning_rate": 3.9716312056737595e-06, | |
| "loss": 6.8335, | |
| "num_input_tokens_seen": 24772608, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0025952577562817036, | |
| "grad_norm": 18.625, | |
| "learning_rate": 4.160756501182033e-06, | |
| "loss": 6.6761, | |
| "num_input_tokens_seen": 25952256, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.002713224017930872, | |
| "grad_norm": 16.0, | |
| "learning_rate": 4.349881796690308e-06, | |
| "loss": 6.6474, | |
| "num_input_tokens_seen": 27131904, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00283119027958004, | |
| "grad_norm": 18.0, | |
| "learning_rate": 4.539007092198582e-06, | |
| "loss": 6.6062, | |
| "num_input_tokens_seen": 28311552, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0029491565412292082, | |
| "grad_norm": 17.5, | |
| "learning_rate": 4.728132387706856e-06, | |
| "loss": 6.6435, | |
| "num_input_tokens_seen": 29491200, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003067122802878377, | |
| "grad_norm": 14.25, | |
| "learning_rate": 4.9172576832151305e-06, | |
| "loss": 6.57, | |
| "num_input_tokens_seen": 30670848, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.003185089064527545, | |
| "grad_norm": 13.3125, | |
| "learning_rate": 5.106382978723404e-06, | |
| "loss": 6.4037, | |
| "num_input_tokens_seen": 31850496, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0033030553261767133, | |
| "grad_norm": 10.8125, | |
| "learning_rate": 5.2955082742316784e-06, | |
| "loss": 6.2927, | |
| "num_input_tokens_seen": 33030144, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.003421021587825882, | |
| "grad_norm": 9.75, | |
| "learning_rate": 5.484633569739954e-06, | |
| "loss": 6.2084, | |
| "num_input_tokens_seen": 34209792, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.00353898784947505, | |
| "grad_norm": 10.25, | |
| "learning_rate": 5.673758865248228e-06, | |
| "loss": 6.2349, | |
| "num_input_tokens_seen": 35389440, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0036569541111242184, | |
| "grad_norm": 10.8125, | |
| "learning_rate": 5.862884160756502e-06, | |
| "loss": 6.155, | |
| "num_input_tokens_seen": 36569088, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.003774920372773387, | |
| "grad_norm": 10.0, | |
| "learning_rate": 6.052009456264776e-06, | |
| "loss": 6.1846, | |
| "num_input_tokens_seen": 37748736, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.003892886634422555, | |
| "grad_norm": 8.0, | |
| "learning_rate": 6.24113475177305e-06, | |
| "loss": 6.0656, | |
| "num_input_tokens_seen": 38928384, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004010852896071723, | |
| "grad_norm": 8.0625, | |
| "learning_rate": 6.430260047281325e-06, | |
| "loss": 5.9873, | |
| "num_input_tokens_seen": 40108032, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004128819157720892, | |
| "grad_norm": 8.875, | |
| "learning_rate": 6.619385342789598e-06, | |
| "loss": 6.0008, | |
| "num_input_tokens_seen": 41287680, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00424678541937006, | |
| "grad_norm": 7.34375, | |
| "learning_rate": 6.808510638297873e-06, | |
| "loss": 6.0852, | |
| "num_input_tokens_seen": 42467328, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004364751681019229, | |
| "grad_norm": 6.28125, | |
| "learning_rate": 6.997635933806147e-06, | |
| "loss": 5.8264, | |
| "num_input_tokens_seen": 43646976, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.004482717942668397, | |
| "grad_norm": 6.75, | |
| "learning_rate": 7.186761229314421e-06, | |
| "loss": 5.9511, | |
| "num_input_tokens_seen": 44826624, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.004600684204317565, | |
| "grad_norm": 6.96875, | |
| "learning_rate": 7.375886524822695e-06, | |
| "loss": 5.8042, | |
| "num_input_tokens_seen": 46006272, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0047186504659667335, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 7.565011820330969e-06, | |
| "loss": 5.8955, | |
| "num_input_tokens_seen": 47185920, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004836616727615902, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 7.754137115839244e-06, | |
| "loss": 5.7764, | |
| "num_input_tokens_seen": 48365568, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.00495458298926507, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 7.943262411347519e-06, | |
| "loss": 5.7784, | |
| "num_input_tokens_seen": 49545216, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005072549250914238, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 8.132387706855792e-06, | |
| "loss": 5.7388, | |
| "num_input_tokens_seen": 50724864, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.005190515512563407, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 8.321513002364066e-06, | |
| "loss": 5.7821, | |
| "num_input_tokens_seen": 51904512, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0053084817742125754, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 8.510638297872341e-06, | |
| "loss": 5.6466, | |
| "num_input_tokens_seen": 53084160, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005426448035861744, | |
| "grad_norm": 4.125, | |
| "learning_rate": 8.699763593380616e-06, | |
| "loss": 5.6224, | |
| "num_input_tokens_seen": 54263808, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005544414297510912, | |
| "grad_norm": 5.0, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 5.9019, | |
| "num_input_tokens_seen": 55443456, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.00566238055916008, | |
| "grad_norm": 4.0, | |
| "learning_rate": 9.078014184397164e-06, | |
| "loss": 5.5812, | |
| "num_input_tokens_seen": 56623104, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.005780346820809248, | |
| "grad_norm": 3.796875, | |
| "learning_rate": 9.267139479905439e-06, | |
| "loss": 5.633, | |
| "num_input_tokens_seen": 57802752, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0058983130824584165, | |
| "grad_norm": 3.84375, | |
| "learning_rate": 9.456264775413712e-06, | |
| "loss": 5.5031, | |
| "num_input_tokens_seen": 58982400, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0060162793441075856, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 9.645390070921986e-06, | |
| "loss": 5.5146, | |
| "num_input_tokens_seen": 60162048, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.006134245605756754, | |
| "grad_norm": 3.609375, | |
| "learning_rate": 9.834515366430261e-06, | |
| "loss": 5.3805, | |
| "num_input_tokens_seen": 61341696, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.006252211867405922, | |
| "grad_norm": 3.234375, | |
| "learning_rate": 1.0023640661938535e-05, | |
| "loss": 5.4098, | |
| "num_input_tokens_seen": 62521344, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.00637017812905509, | |
| "grad_norm": 3.40625, | |
| "learning_rate": 1.0212765957446808e-05, | |
| "loss": 5.3773, | |
| "num_input_tokens_seen": 63700992, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.006488144390704258, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 1.0401891252955083e-05, | |
| "loss": 5.3287, | |
| "num_input_tokens_seen": 64880640, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.006606110652353427, | |
| "grad_norm": 3.046875, | |
| "learning_rate": 1.0591016548463357e-05, | |
| "loss": 5.2282, | |
| "num_input_tokens_seen": 66060288, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.006724076914002596, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 1.0780141843971632e-05, | |
| "loss": 5.2967, | |
| "num_input_tokens_seen": 67239936, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.006842043175651764, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 1.0969267139479907e-05, | |
| "loss": 5.1126, | |
| "num_input_tokens_seen": 68419584, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.006960009437300932, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 1.1158392434988181e-05, | |
| "loss": 5.3309, | |
| "num_input_tokens_seen": 69599232, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0070779756989501, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 1.1347517730496456e-05, | |
| "loss": 5.2134, | |
| "num_input_tokens_seen": 70778880, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0071959419605992685, | |
| "grad_norm": 3.546875, | |
| "learning_rate": 1.153664302600473e-05, | |
| "loss": 5.1972, | |
| "num_input_tokens_seen": 71958528, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.007313908222248437, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 1.1725768321513003e-05, | |
| "loss": 5.0123, | |
| "num_input_tokens_seen": 73138176, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.007431874483897605, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 1.1914893617021277e-05, | |
| "loss": 5.1108, | |
| "num_input_tokens_seen": 74317824, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.007549840745546774, | |
| "grad_norm": 3.609375, | |
| "learning_rate": 1.2104018912529552e-05, | |
| "loss": 5.2287, | |
| "num_input_tokens_seen": 75497472, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.007667807007195942, | |
| "grad_norm": 2.703125, | |
| "learning_rate": 1.2293144208037825e-05, | |
| "loss": 5.0902, | |
| "num_input_tokens_seen": 76677120, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.00778577326884511, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 1.24822695035461e-05, | |
| "loss": 5.1526, | |
| "num_input_tokens_seen": 77856768, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.007903739530494279, | |
| "grad_norm": 3.359375, | |
| "learning_rate": 1.2671394799054376e-05, | |
| "loss": 4.8855, | |
| "num_input_tokens_seen": 79036416, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.008021705792143447, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.286052009456265e-05, | |
| "loss": 5.0226, | |
| "num_input_tokens_seen": 80216064, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.008139672053792615, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 1.3049645390070925e-05, | |
| "loss": 5.1366, | |
| "num_input_tokens_seen": 81395712, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.008257638315441783, | |
| "grad_norm": 3.71875, | |
| "learning_rate": 1.3238770685579197e-05, | |
| "loss": 5.0749, | |
| "num_input_tokens_seen": 82575360, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.008375604577090951, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.3427895981087472e-05, | |
| "loss": 4.8899, | |
| "num_input_tokens_seen": 83755008, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.00849357083874012, | |
| "grad_norm": 3.140625, | |
| "learning_rate": 1.3617021276595745e-05, | |
| "loss": 4.8809, | |
| "num_input_tokens_seen": 84934656, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.008611537100389288, | |
| "grad_norm": 3.296875, | |
| "learning_rate": 1.380614657210402e-05, | |
| "loss": 4.8839, | |
| "num_input_tokens_seen": 86114304, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.008729503362038458, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 1.3995271867612294e-05, | |
| "loss": 4.9931, | |
| "num_input_tokens_seen": 87293952, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.008847469623687626, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.418439716312057e-05, | |
| "loss": 4.8041, | |
| "num_input_tokens_seen": 88473600, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.008965435885336794, | |
| "grad_norm": 3.5625, | |
| "learning_rate": 1.4373522458628843e-05, | |
| "loss": 4.8611, | |
| "num_input_tokens_seen": 89653248, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.009083402146985962, | |
| "grad_norm": 3.734375, | |
| "learning_rate": 1.4562647754137118e-05, | |
| "loss": 4.7747, | |
| "num_input_tokens_seen": 90832896, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.00920136840863513, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 1.475177304964539e-05, | |
| "loss": 4.6884, | |
| "num_input_tokens_seen": 92012544, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.009319334670284299, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 1.4940898345153665e-05, | |
| "loss": 4.6617, | |
| "num_input_tokens_seen": 93192192, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.009437300931933467, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.5130023640661939e-05, | |
| "loss": 4.6174, | |
| "num_input_tokens_seen": 94371840, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.009555267193582635, | |
| "grad_norm": 3.71875, | |
| "learning_rate": 1.5319148936170214e-05, | |
| "loss": 4.5483, | |
| "num_input_tokens_seen": 95551488, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.009673233455231803, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 1.5508274231678487e-05, | |
| "loss": 4.604, | |
| "num_input_tokens_seen": 96731136, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.009791199716880972, | |
| "grad_norm": 3.09375, | |
| "learning_rate": 1.5697399527186764e-05, | |
| "loss": 4.5806, | |
| "num_input_tokens_seen": 97910784, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.00990916597853014, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 1.5886524822695038e-05, | |
| "loss": 4.4723, | |
| "num_input_tokens_seen": 99090432, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.010027132240179308, | |
| "grad_norm": 3.8125, | |
| "learning_rate": 1.607565011820331e-05, | |
| "loss": 4.4723, | |
| "num_input_tokens_seen": 100270080, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.010145098501828476, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 1.6264775413711585e-05, | |
| "loss": 4.4519, | |
| "num_input_tokens_seen": 101449728, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.010263064763477646, | |
| "grad_norm": 5.53125, | |
| "learning_rate": 1.645390070921986e-05, | |
| "loss": 4.4077, | |
| "num_input_tokens_seen": 102629376, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.010381031025126814, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 1.6643026004728132e-05, | |
| "loss": 4.5295, | |
| "num_input_tokens_seen": 103809024, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.010498997286775983, | |
| "grad_norm": 3.484375, | |
| "learning_rate": 1.683215130023641e-05, | |
| "loss": 4.3235, | |
| "num_input_tokens_seen": 104988672, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.010616963548425151, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 1.7021276595744682e-05, | |
| "loss": 4.3245, | |
| "num_input_tokens_seen": 106168320, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.010734929810074319, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 1.7210401891252956e-05, | |
| "loss": 4.2554, | |
| "num_input_tokens_seen": 107347968, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.010852896071723487, | |
| "grad_norm": 3.671875, | |
| "learning_rate": 1.7399527186761233e-05, | |
| "loss": 4.2572, | |
| "num_input_tokens_seen": 108527616, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.010970862333372655, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.7588652482269506e-05, | |
| "loss": 4.2442, | |
| "num_input_tokens_seen": 109707264, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.011088828595021824, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 4.3006, | |
| "num_input_tokens_seen": 110886912, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.011206794856670992, | |
| "grad_norm": 3.171875, | |
| "learning_rate": 1.7966903073286054e-05, | |
| "loss": 4.2813, | |
| "num_input_tokens_seen": 112066560, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.01132476111832016, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 1.8156028368794327e-05, | |
| "loss": 4.1186, | |
| "num_input_tokens_seen": 113246208, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.011442727379969328, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 1.83451536643026e-05, | |
| "loss": 4.1652, | |
| "num_input_tokens_seen": 114425856, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.011560693641618497, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.8534278959810878e-05, | |
| "loss": 4.1923, | |
| "num_input_tokens_seen": 115605504, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.011678659903267665, | |
| "grad_norm": 3.359375, | |
| "learning_rate": 1.872340425531915e-05, | |
| "loss": 4.0728, | |
| "num_input_tokens_seen": 116785152, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.011796626164916833, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 1.8912529550827425e-05, | |
| "loss": 4.2189, | |
| "num_input_tokens_seen": 117964800, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.011914592426566003, | |
| "grad_norm": 3.109375, | |
| "learning_rate": 1.91016548463357e-05, | |
| "loss": 4.0632, | |
| "num_input_tokens_seen": 119144448, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.012032558688215171, | |
| "grad_norm": 4.40625, | |
| "learning_rate": 1.929078014184397e-05, | |
| "loss": 3.8775, | |
| "num_input_tokens_seen": 120324096, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.01215052494986434, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 1.9479905437352245e-05, | |
| "loss": 3.8658, | |
| "num_input_tokens_seen": 121503744, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.012268491211513508, | |
| "grad_norm": 3.703125, | |
| "learning_rate": 1.9669030732860522e-05, | |
| "loss": 3.9888, | |
| "num_input_tokens_seen": 122683392, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.012386457473162676, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 1.9858156028368796e-05, | |
| "loss": 3.9439, | |
| "num_input_tokens_seen": 123863040, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.012504423734811844, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 2.004728132387707e-05, | |
| "loss": 4.0098, | |
| "num_input_tokens_seen": 125042688, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.012622389996461012, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 2.0236406619385343e-05, | |
| "loss": 3.9454, | |
| "num_input_tokens_seen": 126222336, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.01274035625811018, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 2.0425531914893616e-05, | |
| "loss": 3.8491, | |
| "num_input_tokens_seen": 127401984, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.012858322519759349, | |
| "grad_norm": 3.59375, | |
| "learning_rate": 2.0614657210401893e-05, | |
| "loss": 3.9602, | |
| "num_input_tokens_seen": 128581632, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.012976288781408517, | |
| "grad_norm": 5.25, | |
| "learning_rate": 2.0803782505910167e-05, | |
| "loss": 3.9542, | |
| "num_input_tokens_seen": 129761280, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.013094255043057685, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 2.099290780141844e-05, | |
| "loss": 3.7846, | |
| "num_input_tokens_seen": 130940928, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.013212221304706853, | |
| "grad_norm": 3.484375, | |
| "learning_rate": 2.1182033096926714e-05, | |
| "loss": 3.9128, | |
| "num_input_tokens_seen": 132120576, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.013330187566356021, | |
| "grad_norm": 7.4375, | |
| "learning_rate": 2.137115839243499e-05, | |
| "loss": 3.7365, | |
| "num_input_tokens_seen": 133300224, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.013448153828005191, | |
| "grad_norm": 3.6875, | |
| "learning_rate": 2.1560283687943264e-05, | |
| "loss": 3.8298, | |
| "num_input_tokens_seen": 134479872, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.01356612008965436, | |
| "grad_norm": 11.25, | |
| "learning_rate": 2.1749408983451538e-05, | |
| "loss": 3.9192, | |
| "num_input_tokens_seen": 135659520, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.013684086351303528, | |
| "grad_norm": 9.875, | |
| "learning_rate": 2.1938534278959815e-05, | |
| "loss": 3.7628, | |
| "num_input_tokens_seen": 136839168, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.013802052612952696, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 2.2127659574468088e-05, | |
| "loss": 3.7212, | |
| "num_input_tokens_seen": 138018816, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.013920018874601864, | |
| "grad_norm": 6.875, | |
| "learning_rate": 2.2316784869976362e-05, | |
| "loss": 3.8291, | |
| "num_input_tokens_seen": 139198464, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.014037985136251032, | |
| "grad_norm": 3.984375, | |
| "learning_rate": 2.2505910165484635e-05, | |
| "loss": 3.7104, | |
| "num_input_tokens_seen": 140378112, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.0141559513979002, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 2.2695035460992912e-05, | |
| "loss": 3.6898, | |
| "num_input_tokens_seen": 141557760, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.014273917659549369, | |
| "grad_norm": 3.828125, | |
| "learning_rate": 2.2884160756501186e-05, | |
| "loss": 3.61, | |
| "num_input_tokens_seen": 142737408, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.014391883921198537, | |
| "grad_norm": 4.875, | |
| "learning_rate": 2.307328605200946e-05, | |
| "loss": 3.6886, | |
| "num_input_tokens_seen": 143917056, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.014509850182847705, | |
| "grad_norm": 4.75, | |
| "learning_rate": 2.326241134751773e-05, | |
| "loss": 3.6435, | |
| "num_input_tokens_seen": 145096704, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.014627816444496873, | |
| "grad_norm": 3.75, | |
| "learning_rate": 2.3451536643026006e-05, | |
| "loss": 3.6619, | |
| "num_input_tokens_seen": 146276352, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.014745782706146042, | |
| "grad_norm": 5.375, | |
| "learning_rate": 2.364066193853428e-05, | |
| "loss": 3.631, | |
| "num_input_tokens_seen": 147456000, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.01486374896779521, | |
| "grad_norm": 4.125, | |
| "learning_rate": 2.3829787234042553e-05, | |
| "loss": 3.6482, | |
| "num_input_tokens_seen": 148635648, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.014981715229444378, | |
| "grad_norm": 7.78125, | |
| "learning_rate": 2.4018912529550827e-05, | |
| "loss": 3.6785, | |
| "num_input_tokens_seen": 149815296, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.015099681491093548, | |
| "grad_norm": 7.0, | |
| "learning_rate": 2.4208037825059104e-05, | |
| "loss": 3.6113, | |
| "num_input_tokens_seen": 150994944, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.015217647752742716, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 2.4397163120567377e-05, | |
| "loss": 3.6015, | |
| "num_input_tokens_seen": 152174592, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.015335614014391884, | |
| "grad_norm": 4.1875, | |
| "learning_rate": 2.458628841607565e-05, | |
| "loss": 3.5241, | |
| "num_input_tokens_seen": 153354240, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.015453580276041053, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 2.4775413711583928e-05, | |
| "loss": 3.6007, | |
| "num_input_tokens_seen": 154533888, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.01557154653769022, | |
| "grad_norm": 3.046875, | |
| "learning_rate": 2.49645390070922e-05, | |
| "loss": 3.5949, | |
| "num_input_tokens_seen": 155713536, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.01568951279933939, | |
| "grad_norm": 3.265625, | |
| "learning_rate": 2.5153664302600475e-05, | |
| "loss": 3.5403, | |
| "num_input_tokens_seen": 156893184, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.015807479060988557, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 2.5342789598108752e-05, | |
| "loss": 3.5399, | |
| "num_input_tokens_seen": 158072832, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.015925445322637725, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 2.5531914893617025e-05, | |
| "loss": 3.5408, | |
| "num_input_tokens_seen": 159252480, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.016043411584286894, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 2.57210401891253e-05, | |
| "loss": 3.4678, | |
| "num_input_tokens_seen": 160432128, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.016161377845936062, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 2.5910165484633572e-05, | |
| "loss": 3.6019, | |
| "num_input_tokens_seen": 161611776, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.01627934410758523, | |
| "grad_norm": 1.96875, | |
| "learning_rate": 2.609929078014185e-05, | |
| "loss": 3.4525, | |
| "num_input_tokens_seen": 162791424, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.0163973103692344, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 2.628841607565012e-05, | |
| "loss": 3.557, | |
| "num_input_tokens_seen": 163971072, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.016515276630883566, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 2.6477541371158393e-05, | |
| "loss": 3.5324, | |
| "num_input_tokens_seen": 165150720, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.016633242892532735, | |
| "grad_norm": 3.703125, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 3.4707, | |
| "num_input_tokens_seen": 166330368, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.016751209154181903, | |
| "grad_norm": 3.53125, | |
| "learning_rate": 2.6855791962174944e-05, | |
| "loss": 3.3545, | |
| "num_input_tokens_seen": 167510016, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.01686917541583107, | |
| "grad_norm": 1.7890625, | |
| "learning_rate": 2.7044917257683217e-05, | |
| "loss": 3.4051, | |
| "num_input_tokens_seen": 168689664, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.01698714167748024, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 2.723404255319149e-05, | |
| "loss": 3.4119, | |
| "num_input_tokens_seen": 169869312, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.017105107939129408, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 2.7423167848699764e-05, | |
| "loss": 3.5149, | |
| "num_input_tokens_seen": 171048960, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.017223074200778576, | |
| "grad_norm": 3.671875, | |
| "learning_rate": 2.761229314420804e-05, | |
| "loss": 3.3442, | |
| "num_input_tokens_seen": 172228608, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.017341040462427744, | |
| "grad_norm": 3.453125, | |
| "learning_rate": 2.7801418439716315e-05, | |
| "loss": 3.3277, | |
| "num_input_tokens_seen": 173408256, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.017459006724076916, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 2.7990543735224588e-05, | |
| "loss": 3.3905, | |
| "num_input_tokens_seen": 174587904, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.017576972985726084, | |
| "grad_norm": 2.0, | |
| "learning_rate": 2.8179669030732865e-05, | |
| "loss": 3.276, | |
| "num_input_tokens_seen": 175767552, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.017694939247375252, | |
| "grad_norm": 4.0, | |
| "learning_rate": 2.836879432624114e-05, | |
| "loss": 3.3211, | |
| "num_input_tokens_seen": 176947200, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01781290550902442, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 2.8557919621749412e-05, | |
| "loss": 3.3483, | |
| "num_input_tokens_seen": 178126848, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.01793087177067359, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 2.8747044917257686e-05, | |
| "loss": 3.3391, | |
| "num_input_tokens_seen": 179306496, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.018048838032322757, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 2.8936170212765963e-05, | |
| "loss": 3.4719, | |
| "num_input_tokens_seen": 180486144, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.018166804293971925, | |
| "grad_norm": 3.171875, | |
| "learning_rate": 2.9125295508274236e-05, | |
| "loss": 3.2727, | |
| "num_input_tokens_seen": 181665792, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.018284770555621093, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 2.9314420803782506e-05, | |
| "loss": 3.284, | |
| "num_input_tokens_seen": 182845440, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.01840273681727026, | |
| "grad_norm": 3.25, | |
| "learning_rate": 2.950354609929078e-05, | |
| "loss": 3.2279, | |
| "num_input_tokens_seen": 184025088, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.01852070307891943, | |
| "grad_norm": 3.71875, | |
| "learning_rate": 2.9692671394799057e-05, | |
| "loss": 3.2438, | |
| "num_input_tokens_seen": 185204736, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.018638669340568598, | |
| "grad_norm": 3.875, | |
| "learning_rate": 2.988179669030733e-05, | |
| "loss": 3.3257, | |
| "num_input_tokens_seen": 186384384, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.018756635602217766, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 3.0070921985815604e-05, | |
| "loss": 3.2727, | |
| "num_input_tokens_seen": 187564032, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.018874601863866934, | |
| "grad_norm": 4.125, | |
| "learning_rate": 3.0260047281323877e-05, | |
| "loss": 3.245, | |
| "num_input_tokens_seen": 188743680, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.018992568125516102, | |
| "grad_norm": 3.640625, | |
| "learning_rate": 3.0449172576832154e-05, | |
| "loss": 3.1904, | |
| "num_input_tokens_seen": 189923328, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.01911053438716527, | |
| "grad_norm": 2.625, | |
| "learning_rate": 3.063829787234043e-05, | |
| "loss": 3.2754, | |
| "num_input_tokens_seen": 191102976, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.01922850064881444, | |
| "grad_norm": 3.578125, | |
| "learning_rate": 3.0827423167848705e-05, | |
| "loss": 3.1889, | |
| "num_input_tokens_seen": 192282624, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.019346466910463607, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 3.1016548463356975e-05, | |
| "loss": 3.2809, | |
| "num_input_tokens_seen": 193462272, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.019464433172112775, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 3.120567375886525e-05, | |
| "loss": 3.1929, | |
| "num_input_tokens_seen": 194641920, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.019582399433761943, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 3.139479905437353e-05, | |
| "loss": 3.1474, | |
| "num_input_tokens_seen": 195821568, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.01970036569541111, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 3.15839243498818e-05, | |
| "loss": 3.0433, | |
| "num_input_tokens_seen": 197001216, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.01981833195706028, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 3.1773049645390076e-05, | |
| "loss": 3.1527, | |
| "num_input_tokens_seen": 198180864, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.019936298218709448, | |
| "grad_norm": 3.5, | |
| "learning_rate": 3.196217494089835e-05, | |
| "loss": 3.2145, | |
| "num_input_tokens_seen": 199360512, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.020054264480358616, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 3.215130023640662e-05, | |
| "loss": 3.2642, | |
| "num_input_tokens_seen": 200540160, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.020172230742007784, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 3.234042553191489e-05, | |
| "loss": 3.1286, | |
| "num_input_tokens_seen": 201719808, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.020290197003656953, | |
| "grad_norm": 8.1875, | |
| "learning_rate": 3.252955082742317e-05, | |
| "loss": 3.1274, | |
| "num_input_tokens_seen": 202899456, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 6.375, | |
| "learning_rate": 3.271867612293144e-05, | |
| "loss": 3.096, | |
| "num_input_tokens_seen": 204079104, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.020526129526955292, | |
| "grad_norm": 5.8125, | |
| "learning_rate": 3.290780141843972e-05, | |
| "loss": 3.1647, | |
| "num_input_tokens_seen": 205258752, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.02064409578860446, | |
| "grad_norm": 5.6875, | |
| "learning_rate": 3.3096926713947994e-05, | |
| "loss": 3.269, | |
| "num_input_tokens_seen": 206438400, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.02076206205025363, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 3.3286052009456264e-05, | |
| "loss": 3.2106, | |
| "num_input_tokens_seen": 207618048, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.020880028311902797, | |
| "grad_norm": 3.109375, | |
| "learning_rate": 3.347517730496454e-05, | |
| "loss": 3.1545, | |
| "num_input_tokens_seen": 208797696, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.020997994573551965, | |
| "grad_norm": 6.6875, | |
| "learning_rate": 3.366430260047282e-05, | |
| "loss": 3.1045, | |
| "num_input_tokens_seen": 209977344, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.021115960835201134, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 3.385342789598109e-05, | |
| "loss": 3.0496, | |
| "num_input_tokens_seen": 211156992, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.021233927096850302, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 3.4042553191489365e-05, | |
| "loss": 3.081, | |
| "num_input_tokens_seen": 212336640, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02135189335849947, | |
| "grad_norm": 3.921875, | |
| "learning_rate": 3.423167848699764e-05, | |
| "loss": 3.0552, | |
| "num_input_tokens_seen": 213516288, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.021469859620148638, | |
| "grad_norm": 4.5, | |
| "learning_rate": 3.442080378250591e-05, | |
| "loss": 3.0172, | |
| "num_input_tokens_seen": 214695936, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.021587825881797806, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 3.460992907801419e-05, | |
| "loss": 3.1379, | |
| "num_input_tokens_seen": 215875584, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.021705792143446975, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 3.4799054373522466e-05, | |
| "loss": 3.1235, | |
| "num_input_tokens_seen": 217055232, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.021823758405096143, | |
| "grad_norm": 3.78125, | |
| "learning_rate": 3.4988179669030736e-05, | |
| "loss": 3.1189, | |
| "num_input_tokens_seen": 218234880, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.02194172466674531, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 3.517730496453901e-05, | |
| "loss": 3.0035, | |
| "num_input_tokens_seen": 219414528, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.02205969092839448, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 3.536643026004728e-05, | |
| "loss": 3.0478, | |
| "num_input_tokens_seen": 220594176, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.022177657190043647, | |
| "grad_norm": 5.8125, | |
| "learning_rate": 3.555555555555555e-05, | |
| "loss": 3.0777, | |
| "num_input_tokens_seen": 221773824, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.022295623451692816, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 3.574468085106383e-05, | |
| "loss": 3.0665, | |
| "num_input_tokens_seen": 222953472, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.022413589713341984, | |
| "grad_norm": 4.25, | |
| "learning_rate": 3.593380614657211e-05, | |
| "loss": 3.0271, | |
| "num_input_tokens_seen": 224133120, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.022531555974991152, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 3.612293144208038e-05, | |
| "loss": 3.033, | |
| "num_input_tokens_seen": 225312768, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.02264952223664032, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 3.6312056737588654e-05, | |
| "loss": 3.143, | |
| "num_input_tokens_seen": 226492416, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.02276748849828949, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 3.650118203309693e-05, | |
| "loss": 3.0347, | |
| "num_input_tokens_seen": 227672064, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.022885454759938657, | |
| "grad_norm": 4.65625, | |
| "learning_rate": 3.66903073286052e-05, | |
| "loss": 3.07, | |
| "num_input_tokens_seen": 228851712, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.023003421021587825, | |
| "grad_norm": 3.90625, | |
| "learning_rate": 3.687943262411348e-05, | |
| "loss": 3.0225, | |
| "num_input_tokens_seen": 230031360, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.023121387283236993, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 3.7068557919621755e-05, | |
| "loss": 3.0222, | |
| "num_input_tokens_seen": 231211008, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.02323935354488616, | |
| "grad_norm": 3.84375, | |
| "learning_rate": 3.7257683215130025e-05, | |
| "loss": 2.9755, | |
| "num_input_tokens_seen": 232390656, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.02335731980653533, | |
| "grad_norm": 5.0, | |
| "learning_rate": 3.74468085106383e-05, | |
| "loss": 3.0163, | |
| "num_input_tokens_seen": 233570304, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.023475286068184498, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 3.763593380614658e-05, | |
| "loss": 2.9553, | |
| "num_input_tokens_seen": 234749952, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.023593252329833666, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 3.782505910165485e-05, | |
| "loss": 3.015, | |
| "num_input_tokens_seen": 235929600, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.023593252329833666, | |
| "eval_wikipedia_loss": 2.9615590572357178, | |
| "eval_wikipedia_runtime": 172.3085, | |
| "eval_wikipedia_samples_per_second": 4.074, | |
| "eval_wikipedia_steps_per_second": 0.174, | |
| "num_input_tokens_seen": 235929600, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.023593252329833666, | |
| "eval_toxicity_loss": 4.73836088180542, | |
| "eval_toxicity_runtime": 0.999, | |
| "eval_toxicity_samples_per_second": 2.002, | |
| "eval_toxicity_steps_per_second": 1.001, | |
| "num_input_tokens_seen": 235929600, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 8477, | |
| "num_input_tokens_seen": 235929600, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.865862240160973e+18, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |