| { | |
| "best_metric": 4.398462772369385, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.028526601055484237, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002852660105548424, | |
| "grad_norm": 1.549706220626831, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 3.0479, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002852660105548424, | |
| "eval_loss": 4.6384663581848145, | |
| "eval_runtime": 37.2049, | |
| "eval_samples_per_second": 158.689, | |
| "eval_steps_per_second": 39.672, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005705320211096848, | |
| "grad_norm": 1.838876485824585, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 3.5974, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008557980316645272, | |
| "grad_norm": 1.805705189704895, | |
| "learning_rate": 1.5e-06, | |
| "loss": 3.6121, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011410640422193695, | |
| "grad_norm": 1.8714826107025146, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 3.7557, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001426330052774212, | |
| "grad_norm": 1.939781904220581, | |
| "learning_rate": 2.5e-06, | |
| "loss": 3.8603, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017115960633290544, | |
| "grad_norm": 1.8265411853790283, | |
| "learning_rate": 3e-06, | |
| "loss": 3.935, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019968620738838967, | |
| "grad_norm": 1.759603500366211, | |
| "learning_rate": 3.5e-06, | |
| "loss": 3.8189, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002282128084438739, | |
| "grad_norm": 1.814140796661377, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 3.9246, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025673940949935813, | |
| "grad_norm": 1.8928650617599487, | |
| "learning_rate": 4.5e-06, | |
| "loss": 4.0013, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002852660105548424, | |
| "grad_norm": 1.837830901145935, | |
| "learning_rate": 5e-06, | |
| "loss": 3.9932, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0031379261161032664, | |
| "grad_norm": 1.8006929159164429, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 4.0146, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0034231921266581087, | |
| "grad_norm": 1.9046270847320557, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 4.1938, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003708458137212951, | |
| "grad_norm": 2.0485992431640625, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 4.2668, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003993724147767793, | |
| "grad_norm": 1.9657994508743286, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 4.1174, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004278990158322636, | |
| "grad_norm": 1.9667850732803345, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 4.2577, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004564256168877478, | |
| "grad_norm": 2.075460433959961, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 4.1323, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004849522179432321, | |
| "grad_norm": 2.0017716884613037, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 4.0343, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005134788189987163, | |
| "grad_norm": 2.005661725997925, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 4.1525, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005420054200542005, | |
| "grad_norm": 2.1485018730163574, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 4.4036, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005705320211096848, | |
| "grad_norm": 2.207129716873169, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 4.4609, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00599058622165169, | |
| "grad_norm": 2.4457483291625977, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 4.4866, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006275852232206533, | |
| "grad_norm": 2.37099027633667, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 4.5695, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006561118242761375, | |
| "grad_norm": 2.235172986984253, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 4.4886, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0068463842533162175, | |
| "grad_norm": 2.325352191925049, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 4.687, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007131650263871059, | |
| "grad_norm": 2.443951368331909, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 4.7515, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007416916274425902, | |
| "grad_norm": 2.2243640422821045, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 4.6517, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007702182284980745, | |
| "grad_norm": 2.2603063583374023, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 4.8584, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007987448295535587, | |
| "grad_norm": 2.5627048015594482, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 4.885, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00827271430609043, | |
| "grad_norm": 2.3629963397979736, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 4.7514, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008557980316645272, | |
| "grad_norm": 2.244079113006592, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 4.5837, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008843246327200113, | |
| "grad_norm": 2.2497127056121826, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 4.4709, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009128512337754956, | |
| "grad_norm": 2.303358793258667, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 4.5807, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009413778348309799, | |
| "grad_norm": 2.5985865592956543, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 4.8237, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009699044358864642, | |
| "grad_norm": 2.4008922576904297, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 4.805, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009984310369419484, | |
| "grad_norm": 2.3389854431152344, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 4.7285, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010269576379974325, | |
| "grad_norm": 2.4246208667755127, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 4.6435, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010554842390529168, | |
| "grad_norm": 2.559217929840088, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 4.8284, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01084010840108401, | |
| "grad_norm": 2.4570200443267822, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 4.831, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.011125374411638854, | |
| "grad_norm": 2.6529717445373535, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 4.9018, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011410640422193696, | |
| "grad_norm": 2.561655044555664, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 4.7884, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011695906432748537, | |
| "grad_norm": 2.514221668243408, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 4.9847, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01198117244330338, | |
| "grad_norm": 2.6552371978759766, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 5.1516, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.012266438453858223, | |
| "grad_norm": 2.5640077590942383, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 5.0659, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012551704464413066, | |
| "grad_norm": 2.783721685409546, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 5.2679, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012836970474967908, | |
| "grad_norm": 2.8886775970458984, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 5.1164, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01312223648552275, | |
| "grad_norm": 3.1505682468414307, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 5.4645, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013407502496077592, | |
| "grad_norm": 3.064004898071289, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 5.4745, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013692768506632435, | |
| "grad_norm": 3.032217025756836, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 5.3049, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013978034517187278, | |
| "grad_norm": 3.414022922515869, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 5.5081, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.014263300527742119, | |
| "grad_norm": 3.856145143508911, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 5.9213, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014263300527742119, | |
| "eval_loss": 4.4730048179626465, | |
| "eval_runtime": 37.0241, | |
| "eval_samples_per_second": 159.464, | |
| "eval_steps_per_second": 39.866, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014548566538296961, | |
| "grad_norm": 1.7294424772262573, | |
| "learning_rate": 2.847932752400164e-06, | |
| "loss": 3.1736, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.014833832548851804, | |
| "grad_norm": 1.8418482542037964, | |
| "learning_rate": 2.761321158169134e-06, | |
| "loss": 3.4268, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.015119098559406647, | |
| "grad_norm": 2.02036190032959, | |
| "learning_rate": 2.6743911843603134e-06, | |
| "loss": 3.7533, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.01540436456996149, | |
| "grad_norm": 1.7710672616958618, | |
| "learning_rate": 2.587248741756253e-06, | |
| "loss": 3.4441, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.015689630580516332, | |
| "grad_norm": 1.7376676797866821, | |
| "learning_rate": 2.5e-06, | |
| "loss": 3.3789, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.015974896591071173, | |
| "grad_norm": 1.8672767877578735, | |
| "learning_rate": 2.4127512582437486e-06, | |
| "loss": 3.7761, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.016260162601626018, | |
| "grad_norm": 1.9220268726348877, | |
| "learning_rate": 2.325608815639687e-06, | |
| "loss": 3.7599, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.01654542861218086, | |
| "grad_norm": 1.7978780269622803, | |
| "learning_rate": 2.238678841830867e-06, | |
| "loss": 3.542, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0168306946227357, | |
| "grad_norm": 1.8631057739257812, | |
| "learning_rate": 2.1520672475998374e-06, | |
| "loss": 3.89, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.017115960633290545, | |
| "grad_norm": 1.9112904071807861, | |
| "learning_rate": 2.0658795558326745e-06, | |
| "loss": 3.9064, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.017401226643845386, | |
| "grad_norm": 1.8794102668762207, | |
| "learning_rate": 1.9802207729556023e-06, | |
| "loss": 3.7488, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.017686492654400227, | |
| "grad_norm": 1.7349375486373901, | |
| "learning_rate": 1.895195261000831e-06, | |
| "loss": 3.9465, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.01797175866495507, | |
| "grad_norm": 1.9494880437850952, | |
| "learning_rate": 1.8109066104575023e-06, | |
| "loss": 3.9429, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.018257024675509912, | |
| "grad_norm": 1.9176416397094727, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 4.0286, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.018542290686064757, | |
| "grad_norm": 1.9241676330566406, | |
| "learning_rate": 1.6449496416858285e-06, | |
| "loss": 4.0452, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.018827556696619598, | |
| "grad_norm": 1.9808131456375122, | |
| "learning_rate": 1.56348351646022e-06, | |
| "loss": 4.0911, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.01911282270717444, | |
| "grad_norm": 2.1437771320343018, | |
| "learning_rate": 1.4831583923105e-06, | |
| "loss": 4.3343, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.019398088717729283, | |
| "grad_norm": 2.098871946334839, | |
| "learning_rate": 1.4040721330273063e-06, | |
| "loss": 4.1912, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.019683354728284124, | |
| "grad_norm": 1.9121192693710327, | |
| "learning_rate": 1.3263210930352737e-06, | |
| "loss": 3.9316, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.01996862073883897, | |
| "grad_norm": 2.1575756072998047, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "loss": 4.2355, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02025388674939381, | |
| "grad_norm": 2.0468432903289795, | |
| "learning_rate": 1.1752018394169882e-06, | |
| "loss": 4.2079, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.02053915275994865, | |
| "grad_norm": 2.1697824001312256, | |
| "learning_rate": 1.1020177413231334e-06, | |
| "loss": 4.3365, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.020824418770503495, | |
| "grad_norm": 2.1824512481689453, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 4.2945, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.021109684781058336, | |
| "grad_norm": 2.1010141372680664, | |
| "learning_rate": 9.608463116858544e-07, | |
| "loss": 4.3266, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.02139495079161318, | |
| "grad_norm": 2.166463851928711, | |
| "learning_rate": 8.930309757836517e-07, | |
| "loss": 4.2321, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02168021680216802, | |
| "grad_norm": 2.4518635272979736, | |
| "learning_rate": 8.271734841028553e-07, | |
| "loss": 4.4078, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.021965482812722863, | |
| "grad_norm": 2.344184398651123, | |
| "learning_rate": 7.633540738525066e-07, | |
| "loss": 4.5186, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.022250748823277707, | |
| "grad_norm": 2.274261713027954, | |
| "learning_rate": 7.016504991533727e-07, | |
| "loss": 4.3573, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.022536014833832548, | |
| "grad_norm": 2.2358288764953613, | |
| "learning_rate": 6.421379363065142e-07, | |
| "loss": 4.5504, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.022821280844387393, | |
| "grad_norm": 2.2493133544921875, | |
| "learning_rate": 5.848888922025553e-07, | |
| "loss": 4.584, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.023106546854942234, | |
| "grad_norm": 2.253169059753418, | |
| "learning_rate": 5.299731159831953e-07, | |
| "loss": 4.5174, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 2.337402582168579, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 4.506, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.02367707887605192, | |
| "grad_norm": 2.3492746353149414, | |
| "learning_rate": 4.27406068612396e-07, | |
| "loss": 4.5267, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.02396234488660676, | |
| "grad_norm": 2.207144260406494, | |
| "learning_rate": 3.798797596089351e-07, | |
| "loss": 4.6889, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.024247610897161605, | |
| "grad_norm": 2.466681480407715, | |
| "learning_rate": 3.3493649053890325e-07, | |
| "loss": 4.7795, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.024532876907716446, | |
| "grad_norm": 2.5349717140197754, | |
| "learning_rate": 2.9263101785268253e-07, | |
| "loss": 4.6551, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.024818142918271287, | |
| "grad_norm": 2.4833574295043945, | |
| "learning_rate": 2.53014884252083e-07, | |
| "loss": 4.7014, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.02510340892882613, | |
| "grad_norm": 2.309326410293579, | |
| "learning_rate": 2.1613635589349756e-07, | |
| "loss": 4.4093, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.025388674939380972, | |
| "grad_norm": 2.554025173187256, | |
| "learning_rate": 1.8204036358303173e-07, | |
| "loss": 4.8266, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.025673940949935817, | |
| "grad_norm": 2.5444960594177246, | |
| "learning_rate": 1.507684480352292e-07, | |
| "loss": 4.8623, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.025959206960490658, | |
| "grad_norm": 2.548241138458252, | |
| "learning_rate": 1.223587092621162e-07, | |
| "loss": 4.7327, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0262444729710455, | |
| "grad_norm": 2.4548227787017822, | |
| "learning_rate": 9.684576015420277e-08, | |
| "loss": 4.793, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.026529738981600343, | |
| "grad_norm": 2.6474790573120117, | |
| "learning_rate": 7.426068431000883e-08, | |
| "loss": 4.7439, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.026815004992155184, | |
| "grad_norm": 2.674259901046753, | |
| "learning_rate": 5.463099816548578e-08, | |
| "loss": 4.9857, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.02710027100271003, | |
| "grad_norm": 2.7254526615142822, | |
| "learning_rate": 3.798061746947995e-08, | |
| "loss": 5.0972, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.02738553701326487, | |
| "grad_norm": 2.9822192192077637, | |
| "learning_rate": 2.4329828146074096e-08, | |
| "loss": 5.3265, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.02767080302381971, | |
| "grad_norm": 2.92980694770813, | |
| "learning_rate": 1.3695261579316776e-08, | |
| "loss": 5.0558, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.027956069034374555, | |
| "grad_norm": 2.8623178005218506, | |
| "learning_rate": 6.089874350439507e-09, | |
| "loss": 5.2151, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.028241335044929396, | |
| "grad_norm": 3.296135663986206, | |
| "learning_rate": 1.5229324522605949e-09, | |
| "loss": 5.4848, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.028526601055484237, | |
| "grad_norm": 3.891191005706787, | |
| "learning_rate": 0.0, | |
| "loss": 5.632, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.028526601055484237, | |
| "eval_loss": 4.398462772369385, | |
| "eval_runtime": 37.0281, | |
| "eval_samples_per_second": 159.446, | |
| "eval_steps_per_second": 39.862, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2783693600980992.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |