| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9963008631319359, | |
| "eval_steps": 500, | |
| "global_step": 101, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009864364981504316, | |
| "grad_norm": 0.7294987440109253, | |
| "learning_rate": 4.998790705729971e-05, | |
| "loss": 1.0213, | |
| "num_input_tokens_seen": 2097152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01972872996300863, | |
| "grad_norm": 0.5664029717445374, | |
| "learning_rate": 4.995163992833986e-05, | |
| "loss": 1.0136, | |
| "num_input_tokens_seen": 4194304, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.029593094944512947, | |
| "grad_norm": 0.42022261023521423, | |
| "learning_rate": 4.989123369922547e-05, | |
| "loss": 0.9404, | |
| "num_input_tokens_seen": 6291456, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03945745992601726, | |
| "grad_norm": 0.3317222595214844, | |
| "learning_rate": 4.980674680908192e-05, | |
| "loss": 0.953, | |
| "num_input_tokens_seen": 8388608, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04932182490752158, | |
| "grad_norm": 0.2700234651565552, | |
| "learning_rate": 4.969826099351892e-05, | |
| "loss": 0.9453, | |
| "num_input_tokens_seen": 10485760, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.059186189889025895, | |
| "grad_norm": 0.23365087807178497, | |
| "learning_rate": 4.9565881205556594e-05, | |
| "loss": 0.9111, | |
| "num_input_tokens_seen": 12582912, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0690505548705302, | |
| "grad_norm": 0.17710435390472412, | |
| "learning_rate": 4.940973551409018e-05, | |
| "loss": 0.878, | |
| "num_input_tokens_seen": 14680064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07891491985203453, | |
| "grad_norm": 0.17090857028961182, | |
| "learning_rate": 4.922997497999166e-05, | |
| "loss": 0.914, | |
| "num_input_tokens_seen": 16777216, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08877928483353884, | |
| "grad_norm": 0.18688030540943146, | |
| "learning_rate": 4.9026773509968115e-05, | |
| "loss": 0.8649, | |
| "num_input_tokens_seen": 18874368, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09864364981504316, | |
| "grad_norm": 0.19690372049808502, | |
| "learning_rate": 4.8800327688318246e-05, | |
| "loss": 0.9029, | |
| "num_input_tokens_seen": 20971520, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10850801479654747, | |
| "grad_norm": 0.16644370555877686, | |
| "learning_rate": 4.855085658674973e-05, | |
| "loss": 0.882, | |
| "num_input_tokens_seen": 23068672, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11837237977805179, | |
| "grad_norm": 0.1807110756635666, | |
| "learning_rate": 4.827860155244149e-05, | |
| "loss": 0.8438, | |
| "num_input_tokens_seen": 25165824, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1282367447595561, | |
| "grad_norm": 0.16156087815761566, | |
| "learning_rate": 4.798382597455591e-05, | |
| "loss": 0.8743, | |
| "num_input_tokens_seen": 27262976, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1381011097410604, | |
| "grad_norm": 0.14602774381637573, | |
| "learning_rate": 4.7666815029426816e-05, | |
| "loss": 0.8736, | |
| "num_input_tokens_seen": 29360128, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14796547472256474, | |
| "grad_norm": 0.15224798023700714, | |
| "learning_rate": 4.732787540466979e-05, | |
| "loss": 0.8687, | |
| "num_input_tokens_seen": 31457280, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15782983970406905, | |
| "grad_norm": 0.14535664021968842, | |
| "learning_rate": 4.696733500248172e-05, | |
| "loss": 0.864, | |
| "num_input_tokens_seen": 33554432, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16769420468557336, | |
| "grad_norm": 0.1372939944267273, | |
| "learning_rate": 4.658554262241659e-05, | |
| "loss": 0.8877, | |
| "num_input_tokens_seen": 35651584, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17755856966707767, | |
| "grad_norm": 0.1264754980802536, | |
| "learning_rate": 4.6182867623944436e-05, | |
| "loss": 0.8749, | |
| "num_input_tokens_seen": 37748736, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.187422934648582, | |
| "grad_norm": 0.11968766152858734, | |
| "learning_rate": 4.575969956911994e-05, | |
| "loss": 0.8338, | |
| "num_input_tokens_seen": 39845888, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19728729963008632, | |
| "grad_norm": 0.1143808588385582, | |
| "learning_rate": 4.531644784570626e-05, | |
| "loss": 0.8294, | |
| "num_input_tokens_seen": 41943040, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20715166461159062, | |
| "grad_norm": 0.12028194963932037, | |
| "learning_rate": 4.485354127111884e-05, | |
| "loss": 0.8666, | |
| "num_input_tokens_seen": 44040192, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21701602959309493, | |
| "grad_norm": 0.11237838119268417, | |
| "learning_rate": 4.437142767757225e-05, | |
| "loss": 0.8038, | |
| "num_input_tokens_seen": 46137344, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22688039457459927, | |
| "grad_norm": 0.1187497228384018, | |
| "learning_rate": 4.387057347883143e-05, | |
| "loss": 0.8492, | |
| "num_input_tokens_seen": 48234496, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.23674475955610358, | |
| "grad_norm": 0.11182423681020737, | |
| "learning_rate": 4.335146321898651e-05, | |
| "loss": 0.8047, | |
| "num_input_tokens_seen": 50331648, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2466091245376079, | |
| "grad_norm": 0.118191197514534, | |
| "learning_rate": 4.281459910368768e-05, | |
| "loss": 0.8521, | |
| "num_input_tokens_seen": 52428800, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2564734895191122, | |
| "grad_norm": 0.09803211688995361, | |
| "learning_rate": 4.226050051429367e-05, | |
| "loss": 0.8133, | |
| "num_input_tokens_seen": 54525952, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.26633785450061653, | |
| "grad_norm": 0.10156495869159698, | |
| "learning_rate": 4.168970350540384e-05, | |
| "loss": 0.8365, | |
| "num_input_tokens_seen": 56623104, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2762022194821208, | |
| "grad_norm": 0.10211872309446335, | |
| "learning_rate": 4.110276028625995e-05, | |
| "loss": 0.8094, | |
| "num_input_tokens_seen": 58720256, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.28606658446362515, | |
| "grad_norm": 0.10365650057792664, | |
| "learning_rate": 4.050023868651938e-05, | |
| "loss": 0.8174, | |
| "num_input_tokens_seen": 60817408, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2959309494451295, | |
| "grad_norm": 0.09515471011400223, | |
| "learning_rate": 3.988272160691665e-05, | |
| "loss": 0.8278, | |
| "num_input_tokens_seen": 62914560, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.30579531442663377, | |
| "grad_norm": 0.10051083564758301, | |
| "learning_rate": 3.925080645534457e-05, | |
| "loss": 0.8425, | |
| "num_input_tokens_seen": 65011712, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3156596794081381, | |
| "grad_norm": 0.0998254269361496, | |
| "learning_rate": 3.8605104568900685e-05, | |
| "loss": 0.8145, | |
| "num_input_tokens_seen": 67108864, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.32552404438964244, | |
| "grad_norm": 0.109571672976017, | |
| "learning_rate": 3.7946240622458135e-05, | |
| "loss": 0.8322, | |
| "num_input_tokens_seen": 69206016, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3353884093711467, | |
| "grad_norm": 0.09529263526201248, | |
| "learning_rate": 3.7274852024333054e-05, | |
| "loss": 0.8114, | |
| "num_input_tokens_seen": 71303168, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.34525277435265106, | |
| "grad_norm": 0.09562862664461136, | |
| "learning_rate": 3.6591588299633186e-05, | |
| "loss": 0.8091, | |
| "num_input_tokens_seen": 73400320, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.35511713933415534, | |
| "grad_norm": 0.09187028557062149, | |
| "learning_rate": 3.589711046188428e-05, | |
| "loss": 0.7743, | |
| "num_input_tokens_seen": 75497472, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3649815043156597, | |
| "grad_norm": 0.09879715740680695, | |
| "learning_rate": 3.519209037354222e-05, | |
| "loss": 0.8368, | |
| "num_input_tokens_seen": 77594624, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.374845869297164, | |
| "grad_norm": 0.0839247927069664, | |
| "learning_rate": 3.447721009600949e-05, | |
| "loss": 0.8177, | |
| "num_input_tokens_seen": 79691776, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3847102342786683, | |
| "grad_norm": 0.09094128012657166, | |
| "learning_rate": 3.3753161229784766e-05, | |
| "loss": 0.8109, | |
| "num_input_tokens_seen": 81788928, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.39457459926017263, | |
| "grad_norm": 0.09645260125398636, | |
| "learning_rate": 3.302064424538419e-05, | |
| "loss": 0.827, | |
| "num_input_tokens_seen": 83886080, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.40443896424167697, | |
| "grad_norm": 0.08931674808263779, | |
| "learning_rate": 3.228036780568131e-05, | |
| "loss": 0.8167, | |
| "num_input_tokens_seen": 85983232, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.41430332922318125, | |
| "grad_norm": 0.08245021849870682, | |
| "learning_rate": 3.153304808032152e-05, | |
| "loss": 0.8073, | |
| "num_input_tokens_seen": 88080384, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4241676942046856, | |
| "grad_norm": 0.08803369104862213, | |
| "learning_rate": 3.077940805287425e-05, | |
| "loss": 0.7793, | |
| "num_input_tokens_seen": 90177536, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.43403205918618987, | |
| "grad_norm": 0.08340983092784882, | |
| "learning_rate": 3.0020176821392964e-05, | |
| "loss": 0.8096, | |
| "num_input_tokens_seen": 92274688, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4438964241676942, | |
| "grad_norm": 0.09057221561670303, | |
| "learning_rate": 2.925608889305997e-05, | |
| "loss": 0.8212, | |
| "num_input_tokens_seen": 94371840, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.45376078914919854, | |
| "grad_norm": 0.08546467870473862, | |
| "learning_rate": 2.848788347359808e-05, | |
| "loss": 0.8151, | |
| "num_input_tokens_seen": 96468992, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4636251541307028, | |
| "grad_norm": 0.08286646008491516, | |
| "learning_rate": 2.7716303752136864e-05, | |
| "loss": 0.8331, | |
| "num_input_tokens_seen": 98566144, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.47348951911220716, | |
| "grad_norm": 0.08105745166540146, | |
| "learning_rate": 2.6942096182225162e-05, | |
| "loss": 0.8003, | |
| "num_input_tokens_seen": 100663296, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4833538840937115, | |
| "grad_norm": 0.07993409782648087, | |
| "learning_rate": 2.616600975968544e-05, | |
| "loss": 0.8214, | |
| "num_input_tokens_seen": 102760448, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4932182490752158, | |
| "grad_norm": 0.08382619917392731, | |
| "learning_rate": 2.5388795298008776e-05, | |
| "loss": 0.8118, | |
| "num_input_tokens_seen": 104857600, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5030826140567201, | |
| "grad_norm": 0.08271751552820206, | |
| "learning_rate": 2.4611204701991227e-05, | |
| "loss": 0.8382, | |
| "num_input_tokens_seen": 106954752, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5129469790382244, | |
| "grad_norm": 0.07375568896532059, | |
| "learning_rate": 2.3833990240314562e-05, | |
| "loss": 0.8099, | |
| "num_input_tokens_seen": 109051904, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5228113440197287, | |
| "grad_norm": 0.07492537051439285, | |
| "learning_rate": 2.3057903817774843e-05, | |
| "loss": 0.7914, | |
| "num_input_tokens_seen": 111149056, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5326757090012331, | |
| "grad_norm": 0.07812082767486572, | |
| "learning_rate": 2.2283696247863135e-05, | |
| "loss": 0.8104, | |
| "num_input_tokens_seen": 113246208, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5425400739827374, | |
| "grad_norm": 0.07944825291633606, | |
| "learning_rate": 2.1512116526401928e-05, | |
| "loss": 0.8125, | |
| "num_input_tokens_seen": 115343360, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5524044389642416, | |
| "grad_norm": 0.07352437824010849, | |
| "learning_rate": 2.0743911106940034e-05, | |
| "loss": 0.8198, | |
| "num_input_tokens_seen": 117440512, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.562268803945746, | |
| "grad_norm": 0.07700145244598389, | |
| "learning_rate": 1.9979823178607042e-05, | |
| "loss": 0.8019, | |
| "num_input_tokens_seen": 119537664, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5721331689272503, | |
| "grad_norm": 0.07811249792575836, | |
| "learning_rate": 1.9220591947125766e-05, | |
| "loss": 0.8141, | |
| "num_input_tokens_seen": 121634816, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5819975339087546, | |
| "grad_norm": 0.07361660897731781, | |
| "learning_rate": 1.846695191967849e-05, | |
| "loss": 0.7985, | |
| "num_input_tokens_seen": 123731968, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.591861898890259, | |
| "grad_norm": 0.07933210581541061, | |
| "learning_rate": 1.7719632194318702e-05, | |
| "loss": 0.7998, | |
| "num_input_tokens_seen": 125829120, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6017262638717632, | |
| "grad_norm": 0.0801980197429657, | |
| "learning_rate": 1.6979355754615814e-05, | |
| "loss": 0.7988, | |
| "num_input_tokens_seen": 127926272, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.6115906288532675, | |
| "grad_norm": 0.07316846400499344, | |
| "learning_rate": 1.6246838770215233e-05, | |
| "loss": 0.8016, | |
| "num_input_tokens_seen": 130023424, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.6214549938347719, | |
| "grad_norm": 0.0750172808766365, | |
| "learning_rate": 1.552278990399052e-05, | |
| "loss": 0.8162, | |
| "num_input_tokens_seen": 132120576, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6313193588162762, | |
| "grad_norm": 0.07336606830358505, | |
| "learning_rate": 1.4807909626457782e-05, | |
| "loss": 0.8258, | |
| "num_input_tokens_seen": 134217728, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.6411837237977805, | |
| "grad_norm": 0.07929656654596329, | |
| "learning_rate": 1.4102889538115723e-05, | |
| "loss": 0.8063, | |
| "num_input_tokens_seen": 136314880, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6510480887792849, | |
| "grad_norm": 0.08207987248897552, | |
| "learning_rate": 1.3408411700366813e-05, | |
| "loss": 0.8116, | |
| "num_input_tokens_seen": 138412032, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6609124537607891, | |
| "grad_norm": 0.07338231056928635, | |
| "learning_rate": 1.2725147975666948e-05, | |
| "loss": 0.785, | |
| "num_input_tokens_seen": 140509184, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.6707768187422934, | |
| "grad_norm": 0.08025672286748886, | |
| "learning_rate": 1.2053759377541866e-05, | |
| "loss": 0.8049, | |
| "num_input_tokens_seen": 142606336, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.6806411837237978, | |
| "grad_norm": 0.07760636508464813, | |
| "learning_rate": 1.1394895431099314e-05, | |
| "loss": 0.8034, | |
| "num_input_tokens_seen": 144703488, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6905055487053021, | |
| "grad_norm": 0.07995034009218216, | |
| "learning_rate": 1.0749193544655434e-05, | |
| "loss": 0.7949, | |
| "num_input_tokens_seen": 146800640, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7003699136868065, | |
| "grad_norm": 0.07639381289482117, | |
| "learning_rate": 1.0117278393083358e-05, | |
| "loss": 0.8024, | |
| "num_input_tokens_seen": 148897792, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.7102342786683107, | |
| "grad_norm": 0.0737844705581665, | |
| "learning_rate": 9.499761313480626e-06, | |
| "loss": 0.7608, | |
| "num_input_tokens_seen": 150994944, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.720098643649815, | |
| "grad_norm": 0.07084383070468903, | |
| "learning_rate": 8.897239713740058e-06, | |
| "loss": 0.8012, | |
| "num_input_tokens_seen": 153092096, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.7299630086313194, | |
| "grad_norm": 0.07751645892858505, | |
| "learning_rate": 8.31029649459616e-06, | |
| "loss": 0.7688, | |
| "num_input_tokens_seen": 155189248, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.7398273736128237, | |
| "grad_norm": 0.07183132320642471, | |
| "learning_rate": 7.739499485706334e-06, | |
| "loss": 0.8023, | |
| "num_input_tokens_seen": 157286400, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.749691738594328, | |
| "grad_norm": 0.07271506637334824, | |
| "learning_rate": 7.185400896312328e-06, | |
| "loss": 0.7809, | |
| "num_input_tokens_seen": 159383552, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.7595561035758323, | |
| "grad_norm": 0.07422608137130737, | |
| "learning_rate": 6.648536781013495e-06, | |
| "loss": 0.8083, | |
| "num_input_tokens_seen": 161480704, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.7694204685573366, | |
| "grad_norm": 0.07867728918790817, | |
| "learning_rate": 6.12942652116858e-06, | |
| "loss": 0.7903, | |
| "num_input_tokens_seen": 163577856, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.7792848335388409, | |
| "grad_norm": 0.07830856740474701, | |
| "learning_rate": 5.628572322427755e-06, | |
| "loss": 0.7904, | |
| "num_input_tokens_seen": 165675008, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.7891491985203453, | |
| "grad_norm": 0.07836252450942993, | |
| "learning_rate": 5.1464587288811624e-06, | |
| "loss": 0.797, | |
| "num_input_tokens_seen": 167772160, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7990135635018496, | |
| "grad_norm": 0.07151419669389725, | |
| "learning_rate": 4.683552154293747e-06, | |
| "loss": 0.7636, | |
| "num_input_tokens_seen": 169869312, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.8088779284833539, | |
| "grad_norm": 0.07672585546970367, | |
| "learning_rate": 4.240300430880062e-06, | |
| "loss": 0.7818, | |
| "num_input_tokens_seen": 171966464, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.8187422934648582, | |
| "grad_norm": 0.08120947331190109, | |
| "learning_rate": 3.817132376055565e-06, | |
| "loss": 0.7914, | |
| "num_input_tokens_seen": 174063616, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.8286066584463625, | |
| "grad_norm": 0.07581306993961334, | |
| "learning_rate": 3.4144573775834134e-06, | |
| "loss": 0.7985, | |
| "num_input_tokens_seen": 176160768, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.8384710234278668, | |
| "grad_norm": 0.08039968460798264, | |
| "learning_rate": 3.0326649975182865e-06, | |
| "loss": 0.7868, | |
| "num_input_tokens_seen": 178257920, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8483353884093712, | |
| "grad_norm": 0.07282786071300507, | |
| "learning_rate": 2.672124595330214e-06, | |
| "loss": 0.7972, | |
| "num_input_tokens_seen": 180355072, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.8581997533908755, | |
| "grad_norm": 0.07389923185110092, | |
| "learning_rate": 2.333184970573188e-06, | |
| "loss": 0.7933, | |
| "num_input_tokens_seen": 182452224, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.8680641183723797, | |
| "grad_norm": 0.07451856881380081, | |
| "learning_rate": 2.0161740254440896e-06, | |
| "loss": 0.7695, | |
| "num_input_tokens_seen": 184549376, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.8779284833538841, | |
| "grad_norm": 0.0740065649151802, | |
| "learning_rate": 1.7213984475585144e-06, | |
| "loss": 0.7929, | |
| "num_input_tokens_seen": 186646528, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.8877928483353884, | |
| "grad_norm": 0.07559362053871155, | |
| "learning_rate": 1.4491434132502729e-06, | |
| "loss": 0.7995, | |
| "num_input_tokens_seen": 188743680, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8976572133168927, | |
| "grad_norm": 0.07598087936639786, | |
| "learning_rate": 1.1996723116817516e-06, | |
| "loss": 0.7857, | |
| "num_input_tokens_seen": 190840832, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.9075215782983971, | |
| "grad_norm": 0.0752101019024849, | |
| "learning_rate": 9.732264900318866e-07, | |
| "loss": 0.8215, | |
| "num_input_tokens_seen": 192937984, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.9173859432799013, | |
| "grad_norm": 0.07947240769863129, | |
| "learning_rate": 7.700250200083469e-07, | |
| "loss": 0.7931, | |
| "num_input_tokens_seen": 195035136, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.9272503082614056, | |
| "grad_norm": 0.07513375580310822, | |
| "learning_rate": 5.90264485909825e-07, | |
| "loss": 0.7927, | |
| "num_input_tokens_seen": 197132288, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.93711467324291, | |
| "grad_norm": 0.0716259703040123, | |
| "learning_rate": 4.341187944434083e-07, | |
| "loss": 0.7787, | |
| "num_input_tokens_seen": 199229440, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9469790382244143, | |
| "grad_norm": 0.07607847452163696, | |
| "learning_rate": 3.017390064810832e-07, | |
| "loss": 0.7771, | |
| "num_input_tokens_seen": 201326592, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.9568434032059187, | |
| "grad_norm": 0.07854241132736206, | |
| "learning_rate": 1.9325319091808847e-07, | |
| "loss": 0.7931, | |
| "num_input_tokens_seen": 203423744, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.966707768187423, | |
| "grad_norm": 0.07781317085027695, | |
| "learning_rate": 1.0876630077453487e-07, | |
| "loss": 0.7902, | |
| "num_input_tokens_seen": 205520896, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.9765721331689272, | |
| "grad_norm": 0.07628636062145233, | |
| "learning_rate": 4.836007166014178e-08, | |
| "loss": 0.7906, | |
| "num_input_tokens_seen": 207618048, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.9864364981504316, | |
| "grad_norm": 0.07593634724617004, | |
| "learning_rate": 1.2092942700298038e-08, | |
| "loss": 0.8083, | |
| "num_input_tokens_seen": 209715200, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9963008631319359, | |
| "grad_norm": 0.074070043861866, | |
| "learning_rate": 0.0, | |
| "loss": 0.7963, | |
| "num_input_tokens_seen": 211812352, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.9963008631319359, | |
| "num_input_tokens_seen": 211812352, | |
| "step": 101, | |
| "total_flos": 8.985866598858359e+18, | |
| "train_loss": 0.8237513356869763, | |
| "train_runtime": 15586.605, | |
| "train_samples_per_second": 3.328, | |
| "train_steps_per_second": 0.006 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 101, | |
| "num_input_tokens_seen": 211812352, | |
| "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": 8.985866598858359e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |