| { | |
| "best_metric": 1.0187755823135376, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.027062683941679915, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00027062683941679914, | |
| "grad_norm": 0.5000702738761902, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.8662, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027062683941679914, | |
| "eval_loss": 1.2486605644226074, | |
| "eval_runtime": 576.5633, | |
| "eval_samples_per_second": 10.795, | |
| "eval_steps_per_second": 2.699, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005412536788335983, | |
| "grad_norm": 0.7091050744056702, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.8844, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008118805182503975, | |
| "grad_norm": 0.7198283076286316, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.8736, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010825073576671966, | |
| "grad_norm": 0.7402541041374207, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.9226, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013531341970839958, | |
| "grad_norm": 0.6890178918838501, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.9618, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001623761036500795, | |
| "grad_norm": 0.7613320350646973, | |
| "learning_rate": 3e-06, | |
| "loss": 0.9509, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001894387875917594, | |
| "grad_norm": 0.8056195378303528, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.9464, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002165014715334393, | |
| "grad_norm": 0.8153071403503418, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.9766, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024356415547511926, | |
| "grad_norm": 0.8731986284255981, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.9854, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027062683941679916, | |
| "grad_norm": 0.8255438804626465, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0802, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0029768952335847906, | |
| "grad_norm": 0.8778969645500183, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 0.9281, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00324752207300159, | |
| "grad_norm": 0.7399764657020569, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 1.0072, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003518148912418389, | |
| "grad_norm": 0.9628943800926208, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 0.9862, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003788775751835188, | |
| "grad_norm": 0.8942387104034424, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 1.0352, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004059402591251988, | |
| "grad_norm": 0.9490991234779358, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 1.0584, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004330029430668786, | |
| "grad_norm": 0.9122024178504944, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 1.0072, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004600656270085586, | |
| "grad_norm": 0.7996208667755127, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 1.1048, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004871283109502385, | |
| "grad_norm": 0.9378483891487122, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 1.0365, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005141909948919184, | |
| "grad_norm": 0.8539978861808777, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.9979, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005412536788335983, | |
| "grad_norm": 0.9930011630058289, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 1.0151, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005683163627752783, | |
| "grad_norm": 0.9113985300064087, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 1.0266, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005953790467169581, | |
| "grad_norm": 0.9310271739959717, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 0.998, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006224417306586381, | |
| "grad_norm": 1.0234174728393555, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 1.0837, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00649504414600318, | |
| "grad_norm": 0.890159010887146, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 1.0044, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006765670985419979, | |
| "grad_norm": 1.1107178926467896, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 1.1168, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007036297824836778, | |
| "grad_norm": 1.1049308776855469, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 1.1942, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007306924664253578, | |
| "grad_norm": 1.1453604698181152, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 1.0531, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007577551503670376, | |
| "grad_norm": 1.0684839487075806, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 1.0973, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007848178343087176, | |
| "grad_norm": 1.1629831790924072, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 1.0673, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008118805182503975, | |
| "grad_norm": 1.0914651155471802, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 1.1575, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008389432021920775, | |
| "grad_norm": 1.3187044858932495, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 1.223, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008660058861337572, | |
| "grad_norm": 1.2369117736816406, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 1.1662, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008930685700754372, | |
| "grad_norm": 1.3803397417068481, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 1.1548, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009201312540171171, | |
| "grad_norm": 1.3240615129470825, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 1.1982, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00947193937958797, | |
| "grad_norm": 1.5324469804763794, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 1.1681, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00974256621900477, | |
| "grad_norm": 1.323723554611206, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 1.1543, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01001319305842157, | |
| "grad_norm": 1.5759074687957764, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 1.1227, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010283819897838367, | |
| "grad_norm": 1.6370131969451904, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 1.1549, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010554446737255167, | |
| "grad_norm": 1.5213303565979004, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 1.1308, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010825073576671966, | |
| "grad_norm": 1.753510594367981, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.2172, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011095700416088766, | |
| "grad_norm": 1.6697436571121216, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 1.1446, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011366327255505565, | |
| "grad_norm": 1.6956145763397217, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 1.0812, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011636954094922363, | |
| "grad_norm": 1.6840723752975464, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 1.1333, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011907580934339163, | |
| "grad_norm": 1.8532711267471313, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 1.2552, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012178207773755962, | |
| "grad_norm": 2.4561421871185303, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 1.3493, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012448834613172761, | |
| "grad_norm": 2.4903533458709717, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 1.2094, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012719461452589561, | |
| "grad_norm": 3.978550910949707, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 1.508, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01299008829200636, | |
| "grad_norm": 6.7383856773376465, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 1.5481, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013260715131423158, | |
| "grad_norm": 7.621368885040283, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 1.7839, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013531341970839958, | |
| "grad_norm": 7.821316242218018, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 1.8119, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013531341970839958, | |
| "eval_loss": 1.0674021244049072, | |
| "eval_runtime": 581.3896, | |
| "eval_samples_per_second": 10.705, | |
| "eval_steps_per_second": 2.676, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013801968810256757, | |
| "grad_norm": 0.5559863448143005, | |
| "learning_rate": 2.847932752400164e-06, | |
| "loss": 0.7655, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.014072595649673557, | |
| "grad_norm": 0.678560197353363, | |
| "learning_rate": 2.761321158169134e-06, | |
| "loss": 0.803, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.014343222489090356, | |
| "grad_norm": 0.6894142627716064, | |
| "learning_rate": 2.6743911843603134e-06, | |
| "loss": 0.8397, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.014613849328507155, | |
| "grad_norm": 0.7735072374343872, | |
| "learning_rate": 2.587248741756253e-06, | |
| "loss": 0.8653, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.014884476167923953, | |
| "grad_norm": 0.7143723964691162, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.8341, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.015155103007340753, | |
| "grad_norm": 0.7415910959243774, | |
| "learning_rate": 2.4127512582437486e-06, | |
| "loss": 0.8152, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.015425729846757552, | |
| "grad_norm": 0.8374602794647217, | |
| "learning_rate": 2.325608815639687e-06, | |
| "loss": 0.8897, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.01569635668617435, | |
| "grad_norm": 0.8707734942436218, | |
| "learning_rate": 2.238678841830867e-06, | |
| "loss": 0.9219, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.01596698352559115, | |
| "grad_norm": 0.815484881401062, | |
| "learning_rate": 2.1520672475998374e-06, | |
| "loss": 0.8614, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.01623761036500795, | |
| "grad_norm": 0.7766671776771545, | |
| "learning_rate": 2.0658795558326745e-06, | |
| "loss": 0.8877, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01650823720442475, | |
| "grad_norm": 0.8103740215301514, | |
| "learning_rate": 1.9802207729556023e-06, | |
| "loss": 0.9241, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.01677886404384155, | |
| "grad_norm": 0.9171229004859924, | |
| "learning_rate": 1.895195261000831e-06, | |
| "loss": 0.9715, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.017049490883258345, | |
| "grad_norm": 0.823610246181488, | |
| "learning_rate": 1.8109066104575023e-06, | |
| "loss": 0.9178, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.017320117722675145, | |
| "grad_norm": 0.8297237157821655, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.9384, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.017590744562091944, | |
| "grad_norm": 0.8308224678039551, | |
| "learning_rate": 1.6449496416858285e-06, | |
| "loss": 0.91, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.017861371401508744, | |
| "grad_norm": 0.8265281319618225, | |
| "learning_rate": 1.56348351646022e-06, | |
| "loss": 0.8696, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.018131998240925543, | |
| "grad_norm": 0.8544564843177795, | |
| "learning_rate": 1.4831583923105e-06, | |
| "loss": 0.9598, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.018402625080342343, | |
| "grad_norm": 0.9564810991287231, | |
| "learning_rate": 1.4040721330273063e-06, | |
| "loss": 0.9123, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.018673251919759142, | |
| "grad_norm": 0.9041321873664856, | |
| "learning_rate": 1.3263210930352737e-06, | |
| "loss": 0.9157, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.01894387875917594, | |
| "grad_norm": 0.9885373711585999, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "loss": 0.9612, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01921450559859274, | |
| "grad_norm": 0.9514999389648438, | |
| "learning_rate": 1.1752018394169882e-06, | |
| "loss": 0.969, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.01948513243800954, | |
| "grad_norm": 0.9459763169288635, | |
| "learning_rate": 1.1020177413231334e-06, | |
| "loss": 0.9962, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.01975575927742634, | |
| "grad_norm": 0.9458332657814026, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 0.9358, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.02002638611684314, | |
| "grad_norm": 0.9821689128875732, | |
| "learning_rate": 9.608463116858544e-07, | |
| "loss": 1.0361, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.020297012956259936, | |
| "grad_norm": 0.951698362827301, | |
| "learning_rate": 8.930309757836517e-07, | |
| "loss": 1.0104, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.020567639795676735, | |
| "grad_norm": 1.0073827505111694, | |
| "learning_rate": 8.271734841028553e-07, | |
| "loss": 0.9367, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.020838266635093534, | |
| "grad_norm": 1.1683809757232666, | |
| "learning_rate": 7.633540738525066e-07, | |
| "loss": 1.0249, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.021108893474510334, | |
| "grad_norm": 1.0686205625534058, | |
| "learning_rate": 7.016504991533727e-07, | |
| "loss": 1.0685, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.021379520313927133, | |
| "grad_norm": 0.9999198317527771, | |
| "learning_rate": 6.421379363065142e-07, | |
| "loss": 0.9795, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.021650147153343933, | |
| "grad_norm": 1.199865460395813, | |
| "learning_rate": 5.848888922025553e-07, | |
| "loss": 1.1232, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.021920773992760732, | |
| "grad_norm": 1.196691870689392, | |
| "learning_rate": 5.299731159831953e-07, | |
| "loss": 1.0305, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.022191400832177532, | |
| "grad_norm": 1.3286807537078857, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 1.0715, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.02246202767159433, | |
| "grad_norm": 1.3111743927001953, | |
| "learning_rate": 4.27406068612396e-07, | |
| "loss": 1.053, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.02273265451101113, | |
| "grad_norm": 1.197509527206421, | |
| "learning_rate": 3.798797596089351e-07, | |
| "loss": 1.1335, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.02300328135042793, | |
| "grad_norm": 1.2589415311813354, | |
| "learning_rate": 3.3493649053890325e-07, | |
| "loss": 1.0684, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.023273908189844726, | |
| "grad_norm": 1.5249485969543457, | |
| "learning_rate": 2.9263101785268253e-07, | |
| "loss": 1.1123, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.023544535029261526, | |
| "grad_norm": 1.3184010982513428, | |
| "learning_rate": 2.53014884252083e-07, | |
| "loss": 1.0367, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.023815161868678325, | |
| "grad_norm": 1.3574773073196411, | |
| "learning_rate": 2.1613635589349756e-07, | |
| "loss": 1.1233, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.024085788708095125, | |
| "grad_norm": 1.364808440208435, | |
| "learning_rate": 1.8204036358303173e-07, | |
| "loss": 1.0077, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.024356415547511924, | |
| "grad_norm": 1.426081657409668, | |
| "learning_rate": 1.507684480352292e-07, | |
| "loss": 1.0295, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.024627042386928723, | |
| "grad_norm": 1.6618572473526, | |
| "learning_rate": 1.223587092621162e-07, | |
| "loss": 0.9982, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.024897669226345523, | |
| "grad_norm": 1.6236708164215088, | |
| "learning_rate": 9.684576015420277e-08, | |
| "loss": 1.058, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.025168296065762322, | |
| "grad_norm": 1.7425477504730225, | |
| "learning_rate": 7.426068431000883e-08, | |
| "loss": 1.0255, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.025438922905179122, | |
| "grad_norm": 1.9277325868606567, | |
| "learning_rate": 5.463099816548578e-08, | |
| "loss": 1.2349, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.02570954974459592, | |
| "grad_norm": 1.8921107053756714, | |
| "learning_rate": 3.798061746947995e-08, | |
| "loss": 1.1955, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.02598017658401272, | |
| "grad_norm": 2.8468291759490967, | |
| "learning_rate": 2.4329828146074096e-08, | |
| "loss": 1.4125, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.02625080342342952, | |
| "grad_norm": 3.475755453109741, | |
| "learning_rate": 1.3695261579316776e-08, | |
| "loss": 1.3095, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.026521430262846316, | |
| "grad_norm": 4.424863815307617, | |
| "learning_rate": 6.089874350439507e-09, | |
| "loss": 1.3732, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.026792057102263116, | |
| "grad_norm": 5.109591960906982, | |
| "learning_rate": 1.5229324522605949e-09, | |
| "loss": 1.2857, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.027062683941679915, | |
| "grad_norm": 6.888213157653809, | |
| "learning_rate": 0.0, | |
| "loss": 1.4212, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.027062683941679915, | |
| "eval_loss": 1.0187755823135376, | |
| "eval_runtime": 580.4087, | |
| "eval_samples_per_second": 10.723, | |
| "eval_steps_per_second": 2.681, | |
| "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": 1.539540430796882e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |