| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9927710843373494, | |
| "eval_steps": 500, | |
| "global_step": 103, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00963855421686747, | |
| "grad_norm": 0.7313525676727295, | |
| "learning_rate": 4.998837209058379e-05, | |
| "loss": 1.2542, | |
| "num_input_tokens_seen": 2097152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01927710843373494, | |
| "grad_norm": 0.7724310159683228, | |
| "learning_rate": 4.9953499178997346e-05, | |
| "loss": 1.2368, | |
| "num_input_tokens_seen": 4194304, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02891566265060241, | |
| "grad_norm": 0.7648841738700867, | |
| "learning_rate": 4.9895413705165234e-05, | |
| "loss": 1.1874, | |
| "num_input_tokens_seen": 6291456, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03855421686746988, | |
| "grad_norm": 0.6278133392333984, | |
| "learning_rate": 4.98141697020977e-05, | |
| "loss": 1.1094, | |
| "num_input_tokens_seen": 8388608, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04819277108433735, | |
| "grad_norm": 0.5364275574684143, | |
| "learning_rate": 4.970984274562741e-05, | |
| "loss": 1.0771, | |
| "num_input_tokens_seen": 10485760, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05783132530120482, | |
| "grad_norm": 0.4229595363140106, | |
| "learning_rate": 4.958252988410631e-05, | |
| "loss": 1.0465, | |
| "num_input_tokens_seen": 12582912, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06746987951807229, | |
| "grad_norm": 0.3765781819820404, | |
| "learning_rate": 4.9432349548128124e-05, | |
| "loss": 1.0828, | |
| "num_input_tokens_seen": 14680064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07710843373493977, | |
| "grad_norm": 0.3276417553424835, | |
| "learning_rate": 4.925944144036026e-05, | |
| "loss": 1.0584, | |
| "num_input_tokens_seen": 16777216, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08674698795180723, | |
| "grad_norm": 0.2784905433654785, | |
| "learning_rate": 4.90639664055879e-05, | |
| "loss": 1.0203, | |
| "num_input_tokens_seen": 18874368, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0963855421686747, | |
| "grad_norm": 0.24603000283241272, | |
| "learning_rate": 4.884610628109082e-05, | |
| "loss": 1.0074, | |
| "num_input_tokens_seen": 20971520, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10602409638554217, | |
| "grad_norm": 0.21994058787822723, | |
| "learning_rate": 4.860606372749247e-05, | |
| "loss": 1.0076, | |
| "num_input_tokens_seen": 23068672, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11566265060240964, | |
| "grad_norm": 0.1868952363729477, | |
| "learning_rate": 4.8344062040238395e-05, | |
| "loss": 0.9358, | |
| "num_input_tokens_seen": 25165824, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12530120481927712, | |
| "grad_norm": 0.1867723912000656, | |
| "learning_rate": 4.806034494187949e-05, | |
| "loss": 0.9963, | |
| "num_input_tokens_seen": 27262976, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13493975903614458, | |
| "grad_norm": 0.1620677411556244, | |
| "learning_rate": 4.775517635535332e-05, | |
| "loss": 0.9646, | |
| "num_input_tokens_seen": 29360128, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14457831325301204, | |
| "grad_norm": 0.14515823125839233, | |
| "learning_rate": 4.742884015847436e-05, | |
| "loss": 0.9749, | |
| "num_input_tokens_seen": 31457280, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15421686746987953, | |
| "grad_norm": 0.12092889100313187, | |
| "learning_rate": 4.708163991986152e-05, | |
| "loss": 0.9222, | |
| "num_input_tokens_seen": 33554432, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.163855421686747, | |
| "grad_norm": 0.11052511632442474, | |
| "learning_rate": 4.6713898616548724e-05, | |
| "loss": 0.9341, | |
| "num_input_tokens_seen": 35651584, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17349397590361446, | |
| "grad_norm": 0.09935510903596878, | |
| "learning_rate": 4.6325958333541044e-05, | |
| "loss": 0.9262, | |
| "num_input_tokens_seen": 37748736, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18313253012048192, | |
| "grad_norm": 0.09447427093982697, | |
| "learning_rate": 4.591817994559605e-05, | |
| "loss": 0.9563, | |
| "num_input_tokens_seen": 39845888, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1927710843373494, | |
| "grad_norm": 0.08354643732309341, | |
| "learning_rate": 4.5490942781526316e-05, | |
| "loss": 0.9378, | |
| "num_input_tokens_seen": 41943040, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20240963855421687, | |
| "grad_norm": 0.08155971020460129, | |
| "learning_rate": 4.504464427133527e-05, | |
| "loss": 0.9421, | |
| "num_input_tokens_seen": 44040192, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21204819277108433, | |
| "grad_norm": 0.07310276478528976, | |
| "learning_rate": 4.457969957651484e-05, | |
| "loss": 0.9219, | |
| "num_input_tokens_seen": 46137344, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2216867469879518, | |
| "grad_norm": 0.06967604160308838, | |
| "learning_rate": 4.409654120384862e-05, | |
| "loss": 0.9108, | |
| "num_input_tokens_seen": 48234496, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.23132530120481928, | |
| "grad_norm": 0.06935103982686996, | |
| "learning_rate": 4.35956186030799e-05, | |
| "loss": 0.9331, | |
| "num_input_tokens_seen": 50331648, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.24096385542168675, | |
| "grad_norm": 0.06473473459482193, | |
| "learning_rate": 4.307739774881878e-05, | |
| "loss": 0.9405, | |
| "num_input_tokens_seen": 52428800, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.25060240963855424, | |
| "grad_norm": 0.06642216444015503, | |
| "learning_rate": 4.254236070707733e-05, | |
| "loss": 0.9667, | |
| "num_input_tokens_seen": 54525952, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.26024096385542167, | |
| "grad_norm": 0.06075766310095787, | |
| "learning_rate": 4.1991005186836005e-05, | |
| "loss": 0.935, | |
| "num_input_tokens_seen": 56623104, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.26987951807228916, | |
| "grad_norm": 0.05267713591456413, | |
| "learning_rate": 4.142384407705846e-05, | |
| "loss": 0.8985, | |
| "num_input_tokens_seen": 58720256, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.27951807228915665, | |
| "grad_norm": 0.052896805107593536, | |
| "learning_rate": 4.084140496958538e-05, | |
| "loss": 0.8879, | |
| "num_input_tokens_seen": 60817408, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": 0.054511502385139465, | |
| "learning_rate": 4.024422966835136e-05, | |
| "loss": 0.9086, | |
| "num_input_tokens_seen": 62914560, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2987951807228916, | |
| "grad_norm": 0.05628665164113045, | |
| "learning_rate": 3.963287368538106e-05, | |
| "loss": 0.9437, | |
| "num_input_tokens_seen": 65011712, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.30843373493975906, | |
| "grad_norm": 0.05085182189941406, | |
| "learning_rate": 3.900790572403376e-05, | |
| "loss": 0.916, | |
| "num_input_tokens_seen": 67108864, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3180722891566265, | |
| "grad_norm": 0.05213847756385803, | |
| "learning_rate": 3.836990714997686e-05, | |
| "loss": 0.9433, | |
| "num_input_tokens_seen": 69206016, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.327710843373494, | |
| "grad_norm": 0.050841424614191055, | |
| "learning_rate": 3.7719471450380514e-05, | |
| "loss": 0.9276, | |
| "num_input_tokens_seen": 71303168, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3373493975903614, | |
| "grad_norm": 0.050464361906051636, | |
| "learning_rate": 3.7057203681836406e-05, | |
| "loss": 0.918, | |
| "num_input_tokens_seen": 73400320, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3469879518072289, | |
| "grad_norm": 0.047950029373168945, | |
| "learning_rate": 3.638371990751428e-05, | |
| "loss": 0.8979, | |
| "num_input_tokens_seen": 75497472, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3566265060240964, | |
| "grad_norm": 0.04698570817708969, | |
| "learning_rate": 3.569964662407983e-05, | |
| "loss": 0.9065, | |
| "num_input_tokens_seen": 77594624, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.36626506024096384, | |
| "grad_norm": 0.047698017209768295, | |
| "learning_rate": 3.500562017890695e-05, | |
| "loss": 0.9405, | |
| "num_input_tokens_seen": 79691776, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3759036144578313, | |
| "grad_norm": 0.04816911369562149, | |
| "learning_rate": 3.430228617812661e-05, | |
| "loss": 0.9263, | |
| "num_input_tokens_seen": 81788928, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3855421686746988, | |
| "grad_norm": 0.04724708944559097, | |
| "learning_rate": 3.3590298886062833e-05, | |
| "loss": 0.9243, | |
| "num_input_tokens_seen": 83886080, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.39518072289156625, | |
| "grad_norm": 0.04571336507797241, | |
| "learning_rate": 3.2870320616614626e-05, | |
| "loss": 0.9201, | |
| "num_input_tokens_seen": 85983232, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.40481927710843374, | |
| "grad_norm": 0.045291587710380554, | |
| "learning_rate": 3.21430211171499e-05, | |
| "loss": 0.9015, | |
| "num_input_tokens_seen": 88080384, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.41445783132530123, | |
| "grad_norm": 0.04433094710111618, | |
| "learning_rate": 3.140907694548451e-05, | |
| "loss": 0.9104, | |
| "num_input_tokens_seen": 90177536, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.42409638554216866, | |
| "grad_norm": 0.04381513595581055, | |
| "learning_rate": 3.066917084052603e-05, | |
| "loss": 0.9194, | |
| "num_input_tokens_seen": 92274688, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.43373493975903615, | |
| "grad_norm": 0.04662506654858589, | |
| "learning_rate": 2.9923991087167658e-05, | |
| "loss": 0.9575, | |
| "num_input_tokens_seen": 94371840, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4433734939759036, | |
| "grad_norm": 0.044867418706417084, | |
| "learning_rate": 2.9174230876023058e-05, | |
| "loss": 0.8922, | |
| "num_input_tokens_seen": 96468992, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4530120481927711, | |
| "grad_norm": 0.04386744648218155, | |
| "learning_rate": 2.8420587658597757e-05, | |
| "loss": 0.9125, | |
| "num_input_tokens_seen": 98566144, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.46265060240963857, | |
| "grad_norm": 0.044598404318094254, | |
| "learning_rate": 2.7663762498496905e-05, | |
| "loss": 0.8989, | |
| "num_input_tokens_seen": 100663296, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.472289156626506, | |
| "grad_norm": 0.04060734063386917, | |
| "learning_rate": 2.6904459419272955e-05, | |
| "loss": 0.8719, | |
| "num_input_tokens_seen": 102760448, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4819277108433735, | |
| "grad_norm": 0.045836638659238815, | |
| "learning_rate": 2.6143384749519866e-05, | |
| "loss": 0.9074, | |
| "num_input_tokens_seen": 104857600, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.491566265060241, | |
| "grad_norm": 0.04294141009449959, | |
| "learning_rate": 2.538124646582315e-05, | |
| "loss": 0.8911, | |
| "num_input_tokens_seen": 106954752, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5012048192771085, | |
| "grad_norm": 0.045149002224206924, | |
| "learning_rate": 2.4618753534176856e-05, | |
| "loss": 0.9314, | |
| "num_input_tokens_seen": 109051904, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5108433734939759, | |
| "grad_norm": 0.041385799646377563, | |
| "learning_rate": 2.385661525048014e-05, | |
| "loss": 0.9104, | |
| "num_input_tokens_seen": 111149056, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5204819277108433, | |
| "grad_norm": 0.043126098811626434, | |
| "learning_rate": 2.3095540580727055e-05, | |
| "loss": 0.8854, | |
| "num_input_tokens_seen": 113246208, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5301204819277109, | |
| "grad_norm": 0.04146340861916542, | |
| "learning_rate": 2.23362375015031e-05, | |
| "loss": 0.8827, | |
| "num_input_tokens_seen": 115343360, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5397590361445783, | |
| "grad_norm": 0.04183032736182213, | |
| "learning_rate": 2.157941234140225e-05, | |
| "loss": 0.9197, | |
| "num_input_tokens_seen": 117440512, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.5493975903614458, | |
| "grad_norm": 0.040669653564691544, | |
| "learning_rate": 2.082576912397695e-05, | |
| "loss": 0.9112, | |
| "num_input_tokens_seen": 119537664, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5590361445783133, | |
| "grad_norm": 0.03980317711830139, | |
| "learning_rate": 2.0076008912832355e-05, | |
| "loss": 0.8954, | |
| "num_input_tokens_seen": 121634816, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5686746987951807, | |
| "grad_norm": 0.039486825466156006, | |
| "learning_rate": 1.933082915947398e-05, | |
| "loss": 0.8575, | |
| "num_input_tokens_seen": 123731968, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5783132530120482, | |
| "grad_norm": 0.04150194674730301, | |
| "learning_rate": 1.8590923054515503e-05, | |
| "loss": 0.8983, | |
| "num_input_tokens_seen": 125829120, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5879518072289157, | |
| "grad_norm": 0.041630711406469345, | |
| "learning_rate": 1.7856978882850113e-05, | |
| "loss": 0.8819, | |
| "num_input_tokens_seen": 127926272, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5975903614457831, | |
| "grad_norm": 0.04325857758522034, | |
| "learning_rate": 1.7129679383385383e-05, | |
| "loss": 0.9067, | |
| "num_input_tokens_seen": 130023424, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.6072289156626506, | |
| "grad_norm": 0.041175901889801025, | |
| "learning_rate": 1.6409701113937183e-05, | |
| "loss": 0.9054, | |
| "num_input_tokens_seen": 132120576, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6168674698795181, | |
| "grad_norm": 0.04035747051239014, | |
| "learning_rate": 1.5697713821873398e-05, | |
| "loss": 0.8938, | |
| "num_input_tokens_seen": 134217728, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.6265060240963856, | |
| "grad_norm": 0.040536992251873016, | |
| "learning_rate": 1.4994379821093049e-05, | |
| "loss": 0.8964, | |
| "num_input_tokens_seen": 136314880, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.636144578313253, | |
| "grad_norm": 0.03936683386564255, | |
| "learning_rate": 1.430035337592018e-05, | |
| "loss": 0.8979, | |
| "num_input_tokens_seen": 138412032, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6457831325301204, | |
| "grad_norm": 0.042347777634859085, | |
| "learning_rate": 1.3616280092485717e-05, | |
| "loss": 0.9085, | |
| "num_input_tokens_seen": 140509184, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.655421686746988, | |
| "grad_norm": 0.039885543286800385, | |
| "learning_rate": 1.2942796318163595e-05, | |
| "loss": 0.9091, | |
| "num_input_tokens_seen": 142606336, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.6650602409638554, | |
| "grad_norm": 0.04115555062890053, | |
| "learning_rate": 1.2280528549619485e-05, | |
| "loss": 0.8615, | |
| "num_input_tokens_seen": 144703488, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6746987951807228, | |
| "grad_norm": 0.041039761155843735, | |
| "learning_rate": 1.1630092850023147e-05, | |
| "loss": 0.8873, | |
| "num_input_tokens_seen": 146800640, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6843373493975904, | |
| "grad_norm": 0.04071088135242462, | |
| "learning_rate": 1.0992094275966256e-05, | |
| "loss": 0.8958, | |
| "num_input_tokens_seen": 148897792, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6939759036144578, | |
| "grad_norm": 0.04651007801294327, | |
| "learning_rate": 1.0367126314618947e-05, | |
| "loss": 0.9171, | |
| "num_input_tokens_seen": 150994944, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.7036144578313253, | |
| "grad_norm": 0.03853911906480789, | |
| "learning_rate": 9.755770331648642e-06, | |
| "loss": 0.9064, | |
| "num_input_tokens_seen": 153092096, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.7132530120481928, | |
| "grad_norm": 0.03924622759222984, | |
| "learning_rate": 9.15859503041462e-06, | |
| "loss": 0.9176, | |
| "num_input_tokens_seen": 155189248, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 0.04030469059944153, | |
| "learning_rate": 8.576155922941548e-06, | |
| "loss": 0.8882, | |
| "num_input_tokens_seen": 157286400, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7325301204819277, | |
| "grad_norm": 0.03955009952187538, | |
| "learning_rate": 8.008994813163995e-06, | |
| "loss": 0.9081, | |
| "num_input_tokens_seen": 159383552, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.7421686746987952, | |
| "grad_norm": 0.041652191430330276, | |
| "learning_rate": 7.457639292922675e-06, | |
| "loss": 0.8861, | |
| "num_input_tokens_seen": 161480704, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.7518072289156627, | |
| "grad_norm": 0.041008081287145615, | |
| "learning_rate": 6.92260225118122e-06, | |
| "loss": 0.8766, | |
| "num_input_tokens_seen": 163577856, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.7614457831325301, | |
| "grad_norm": 0.039367541670799255, | |
| "learning_rate": 6.4043813969201004e-06, | |
| "loss": 0.8789, | |
| "num_input_tokens_seen": 165675008, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.7710843373493976, | |
| "grad_norm": 0.039804939180612564, | |
| "learning_rate": 5.903458796151381e-06, | |
| "loss": 0.8952, | |
| "num_input_tokens_seen": 167772160, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7807228915662651, | |
| "grad_norm": 0.03992246836423874, | |
| "learning_rate": 5.420300423485167e-06, | |
| "loss": 0.8847, | |
| "num_input_tokens_seen": 169869312, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7903614457831325, | |
| "grad_norm": 0.03980246186256409, | |
| "learning_rate": 4.95535572866474e-06, | |
| "loss": 0.8848, | |
| "num_input_tokens_seen": 171966464, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.038608700037002563, | |
| "learning_rate": 4.5090572184736864e-06, | |
| "loss": 0.8884, | |
| "num_input_tokens_seen": 174063616, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.8096385542168675, | |
| "grad_norm": 0.03972884640097618, | |
| "learning_rate": 4.081820054403948e-06, | |
| "loss": 0.8885, | |
| "num_input_tokens_seen": 176160768, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.8192771084337349, | |
| "grad_norm": 0.037002868950366974, | |
| "learning_rate": 3.674041666458963e-06, | |
| "loss": 0.8821, | |
| "num_input_tokens_seen": 178257920, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8289156626506025, | |
| "grad_norm": 0.039480820298194885, | |
| "learning_rate": 3.2861013834512846e-06, | |
| "loss": 0.9095, | |
| "num_input_tokens_seen": 180355072, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.8385542168674699, | |
| "grad_norm": 0.039000798016786575, | |
| "learning_rate": 2.918360080138485e-06, | |
| "loss": 0.8505, | |
| "num_input_tokens_seen": 182452224, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.8481927710843373, | |
| "grad_norm": 0.03906833752989769, | |
| "learning_rate": 2.57115984152565e-06, | |
| "loss": 0.8776, | |
| "num_input_tokens_seen": 184549376, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.8578313253012049, | |
| "grad_norm": 0.040421612560749054, | |
| "learning_rate": 2.2448236446466846e-06, | |
| "loss": 0.8932, | |
| "num_input_tokens_seen": 186646528, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.8674698795180723, | |
| "grad_norm": 0.03807380422949791, | |
| "learning_rate": 1.939655058120521e-06, | |
| "loss": 0.8887, | |
| "num_input_tokens_seen": 188743680, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8771084337349397, | |
| "grad_norm": 0.03808167204260826, | |
| "learning_rate": 1.6559379597616137e-06, | |
| "loss": 0.8613, | |
| "num_input_tokens_seen": 190840832, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.8867469879518072, | |
| "grad_norm": 0.03954986855387688, | |
| "learning_rate": 1.3939362725075345e-06, | |
| "loss": 0.9218, | |
| "num_input_tokens_seen": 192937984, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.8963855421686747, | |
| "grad_norm": 0.03984986990690231, | |
| "learning_rate": 1.1538937189091825e-06, | |
| "loss": 0.9037, | |
| "num_input_tokens_seen": 195035136, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.9060240963855422, | |
| "grad_norm": 0.03950276970863342, | |
| "learning_rate": 9.360335944121029e-07, | |
| "loss": 0.8971, | |
| "num_input_tokens_seen": 197132288, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.9156626506024096, | |
| "grad_norm": 0.04189635440707207, | |
| "learning_rate": 7.405585596397313e-07, | |
| "loss": 0.9131, | |
| "num_input_tokens_seen": 199229440, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9253012048192771, | |
| "grad_norm": 0.04141265153884888, | |
| "learning_rate": 5.676504518718761e-07, | |
| "loss": 0.9085, | |
| "num_input_tokens_seen": 201326592, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.9349397590361446, | |
| "grad_norm": 0.03829219564795494, | |
| "learning_rate": 4.1747011589368947e-07, | |
| "loss": 0.8804, | |
| "num_input_tokens_seen": 203423744, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.944578313253012, | |
| "grad_norm": 0.0407879464328289, | |
| "learning_rate": 2.9015725437259724e-07, | |
| "loss": 0.8935, | |
| "num_input_tokens_seen": 205520896, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.9542168674698795, | |
| "grad_norm": 0.04065724089741707, | |
| "learning_rate": 1.8583029790230355e-07, | |
| "loss": 0.8984, | |
| "num_input_tokens_seen": 207618048, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.963855421686747, | |
| "grad_norm": 0.04242575168609619, | |
| "learning_rate": 1.0458629483476867e-07, | |
| "loss": 0.9129, | |
| "num_input_tokens_seen": 209715200, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9734939759036144, | |
| "grad_norm": 0.04202008619904518, | |
| "learning_rate": 4.650082100265407e-08, | |
| "loss": 0.9183, | |
| "num_input_tokens_seen": 211812352, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.983132530120482, | |
| "grad_norm": 0.04002172499895096, | |
| "learning_rate": 1.1627909416211947e-08, | |
| "loss": 0.8792, | |
| "num_input_tokens_seen": 213909504, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.9927710843373494, | |
| "grad_norm": 0.03849833831191063, | |
| "learning_rate": 0.0, | |
| "loss": 0.8806, | |
| "num_input_tokens_seen": 216006656, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.9927710843373494, | |
| "num_input_tokens_seen": 216006656, | |
| "step": 103, | |
| "total_flos": 9.558846039650206e+18, | |
| "train_loss": 0.9284970314757338, | |
| "train_runtime": 17321.2957, | |
| "train_samples_per_second": 3.064, | |
| "train_steps_per_second": 0.006 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 103, | |
| "num_input_tokens_seen": 216006656, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.558846039650206e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |