| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9989801121876594, | |
| "eval_steps": 245, | |
| "global_step": 980, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002039775624681285, | |
| "grad_norm": 0.08994754403829575, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002039775624681285, | |
| "eval_loss": 2.6805498600006104, | |
| "eval_runtime": 48.2372, | |
| "eval_samples_per_second": 17.124, | |
| "eval_steps_per_second": 2.156, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00407955124936257, | |
| "grad_norm": 0.09641231596469879, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7875, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006119326874043855, | |
| "grad_norm": 0.10044872015714645, | |
| "learning_rate": 6e-05, | |
| "loss": 2.6516, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00815910249872514, | |
| "grad_norm": 0.08677750825881958, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4109, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010198878123406425, | |
| "grad_norm": 0.10869669914245605, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6336, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01223865374808771, | |
| "grad_norm": 0.1180991679430008, | |
| "learning_rate": 0.00012, | |
| "loss": 2.6001, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014278429372768995, | |
| "grad_norm": 0.1641693264245987, | |
| "learning_rate": 0.00014, | |
| "loss": 2.9137, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01631820499745028, | |
| "grad_norm": 0.17794281244277954, | |
| "learning_rate": 0.00016, | |
| "loss": 2.835, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018357980622131564, | |
| "grad_norm": 0.16260501742362976, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6015, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02039775624681285, | |
| "grad_norm": 0.13795699179172516, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2552, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022437531871494134, | |
| "grad_norm": 0.15532873570919037, | |
| "learning_rate": 0.00019999947552365961, | |
| "loss": 2.4393, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02447730749617542, | |
| "grad_norm": 0.159002423286438, | |
| "learning_rate": 0.00019999790210013988, | |
| "loss": 2.7684, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.026517083120856707, | |
| "grad_norm": 0.17115084826946259, | |
| "learning_rate": 0.0001999952797459453, | |
| "loss": 2.2409, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02855685874553799, | |
| "grad_norm": 0.26108402013778687, | |
| "learning_rate": 0.0001999916084885832, | |
| "loss": 2.6388, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.030596634370219276, | |
| "grad_norm": 0.29758986830711365, | |
| "learning_rate": 0.00019998688836656323, | |
| "loss": 2.4358, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03263640999490056, | |
| "grad_norm": 0.2338196337223053, | |
| "learning_rate": 0.0001999811194293973, | |
| "loss": 2.3898, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03467618561958185, | |
| "grad_norm": 0.2143183797597885, | |
| "learning_rate": 0.00019997430173759875, | |
| "loss": 2.6874, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03671596124426313, | |
| "grad_norm": 0.19598309695720673, | |
| "learning_rate": 0.00019996643536268204, | |
| "loss": 2.409, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.038755736868944415, | |
| "grad_norm": 0.16046980023384094, | |
| "learning_rate": 0.00019995752038716168, | |
| "loss": 2.2378, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0407955124936257, | |
| "grad_norm": 0.15274696052074432, | |
| "learning_rate": 0.00019994755690455152, | |
| "loss": 2.3413, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04283528811830699, | |
| "grad_norm": 0.24761317670345306, | |
| "learning_rate": 0.0001999365450193638, | |
| "loss": 2.3382, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04487506374298827, | |
| "grad_norm": 0.2602517604827881, | |
| "learning_rate": 0.00019992448484710797, | |
| "loss": 2.3355, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.046914839367669554, | |
| "grad_norm": 0.25506100058555603, | |
| "learning_rate": 0.00019991137651428957, | |
| "loss": 2.4828, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04895461499235084, | |
| "grad_norm": 0.19493895769119263, | |
| "learning_rate": 0.0001998972201584088, | |
| "loss": 2.3154, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05099439061703213, | |
| "grad_norm": 0.16005843877792358, | |
| "learning_rate": 0.0001998820159279591, | |
| "loss": 2.1472, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.053034166241713414, | |
| "grad_norm": 0.17840257287025452, | |
| "learning_rate": 0.00019986576398242566, | |
| "loss": 2.1624, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05507394186639469, | |
| "grad_norm": 0.15280942618846893, | |
| "learning_rate": 0.0001998484644922837, | |
| "loss": 2.0526, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05711371749107598, | |
| "grad_norm": 0.16933050751686096, | |
| "learning_rate": 0.00019983011763899673, | |
| "loss": 2.2176, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.059153493115757266, | |
| "grad_norm": 0.21265609562397003, | |
| "learning_rate": 0.0001998107236150145, | |
| "loss": 2.2559, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06119326874043855, | |
| "grad_norm": 0.19340573251247406, | |
| "learning_rate": 0.00019979028262377118, | |
| "loss": 2.3202, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06323304436511984, | |
| "grad_norm": 0.16693681478500366, | |
| "learning_rate": 0.0001997687948796831, | |
| "loss": 2.0623, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06527281998980113, | |
| "grad_norm": 0.18830184638500214, | |
| "learning_rate": 0.00019974626060814647, | |
| "loss": 2.1929, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06731259561448241, | |
| "grad_norm": 0.16206099092960358, | |
| "learning_rate": 0.0001997226800455352, | |
| "loss": 2.3048, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0693523712391637, | |
| "grad_norm": 0.21650008857250214, | |
| "learning_rate": 0.00019969805343919821, | |
| "loss": 2.2928, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07139214686384497, | |
| "grad_norm": 0.19560708105564117, | |
| "learning_rate": 0.00019967238104745696, | |
| "loss": 2.4389, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07343192248852626, | |
| "grad_norm": 0.17428375780582428, | |
| "learning_rate": 0.00019964566313960264, | |
| "loss": 2.1017, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07547169811320754, | |
| "grad_norm": 0.14846819639205933, | |
| "learning_rate": 0.00019961789999589356, | |
| "loss": 2.0431, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07751147373788883, | |
| "grad_norm": 0.14796215295791626, | |
| "learning_rate": 0.00019958909190755187, | |
| "loss": 2.0363, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07955124936257012, | |
| "grad_norm": 0.17396488785743713, | |
| "learning_rate": 0.0001995592391767608, | |
| "loss": 2.0835, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0815910249872514, | |
| "grad_norm": 0.1914213001728058, | |
| "learning_rate": 0.0001995283421166614, | |
| "loss": 2.0242, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08363080061193269, | |
| "grad_norm": 0.16040053963661194, | |
| "learning_rate": 0.00019949640105134918, | |
| "loss": 2.2171, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08567057623661398, | |
| "grad_norm": 0.16291815042495728, | |
| "learning_rate": 0.00019946341631587087, | |
| "loss": 2.2144, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08771035186129526, | |
| "grad_norm": 0.16890890896320343, | |
| "learning_rate": 0.00019942938825622065, | |
| "loss": 2.0775, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08975012748597654, | |
| "grad_norm": 0.18898645043373108, | |
| "learning_rate": 0.0001993943172293368, | |
| "loss": 2.262, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09178990311065782, | |
| "grad_norm": 0.19105440378189087, | |
| "learning_rate": 0.00019935820360309777, | |
| "loss": 2.0232, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09382967873533911, | |
| "grad_norm": 0.17944768071174622, | |
| "learning_rate": 0.00019932104775631846, | |
| "loss": 2.2564, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0958694543600204, | |
| "grad_norm": 0.1691497266292572, | |
| "learning_rate": 0.0001992828500787461, | |
| "loss": 2.0249, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09790922998470168, | |
| "grad_norm": 0.18704521656036377, | |
| "learning_rate": 0.00019924361097105623, | |
| "loss": 2.2058, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09994900560938297, | |
| "grad_norm": 0.24133948981761932, | |
| "learning_rate": 0.00019920333084484857, | |
| "loss": 2.2835, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10198878123406425, | |
| "grad_norm": 0.210649773478508, | |
| "learning_rate": 0.00019916201012264254, | |
| "loss": 2.1052, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10402855685874554, | |
| "grad_norm": 0.19624340534210205, | |
| "learning_rate": 0.00019911964923787295, | |
| "loss": 2.2474, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.10606833248342683, | |
| "grad_norm": 0.2529032230377197, | |
| "learning_rate": 0.0001990762486348855, | |
| "loss": 1.9782, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 0.2078029066324234, | |
| "learning_rate": 0.00019903180876893194, | |
| "loss": 2.3627, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.11014788373278939, | |
| "grad_norm": 0.23153568804264069, | |
| "learning_rate": 0.00019898633010616542, | |
| "loss": 1.9749, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.11218765935747067, | |
| "grad_norm": 0.20798815786838531, | |
| "learning_rate": 0.00019893981312363562, | |
| "loss": 2.111, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.11422743498215196, | |
| "grad_norm": 0.20742167532444, | |
| "learning_rate": 0.00019889225830928365, | |
| "loss": 2.113, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.11626721060683325, | |
| "grad_norm": 0.21235893666744232, | |
| "learning_rate": 0.00019884366616193706, | |
| "loss": 2.0307, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.11830698623151453, | |
| "grad_norm": 0.19754983484745026, | |
| "learning_rate": 0.0001987940371913044, | |
| "loss": 1.9883, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.12034676185619582, | |
| "grad_norm": 0.20224173367023468, | |
| "learning_rate": 0.0001987433719179702, | |
| "loss": 2.0299, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.1223865374808771, | |
| "grad_norm": 0.20431111752986908, | |
| "learning_rate": 0.00019869167087338907, | |
| "loss": 2.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12442631310555839, | |
| "grad_norm": 0.21355204284191132, | |
| "learning_rate": 0.00019863893459988062, | |
| "loss": 1.9365, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.12646608873023968, | |
| "grad_norm": 0.2394651174545288, | |
| "learning_rate": 0.00019858516365062334, | |
| "loss": 1.9264, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.12850586435492095, | |
| "grad_norm": 0.20690159499645233, | |
| "learning_rate": 0.00019853035858964906, | |
| "loss": 1.9777, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.13054563997960225, | |
| "grad_norm": 0.21029432117938995, | |
| "learning_rate": 0.00019847451999183694, | |
| "loss": 2.2063, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.13258541560428352, | |
| "grad_norm": 0.2483580857515335, | |
| "learning_rate": 0.00019841764844290744, | |
| "loss": 1.9817, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.13462519122896482, | |
| "grad_norm": 0.2200578898191452, | |
| "learning_rate": 0.0001983597445394162, | |
| "loss": 1.8286, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.1366649668536461, | |
| "grad_norm": 0.23194506764411926, | |
| "learning_rate": 0.00019830080888874778, | |
| "loss": 1.8918, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.1387047424783274, | |
| "grad_norm": 0.2092316597700119, | |
| "learning_rate": 0.00019824084210910925, | |
| "loss": 2.0326, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.14074451810300867, | |
| "grad_norm": 0.226849764585495, | |
| "learning_rate": 0.00019817984482952376, | |
| "loss": 2.1387, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.14278429372768994, | |
| "grad_norm": 0.25519493222236633, | |
| "learning_rate": 0.0001981178176898239, | |
| "loss": 1.9261, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14482406935237124, | |
| "grad_norm": 0.2155541330575943, | |
| "learning_rate": 0.00019805476134064507, | |
| "loss": 2.2176, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.14686384497705252, | |
| "grad_norm": 0.23612210154533386, | |
| "learning_rate": 0.00019799067644341844, | |
| "loss": 2.1125, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.14890362060173382, | |
| "grad_norm": 0.2563931941986084, | |
| "learning_rate": 0.00019792556367036432, | |
| "loss": 1.9459, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.1509433962264151, | |
| "grad_norm": 0.34834709763526917, | |
| "learning_rate": 0.0001978594237044849, | |
| "loss": 2.091, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.1529831718510964, | |
| "grad_norm": 0.221855029463768, | |
| "learning_rate": 0.00019779225723955707, | |
| "loss": 1.8867, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.15502294747577766, | |
| "grad_norm": 0.2613975405693054, | |
| "learning_rate": 0.0001977240649801253, | |
| "loss": 1.9889, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.15706272310045896, | |
| "grad_norm": 0.3117937743663788, | |
| "learning_rate": 0.00019765484764149415, | |
| "loss": 2.0743, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.15910249872514023, | |
| "grad_norm": 0.23428964614868164, | |
| "learning_rate": 0.00019758460594972068, | |
| "loss": 2.1752, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.1611422743498215, | |
| "grad_norm": 0.23182815313339233, | |
| "learning_rate": 0.00019751334064160706, | |
| "loss": 1.9315, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.1631820499745028, | |
| "grad_norm": 0.3055015206336975, | |
| "learning_rate": 0.00019744105246469263, | |
| "loss": 2.0348, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16522182559918408, | |
| "grad_norm": 0.22985045611858368, | |
| "learning_rate": 0.00019736774217724614, | |
| "loss": 1.792, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.16726160122386538, | |
| "grad_norm": 0.2585189938545227, | |
| "learning_rate": 0.00019729341054825782, | |
| "loss": 2.0945, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.16930137684854665, | |
| "grad_norm": 0.2798707187175751, | |
| "learning_rate": 0.00019721805835743134, | |
| "loss": 2.0114, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.17134115247322795, | |
| "grad_norm": 0.2886582016944885, | |
| "learning_rate": 0.00019714168639517544, | |
| "loss": 2.0575, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.17338092809790923, | |
| "grad_norm": 0.2944013178348541, | |
| "learning_rate": 0.00019706429546259593, | |
| "loss": 2.1074, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.17542070372259053, | |
| "grad_norm": 0.318002313375473, | |
| "learning_rate": 0.00019698588637148703, | |
| "loss": 1.9883, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.1774604793472718, | |
| "grad_norm": 0.256496787071228, | |
| "learning_rate": 0.00019690645994432305, | |
| "loss": 1.8408, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.17950025497195307, | |
| "grad_norm": 0.3593447208404541, | |
| "learning_rate": 0.0001968260170142496, | |
| "loss": 1.9313, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.18154003059663437, | |
| "grad_norm": 0.4645783305168152, | |
| "learning_rate": 0.00019674455842507492, | |
| "loss": 1.9448, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.18357980622131564, | |
| "grad_norm": 0.2802218198776245, | |
| "learning_rate": 0.00019666208503126112, | |
| "loss": 1.9091, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18561958184599694, | |
| "grad_norm": 0.39699026942253113, | |
| "learning_rate": 0.00019657859769791505, | |
| "loss": 1.9936, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.18765935747067822, | |
| "grad_norm": 0.4515025317668915, | |
| "learning_rate": 0.00019649409730077935, | |
| "loss": 2.2269, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.18969913309535952, | |
| "grad_norm": 0.24775496125221252, | |
| "learning_rate": 0.00019640858472622316, | |
| "loss": 1.8843, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.1917389087200408, | |
| "grad_norm": 0.35014575719833374, | |
| "learning_rate": 0.00019632206087123296, | |
| "loss": 2.0159, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.1937786843447221, | |
| "grad_norm": 0.4293341040611267, | |
| "learning_rate": 0.00019623452664340306, | |
| "loss": 2.1129, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.19581845996940336, | |
| "grad_norm": 0.249364972114563, | |
| "learning_rate": 0.000196145982960926, | |
| "loss": 2.1385, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.19785823559408466, | |
| "grad_norm": 0.3796793222427368, | |
| "learning_rate": 0.00019605643075258321, | |
| "loss": 1.9737, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.19989801121876594, | |
| "grad_norm": 0.41410332918167114, | |
| "learning_rate": 0.00019596587095773495, | |
| "loss": 1.895, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2019377868434472, | |
| "grad_norm": 0.2810049057006836, | |
| "learning_rate": 0.0001958743045263106, | |
| "loss": 1.9859, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2039775624681285, | |
| "grad_norm": 0.37417009472846985, | |
| "learning_rate": 0.00019578173241879872, | |
| "loss": 1.9447, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.20601733809280978, | |
| "grad_norm": 0.33988890051841736, | |
| "learning_rate": 0.0001956881556062369, | |
| "loss": 1.8362, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.20805711371749108, | |
| "grad_norm": 0.27952101826667786, | |
| "learning_rate": 0.00019559357507020162, | |
| "loss": 1.9745, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.21009688934217235, | |
| "grad_norm": 0.24870562553405762, | |
| "learning_rate": 0.00019549799180279792, | |
| "loss": 1.8926, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.21213666496685366, | |
| "grad_norm": 0.33430561423301697, | |
| "learning_rate": 0.00019540140680664913, | |
| "loss": 2.0914, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.21417644059153493, | |
| "grad_norm": 0.3203825056552887, | |
| "learning_rate": 0.0001953038210948861, | |
| "loss": 2.0238, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 0.2822887897491455, | |
| "learning_rate": 0.00019520523569113677, | |
| "loss": 2.053, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.2182559918408975, | |
| "grad_norm": 0.31055620312690735, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.8936, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.22029576746557877, | |
| "grad_norm": 0.3920172452926636, | |
| "learning_rate": 0.0001950050699546116, | |
| "loss": 2.1061, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.22233554309026007, | |
| "grad_norm": 0.2737603187561035, | |
| "learning_rate": 0.00019490349172147963, | |
| "loss": 2.0772, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.22437531871494135, | |
| "grad_norm": 0.27526190876960754, | |
| "learning_rate": 0.00019480091799562704, | |
| "loss": 1.9078, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.22641509433962265, | |
| "grad_norm": 0.3213340938091278, | |
| "learning_rate": 0.00019469734985300371, | |
| "loss": 1.8632, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.22845486996430392, | |
| "grad_norm": 0.3409796953201294, | |
| "learning_rate": 0.00019459278837999046, | |
| "loss": 1.8264, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.23049464558898522, | |
| "grad_norm": 0.2637316882610321, | |
| "learning_rate": 0.00019448723467338763, | |
| "loss": 1.9274, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.2325344212136665, | |
| "grad_norm": 0.2738693952560425, | |
| "learning_rate": 0.00019438068984040365, | |
| "loss": 2.0925, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.2345741968383478, | |
| "grad_norm": 0.43626368045806885, | |
| "learning_rate": 0.00019427315499864344, | |
| "loss": 1.9424, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.23661397246302907, | |
| "grad_norm": 0.3207686245441437, | |
| "learning_rate": 0.00019416463127609656, | |
| "loss": 1.8188, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.23865374808771037, | |
| "grad_norm": 0.28913381695747375, | |
| "learning_rate": 0.0001940551198111255, | |
| "loss": 1.9561, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.24069352371239164, | |
| "grad_norm": 0.3558366894721985, | |
| "learning_rate": 0.00019394462175245381, | |
| "loss": 1.8839, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.2427332993370729, | |
| "grad_norm": 0.3230222463607788, | |
| "learning_rate": 0.0001938331382591537, | |
| "loss": 1.8197, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.2447730749617542, | |
| "grad_norm": 0.31508007645606995, | |
| "learning_rate": 0.00019372067050063438, | |
| "loss": 2.0963, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.24681285058643548, | |
| "grad_norm": 0.28743404150009155, | |
| "learning_rate": 0.00019360721965662933, | |
| "loss": 1.8382, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.24885262621111678, | |
| "grad_norm": 0.32556018233299255, | |
| "learning_rate": 0.00019349278691718427, | |
| "loss": 1.8255, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.2508924018357981, | |
| "grad_norm": 0.3947349488735199, | |
| "learning_rate": 0.00019337737348264447, | |
| "loss": 2.1048, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.25293217746047936, | |
| "grad_norm": 0.280627965927124, | |
| "learning_rate": 0.00019326098056364222, | |
| "loss": 1.7557, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.25497195308516063, | |
| "grad_norm": 0.34356269240379333, | |
| "learning_rate": 0.00019314360938108425, | |
| "loss": 1.9692, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2570117287098419, | |
| "grad_norm": 0.30822035670280457, | |
| "learning_rate": 0.00019302526116613864, | |
| "loss": 1.9135, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.2590515043345232, | |
| "grad_norm": 0.28359460830688477, | |
| "learning_rate": 0.00019290593716022217, | |
| "loss": 2.0667, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.2610912799592045, | |
| "grad_norm": 0.2782716751098633, | |
| "learning_rate": 0.00019278563861498723, | |
| "loss": 1.7958, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.2631310555838858, | |
| "grad_norm": 0.2571290135383606, | |
| "learning_rate": 0.00019266436679230865, | |
| "loss": 2.1198, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.26517083120856705, | |
| "grad_norm": 0.3336668908596039, | |
| "learning_rate": 0.00019254212296427044, | |
| "loss": 1.8137, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2672106068332483, | |
| "grad_norm": 0.23998981714248657, | |
| "learning_rate": 0.00019241890841315248, | |
| "loss": 2.0071, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.26925038245792965, | |
| "grad_norm": 0.3191507160663605, | |
| "learning_rate": 0.0001922947244314172, | |
| "loss": 2.0239, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.2712901580826109, | |
| "grad_norm": 0.30696266889572144, | |
| "learning_rate": 0.0001921695723216957, | |
| "loss": 2.2377, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.2733299337072922, | |
| "grad_norm": 0.2688175439834595, | |
| "learning_rate": 0.00019204345339677442, | |
| "loss": 1.8686, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.27536970933197347, | |
| "grad_norm": 0.27408865094184875, | |
| "learning_rate": 0.00019191636897958122, | |
| "loss": 2.0253, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.2774094849566548, | |
| "grad_norm": 0.2917419672012329, | |
| "learning_rate": 0.00019178832040317155, | |
| "loss": 1.905, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.27944926058133607, | |
| "grad_norm": 0.27972346544265747, | |
| "learning_rate": 0.0001916593090107143, | |
| "loss": 1.8001, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.28148903620601734, | |
| "grad_norm": 0.2744503915309906, | |
| "learning_rate": 0.00019152933615547798, | |
| "loss": 1.9057, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.2835288118306986, | |
| "grad_norm": 0.27640461921691895, | |
| "learning_rate": 0.0001913984032008163, | |
| "loss": 2.0683, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.2855685874553799, | |
| "grad_norm": 0.28741398453712463, | |
| "learning_rate": 0.00019126651152015403, | |
| "loss": 1.9567, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2876083630800612, | |
| "grad_norm": 0.31334587931632996, | |
| "learning_rate": 0.0001911336624969725, | |
| "loss": 1.8974, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.2896481387047425, | |
| "grad_norm": 0.2697933614253998, | |
| "learning_rate": 0.00019099985752479506, | |
| "loss": 1.8786, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.29168791432942376, | |
| "grad_norm": 0.2917918562889099, | |
| "learning_rate": 0.00019086509800717258, | |
| "loss": 2.0443, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.29372768995410503, | |
| "grad_norm": 0.2908966541290283, | |
| "learning_rate": 0.00019072938535766865, | |
| "loss": 1.9817, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.29576746557878636, | |
| "grad_norm": 0.2819146513938904, | |
| "learning_rate": 0.0001905927209998447, | |
| "loss": 2.0689, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.29780724120346763, | |
| "grad_norm": 0.3112149238586426, | |
| "learning_rate": 0.0001904551063672452, | |
| "loss": 1.9045, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.2998470168281489, | |
| "grad_norm": 0.2511192560195923, | |
| "learning_rate": 0.00019031654290338254, | |
| "loss": 2.007, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.3018867924528302, | |
| "grad_norm": 0.2944158911705017, | |
| "learning_rate": 0.00019017703206172185, | |
| "loss": 1.9059, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.30392656807751145, | |
| "grad_norm": 0.2799970209598541, | |
| "learning_rate": 0.0001900365753056659, | |
| "loss": 1.8268, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.3059663437021928, | |
| "grad_norm": 0.3119431436061859, | |
| "learning_rate": 0.00018989517410853955, | |
| "loss": 1.7999, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.30800611932687405, | |
| "grad_norm": 0.27174267172813416, | |
| "learning_rate": 0.00018975282995357446, | |
| "loss": 1.8971, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.3100458949515553, | |
| "grad_norm": 0.3147140443325043, | |
| "learning_rate": 0.00018960954433389345, | |
| "loss": 1.9755, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.3120856705762366, | |
| "grad_norm": 0.27466344833374023, | |
| "learning_rate": 0.00018946531875249493, | |
| "loss": 1.9819, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.3141254462009179, | |
| "grad_norm": 0.2912920117378235, | |
| "learning_rate": 0.00018932015472223693, | |
| "loss": 2.1079, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.3161652218255992, | |
| "grad_norm": 0.3123255968093872, | |
| "learning_rate": 0.00018917405376582145, | |
| "loss": 1.93, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.31820499745028047, | |
| "grad_norm": 0.3270852565765381, | |
| "learning_rate": 0.0001890270174157784, | |
| "loss": 1.8386, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.32024477307496174, | |
| "grad_norm": 0.30445969104766846, | |
| "learning_rate": 0.00018887904721444953, | |
| "loss": 2.1993, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.322284548699643, | |
| "grad_norm": 0.2974015474319458, | |
| "learning_rate": 0.00018873014471397224, | |
| "loss": 1.8965, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.32432432432432434, | |
| "grad_norm": 0.3236542046070099, | |
| "learning_rate": 0.00018858031147626325, | |
| "loss": 2.041, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.3263640999490056, | |
| "grad_norm": 0.2958833575248718, | |
| "learning_rate": 0.00018842954907300236, | |
| "loss": 1.8681, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3284038755736869, | |
| "grad_norm": 0.27163368463516235, | |
| "learning_rate": 0.00018827785908561584, | |
| "loss": 1.9664, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.33044365119836816, | |
| "grad_norm": 0.2662605941295624, | |
| "learning_rate": 0.0001881252431052599, | |
| "loss": 1.9255, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.3324834268230495, | |
| "grad_norm": 0.2995011508464813, | |
| "learning_rate": 0.00018797170273280388, | |
| "loss": 2.1172, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.33452320244773076, | |
| "grad_norm": 0.2997836768627167, | |
| "learning_rate": 0.00018781723957881372, | |
| "loss": 1.9044, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.33656297807241203, | |
| "grad_norm": 0.2867211401462555, | |
| "learning_rate": 0.0001876618552635348, | |
| "loss": 1.8, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.3386027536970933, | |
| "grad_norm": 0.2972771227359772, | |
| "learning_rate": 0.000187505551416875, | |
| "loss": 1.7879, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.3406425293217746, | |
| "grad_norm": 0.27393755316734314, | |
| "learning_rate": 0.00018734832967838775, | |
| "loss": 2.1209, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.3426823049464559, | |
| "grad_norm": 0.31422799825668335, | |
| "learning_rate": 0.00018719019169725472, | |
| "loss": 1.9435, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.3447220805711372, | |
| "grad_norm": 0.3372005224227905, | |
| "learning_rate": 0.00018703113913226847, | |
| "loss": 2.0911, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.34676185619581845, | |
| "grad_norm": 0.29995280504226685, | |
| "learning_rate": 0.00018687117365181512, | |
| "loss": 1.9077, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3488016318204997, | |
| "grad_norm": 0.2770789861679077, | |
| "learning_rate": 0.0001867102969338569, | |
| "loss": 1.7649, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.35084140744518105, | |
| "grad_norm": 0.2982628047466278, | |
| "learning_rate": 0.00018654851066591448, | |
| "loss": 2.0258, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.3528811830698623, | |
| "grad_norm": 0.2924087643623352, | |
| "learning_rate": 0.0001863858165450492, | |
| "loss": 1.9533, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.3549209586945436, | |
| "grad_norm": 0.29398518800735474, | |
| "learning_rate": 0.0001862222162778454, | |
| "loss": 1.8298, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.35696073431922487, | |
| "grad_norm": 0.34897300601005554, | |
| "learning_rate": 0.00018605771158039253, | |
| "loss": 1.7459, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.35900050994390614, | |
| "grad_norm": 0.33509624004364014, | |
| "learning_rate": 0.00018589230417826697, | |
| "loss": 1.8843, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.36104028556858747, | |
| "grad_norm": 0.30635756254196167, | |
| "learning_rate": 0.00018572599580651415, | |
| "loss": 2.0315, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.36308006119326874, | |
| "grad_norm": 0.3544027805328369, | |
| "learning_rate": 0.00018555878820963013, | |
| "loss": 1.9821, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.36511983681795, | |
| "grad_norm": 0.283241331577301, | |
| "learning_rate": 0.00018539068314154354, | |
| "loss": 1.7482, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.3671596124426313, | |
| "grad_norm": 0.2630005478858948, | |
| "learning_rate": 0.00018522168236559695, | |
| "loss": 1.887, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3691993880673126, | |
| "grad_norm": 0.2816585898399353, | |
| "learning_rate": 0.00018505178765452853, | |
| "loss": 1.8995, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.3712391636919939, | |
| "grad_norm": 0.30843281745910645, | |
| "learning_rate": 0.00018488100079045344, | |
| "loss": 1.943, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.37327893931667516, | |
| "grad_norm": 0.30149805545806885, | |
| "learning_rate": 0.00018470932356484508, | |
| "loss": 1.8764, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.37531871494135643, | |
| "grad_norm": 0.27851638197898865, | |
| "learning_rate": 0.00018453675777851627, | |
| "loss": 1.8901, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.37735849056603776, | |
| "grad_norm": 0.34025222063064575, | |
| "learning_rate": 0.00018436330524160047, | |
| "loss": 2.167, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.37939826619071904, | |
| "grad_norm": 0.3183801472187042, | |
| "learning_rate": 0.0001841889677735327, | |
| "loss": 1.9419, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.3814380418154003, | |
| "grad_norm": 0.3072781562805176, | |
| "learning_rate": 0.00018401374720303056, | |
| "loss": 1.9817, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.3834778174400816, | |
| "grad_norm": 0.2894771993160248, | |
| "learning_rate": 0.00018383764536807485, | |
| "loss": 2.114, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.38551759306476285, | |
| "grad_norm": 0.3198698163032532, | |
| "learning_rate": 0.0001836606641158905, | |
| "loss": 1.8609, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.3875573686894442, | |
| "grad_norm": 0.3462139964103699, | |
| "learning_rate": 0.00018348280530292713, | |
| "loss": 1.7753, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.38959714431412545, | |
| "grad_norm": 0.2793361246585846, | |
| "learning_rate": 0.00018330407079483952, | |
| "loss": 2.1784, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.3916369199388067, | |
| "grad_norm": 0.29519417881965637, | |
| "learning_rate": 0.0001831244624664681, | |
| "loss": 1.9627, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.393676695563488, | |
| "grad_norm": 0.3317961096763611, | |
| "learning_rate": 0.00018294398220181917, | |
| "loss": 1.7643, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.3957164711881693, | |
| "grad_norm": 0.3138796091079712, | |
| "learning_rate": 0.0001827626318940454, | |
| "loss": 1.792, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.3977562468128506, | |
| "grad_norm": 0.30172964930534363, | |
| "learning_rate": 0.00018258041344542566, | |
| "loss": 1.8828, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.3997960224375319, | |
| "grad_norm": 0.3473678529262543, | |
| "learning_rate": 0.00018239732876734527, | |
| "loss": 1.9373, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.40183579806221315, | |
| "grad_norm": 0.3263239562511444, | |
| "learning_rate": 0.00018221337978027583, | |
| "loss": 1.9933, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.4038755736868944, | |
| "grad_norm": 0.32656848430633545, | |
| "learning_rate": 0.00018202856841375518, | |
| "loss": 1.8501, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.40591534931157575, | |
| "grad_norm": 0.3206334412097931, | |
| "learning_rate": 0.00018184289660636715, | |
| "loss": 2.0026, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.407955124936257, | |
| "grad_norm": 0.31711164116859436, | |
| "learning_rate": 0.0001816563663057211, | |
| "loss": 1.9573, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4099949005609383, | |
| "grad_norm": 0.2891688048839569, | |
| "learning_rate": 0.00018146897946843163, | |
| "loss": 1.939, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.41203467618561956, | |
| "grad_norm": 0.3304015100002289, | |
| "learning_rate": 0.000181280738060098, | |
| "loss": 1.874, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.4140744518103009, | |
| "grad_norm": 0.2902586758136749, | |
| "learning_rate": 0.0001810916440552835, | |
| "loss": 1.8516, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.41611422743498216, | |
| "grad_norm": 0.3066134452819824, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.909, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.41815400305966344, | |
| "grad_norm": 0.2844925820827484, | |
| "learning_rate": 0.00018071090619916093, | |
| "loss": 1.8373, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.4201937786843447, | |
| "grad_norm": 0.2905077338218689, | |
| "learning_rate": 0.00018051926634161282, | |
| "loss": 1.8031, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.422233554309026, | |
| "grad_norm": 0.3110411763191223, | |
| "learning_rate": 0.00018032678187506187, | |
| "loss": 1.9915, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.4242733299337073, | |
| "grad_norm": 0.27634483575820923, | |
| "learning_rate": 0.00018013345481857903, | |
| "loss": 2.0072, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.4263131055583886, | |
| "grad_norm": 0.29069051146507263, | |
| "learning_rate": 0.0001799392872000736, | |
| "loss": 2.0632, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.42835288118306986, | |
| "grad_norm": 0.28966760635375977, | |
| "learning_rate": 0.00017974428105627208, | |
| "loss": 1.8184, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.43039265680775113, | |
| "grad_norm": 0.2768760621547699, | |
| "learning_rate": 0.00017954843843269664, | |
| "loss": 1.8344, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 0.30277568101882935, | |
| "learning_rate": 0.0001793517613836437, | |
| "loss": 1.931, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.43447220805711373, | |
| "grad_norm": 0.30833378434181213, | |
| "learning_rate": 0.00017915425197216245, | |
| "loss": 1.8319, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.436511983681795, | |
| "grad_norm": 0.2517772316932678, | |
| "learning_rate": 0.00017895591227003315, | |
| "loss": 2.0335, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.4385517593064763, | |
| "grad_norm": 0.3051300346851349, | |
| "learning_rate": 0.00017875674435774547, | |
| "loss": 1.8523, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.44059153493115755, | |
| "grad_norm": 0.331875741481781, | |
| "learning_rate": 0.00017855675032447648, | |
| "loss": 1.902, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.4426313105558389, | |
| "grad_norm": 0.3102109134197235, | |
| "learning_rate": 0.00017835593226806903, | |
| "loss": 1.9391, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.44467108618052015, | |
| "grad_norm": 0.28581124544143677, | |
| "learning_rate": 0.00017815429229500946, | |
| "loss": 1.9595, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.4467108618052014, | |
| "grad_norm": 0.2874554693698883, | |
| "learning_rate": 0.00017795183252040567, | |
| "loss": 1.8683, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.4487506374298827, | |
| "grad_norm": 0.3131530284881592, | |
| "learning_rate": 0.00017774855506796496, | |
| "loss": 2.003, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.450790413054564, | |
| "grad_norm": 0.3006989359855652, | |
| "learning_rate": 0.0001775444620699715, | |
| "loss": 1.8058, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.4528301886792453, | |
| "grad_norm": 0.29621464014053345, | |
| "learning_rate": 0.0001773395556672644, | |
| "loss": 1.9781, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.45486996430392657, | |
| "grad_norm": 0.325095534324646, | |
| "learning_rate": 0.00017713383800921478, | |
| "loss": 1.8633, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.45690973992860784, | |
| "grad_norm": 0.306911826133728, | |
| "learning_rate": 0.00017692731125370354, | |
| "loss": 1.9318, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.4589495155532891, | |
| "grad_norm": 0.335014283657074, | |
| "learning_rate": 0.00017671997756709863, | |
| "loss": 1.7637, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.46098929117797044, | |
| "grad_norm": 0.28670719265937805, | |
| "learning_rate": 0.00017651183912423228, | |
| "loss": 1.988, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.4630290668026517, | |
| "grad_norm": 0.2969343364238739, | |
| "learning_rate": 0.00017630289810837834, | |
| "loss": 1.7984, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.465068842427333, | |
| "grad_norm": 0.3015127182006836, | |
| "learning_rate": 0.0001760931567112291, | |
| "loss": 1.7022, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.46710861805201426, | |
| "grad_norm": 0.32308632135391235, | |
| "learning_rate": 0.00017588261713287267, | |
| "loss": 1.8067, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.4691483936766956, | |
| "grad_norm": 0.30818650126457214, | |
| "learning_rate": 0.00017567128158176953, | |
| "loss": 1.7096, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.47118816930137686, | |
| "grad_norm": 0.28488847613334656, | |
| "learning_rate": 0.00017545915227472965, | |
| "loss": 1.8784, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.47322794492605813, | |
| "grad_norm": 0.3801325857639313, | |
| "learning_rate": 0.00017524623143688902, | |
| "loss": 1.9555, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.4752677205507394, | |
| "grad_norm": 0.31661075353622437, | |
| "learning_rate": 0.00017503252130168657, | |
| "loss": 1.8717, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.47730749617542073, | |
| "grad_norm": 0.296003520488739, | |
| "learning_rate": 0.00017481802411084042, | |
| "loss": 1.7293, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.479347271800102, | |
| "grad_norm": 0.3210139274597168, | |
| "learning_rate": 0.0001746027421143246, | |
| "loss": 1.9587, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.4813870474247833, | |
| "grad_norm": 0.2968738079071045, | |
| "learning_rate": 0.00017438667757034546, | |
| "loss": 2.0743, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.48342682304946455, | |
| "grad_norm": 0.3373945355415344, | |
| "learning_rate": 0.00017416983274531775, | |
| "loss": 1.8239, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.4854665986741458, | |
| "grad_norm": 0.29180705547332764, | |
| "learning_rate": 0.0001739522099138411, | |
| "loss": 1.9563, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.48750637429882715, | |
| "grad_norm": 0.342316597700119, | |
| "learning_rate": 0.00017373381135867604, | |
| "loss": 1.9012, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.4895461499235084, | |
| "grad_norm": 0.29859068989753723, | |
| "learning_rate": 0.00017351463937072004, | |
| "loss": 1.723, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4915859255481897, | |
| "grad_norm": 0.32331928610801697, | |
| "learning_rate": 0.0001732946962489836, | |
| "loss": 1.9278, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.49362570117287097, | |
| "grad_norm": 0.3604521155357361, | |
| "learning_rate": 0.00017307398430056593, | |
| "loss": 1.9691, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.4956654767975523, | |
| "grad_norm": 0.30965346097946167, | |
| "learning_rate": 0.000172852505840631, | |
| "loss": 1.7225, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.49770525242223357, | |
| "grad_norm": 0.2769593894481659, | |
| "learning_rate": 0.00017263026319238301, | |
| "loss": 1.7938, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.49974502804691484, | |
| "grad_norm": 0.33169788122177124, | |
| "learning_rate": 0.00017240725868704218, | |
| "loss": 1.6576, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.49974502804691484, | |
| "eval_loss": 1.874290943145752, | |
| "eval_runtime": 49.8203, | |
| "eval_samples_per_second": 16.58, | |
| "eval_steps_per_second": 2.088, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.5017848036715962, | |
| "grad_norm": 0.3088040053844452, | |
| "learning_rate": 0.00017218349466382023, | |
| "loss": 1.7977, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.5038245792962774, | |
| "grad_norm": 0.3247360289096832, | |
| "learning_rate": 0.0001719589734698959, | |
| "loss": 1.9595, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.5058643549209587, | |
| "grad_norm": 0.30020302534103394, | |
| "learning_rate": 0.00017173369746039025, | |
| "loss": 1.7303, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.50790413054564, | |
| "grad_norm": 0.2880503833293915, | |
| "learning_rate": 0.00017150766899834204, | |
| "loss": 1.9203, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.5099439061703213, | |
| "grad_norm": 0.2775571048259735, | |
| "learning_rate": 0.00017128089045468294, | |
| "loss": 1.8347, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5119836817950025, | |
| "grad_norm": 0.31517794728279114, | |
| "learning_rate": 0.00017105336420821247, | |
| "loss": 1.9258, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.5140234574196838, | |
| "grad_norm": 0.315845251083374, | |
| "learning_rate": 0.0001708250926455733, | |
| "loss": 1.6125, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.5160632330443651, | |
| "grad_norm": 0.3020716607570648, | |
| "learning_rate": 0.00017059607816122618, | |
| "loss": 2.036, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.5181030086690463, | |
| "grad_norm": 0.3116091787815094, | |
| "learning_rate": 0.00017036632315742462, | |
| "loss": 1.7882, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.5201427842937277, | |
| "grad_norm": 0.2845454216003418, | |
| "learning_rate": 0.00017013583004418993, | |
| "loss": 1.9165, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.522182559918409, | |
| "grad_norm": 0.3218507468700409, | |
| "learning_rate": 0.00016990460123928575, | |
| "loss": 1.9143, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.5242223355430903, | |
| "grad_norm": 0.32271113991737366, | |
| "learning_rate": 0.00016967263916819287, | |
| "loss": 1.7233, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.5262621111677716, | |
| "grad_norm": 0.32956361770629883, | |
| "learning_rate": 0.00016943994626408363, | |
| "loss": 2.1151, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.5283018867924528, | |
| "grad_norm": 0.309712678194046, | |
| "learning_rate": 0.0001692065249677965, | |
| "loss": 1.7285, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.5303416624171341, | |
| "grad_norm": 0.3099533021450043, | |
| "learning_rate": 0.00016897237772781044, | |
| "loss": 1.8461, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5323814380418154, | |
| "grad_norm": 0.2932775914669037, | |
| "learning_rate": 0.00016873750700021915, | |
| "loss": 1.869, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.5344212136664966, | |
| "grad_norm": 0.2912542223930359, | |
| "learning_rate": 0.00016850191524870546, | |
| "loss": 1.7672, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.536460989291178, | |
| "grad_norm": 0.33142998814582825, | |
| "learning_rate": 0.00016826560494451537, | |
| "loss": 1.8723, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.5385007649158593, | |
| "grad_norm": 0.26213347911834717, | |
| "learning_rate": 0.00016802857856643215, | |
| "loss": 1.6971, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 0.2854675352573395, | |
| "learning_rate": 0.00016779083860075033, | |
| "loss": 1.8517, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.5425803161652218, | |
| "grad_norm": 0.3256230354309082, | |
| "learning_rate": 0.00016755238754124965, | |
| "loss": 1.9159, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.5446200917899031, | |
| "grad_norm": 0.30096253752708435, | |
| "learning_rate": 0.00016731322788916892, | |
| "loss": 1.7229, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.5466598674145844, | |
| "grad_norm": 0.2952723801136017, | |
| "learning_rate": 0.00016707336215317968, | |
| "loss": 1.8191, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.5486996430392657, | |
| "grad_norm": 0.32182615995407104, | |
| "learning_rate": 0.00016683279284936004, | |
| "loss": 1.9188, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.5507394186639469, | |
| "grad_norm": 0.3065682351589203, | |
| "learning_rate": 0.00016659152250116812, | |
| "loss": 1.5902, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5527791942886282, | |
| "grad_norm": 0.27141043543815613, | |
| "learning_rate": 0.00016634955363941574, | |
| "loss": 1.705, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.5548189699133096, | |
| "grad_norm": 0.3703926205635071, | |
| "learning_rate": 0.00016610688880224178, | |
| "loss": 1.9515, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.5568587455379909, | |
| "grad_norm": 0.3434322476387024, | |
| "learning_rate": 0.0001658635305350855, | |
| "loss": 1.6887, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.5588985211626721, | |
| "grad_norm": 0.2847291827201843, | |
| "learning_rate": 0.00016561948139065996, | |
| "loss": 2.0415, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.5609382967873534, | |
| "grad_norm": 0.27591603994369507, | |
| "learning_rate": 0.00016537474392892528, | |
| "loss": 1.8893, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5629780724120347, | |
| "grad_norm": 0.32474270462989807, | |
| "learning_rate": 0.00016512932071706152, | |
| "loss": 1.8589, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.565017848036716, | |
| "grad_norm": 0.33138149976730347, | |
| "learning_rate": 0.0001648832143294422, | |
| "loss": 1.7978, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.5670576236613972, | |
| "grad_norm": 0.321053683757782, | |
| "learning_rate": 0.0001646364273476067, | |
| "loss": 1.911, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.5690973992860785, | |
| "grad_norm": 0.313310444355011, | |
| "learning_rate": 0.00016438896236023375, | |
| "loss": 1.7816, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.5711371749107598, | |
| "grad_norm": 0.2893736958503723, | |
| "learning_rate": 0.000164140821963114, | |
| "loss": 1.7197, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5731769505354412, | |
| "grad_norm": 0.3043624758720398, | |
| "learning_rate": 0.00016389200875912278, | |
| "loss": 1.7415, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.5752167261601224, | |
| "grad_norm": 0.29861506819725037, | |
| "learning_rate": 0.00016364252535819282, | |
| "loss": 1.7317, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.5772565017848037, | |
| "grad_norm": 0.3631903827190399, | |
| "learning_rate": 0.000163392374377287, | |
| "loss": 1.8116, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.579296277409485, | |
| "grad_norm": 0.32387158274650574, | |
| "learning_rate": 0.00016314155844037074, | |
| "loss": 1.8652, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.5813360530341662, | |
| "grad_norm": 0.3442007899284363, | |
| "learning_rate": 0.00016289008017838445, | |
| "loss": 2.0466, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.5833758286588475, | |
| "grad_norm": 0.3226166367530823, | |
| "learning_rate": 0.0001626379422292162, | |
| "loss": 1.8803, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.5854156042835288, | |
| "grad_norm": 0.2765788733959198, | |
| "learning_rate": 0.00016238514723767374, | |
| "loss": 1.8048, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.5874553799082101, | |
| "grad_norm": 0.26808875799179077, | |
| "learning_rate": 0.0001621316978554569, | |
| "loss": 1.9358, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.5894951555328913, | |
| "grad_norm": 0.34248560667037964, | |
| "learning_rate": 0.00016187759674112973, | |
| "loss": 1.7614, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.5915349311575727, | |
| "grad_norm": 0.3485107123851776, | |
| "learning_rate": 0.00016162284656009274, | |
| "loss": 1.7487, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.593574706782254, | |
| "grad_norm": 0.31153398752212524, | |
| "learning_rate": 0.00016136744998455476, | |
| "loss": 2.0895, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.5956144824069353, | |
| "grad_norm": 0.3104468584060669, | |
| "learning_rate": 0.00016111140969350503, | |
| "loss": 1.6566, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.5976542580316165, | |
| "grad_norm": 0.32697245478630066, | |
| "learning_rate": 0.00016085472837268502, | |
| "loss": 1.7631, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.5996940336562978, | |
| "grad_norm": 0.3330870270729065, | |
| "learning_rate": 0.00016059740871456036, | |
| "loss": 1.6047, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.6017338092809791, | |
| "grad_norm": 0.3144790828227997, | |
| "learning_rate": 0.00016033945341829248, | |
| "loss": 1.5975, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.6037735849056604, | |
| "grad_norm": 0.32482099533081055, | |
| "learning_rate": 0.00016008086518971037, | |
| "loss": 1.9879, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.6058133605303416, | |
| "grad_norm": 0.320336252450943, | |
| "learning_rate": 0.0001598216467412822, | |
| "loss": 1.9723, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.6078531361550229, | |
| "grad_norm": 0.2934703528881073, | |
| "learning_rate": 0.00015956180079208682, | |
| "loss": 1.7771, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.6098929117797043, | |
| "grad_norm": 0.3081587851047516, | |
| "learning_rate": 0.0001593013300677853, | |
| "loss": 1.869, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.6119326874043856, | |
| "grad_norm": 0.30365437269210815, | |
| "learning_rate": 0.00015904023730059228, | |
| "loss": 1.795, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6139724630290668, | |
| "grad_norm": 0.3306022882461548, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 1.8786, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.6160122386537481, | |
| "grad_norm": 0.3081189692020416, | |
| "learning_rate": 0.00015851619659898623, | |
| "loss": 1.8389, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.6180520142784294, | |
| "grad_norm": 0.3126586973667145, | |
| "learning_rate": 0.00015825325416151222, | |
| "loss": 1.8404, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.6200917899031106, | |
| "grad_norm": 0.2832873463630676, | |
| "learning_rate": 0.000157989700674967, | |
| "loss": 1.9894, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.6221315655277919, | |
| "grad_norm": 0.3080177903175354, | |
| "learning_rate": 0.00015772553890390197, | |
| "loss": 1.9813, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.6241713411524732, | |
| "grad_norm": 0.30326464772224426, | |
| "learning_rate": 0.00015746077161924905, | |
| "loss": 1.7597, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.6262111167771545, | |
| "grad_norm": 0.3071492910385132, | |
| "learning_rate": 0.00015719540159829184, | |
| "loss": 1.8149, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.6282508924018358, | |
| "grad_norm": 0.3333245515823364, | |
| "learning_rate": 0.00015692943162463628, | |
| "loss": 1.9806, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.6302906680265171, | |
| "grad_norm": 0.2858702838420868, | |
| "learning_rate": 0.0001566628644881815, | |
| "loss": 1.7616, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.6323304436511984, | |
| "grad_norm": 0.27514535188674927, | |
| "learning_rate": 0.00015639570298509064, | |
| "loss": 1.7516, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6343702192758797, | |
| "grad_norm": 0.29323917627334595, | |
| "learning_rate": 0.00015612794991776147, | |
| "loss": 1.8444, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.6364099949005609, | |
| "grad_norm": 0.3227652907371521, | |
| "learning_rate": 0.00015585960809479696, | |
| "loss": 1.8715, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.6384497705252422, | |
| "grad_norm": 0.2898751497268677, | |
| "learning_rate": 0.00015559068033097582, | |
| "loss": 1.9242, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.6404895461499235, | |
| "grad_norm": 0.2990049421787262, | |
| "learning_rate": 0.00015532116944722308, | |
| "loss": 1.7412, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.6425293217746048, | |
| "grad_norm": 0.28128162026405334, | |
| "learning_rate": 0.00015505107827058036, | |
| "loss": 1.7801, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.644569097399286, | |
| "grad_norm": 0.32478880882263184, | |
| "learning_rate": 0.0001547804096341763, | |
| "loss": 1.681, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.6466088730239674, | |
| "grad_norm": 0.31724509596824646, | |
| "learning_rate": 0.00015450916637719684, | |
| "loss": 1.9405, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.6486486486486487, | |
| "grad_norm": 0.36439332365989685, | |
| "learning_rate": 0.00015423735134485536, | |
| "loss": 1.7013, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.65068842427333, | |
| "grad_norm": 0.3085692226886749, | |
| "learning_rate": 0.00015396496738836292, | |
| "loss": 1.7641, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.6527281998980112, | |
| "grad_norm": 0.2774830758571625, | |
| "learning_rate": 0.0001536920173648984, | |
| "loss": 1.6727, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6547679755226925, | |
| "grad_norm": 0.3212391138076782, | |
| "learning_rate": 0.0001534185041375783, | |
| "loss": 1.7221, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.6568077511473738, | |
| "grad_norm": 0.30237263441085815, | |
| "learning_rate": 0.00015314443057542703, | |
| "loss": 1.7456, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.658847526772055, | |
| "grad_norm": 0.2800453305244446, | |
| "learning_rate": 0.00015286979955334652, | |
| "loss": 1.7978, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.6608873023967363, | |
| "grad_norm": 0.28402194380760193, | |
| "learning_rate": 0.00015259461395208628, | |
| "loss": 1.8785, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.6629270780214176, | |
| "grad_norm": 0.3377262353897095, | |
| "learning_rate": 0.000152318876658213, | |
| "loss": 1.7113, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.664966853646099, | |
| "grad_norm": 0.376544326543808, | |
| "learning_rate": 0.00015204259056408046, | |
| "loss": 1.6237, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.6670066292707802, | |
| "grad_norm": 0.3138863742351532, | |
| "learning_rate": 0.00015176575856779904, | |
| "loss": 1.8357, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.6690464048954615, | |
| "grad_norm": 0.40277865529060364, | |
| "learning_rate": 0.00015148838357320537, | |
| "loss": 1.9038, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.6710861805201428, | |
| "grad_norm": 0.2998698055744171, | |
| "learning_rate": 0.0001512104684898319, | |
| "loss": 1.7583, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.6731259561448241, | |
| "grad_norm": 0.33020147681236267, | |
| "learning_rate": 0.00015093201623287631, | |
| "loss": 1.7446, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6751657317695053, | |
| "grad_norm": 0.3545725643634796, | |
| "learning_rate": 0.00015065302972317108, | |
| "loss": 1.8882, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.6772055073941866, | |
| "grad_norm": 0.2989177107810974, | |
| "learning_rate": 0.00015037351188715265, | |
| "loss": 1.7751, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.6792452830188679, | |
| "grad_norm": 0.3225865662097931, | |
| "learning_rate": 0.00015009346565683087, | |
| "loss": 1.8539, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.6812850586435492, | |
| "grad_norm": 0.31957486271858215, | |
| "learning_rate": 0.00014981289396975817, | |
| "loss": 1.6078, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.6833248342682305, | |
| "grad_norm": 0.323512464761734, | |
| "learning_rate": 0.00014953179976899878, | |
| "loss": 1.9539, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.6853646098929118, | |
| "grad_norm": 0.3451762795448303, | |
| "learning_rate": 0.00014925018600309785, | |
| "loss": 1.8435, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.6874043855175931, | |
| "grad_norm": 0.3474057614803314, | |
| "learning_rate": 0.0001489680556260505, | |
| "loss": 1.8385, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.6894441611422744, | |
| "grad_norm": 0.3119589686393738, | |
| "learning_rate": 0.00014868541159727096, | |
| "loss": 1.7582, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.6914839367669556, | |
| "grad_norm": 0.3289264738559723, | |
| "learning_rate": 0.0001484022568815613, | |
| "loss": 1.8391, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.6935237123916369, | |
| "grad_norm": 0.32644519209861755, | |
| "learning_rate": 0.00014811859444908052, | |
| "loss": 1.7676, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6955634880163182, | |
| "grad_norm": 0.2529926002025604, | |
| "learning_rate": 0.00014783442727531328, | |
| "loss": 1.6483, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.6976032636409994, | |
| "grad_norm": 0.39409515261650085, | |
| "learning_rate": 0.00014754975834103877, | |
| "loss": 1.8951, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.6996430392656807, | |
| "grad_norm": 0.312379390001297, | |
| "learning_rate": 0.00014726459063229945, | |
| "loss": 1.8388, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.7016828148903621, | |
| "grad_norm": 0.3048081696033478, | |
| "learning_rate": 0.00014697892714036958, | |
| "loss": 1.9482, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.7037225905150434, | |
| "grad_norm": 0.37214845418930054, | |
| "learning_rate": 0.00014669277086172406, | |
| "loss": 1.8466, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.7057623661397247, | |
| "grad_norm": 0.3273617923259735, | |
| "learning_rate": 0.00014640612479800686, | |
| "loss": 1.5934, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.7078021417644059, | |
| "grad_norm": 0.3283670246601105, | |
| "learning_rate": 0.00014611899195599953, | |
| "loss": 1.7837, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.7098419173890872, | |
| "grad_norm": 0.38148233294487, | |
| "learning_rate": 0.00014583137534758967, | |
| "loss": 1.8952, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.7118816930137685, | |
| "grad_norm": 0.35573315620422363, | |
| "learning_rate": 0.0001455432779897395, | |
| "loss": 1.6698, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.7139214686384497, | |
| "grad_norm": 0.362224280834198, | |
| "learning_rate": 0.00014525470290445392, | |
| "loss": 1.7698, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.715961244263131, | |
| "grad_norm": 0.3312818706035614, | |
| "learning_rate": 0.00014496565311874902, | |
| "loss": 1.7951, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.7180010198878123, | |
| "grad_norm": 0.3737257719039917, | |
| "learning_rate": 0.00014467613166462023, | |
| "loss": 1.9562, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.7200407955124937, | |
| "grad_norm": 0.37132444977760315, | |
| "learning_rate": 0.0001443861415790107, | |
| "loss": 1.9022, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.7220805711371749, | |
| "grad_norm": 0.30398017168045044, | |
| "learning_rate": 0.00014409568590377918, | |
| "loss": 2.0578, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.7241203467618562, | |
| "grad_norm": 0.3135487139225006, | |
| "learning_rate": 0.00014380476768566824, | |
| "loss": 1.777, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.7261601223865375, | |
| "grad_norm": 0.3089943826198578, | |
| "learning_rate": 0.00014351338997627234, | |
| "loss": 1.638, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.7281998980112188, | |
| "grad_norm": 0.2791310250759125, | |
| "learning_rate": 0.00014322155583200576, | |
| "loss": 1.7786, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.7302396736359, | |
| "grad_norm": 0.30986955761909485, | |
| "learning_rate": 0.00014292926831407061, | |
| "loss": 1.7467, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.7322794492605813, | |
| "grad_norm": 0.29783159494400024, | |
| "learning_rate": 0.0001426365304884246, | |
| "loss": 1.6486, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.7343192248852626, | |
| "grad_norm": 0.29579076170921326, | |
| "learning_rate": 0.00014234334542574906, | |
| "loss": 1.665, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7363590005099439, | |
| "grad_norm": 0.31017670035362244, | |
| "learning_rate": 0.00014204971620141647, | |
| "loss": 1.7287, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.7383987761346252, | |
| "grad_norm": 0.34222882986068726, | |
| "learning_rate": 0.00014175564589545854, | |
| "loss": 1.7475, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.7404385517593065, | |
| "grad_norm": 0.2956671714782715, | |
| "learning_rate": 0.00014146113759253362, | |
| "loss": 1.757, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.7424783273839878, | |
| "grad_norm": 0.35265278816223145, | |
| "learning_rate": 0.0001411661943818944, | |
| "loss": 1.6731, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.744518103008669, | |
| "grad_norm": 0.3606823682785034, | |
| "learning_rate": 0.00014087081935735564, | |
| "loss": 1.8684, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.7465578786333503, | |
| "grad_norm": 0.27310827374458313, | |
| "learning_rate": 0.00014057501561726157, | |
| "loss": 1.7656, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.7485976542580316, | |
| "grad_norm": 0.3064682185649872, | |
| "learning_rate": 0.0001402787862644534, | |
| "loss": 1.7646, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.7506374298827129, | |
| "grad_norm": 0.40648531913757324, | |
| "learning_rate": 0.0001399821344062369, | |
| "loss": 1.672, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.7526772055073941, | |
| "grad_norm": 0.28727683424949646, | |
| "learning_rate": 0.00013968506315434974, | |
| "loss": 1.5766, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.7547169811320755, | |
| "grad_norm": 0.30638012290000916, | |
| "learning_rate": 0.00013938757562492873, | |
| "loss": 1.6456, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.7567567567567568, | |
| "grad_norm": 0.3163774311542511, | |
| "learning_rate": 0.0001390896749384773, | |
| "loss": 1.8618, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.7587965323814381, | |
| "grad_norm": 0.36798760294914246, | |
| "learning_rate": 0.00013879136421983266, | |
| "loss": 2.1013, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.7608363080061193, | |
| "grad_norm": 0.30383849143981934, | |
| "learning_rate": 0.00013849264659813312, | |
| "loss": 1.7117, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.7628760836308006, | |
| "grad_norm": 0.35814371705055237, | |
| "learning_rate": 0.0001381935252067852, | |
| "loss": 1.9741, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.7649158592554819, | |
| "grad_norm": 0.29710692167282104, | |
| "learning_rate": 0.00013789400318343068, | |
| "loss": 1.5538, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.7669556348801632, | |
| "grad_norm": 0.30160966515541077, | |
| "learning_rate": 0.0001375940836699139, | |
| "loss": 1.7604, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.7689954105048444, | |
| "grad_norm": 0.28164952993392944, | |
| "learning_rate": 0.0001372937698122487, | |
| "loss": 1.736, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.7710351861295257, | |
| "grad_norm": 0.293729692697525, | |
| "learning_rate": 0.0001369930647605852, | |
| "loss": 1.9099, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.7730749617542071, | |
| "grad_norm": 0.28284940123558044, | |
| "learning_rate": 0.00013669197166917723, | |
| "loss": 1.7251, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.7751147373788884, | |
| "grad_norm": 0.26181384921073914, | |
| "learning_rate": 0.00013639049369634876, | |
| "loss": 1.6381, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7771545130035696, | |
| "grad_norm": 0.3301055431365967, | |
| "learning_rate": 0.00013608863400446113, | |
| "loss": 1.998, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.7791942886282509, | |
| "grad_norm": 0.3116731643676758, | |
| "learning_rate": 0.00013578639575987958, | |
| "loss": 1.8277, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.7812340642529322, | |
| "grad_norm": 0.30362340807914734, | |
| "learning_rate": 0.0001354837821329404, | |
| "loss": 1.888, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.7832738398776135, | |
| "grad_norm": 0.29050615429878235, | |
| "learning_rate": 0.00013518079629791724, | |
| "loss": 1.7116, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.7853136155022947, | |
| "grad_norm": 0.29679572582244873, | |
| "learning_rate": 0.00013487744143298822, | |
| "loss": 1.6066, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.787353391126976, | |
| "grad_norm": 0.3293478488922119, | |
| "learning_rate": 0.0001345737207202023, | |
| "loss": 1.7222, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.7893931667516573, | |
| "grad_norm": 0.34148016571998596, | |
| "learning_rate": 0.000134269637345446, | |
| "loss": 1.7243, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.7914329423763387, | |
| "grad_norm": 0.31480157375335693, | |
| "learning_rate": 0.00013396519449841005, | |
| "loss": 1.8812, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.7934727180010199, | |
| "grad_norm": 0.2998044192790985, | |
| "learning_rate": 0.0001336603953725559, | |
| "loss": 1.9205, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.7955124936257012, | |
| "grad_norm": 0.33707278966903687, | |
| "learning_rate": 0.00013335524316508208, | |
| "loss": 1.9246, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7975522692503825, | |
| "grad_norm": 0.33658990263938904, | |
| "learning_rate": 0.00013304974107689087, | |
| "loss": 1.849, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.7995920448750637, | |
| "grad_norm": 0.2800214886665344, | |
| "learning_rate": 0.00013274389231255466, | |
| "loss": 1.7607, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.801631820499745, | |
| "grad_norm": 0.29528602957725525, | |
| "learning_rate": 0.00013243770008028224, | |
| "loss": 1.6146, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.8036715961244263, | |
| "grad_norm": 0.316123902797699, | |
| "learning_rate": 0.00013213116759188523, | |
| "loss": 1.7578, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.8057113717491076, | |
| "grad_norm": 0.339609295129776, | |
| "learning_rate": 0.0001318242980627444, | |
| "loss": 1.6968, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.8077511473737888, | |
| "grad_norm": 0.29195457696914673, | |
| "learning_rate": 0.00013151709471177588, | |
| "loss": 1.6553, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.8097909229984702, | |
| "grad_norm": 0.3093162477016449, | |
| "learning_rate": 0.00013120956076139746, | |
| "loss": 1.6833, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.8118306986231515, | |
| "grad_norm": 0.343049019575119, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.717, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.8138704742478328, | |
| "grad_norm": 0.30858704447746277, | |
| "learning_rate": 0.0001305935139693874, | |
| "loss": 1.5495, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.815910249872514, | |
| "grad_norm": 0.28386467695236206, | |
| "learning_rate": 0.00013028500758979506, | |
| "loss": 1.8721, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8179500254971953, | |
| "grad_norm": 0.3261226713657379, | |
| "learning_rate": 0.00012997618353480377, | |
| "loss": 1.7956, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.8199898011218766, | |
| "grad_norm": 0.3289451003074646, | |
| "learning_rate": 0.00012966704504383168, | |
| "loss": 1.7322, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.8220295767465579, | |
| "grad_norm": 0.3098496198654175, | |
| "learning_rate": 0.00012935759535959528, | |
| "loss": 1.7224, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.8240693523712391, | |
| "grad_norm": 0.2830435335636139, | |
| "learning_rate": 0.00012904783772807533, | |
| "loss": 1.7597, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.8261091279959204, | |
| "grad_norm": 0.3040255010128021, | |
| "learning_rate": 0.00012873777539848283, | |
| "loss": 1.8111, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.8281489036206018, | |
| "grad_norm": 0.30722421407699585, | |
| "learning_rate": 0.00012842741162322487, | |
| "loss": 1.6308, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.8301886792452831, | |
| "grad_norm": 0.28365135192871094, | |
| "learning_rate": 0.00012811674965787056, | |
| "loss": 1.932, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.8322284548699643, | |
| "grad_norm": 0.26628825068473816, | |
| "learning_rate": 0.00012780579276111702, | |
| "loss": 1.5047, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.8342682304946456, | |
| "grad_norm": 0.3449050486087799, | |
| "learning_rate": 0.00012749454419475487, | |
| "loss": 1.9364, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.8363080061193269, | |
| "grad_norm": 0.2961723208427429, | |
| "learning_rate": 0.0001271830072236343, | |
| "loss": 1.6638, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.8383477817440081, | |
| "grad_norm": 0.2808418273925781, | |
| "learning_rate": 0.00012687118511563075, | |
| "loss": 1.6743, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.8403875573686894, | |
| "grad_norm": 0.30065590143203735, | |
| "learning_rate": 0.0001265590811416105, | |
| "loss": 1.8681, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.8424273329933707, | |
| "grad_norm": 0.311669260263443, | |
| "learning_rate": 0.0001262466985753967, | |
| "loss": 1.7563, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.844467108618052, | |
| "grad_norm": 0.31335267424583435, | |
| "learning_rate": 0.0001259340406937345, | |
| "loss": 1.9591, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.8465068842427333, | |
| "grad_norm": 0.306470662355423, | |
| "learning_rate": 0.00012562111077625722, | |
| "loss": 1.7165, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.8485466598674146, | |
| "grad_norm": 0.278089314699173, | |
| "learning_rate": 0.00012530791210545162, | |
| "loss": 1.7441, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.8505864354920959, | |
| "grad_norm": 0.28886333107948303, | |
| "learning_rate": 0.00012499444796662353, | |
| "loss": 1.7301, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.8526262111167772, | |
| "grad_norm": 0.31261351704597473, | |
| "learning_rate": 0.0001246807216478634, | |
| "loss": 2.062, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.8546659867414584, | |
| "grad_norm": 0.3184990882873535, | |
| "learning_rate": 0.00012436673644001197, | |
| "loss": 2.0039, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.8567057623661397, | |
| "grad_norm": 0.28797486424446106, | |
| "learning_rate": 0.00012405249563662537, | |
| "loss": 1.5982, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.858745537990821, | |
| "grad_norm": 0.32951340079307556, | |
| "learning_rate": 0.00012373800253394102, | |
| "loss": 1.6121, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.8607853136155023, | |
| "grad_norm": 0.28868240118026733, | |
| "learning_rate": 0.00012342326043084266, | |
| "loss": 1.7456, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.8628250892401835, | |
| "grad_norm": 0.3051716387271881, | |
| "learning_rate": 0.00012310827262882615, | |
| "loss": 1.7698, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.3326285183429718, | |
| "learning_rate": 0.00012279304243196436, | |
| "loss": 1.7834, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.8669046404895462, | |
| "grad_norm": 0.3435324430465698, | |
| "learning_rate": 0.00012247757314687297, | |
| "loss": 1.7208, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.8689444161142275, | |
| "grad_norm": 0.35181501507759094, | |
| "learning_rate": 0.00012216186808267546, | |
| "loss": 1.7401, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.8709841917389087, | |
| "grad_norm": 0.30371034145355225, | |
| "learning_rate": 0.00012184593055096854, | |
| "loss": 1.655, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.87302396736359, | |
| "grad_norm": 0.29926905035972595, | |
| "learning_rate": 0.0001215297638657875, | |
| "loss": 1.686, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.8750637429882713, | |
| "grad_norm": 0.32623806595802307, | |
| "learning_rate": 0.0001212133713435712, | |
| "loss": 1.6556, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.8771035186129525, | |
| "grad_norm": 0.32232004404067993, | |
| "learning_rate": 0.00012089675630312754, | |
| "loss": 1.7736, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8791432942376338, | |
| "grad_norm": 0.3392092287540436, | |
| "learning_rate": 0.00012057992206559837, | |
| "loss": 1.8754, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.8811830698623151, | |
| "grad_norm": 0.34549203515052795, | |
| "learning_rate": 0.00012026287195442503, | |
| "loss": 1.7624, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.8832228454869965, | |
| "grad_norm": 0.3612309694290161, | |
| "learning_rate": 0.00011994560929531309, | |
| "loss": 1.6408, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.8852626211116777, | |
| "grad_norm": 0.30541735887527466, | |
| "learning_rate": 0.00011962813741619777, | |
| "loss": 1.6785, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.887302396736359, | |
| "grad_norm": 0.2894171476364136, | |
| "learning_rate": 0.00011931045964720881, | |
| "loss": 1.6609, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.8893421723610403, | |
| "grad_norm": 0.31241005659103394, | |
| "learning_rate": 0.0001189925793206357, | |
| "loss": 1.7421, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.8913819479857216, | |
| "grad_norm": 0.36774688959121704, | |
| "learning_rate": 0.00011867449977089265, | |
| "loss": 1.902, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.8934217236104028, | |
| "grad_norm": 0.3658794164657593, | |
| "learning_rate": 0.00011835622433448361, | |
| "loss": 1.9666, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.8954614992350841, | |
| "grad_norm": 0.33153945207595825, | |
| "learning_rate": 0.00011803775634996734, | |
| "loss": 1.6772, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.8975012748597654, | |
| "grad_norm": 0.34272125363349915, | |
| "learning_rate": 0.0001177190991579223, | |
| "loss": 1.7911, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8995410504844467, | |
| "grad_norm": 0.3852793276309967, | |
| "learning_rate": 0.00011740025610091159, | |
| "loss": 1.7358, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.901580826109128, | |
| "grad_norm": 0.33693379163742065, | |
| "learning_rate": 0.00011708123052344804, | |
| "loss": 1.7078, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.9036206017338093, | |
| "grad_norm": 0.35405832529067993, | |
| "learning_rate": 0.00011676202577195901, | |
| "loss": 1.6454, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.9056603773584906, | |
| "grad_norm": 0.38638654351234436, | |
| "learning_rate": 0.0001164426451947513, | |
| "loss": 1.7611, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.9077001529831719, | |
| "grad_norm": 0.3415047824382782, | |
| "learning_rate": 0.00011612309214197599, | |
| "loss": 1.6206, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.9097399286078531, | |
| "grad_norm": 0.3022047281265259, | |
| "learning_rate": 0.00011580336996559343, | |
| "loss": 1.8017, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.9117797042325344, | |
| "grad_norm": 0.3650202751159668, | |
| "learning_rate": 0.00011548348201933798, | |
| "loss": 1.6507, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.9138194798572157, | |
| "grad_norm": 0.44297119975090027, | |
| "learning_rate": 0.00011516343165868279, | |
| "loss": 1.8607, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.915859255481897, | |
| "grad_norm": 0.3508884906768799, | |
| "learning_rate": 0.00011484322224080472, | |
| "loss": 1.6549, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.9178990311065782, | |
| "grad_norm": 0.31238260865211487, | |
| "learning_rate": 0.00011452285712454904, | |
| "loss": 1.603, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9199388067312596, | |
| "grad_norm": 0.36678579449653625, | |
| "learning_rate": 0.00011420233967039422, | |
| "loss": 1.7984, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.9219785823559409, | |
| "grad_norm": 0.3467310965061188, | |
| "learning_rate": 0.00011388167324041669, | |
| "loss": 1.7691, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.9240183579806222, | |
| "grad_norm": 0.2987074553966522, | |
| "learning_rate": 0.00011356086119825553, | |
| "loss": 1.617, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.9260581336053034, | |
| "grad_norm": 0.2808781862258911, | |
| "learning_rate": 0.00011323990690907733, | |
| "loss": 1.6362, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.9280979092299847, | |
| "grad_norm": 0.356692910194397, | |
| "learning_rate": 0.00011291881373954065, | |
| "loss": 1.7279, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.930137684854666, | |
| "grad_norm": 0.3478505611419678, | |
| "learning_rate": 0.00011259758505776092, | |
| "loss": 1.6011, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.9321774604793472, | |
| "grad_norm": 0.3229358196258545, | |
| "learning_rate": 0.00011227622423327502, | |
| "loss": 1.7874, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.9342172361040285, | |
| "grad_norm": 0.30234581232070923, | |
| "learning_rate": 0.0001119547346370059, | |
| "loss": 1.6098, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.9362570117287098, | |
| "grad_norm": 0.356154203414917, | |
| "learning_rate": 0.00011163311964122734, | |
| "loss": 1.8164, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.9382967873533912, | |
| "grad_norm": 0.35306453704833984, | |
| "learning_rate": 0.00011131138261952845, | |
| "loss": 1.8833, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9403365629780724, | |
| "grad_norm": 0.29947206377983093, | |
| "learning_rate": 0.00011098952694677829, | |
| "loss": 1.6675, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.9423763386027537, | |
| "grad_norm": 0.3290257155895233, | |
| "learning_rate": 0.00011066755599909064, | |
| "loss": 1.7463, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.944416114227435, | |
| "grad_norm": 0.32332712411880493, | |
| "learning_rate": 0.00011034547315378838, | |
| "loss": 1.5748, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.9464558898521163, | |
| "grad_norm": 0.40129172801971436, | |
| "learning_rate": 0.00011002328178936811, | |
| "loss": 1.6484, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.9484956654767975, | |
| "grad_norm": 0.34289342164993286, | |
| "learning_rate": 0.00010970098528546481, | |
| "loss": 1.7533, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.9505354411014788, | |
| "grad_norm": 0.30435630679130554, | |
| "learning_rate": 0.00010937858702281631, | |
| "loss": 1.8037, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.9525752167261601, | |
| "grad_norm": 0.29155558347702026, | |
| "learning_rate": 0.00010905609038322779, | |
| "loss": 1.5628, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.9546149923508415, | |
| "grad_norm": 0.31822967529296875, | |
| "learning_rate": 0.0001087334987495364, | |
| "loss": 1.7222, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.9566547679755227, | |
| "grad_norm": 0.2868748605251312, | |
| "learning_rate": 0.00010841081550557578, | |
| "loss": 1.86, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.958694543600204, | |
| "grad_norm": 0.3066910207271576, | |
| "learning_rate": 0.00010808804403614043, | |
| "loss": 1.7278, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9607343192248853, | |
| "grad_norm": 0.28570494055747986, | |
| "learning_rate": 0.00010776518772695034, | |
| "loss": 1.7328, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.9627740948495666, | |
| "grad_norm": 0.28472283482551575, | |
| "learning_rate": 0.0001074422499646154, | |
| "loss": 1.7311, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.9648138704742478, | |
| "grad_norm": 0.30987489223480225, | |
| "learning_rate": 0.00010711923413659995, | |
| "loss": 1.7628, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.9668536460989291, | |
| "grad_norm": 0.32321545481681824, | |
| "learning_rate": 0.00010679614363118717, | |
| "loss": 1.8949, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.9688934217236104, | |
| "grad_norm": 0.32413583993911743, | |
| "learning_rate": 0.00010647298183744359, | |
| "loss": 1.6379, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.9709331973482916, | |
| "grad_norm": 0.3008846044540405, | |
| "learning_rate": 0.0001061497521451835, | |
| "loss": 1.7546, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.972972972972973, | |
| "grad_norm": 0.3248610198497772, | |
| "learning_rate": 0.00010582645794493337, | |
| "loss": 1.8915, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.9750127485976543, | |
| "grad_norm": 0.3182532489299774, | |
| "learning_rate": 0.00010550310262789649, | |
| "loss": 1.8771, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.9770525242223356, | |
| "grad_norm": 0.317730188369751, | |
| "learning_rate": 0.00010517968958591705, | |
| "loss": 1.7348, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.9790922998470168, | |
| "grad_norm": 0.3585616648197174, | |
| "learning_rate": 0.00010485622221144484, | |
| "loss": 1.6916, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9811320754716981, | |
| "grad_norm": 0.2927946150302887, | |
| "learning_rate": 0.00010453270389749957, | |
| "loss": 1.7284, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.9831718510963794, | |
| "grad_norm": 0.2869007885456085, | |
| "learning_rate": 0.00010420913803763521, | |
| "loss": 1.7312, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.9852116267210607, | |
| "grad_norm": 0.34274759888648987, | |
| "learning_rate": 0.00010388552802590462, | |
| "loss": 1.6405, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.9872514023457419, | |
| "grad_norm": 0.3203391134738922, | |
| "learning_rate": 0.00010356187725682359, | |
| "loss": 1.666, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.9892911779704232, | |
| "grad_norm": 0.3370297849178314, | |
| "learning_rate": 0.00010323818912533561, | |
| "loss": 1.757, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.9913309535951046, | |
| "grad_norm": 0.3095087707042694, | |
| "learning_rate": 0.00010291446702677599, | |
| "loss": 1.7015, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.9933707292197859, | |
| "grad_norm": 0.33249640464782715, | |
| "learning_rate": 0.00010259071435683636, | |
| "loss": 1.9363, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.9954105048444671, | |
| "grad_norm": 0.3441324830055237, | |
| "learning_rate": 0.000102266934511529, | |
| "loss": 1.5975, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.9974502804691484, | |
| "grad_norm": 0.31439101696014404, | |
| "learning_rate": 0.00010194313088715135, | |
| "loss": 1.7025, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.9994900560938297, | |
| "grad_norm": 0.34762027859687805, | |
| "learning_rate": 0.00010161930688025017, | |
| "loss": 1.7399, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9994900560938297, | |
| "eval_loss": 1.752766489982605, | |
| "eval_runtime": 57.5155, | |
| "eval_samples_per_second": 14.361, | |
| "eval_steps_per_second": 1.808, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.001529831718511, | |
| "grad_norm": 0.31156283617019653, | |
| "learning_rate": 0.00010129546588758605, | |
| "loss": 1.6866, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 1.0035696073431923, | |
| "grad_norm": 0.31161120533943176, | |
| "learning_rate": 0.00010097161130609773, | |
| "loss": 1.6071, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.0056093829678736, | |
| "grad_norm": 0.3198174834251404, | |
| "learning_rate": 0.00010064774653286661, | |
| "loss": 1.5485, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.0076491585925549, | |
| "grad_norm": 0.30601778626441956, | |
| "learning_rate": 0.00010032387496508089, | |
| "loss": 1.7225, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.0096889342172362, | |
| "grad_norm": 0.3010168969631195, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5471, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.0117287098419174, | |
| "grad_norm": 0.33606722950935364, | |
| "learning_rate": 9.967612503491914e-05, | |
| "loss": 1.941, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 1.0137684854665987, | |
| "grad_norm": 0.3398125469684601, | |
| "learning_rate": 9.935225346713341e-05, | |
| "loss": 1.6347, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 1.01580826109128, | |
| "grad_norm": 0.3129066228866577, | |
| "learning_rate": 9.902838869390229e-05, | |
| "loss": 1.7006, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 1.0178480367159612, | |
| "grad_norm": 0.31506016850471497, | |
| "learning_rate": 9.870453411241399e-05, | |
| "loss": 1.6346, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 1.0198878123406425, | |
| "grad_norm": 0.3370596766471863, | |
| "learning_rate": 9.838069311974986e-05, | |
| "loss": 1.5556, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0219275879653238, | |
| "grad_norm": 0.34100475907325745, | |
| "learning_rate": 9.805686911284868e-05, | |
| "loss": 1.5844, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 1.023967363590005, | |
| "grad_norm": 0.3352638781070709, | |
| "learning_rate": 9.7733065488471e-05, | |
| "loss": 1.7705, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 1.0260071392146863, | |
| "grad_norm": 0.29297593235969543, | |
| "learning_rate": 9.740928564316368e-05, | |
| "loss": 1.5959, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 1.0280469148393676, | |
| "grad_norm": 0.30612438917160034, | |
| "learning_rate": 9.708553297322406e-05, | |
| "loss": 1.5619, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.0300866904640489, | |
| "grad_norm": 0.32929760217666626, | |
| "learning_rate": 9.676181087466444e-05, | |
| "loss": 1.6273, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.0321264660887302, | |
| "grad_norm": 0.3363798260688782, | |
| "learning_rate": 9.643812274317644e-05, | |
| "loss": 1.5784, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 1.0341662417134114, | |
| "grad_norm": 0.3519752025604248, | |
| "learning_rate": 9.611447197409543e-05, | |
| "loss": 1.6152, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 1.0362060173380927, | |
| "grad_norm": 0.2884860038757324, | |
| "learning_rate": 9.579086196236482e-05, | |
| "loss": 1.6408, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 1.0382457929627742, | |
| "grad_norm": 0.30348899960517883, | |
| "learning_rate": 9.54672961025005e-05, | |
| "loss": 1.6188, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 1.0402855685874555, | |
| "grad_norm": 0.3200111985206604, | |
| "learning_rate": 9.514377778855521e-05, | |
| "loss": 1.8469, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.0423253442121367, | |
| "grad_norm": 0.3585512340068817, | |
| "learning_rate": 9.482031041408296e-05, | |
| "loss": 1.5236, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 1.044365119836818, | |
| "grad_norm": 0.33769890666007996, | |
| "learning_rate": 9.449689737210352e-05, | |
| "loss": 1.5718, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.0464048954614993, | |
| "grad_norm": 0.3171827793121338, | |
| "learning_rate": 9.417354205506663e-05, | |
| "loss": 1.6292, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 1.0484446710861806, | |
| "grad_norm": 0.30314505100250244, | |
| "learning_rate": 9.385024785481654e-05, | |
| "loss": 1.7828, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.0504844467108618, | |
| "grad_norm": 0.3583092987537384, | |
| "learning_rate": 9.352701816255643e-05, | |
| "loss": 1.7287, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.052524222335543, | |
| "grad_norm": 0.3360598087310791, | |
| "learning_rate": 9.320385636881283e-05, | |
| "loss": 1.5975, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.0545639979602244, | |
| "grad_norm": 0.31122949719429016, | |
| "learning_rate": 9.288076586340006e-05, | |
| "loss": 1.64, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 1.0566037735849056, | |
| "grad_norm": 0.32964256405830383, | |
| "learning_rate": 9.255775003538462e-05, | |
| "loss": 1.6612, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.058643549209587, | |
| "grad_norm": 0.3330499529838562, | |
| "learning_rate": 9.223481227304968e-05, | |
| "loss": 1.4896, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 1.0606833248342682, | |
| "grad_norm": 0.3136623799800873, | |
| "learning_rate": 9.19119559638596e-05, | |
| "loss": 1.4403, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.0627231004589495, | |
| "grad_norm": 0.305698037147522, | |
| "learning_rate": 9.158918449442423e-05, | |
| "loss": 1.6269, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 1.0647628760836307, | |
| "grad_norm": 0.311132550239563, | |
| "learning_rate": 9.126650125046361e-05, | |
| "loss": 1.5817, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 1.066802651708312, | |
| "grad_norm": 0.32102203369140625, | |
| "learning_rate": 9.094390961677223e-05, | |
| "loss": 1.6621, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 1.0688424273329933, | |
| "grad_norm": 0.29032936692237854, | |
| "learning_rate": 9.062141297718371e-05, | |
| "loss": 1.6658, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.0708822029576746, | |
| "grad_norm": 0.3275803327560425, | |
| "learning_rate": 9.02990147145352e-05, | |
| "loss": 1.7366, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.072921978582356, | |
| "grad_norm": 0.32101571559906006, | |
| "learning_rate": 8.997671821063191e-05, | |
| "loss": 1.4678, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 1.0749617542070373, | |
| "grad_norm": 0.34086906909942627, | |
| "learning_rate": 8.965452684621164e-05, | |
| "loss": 1.851, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.0770015298317186, | |
| "grad_norm": 0.3514576554298401, | |
| "learning_rate": 8.933244400090937e-05, | |
| "loss": 1.5987, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.0790413054563999, | |
| "grad_norm": 0.37968167662620544, | |
| "learning_rate": 8.901047305322172e-05, | |
| "loss": 1.7313, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 0.31161201000213623, | |
| "learning_rate": 8.868861738047158e-05, | |
| "loss": 1.4166, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.0831208567057624, | |
| "grad_norm": 0.2926504909992218, | |
| "learning_rate": 8.836688035877267e-05, | |
| "loss": 1.5615, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 1.0851606323304437, | |
| "grad_norm": 0.3290373980998993, | |
| "learning_rate": 8.804526536299413e-05, | |
| "loss": 1.5896, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.087200407955125, | |
| "grad_norm": 0.36070388555526733, | |
| "learning_rate": 8.772377576672502e-05, | |
| "loss": 1.6017, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 1.0892401835798062, | |
| "grad_norm": 0.29602184891700745, | |
| "learning_rate": 8.740241494223911e-05, | |
| "loss": 1.5118, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 1.0912799592044875, | |
| "grad_norm": 0.3364042341709137, | |
| "learning_rate": 8.70811862604594e-05, | |
| "loss": 1.5733, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.0933197348291688, | |
| "grad_norm": 0.35308852791786194, | |
| "learning_rate": 8.676009309092272e-05, | |
| "loss": 1.5998, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.09535951045385, | |
| "grad_norm": 0.3395770788192749, | |
| "learning_rate": 8.643913880174448e-05, | |
| "loss": 1.6643, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 1.0973992860785313, | |
| "grad_norm": 0.3173401653766632, | |
| "learning_rate": 8.611832675958336e-05, | |
| "loss": 1.5605, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 1.0994390617032126, | |
| "grad_norm": 0.3106042444705963, | |
| "learning_rate": 8.579766032960582e-05, | |
| "loss": 1.5107, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 1.1014788373278939, | |
| "grad_norm": 0.3313981890678406, | |
| "learning_rate": 8.5477142875451e-05, | |
| "loss": 1.5485, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.1035186129525751, | |
| "grad_norm": 0.36504775285720825, | |
| "learning_rate": 8.515677775919527e-05, | |
| "loss": 1.6587, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.1055583885772564, | |
| "grad_norm": 0.325743705034256, | |
| "learning_rate": 8.48365683413172e-05, | |
| "loss": 1.5985, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 1.1075981642019377, | |
| "grad_norm": 0.3341684341430664, | |
| "learning_rate": 8.451651798066203e-05, | |
| "loss": 1.5058, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 1.109637939826619, | |
| "grad_norm": 0.3337576389312744, | |
| "learning_rate": 8.419663003440657e-05, | |
| "loss": 1.6246, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.1116777154513005, | |
| "grad_norm": 0.3710947334766388, | |
| "learning_rate": 8.387690785802402e-05, | |
| "loss": 1.6237, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.1137174910759817, | |
| "grad_norm": 0.3338005840778351, | |
| "learning_rate": 8.355735480524874e-05, | |
| "loss": 1.6597, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.115757266700663, | |
| "grad_norm": 0.37434127926826477, | |
| "learning_rate": 8.323797422804099e-05, | |
| "loss": 1.5366, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 1.1177970423253443, | |
| "grad_norm": 0.31900352239608765, | |
| "learning_rate": 8.291876947655196e-05, | |
| "loss": 1.8195, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 1.1198368179500255, | |
| "grad_norm": 0.34681376814842224, | |
| "learning_rate": 8.259974389908842e-05, | |
| "loss": 1.6413, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 1.1218765935747068, | |
| "grad_norm": 0.3127409517765045, | |
| "learning_rate": 8.228090084207774e-05, | |
| "loss": 1.7019, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.123916369199388, | |
| "grad_norm": 0.3269082307815552, | |
| "learning_rate": 8.196224365003267e-05, | |
| "loss": 1.6642, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 1.1259561448240694, | |
| "grad_norm": 0.3357929289340973, | |
| "learning_rate": 8.16437756655164e-05, | |
| "loss": 1.515, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.1279959204487506, | |
| "grad_norm": 0.3477891683578491, | |
| "learning_rate": 8.132550022910737e-05, | |
| "loss": 1.5411, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 1.130035696073432, | |
| "grad_norm": 0.3414022624492645, | |
| "learning_rate": 8.100742067936431e-05, | |
| "loss": 1.5473, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 1.1320754716981132, | |
| "grad_norm": 0.3490772247314453, | |
| "learning_rate": 8.068954035279121e-05, | |
| "loss": 1.6757, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.1341152473227945, | |
| "grad_norm": 0.3200000524520874, | |
| "learning_rate": 8.037186258380226e-05, | |
| "loss": 1.5958, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 1.1361550229474757, | |
| "grad_norm": 0.336568146944046, | |
| "learning_rate": 8.005439070468692e-05, | |
| "loss": 1.7993, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 1.138194798572157, | |
| "grad_norm": 0.30839619040489197, | |
| "learning_rate": 7.973712804557501e-05, | |
| "loss": 1.6876, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 1.1402345741968383, | |
| "grad_norm": 0.34785008430480957, | |
| "learning_rate": 7.942007793440164e-05, | |
| "loss": 1.5183, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 1.1422743498215195, | |
| "grad_norm": 0.32502883672714233, | |
| "learning_rate": 7.91032436968725e-05, | |
| "loss": 1.6198, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.144314125446201, | |
| "grad_norm": 0.34975382685661316, | |
| "learning_rate": 7.878662865642881e-05, | |
| "loss": 1.8394, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 1.1463539010708823, | |
| "grad_norm": 0.33375632762908936, | |
| "learning_rate": 7.847023613421251e-05, | |
| "loss": 1.5781, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 1.1483936766955636, | |
| "grad_norm": 0.3376395106315613, | |
| "learning_rate": 7.815406944903147e-05, | |
| "loss": 1.6032, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.1504334523202449, | |
| "grad_norm": 0.3409046530723572, | |
| "learning_rate": 7.78381319173246e-05, | |
| "loss": 1.6174, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.1524732279449261, | |
| "grad_norm": 0.3230804204940796, | |
| "learning_rate": 7.75224268531271e-05, | |
| "loss": 1.5616, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.1545130035696074, | |
| "grad_norm": 0.3072092831134796, | |
| "learning_rate": 7.72069575680357e-05, | |
| "loss": 1.6302, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.1565527791942887, | |
| "grad_norm": 0.32646802067756653, | |
| "learning_rate": 7.689172737117389e-05, | |
| "loss": 1.6233, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 1.15859255481897, | |
| "grad_norm": 0.3212278187274933, | |
| "learning_rate": 7.657673956915735e-05, | |
| "loss": 1.5473, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.1606323304436512, | |
| "grad_norm": 0.3245629668235779, | |
| "learning_rate": 7.626199746605903e-05, | |
| "loss": 1.5801, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 1.1626721060683325, | |
| "grad_norm": 0.35144391655921936, | |
| "learning_rate": 7.594750436337467e-05, | |
| "loss": 1.4983, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.1647118816930138, | |
| "grad_norm": 0.3057266175746918, | |
| "learning_rate": 7.563326355998803e-05, | |
| "loss": 1.6002, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.166751657317695, | |
| "grad_norm": 0.33646106719970703, | |
| "learning_rate": 7.531927835213656e-05, | |
| "loss": 1.5237, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.1687914329423763, | |
| "grad_norm": 0.31540170311927795, | |
| "learning_rate": 7.500555203337647e-05, | |
| "loss": 1.6638, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 1.1708312085670576, | |
| "grad_norm": 0.35494086146354675, | |
| "learning_rate": 7.469208789454838e-05, | |
| "loss": 1.6821, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.1728709841917389, | |
| "grad_norm": 0.3381110727787018, | |
| "learning_rate": 7.437888922374276e-05, | |
| "loss": 1.7844, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.1749107598164201, | |
| "grad_norm": 0.33230093121528625, | |
| "learning_rate": 7.40659593062655e-05, | |
| "loss": 1.669, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.1769505354411014, | |
| "grad_norm": 0.3445635735988617, | |
| "learning_rate": 7.37533014246033e-05, | |
| "loss": 1.6158, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 1.1789903110657827, | |
| "grad_norm": 0.310813307762146, | |
| "learning_rate": 7.344091885838948e-05, | |
| "loss": 1.6848, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.181030086690464, | |
| "grad_norm": 0.3245631754398346, | |
| "learning_rate": 7.312881488436927e-05, | |
| "loss": 1.6653, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 1.1830698623151452, | |
| "grad_norm": 0.33641543984413147, | |
| "learning_rate": 7.281699277636572e-05, | |
| "loss": 1.6324, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.1851096379398267, | |
| "grad_norm": 0.3748520016670227, | |
| "learning_rate": 7.250545580524515e-05, | |
| "loss": 1.7024, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 1.187149413564508, | |
| "grad_norm": 0.3528485894203186, | |
| "learning_rate": 7.2194207238883e-05, | |
| "loss": 1.6821, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 1.1891891891891893, | |
| "grad_norm": 0.3142973780632019, | |
| "learning_rate": 7.188325034212943e-05, | |
| "loss": 1.7549, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 1.1912289648138705, | |
| "grad_norm": 0.33410054445266724, | |
| "learning_rate": 7.157258837677514e-05, | |
| "loss": 1.8369, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.1932687404385518, | |
| "grad_norm": 0.3428086042404175, | |
| "learning_rate": 7.126222460151719e-05, | |
| "loss": 1.603, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.195308516063233, | |
| "grad_norm": 0.3166033625602722, | |
| "learning_rate": 7.095216227192467e-05, | |
| "loss": 1.6375, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 1.1973482916879143, | |
| "grad_norm": 0.29628151655197144, | |
| "learning_rate": 7.064240464040473e-05, | |
| "loss": 1.3848, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 1.1993880673125956, | |
| "grad_norm": 0.3217509090900421, | |
| "learning_rate": 7.033295495616834e-05, | |
| "loss": 1.5988, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.201427842937277, | |
| "grad_norm": 0.3184705078601837, | |
| "learning_rate": 7.002381646519625e-05, | |
| "loss": 1.7149, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 1.2034676185619582, | |
| "grad_norm": 0.3363349139690399, | |
| "learning_rate": 6.971499241020495e-05, | |
| "loss": 1.6204, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.2055073941866394, | |
| "grad_norm": 0.35250142216682434, | |
| "learning_rate": 6.940648603061263e-05, | |
| "loss": 1.7362, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 1.2075471698113207, | |
| "grad_norm": 0.32162901759147644, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.5443, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.209586945436002, | |
| "grad_norm": 0.3331109881401062, | |
| "learning_rate": 6.879043923860257e-05, | |
| "loss": 1.6554, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 1.2116267210606833, | |
| "grad_norm": 0.3188980519771576, | |
| "learning_rate": 6.848290528822416e-05, | |
| "loss": 1.657, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.2136664966853645, | |
| "grad_norm": 0.33444222807884216, | |
| "learning_rate": 6.817570193725564e-05, | |
| "loss": 1.5265, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.2157062723100458, | |
| "grad_norm": 0.3025628626346588, | |
| "learning_rate": 6.786883240811479e-05, | |
| "loss": 1.5125, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.2177460479347273, | |
| "grad_norm": 0.3270890712738037, | |
| "learning_rate": 6.756229991971779e-05, | |
| "loss": 1.7311, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 1.2197858235594086, | |
| "grad_norm": 0.34401583671569824, | |
| "learning_rate": 6.725610768744534e-05, | |
| "loss": 1.6609, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 1.2218255991840898, | |
| "grad_norm": 0.3244417905807495, | |
| "learning_rate": 6.695025892310914e-05, | |
| "loss": 1.71, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 1.2238653748087711, | |
| "grad_norm": 0.3126024901866913, | |
| "learning_rate": 6.664475683491796e-05, | |
| "loss": 1.7029, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2259051504334524, | |
| "grad_norm": 0.3367353677749634, | |
| "learning_rate": 6.633960462744416e-05, | |
| "loss": 1.6139, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 1.2279449260581337, | |
| "grad_norm": 0.3355925679206848, | |
| "learning_rate": 6.603480550158995e-05, | |
| "loss": 1.5975, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.229984701682815, | |
| "grad_norm": 0.3236278295516968, | |
| "learning_rate": 6.5730362654554e-05, | |
| "loss": 1.5147, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.2320244773074962, | |
| "grad_norm": 0.335346519947052, | |
| "learning_rate": 6.542627927979771e-05, | |
| "loss": 1.4939, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.2340642529321775, | |
| "grad_norm": 0.30104824900627136, | |
| "learning_rate": 6.512255856701177e-05, | |
| "loss": 1.6025, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.2361040285568587, | |
| "grad_norm": 0.32115882635116577, | |
| "learning_rate": 6.481920370208274e-05, | |
| "loss": 1.5471, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 1.23814380418154, | |
| "grad_norm": 0.33474794030189514, | |
| "learning_rate": 6.451621786705962e-05, | |
| "loss": 1.5468, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.2401835798062213, | |
| "grad_norm": 0.3239012062549591, | |
| "learning_rate": 6.42136042401204e-05, | |
| "loss": 1.8344, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.2422233554309026, | |
| "grad_norm": 0.3667883574962616, | |
| "learning_rate": 6.39113659955389e-05, | |
| "loss": 1.5429, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 1.2442631310555838, | |
| "grad_norm": 0.32810983061790466, | |
| "learning_rate": 6.360950630365126e-05, | |
| "loss": 1.6717, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.246302906680265, | |
| "grad_norm": 0.3319525420665741, | |
| "learning_rate": 6.330802833082279e-05, | |
| "loss": 1.5021, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 1.2483426823049464, | |
| "grad_norm": 0.3360360264778137, | |
| "learning_rate": 6.300693523941482e-05, | |
| "loss": 1.464, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.2503824579296277, | |
| "grad_norm": 0.3125949203968048, | |
| "learning_rate": 6.270623018775135e-05, | |
| "loss": 1.5397, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 1.252422233554309, | |
| "grad_norm": 0.30626389384269714, | |
| "learning_rate": 6.24059163300861e-05, | |
| "loss": 1.791, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 1.2544620091789902, | |
| "grad_norm": 0.3332500159740448, | |
| "learning_rate": 6.210599681656933e-05, | |
| "loss": 1.5316, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.2565017848036715, | |
| "grad_norm": 0.3248031735420227, | |
| "learning_rate": 6.180647479321485e-05, | |
| "loss": 1.4547, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.2585415604283527, | |
| "grad_norm": 0.29785528779029846, | |
| "learning_rate": 6.15073534018669e-05, | |
| "loss": 1.6137, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 1.2605813360530342, | |
| "grad_norm": 0.3345397412776947, | |
| "learning_rate": 6.120863578016735e-05, | |
| "loss": 1.6357, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 1.2626211116777155, | |
| "grad_norm": 0.323854923248291, | |
| "learning_rate": 6.091032506152274e-05, | |
| "loss": 1.5605, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 1.2646608873023968, | |
| "grad_norm": 0.343605637550354, | |
| "learning_rate": 6.061242437507131e-05, | |
| "loss": 1.6101, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.266700662927078, | |
| "grad_norm": 0.35858821868896484, | |
| "learning_rate": 6.031493684565029e-05, | |
| "loss": 1.6113, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 1.2687404385517593, | |
| "grad_norm": 0.34025838971138, | |
| "learning_rate": 6.00178655937631e-05, | |
| "loss": 1.4651, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.2707802141764406, | |
| "grad_norm": 0.33670589327812195, | |
| "learning_rate": 5.972121373554664e-05, | |
| "loss": 1.5778, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.2728199898011219, | |
| "grad_norm": 0.33113864064216614, | |
| "learning_rate": 5.942498438273849e-05, | |
| "loss": 1.6172, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.2748597654258031, | |
| "grad_norm": 0.3496561646461487, | |
| "learning_rate": 5.9129180642644414e-05, | |
| "loss": 1.5233, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.2768995410504844, | |
| "grad_norm": 0.35048961639404297, | |
| "learning_rate": 5.883380561810563e-05, | |
| "loss": 1.7357, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 1.2789393166751657, | |
| "grad_norm": 0.36025702953338623, | |
| "learning_rate": 5.8538862407466425e-05, | |
| "loss": 1.6267, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 1.280979092299847, | |
| "grad_norm": 0.3353872001171112, | |
| "learning_rate": 5.82443541045415e-05, | |
| "loss": 1.6597, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 1.2830188679245282, | |
| "grad_norm": 0.3378039002418518, | |
| "learning_rate": 5.795028379858355e-05, | |
| "loss": 1.6192, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 1.2850586435492095, | |
| "grad_norm": 0.3405285179615021, | |
| "learning_rate": 5.765665457425102e-05, | |
| "loss": 1.6515, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.287098419173891, | |
| "grad_norm": 0.3546642065048218, | |
| "learning_rate": 5.736346951157544e-05, | |
| "loss": 1.6763, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 1.2891381947985723, | |
| "grad_norm": 0.35471004247665405, | |
| "learning_rate": 5.707073168592942e-05, | |
| "loss": 1.6143, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 1.2911779704232536, | |
| "grad_norm": 0.34378281235694885, | |
| "learning_rate": 5.677844416799424e-05, | |
| "loss": 1.5564, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 1.2932177460479348, | |
| "grad_norm": 0.31412938237190247, | |
| "learning_rate": 5.648661002372768e-05, | |
| "loss": 1.523, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 1.295257521672616, | |
| "grad_norm": 0.4044433534145355, | |
| "learning_rate": 5.6195232314331766e-05, | |
| "loss": 1.8443, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.2972972972972974, | |
| "grad_norm": 0.33771705627441406, | |
| "learning_rate": 5.590431409622081e-05, | |
| "loss": 1.5658, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 1.2993370729219786, | |
| "grad_norm": 0.38285380601882935, | |
| "learning_rate": 5.56138584209893e-05, | |
| "loss": 1.6984, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 1.30137684854666, | |
| "grad_norm": 0.34205278754234314, | |
| "learning_rate": 5.532386833537977e-05, | |
| "loss": 1.5203, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 1.3034166241713412, | |
| "grad_norm": 0.32206758856773376, | |
| "learning_rate": 5.503434688125104e-05, | |
| "loss": 1.5948, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 1.3054563997960225, | |
| "grad_norm": 0.3362283706665039, | |
| "learning_rate": 5.474529709554612e-05, | |
| "loss": 1.7107, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.3074961754207037, | |
| "grad_norm": 0.3668416142463684, | |
| "learning_rate": 5.445672201026054e-05, | |
| "loss": 1.6136, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 1.309535951045385, | |
| "grad_norm": 0.35234856605529785, | |
| "learning_rate": 5.416862465241033e-05, | |
| "loss": 1.4468, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 1.3115757266700663, | |
| "grad_norm": 0.34221404790878296, | |
| "learning_rate": 5.388100804400049e-05, | |
| "loss": 1.6279, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 1.3136155022947476, | |
| "grad_norm": 0.30184850096702576, | |
| "learning_rate": 5.3593875201993174e-05, | |
| "loss": 1.5824, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 1.3156552779194288, | |
| "grad_norm": 0.35658925771713257, | |
| "learning_rate": 5.3307229138275936e-05, | |
| "loss": 1.7841, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.31769505354411, | |
| "grad_norm": 0.3517902195453644, | |
| "learning_rate": 5.302107285963045e-05, | |
| "loss": 1.537, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 1.3197348291687914, | |
| "grad_norm": 0.33700263500213623, | |
| "learning_rate": 5.273540936770058e-05, | |
| "loss": 1.6779, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 1.3217746047934726, | |
| "grad_norm": 0.37334513664245605, | |
| "learning_rate": 5.245024165896126e-05, | |
| "loss": 1.657, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 1.323814380418154, | |
| "grad_norm": 0.33209171891212463, | |
| "learning_rate": 5.2165572724686754e-05, | |
| "loss": 1.5466, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 1.3258541560428352, | |
| "grad_norm": 0.3467157483100891, | |
| "learning_rate": 5.1881405550919493e-05, | |
| "loss": 1.8377, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.3278939316675165, | |
| "grad_norm": 0.3575190305709839, | |
| "learning_rate": 5.1597743118438726e-05, | |
| "loss": 1.6033, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 1.3299337072921977, | |
| "grad_norm": 0.3690027594566345, | |
| "learning_rate": 5.1314588402729044e-05, | |
| "loss": 1.7233, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 1.3319734829168792, | |
| "grad_norm": 0.38401731848716736, | |
| "learning_rate": 5.103194437394952e-05, | |
| "loss": 1.5839, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 1.3340132585415605, | |
| "grad_norm": 0.3264882266521454, | |
| "learning_rate": 5.074981399690218e-05, | |
| "loss": 1.5094, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 1.3360530341662418, | |
| "grad_norm": 0.32658815383911133, | |
| "learning_rate": 5.0468200231001286e-05, | |
| "loss": 1.775, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.338092809790923, | |
| "grad_norm": 0.3544069230556488, | |
| "learning_rate": 5.018710603024187e-05, | |
| "loss": 1.6619, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 1.3401325854156043, | |
| "grad_norm": 0.4113689661026001, | |
| "learning_rate": 4.9906534343169144e-05, | |
| "loss": 1.4896, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 1.3421723610402856, | |
| "grad_norm": 0.3639819324016571, | |
| "learning_rate": 4.962648811284738e-05, | |
| "loss": 1.9133, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 1.3442121366649669, | |
| "grad_norm": 0.3412756621837616, | |
| "learning_rate": 4.934697027682894e-05, | |
| "loss": 1.4732, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 1.3462519122896481, | |
| "grad_norm": 0.3357820510864258, | |
| "learning_rate": 4.9067983767123736e-05, | |
| "loss": 1.5121, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.3482916879143294, | |
| "grad_norm": 0.340202271938324, | |
| "learning_rate": 4.8789531510168163e-05, | |
| "loss": 1.4813, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 1.3503314635390107, | |
| "grad_norm": 0.3804778754711151, | |
| "learning_rate": 4.851161642679466e-05, | |
| "loss": 1.5581, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 1.352371239163692, | |
| "grad_norm": 0.3732028603553772, | |
| "learning_rate": 4.8234241432200965e-05, | |
| "loss": 1.6184, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 1.3544110147883732, | |
| "grad_norm": 0.33145490288734436, | |
| "learning_rate": 4.795740943591955e-05, | |
| "loss": 1.6271, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 1.3564507904130545, | |
| "grad_norm": 0.34722691774368286, | |
| "learning_rate": 4.768112334178699e-05, | |
| "loss": 1.4174, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.3584905660377358, | |
| "grad_norm": 0.3337624669075012, | |
| "learning_rate": 4.74053860479137e-05, | |
| "loss": 1.5257, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 1.3605303416624173, | |
| "grad_norm": 0.3500399887561798, | |
| "learning_rate": 4.7130200446653475e-05, | |
| "loss": 1.6007, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 1.3625701172870985, | |
| "grad_norm": 0.33266812562942505, | |
| "learning_rate": 4.6855569424572955e-05, | |
| "loss": 1.58, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 1.3646098929117798, | |
| "grad_norm": 0.33294910192489624, | |
| "learning_rate": 4.65814958624217e-05, | |
| "loss": 1.6312, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 1.366649668536461, | |
| "grad_norm": 0.34834083914756775, | |
| "learning_rate": 4.630798263510162e-05, | |
| "loss": 1.8115, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.3686894441611424, | |
| "grad_norm": 0.350946307182312, | |
| "learning_rate": 4.6035032611637094e-05, | |
| "loss": 1.4841, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 1.3707292197858236, | |
| "grad_norm": 0.3481386601924896, | |
| "learning_rate": 4.5762648655144666e-05, | |
| "loss": 1.8824, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 1.372768995410505, | |
| "grad_norm": 0.38010773062705994, | |
| "learning_rate": 4.549083362280317e-05, | |
| "loss": 1.6004, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 1.3748087710351862, | |
| "grad_norm": 0.34416502714157104, | |
| "learning_rate": 4.5219590365823714e-05, | |
| "loss": 1.6492, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 1.3768485466598674, | |
| "grad_norm": 0.35469838976860046, | |
| "learning_rate": 4.494892172941965e-05, | |
| "loss": 1.6195, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.3788883222845487, | |
| "grad_norm": 0.3326956033706665, | |
| "learning_rate": 4.467883055277695e-05, | |
| "loss": 1.7463, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 1.38092809790923, | |
| "grad_norm": 0.3437754511833191, | |
| "learning_rate": 4.440931966902418e-05, | |
| "loss": 1.5278, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 1.3829678735339113, | |
| "grad_norm": 0.3093564808368683, | |
| "learning_rate": 4.414039190520308e-05, | |
| "loss": 1.6568, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 1.3850076491585925, | |
| "grad_norm": 0.369819700717926, | |
| "learning_rate": 4.387205008223854e-05, | |
| "loss": 1.6104, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 1.3870474247832738, | |
| "grad_norm": 0.31055358052253723, | |
| "learning_rate": 4.360429701490934e-05, | |
| "loss": 1.5981, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.389087200407955, | |
| "grad_norm": 0.3369213044643402, | |
| "learning_rate": 4.333713551181852e-05, | |
| "loss": 1.5602, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 1.3911269760326364, | |
| "grad_norm": 0.3584446907043457, | |
| "learning_rate": 4.307056837536373e-05, | |
| "loss": 1.3992, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 1.3931667516573176, | |
| "grad_norm": 0.33131203055381775, | |
| "learning_rate": 4.2804598401708175e-05, | |
| "loss": 1.7085, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 1.395206527281999, | |
| "grad_norm": 0.3502407968044281, | |
| "learning_rate": 4.253922838075095e-05, | |
| "loss": 1.6791, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 1.3972463029066802, | |
| "grad_norm": 0.3351820409297943, | |
| "learning_rate": 4.227446109609809e-05, | |
| "loss": 1.7071, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.3992860785313614, | |
| "grad_norm": 0.3804665505886078, | |
| "learning_rate": 4.2010299325033034e-05, | |
| "loss": 1.8445, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 1.4013258541560427, | |
| "grad_norm": 0.326779842376709, | |
| "learning_rate": 4.17467458384878e-05, | |
| "loss": 1.6168, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 1.403365629780724, | |
| "grad_norm": 0.3746296465396881, | |
| "learning_rate": 4.1483803401013796e-05, | |
| "loss": 1.522, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 1.4054054054054055, | |
| "grad_norm": 0.3150007724761963, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.5968, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 1.4074451810300868, | |
| "grad_norm": 0.33969178795814514, | |
| "learning_rate": 4.0959762699407766e-05, | |
| "loss": 1.6025, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.409484956654768, | |
| "grad_norm": 0.3613244593143463, | |
| "learning_rate": 4.0698669932214727e-05, | |
| "loss": 1.7332, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 1.4115247322794493, | |
| "grad_norm": 0.3509519398212433, | |
| "learning_rate": 4.043819920791322e-05, | |
| "loss": 1.5837, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 1.4135645079041306, | |
| "grad_norm": 0.37852659821510315, | |
| "learning_rate": 4.0178353258717804e-05, | |
| "loss": 1.6182, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 1.4156042835288118, | |
| "grad_norm": 0.36975494027137756, | |
| "learning_rate": 3.991913481028965e-05, | |
| "loss": 1.5078, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 1.4176440591534931, | |
| "grad_norm": 0.34122028946876526, | |
| "learning_rate": 3.966054658170754e-05, | |
| "loss": 1.6329, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.4196838347781744, | |
| "grad_norm": 0.3338213562965393, | |
| "learning_rate": 3.940259128543967e-05, | |
| "loss": 1.6355, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 1.4217236104028557, | |
| "grad_norm": 0.3279430866241455, | |
| "learning_rate": 3.9145271627314986e-05, | |
| "loss": 1.6395, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 1.423763386027537, | |
| "grad_norm": 0.3165960907936096, | |
| "learning_rate": 3.8888590306494974e-05, | |
| "loss": 1.4444, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 1.4258031616522182, | |
| "grad_norm": 0.3250195384025574, | |
| "learning_rate": 3.8632550015445256e-05, | |
| "loss": 1.5924, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 1.4278429372768995, | |
| "grad_norm": 0.3744489550590515, | |
| "learning_rate": 3.8377153439907266e-05, | |
| "loss": 1.6443, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.4298827129015808, | |
| "grad_norm": 0.34341734647750854, | |
| "learning_rate": 3.81224032588703e-05, | |
| "loss": 1.6492, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 1.4319224885262622, | |
| "grad_norm": 0.343795508146286, | |
| "learning_rate": 3.786830214454315e-05, | |
| "loss": 1.6409, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 1.4339622641509435, | |
| "grad_norm": 0.3446982800960541, | |
| "learning_rate": 3.7614852762326305e-05, | |
| "loss": 1.6905, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 1.4360020397756248, | |
| "grad_norm": 0.34508073329925537, | |
| "learning_rate": 3.736205777078381e-05, | |
| "loss": 1.5568, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 1.438041815400306, | |
| "grad_norm": 0.3523988425731659, | |
| "learning_rate": 3.710991982161555e-05, | |
| "loss": 1.6096, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.4400815910249873, | |
| "grad_norm": 0.3173058032989502, | |
| "learning_rate": 3.6858441559629306e-05, | |
| "loss": 1.507, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 1.4421213666496686, | |
| "grad_norm": 0.3678998053073883, | |
| "learning_rate": 3.6607625622713e-05, | |
| "loss": 1.5844, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 1.4441611422743499, | |
| "grad_norm": 0.32919788360595703, | |
| "learning_rate": 3.63574746418072e-05, | |
| "loss": 1.791, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 1.4462009178990312, | |
| "grad_norm": 0.35295575857162476, | |
| "learning_rate": 3.610799124087725e-05, | |
| "loss": 1.7232, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 1.4482406935237124, | |
| "grad_norm": 0.31556135416030884, | |
| "learning_rate": 3.585917803688603e-05, | |
| "loss": 1.6823, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.4502804691483937, | |
| "grad_norm": 0.33846956491470337, | |
| "learning_rate": 3.5611037639766265e-05, | |
| "loss": 1.5164, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 1.452320244773075, | |
| "grad_norm": 0.31997138261795044, | |
| "learning_rate": 3.5363572652393326e-05, | |
| "loss": 1.7178, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 1.4543600203977562, | |
| "grad_norm": 0.3398173749446869, | |
| "learning_rate": 3.511678567055786e-05, | |
| "loss": 1.6152, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 1.4563997960224375, | |
| "grad_norm": 0.3304274380207062, | |
| "learning_rate": 3.487067928293848e-05, | |
| "loss": 1.5052, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 1.4584395716471188, | |
| "grad_norm": 0.325420618057251, | |
| "learning_rate": 3.4625256071074773e-05, | |
| "loss": 1.4226, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.4604793472718, | |
| "grad_norm": 0.31153547763824463, | |
| "learning_rate": 3.4380518609340076e-05, | |
| "loss": 1.4929, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 1.4625191228964813, | |
| "grad_norm": 0.32968971133232117, | |
| "learning_rate": 3.4136469464914575e-05, | |
| "loss": 1.3787, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 1.4645588985211626, | |
| "grad_norm": 0.35368427634239197, | |
| "learning_rate": 3.389311119775828e-05, | |
| "loss": 1.8215, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 1.4665986741458439, | |
| "grad_norm": 0.3066471219062805, | |
| "learning_rate": 3.3650446360584275e-05, | |
| "loss": 1.6172, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 1.4686384497705252, | |
| "grad_norm": 0.31443992257118225, | |
| "learning_rate": 3.340847749883191e-05, | |
| "loss": 1.5386, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.4706782253952064, | |
| "grad_norm": 0.3136918246746063, | |
| "learning_rate": 3.316720715064e-05, | |
| "loss": 1.5974, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 1.4727180010198877, | |
| "grad_norm": 0.3218241333961487, | |
| "learning_rate": 3.292663784682036e-05, | |
| "loss": 1.8249, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 1.474757776644569, | |
| "grad_norm": 0.31746232509613037, | |
| "learning_rate": 3.268677211083109e-05, | |
| "loss": 1.6415, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 1.4767975522692502, | |
| "grad_norm": 0.35141000151634216, | |
| "learning_rate": 3.2447612458750365e-05, | |
| "loss": 1.6132, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 1.4788373278939317, | |
| "grad_norm": 0.32248514890670776, | |
| "learning_rate": 3.2209161399249674e-05, | |
| "loss": 1.6643, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.480877103518613, | |
| "grad_norm": 0.3245083689689636, | |
| "learning_rate": 3.197142143356787e-05, | |
| "loss": 1.5616, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 1.4829168791432943, | |
| "grad_norm": 0.33084774017333984, | |
| "learning_rate": 3.173439505548462e-05, | |
| "loss": 1.6546, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 1.4849566547679756, | |
| "grad_norm": 0.3269692063331604, | |
| "learning_rate": 3.149808475129452e-05, | |
| "loss": 1.4821, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 1.4869964303926568, | |
| "grad_norm": 0.3100489675998688, | |
| "learning_rate": 3.126249299978086e-05, | |
| "loss": 1.475, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 1.489036206017338, | |
| "grad_norm": 0.3064831495285034, | |
| "learning_rate": 3.102762227218957e-05, | |
| "loss": 1.443, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.4910759816420194, | |
| "grad_norm": 0.3394755721092224, | |
| "learning_rate": 3.079347503220351e-05, | |
| "loss": 1.6525, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 1.4931157572667006, | |
| "grad_norm": 0.33389967679977417, | |
| "learning_rate": 3.056005373591637e-05, | |
| "loss": 1.5118, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 1.495155532891382, | |
| "grad_norm": 0.3200013339519501, | |
| "learning_rate": 3.032736083180716e-05, | |
| "loss": 1.5438, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 1.4971953085160632, | |
| "grad_norm": 0.34980496764183044, | |
| "learning_rate": 3.0095398760714267e-05, | |
| "loss": 1.5078, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 1.4992350841407445, | |
| "grad_norm": 0.35308340191841125, | |
| "learning_rate": 2.9864169955810084e-05, | |
| "loss": 1.6637, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.4992350841407445, | |
| "eval_loss": 1.695379614830017, | |
| "eval_runtime": 48.7639, | |
| "eval_samples_per_second": 16.939, | |
| "eval_steps_per_second": 2.133, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.501274859765426, | |
| "grad_norm": 0.36427217721939087, | |
| "learning_rate": 2.9633676842575387e-05, | |
| "loss": 1.5404, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 1.5033146353901072, | |
| "grad_norm": 0.3411431908607483, | |
| "learning_rate": 2.940392183877382e-05, | |
| "loss": 1.6793, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 1.5053544110147885, | |
| "grad_norm": 0.3458103537559509, | |
| "learning_rate": 2.9174907354426696e-05, | |
| "loss": 1.4378, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 1.5073941866394698, | |
| "grad_norm": 0.32269302010536194, | |
| "learning_rate": 2.8946635791787545e-05, | |
| "loss": 1.5621, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 1.509433962264151, | |
| "grad_norm": 0.3315049111843109, | |
| "learning_rate": 2.8719109545317103e-05, | |
| "loss": 1.6883, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.5114737378888323, | |
| "grad_norm": 0.34527409076690674, | |
| "learning_rate": 2.8492331001657945e-05, | |
| "loss": 1.6777, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 1.5135135135135136, | |
| "grad_norm": 0.31591078639030457, | |
| "learning_rate": 2.8266302539609745e-05, | |
| "loss": 1.5866, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 1.5155532891381949, | |
| "grad_norm": 0.351625919342041, | |
| "learning_rate": 2.804102653010414e-05, | |
| "loss": 1.6674, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 1.5175930647628761, | |
| "grad_norm": 0.32702285051345825, | |
| "learning_rate": 2.7816505336179798e-05, | |
| "loss": 1.6834, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 1.5196328403875574, | |
| "grad_norm": 0.315550297498703, | |
| "learning_rate": 2.759274131295787e-05, | |
| "loss": 1.6263, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 1.5216726160122387, | |
| "grad_norm": 0.39837682247161865, | |
| "learning_rate": 2.736973680761702e-05, | |
| "loss": 1.5969, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 1.52371239163692, | |
| "grad_norm": 0.3614759147167206, | |
| "learning_rate": 2.7147494159369036e-05, | |
| "loss": 1.5608, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 1.5257521672616012, | |
| "grad_norm": 0.3324558138847351, | |
| "learning_rate": 2.6926015699434072e-05, | |
| "loss": 1.456, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 1.5277919428862825, | |
| "grad_norm": 0.3555881083011627, | |
| "learning_rate": 2.6705303751016408e-05, | |
| "loss": 1.62, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 1.5298317185109638, | |
| "grad_norm": 0.3169229030609131, | |
| "learning_rate": 2.6485360629279987e-05, | |
| "loss": 1.6364, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.531871494135645, | |
| "grad_norm": 0.3641349971294403, | |
| "learning_rate": 2.6266188641323996e-05, | |
| "loss": 1.7575, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 1.5339112697603263, | |
| "grad_norm": 0.3597756624221802, | |
| "learning_rate": 2.6047790086158952e-05, | |
| "loss": 1.7316, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 1.5359510453850076, | |
| "grad_norm": 0.30949273705482483, | |
| "learning_rate": 2.5830167254682257e-05, | |
| "loss": 1.6266, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 1.5379908210096889, | |
| "grad_norm": 0.3243308365345001, | |
| "learning_rate": 2.5613322429654574e-05, | |
| "loss": 1.6186, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 1.5400305966343701, | |
| "grad_norm": 0.34625059366226196, | |
| "learning_rate": 2.5397257885675397e-05, | |
| "loss": 1.4952, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 1.5420703722590514, | |
| "grad_norm": 0.34348833560943604, | |
| "learning_rate": 2.5181975889159615e-05, | |
| "loss": 1.5961, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 1.5441101478837327, | |
| "grad_norm": 0.3473558723926544, | |
| "learning_rate": 2.496747869831345e-05, | |
| "loss": 1.7014, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 1.546149923508414, | |
| "grad_norm": 0.3339255750179291, | |
| "learning_rate": 2.475376856311097e-05, | |
| "loss": 1.5541, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 1.5481896991330952, | |
| "grad_norm": 0.36445924639701843, | |
| "learning_rate": 2.4540847725270378e-05, | |
| "loss": 1.5242, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 1.5502294747577765, | |
| "grad_norm": 0.340023398399353, | |
| "learning_rate": 2.432871841823047e-05, | |
| "loss": 1.5245, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.5522692503824578, | |
| "grad_norm": 0.3025660514831543, | |
| "learning_rate": 2.411738286712735e-05, | |
| "loss": 1.4454, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 1.554309026007139, | |
| "grad_norm": 0.34481656551361084, | |
| "learning_rate": 2.3906843288770886e-05, | |
| "loss": 1.681, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 1.5563488016318205, | |
| "grad_norm": 0.326921284198761, | |
| "learning_rate": 2.3697101891621697e-05, | |
| "loss": 1.5377, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 1.5583885772565018, | |
| "grad_norm": 0.34051257371902466, | |
| "learning_rate": 2.3488160875767717e-05, | |
| "loss": 1.5051, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 1.560428352881183, | |
| "grad_norm": 0.32640084624290466, | |
| "learning_rate": 2.3280022432901383e-05, | |
| "loss": 1.6906, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 1.5624681285058644, | |
| "grad_norm": 0.36335480213165283, | |
| "learning_rate": 2.307268874629649e-05, | |
| "loss": 1.6184, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 1.5645079041305456, | |
| "grad_norm": 0.3171195387840271, | |
| "learning_rate": 2.2866161990785228e-05, | |
| "loss": 1.6957, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 1.566547679755227, | |
| "grad_norm": 0.32760629057884216, | |
| "learning_rate": 2.266044433273562e-05, | |
| "loss": 1.6545, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 1.5685874553799082, | |
| "grad_norm": 0.3048475980758667, | |
| "learning_rate": 2.245553793002849e-05, | |
| "loss": 1.5742, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 1.5706272310045895, | |
| "grad_norm": 0.33032047748565674, | |
| "learning_rate": 2.2251444932035094e-05, | |
| "loss": 1.5138, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.5726670066292707, | |
| "grad_norm": 0.3462781310081482, | |
| "learning_rate": 2.204816747959434e-05, | |
| "loss": 1.6444, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 1.5747067822539522, | |
| "grad_norm": 0.3318116068840027, | |
| "learning_rate": 2.184570770499056e-05, | |
| "loss": 1.7107, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 1.5767465578786335, | |
| "grad_norm": 0.3060275614261627, | |
| "learning_rate": 2.1644067731931007e-05, | |
| "loss": 1.5604, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 1.5787863335033148, | |
| "grad_norm": 0.37004798650741577, | |
| "learning_rate": 2.1443249675523536e-05, | |
| "loss": 1.527, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 1.580826109127996, | |
| "grad_norm": 0.3220769464969635, | |
| "learning_rate": 2.1243255642254578e-05, | |
| "loss": 1.591, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.5828658847526773, | |
| "grad_norm": 0.3345790505409241, | |
| "learning_rate": 2.1044087729966856e-05, | |
| "loss": 1.6216, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 1.5849056603773586, | |
| "grad_norm": 0.36904582381248474, | |
| "learning_rate": 2.0845748027837586e-05, | |
| "loss": 1.4141, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 1.5869454360020399, | |
| "grad_norm": 0.34023916721343994, | |
| "learning_rate": 2.0648238616356332e-05, | |
| "loss": 1.6076, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 1.5889852116267211, | |
| "grad_norm": 0.33998748660087585, | |
| "learning_rate": 2.045156156730338e-05, | |
| "loss": 1.472, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 1.5910249872514024, | |
| "grad_norm": 0.4052400290966034, | |
| "learning_rate": 2.025571894372794e-05, | |
| "loss": 1.6638, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.5930647628760837, | |
| "grad_norm": 0.3488968014717102, | |
| "learning_rate": 2.0060712799926408e-05, | |
| "loss": 1.765, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 1.595104538500765, | |
| "grad_norm": 0.3272939622402191, | |
| "learning_rate": 1.9866545181421013e-05, | |
| "loss": 1.5006, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 1.5971443141254462, | |
| "grad_norm": 0.31578630208969116, | |
| "learning_rate": 1.967321812493813e-05, | |
| "loss": 1.5492, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 1.5991840897501275, | |
| "grad_norm": 0.3504883944988251, | |
| "learning_rate": 1.9480733658387175e-05, | |
| "loss": 1.5501, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 1.6012238653748088, | |
| "grad_norm": 0.3361338675022125, | |
| "learning_rate": 1.9289093800839066e-05, | |
| "loss": 1.5733, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 1.60326364099949, | |
| "grad_norm": 0.37593501806259155, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.5149, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 1.6053034166241713, | |
| "grad_norm": 0.3598549962043762, | |
| "learning_rate": 1.8908355944716517e-05, | |
| "loss": 1.5617, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 1.6073431922488526, | |
| "grad_norm": 0.33485177159309387, | |
| "learning_rate": 1.871926193990202e-05, | |
| "loss": 1.51, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 1.6093829678735339, | |
| "grad_norm": 0.32729336619377136, | |
| "learning_rate": 1.8531020531568378e-05, | |
| "loss": 1.7241, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 1.6114227434982151, | |
| "grad_norm": 0.32850730419158936, | |
| "learning_rate": 1.8343633694278895e-05, | |
| "loss": 1.5208, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.6134625191228964, | |
| "grad_norm": 0.31730756163597107, | |
| "learning_rate": 1.8157103393632868e-05, | |
| "loss": 1.8503, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 1.6155022947475777, | |
| "grad_norm": 0.3501776456832886, | |
| "learning_rate": 1.7971431586244815e-05, | |
| "loss": 1.5293, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 1.617542070372259, | |
| "grad_norm": 0.36974573135375977, | |
| "learning_rate": 1.7786620219724204e-05, | |
| "loss": 1.6683, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 1.6195818459969402, | |
| "grad_norm": 0.3209790885448456, | |
| "learning_rate": 1.7602671232654754e-05, | |
| "loss": 1.5002, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 1.6216216216216215, | |
| "grad_norm": 0.3283923864364624, | |
| "learning_rate": 1.741958655457436e-05, | |
| "loss": 1.5206, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 1.6236613972463028, | |
| "grad_norm": 0.37643903493881226, | |
| "learning_rate": 1.723736810595461e-05, | |
| "loss": 1.5189, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 1.625701172870984, | |
| "grad_norm": 0.3263504207134247, | |
| "learning_rate": 1.7056017798180824e-05, | |
| "loss": 1.5491, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 1.6277409484956655, | |
| "grad_norm": 0.3444812297821045, | |
| "learning_rate": 1.6875537533531948e-05, | |
| "loss": 1.5142, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 1.6297807241203468, | |
| "grad_norm": 0.3257887363433838, | |
| "learning_rate": 1.6695929205160487e-05, | |
| "loss": 1.6884, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 1.631820499745028, | |
| "grad_norm": 0.36854130029678345, | |
| "learning_rate": 1.65171946970729e-05, | |
| "loss": 1.574, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.6338602753697093, | |
| "grad_norm": 0.34607166051864624, | |
| "learning_rate": 1.6339335884109518e-05, | |
| "loss": 1.5739, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 1.6359000509943906, | |
| "grad_norm": 0.3600076138973236, | |
| "learning_rate": 1.6162354631925204e-05, | |
| "loss": 1.6571, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 1.637939826619072, | |
| "grad_norm": 0.3381345868110657, | |
| "learning_rate": 1.598625279696948e-05, | |
| "loss": 1.6067, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 1.6399796022437532, | |
| "grad_norm": 0.33851006627082825, | |
| "learning_rate": 1.5811032226467305e-05, | |
| "loss": 1.5163, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 1.6420193778684344, | |
| "grad_norm": 0.3231305778026581, | |
| "learning_rate": 1.563669475839956e-05, | |
| "loss": 1.614, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 1.6440591534931157, | |
| "grad_norm": 0.3223206400871277, | |
| "learning_rate": 1.5463242221483743e-05, | |
| "loss": 1.4504, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 1.6460989291177972, | |
| "grad_norm": 0.34715861082077026, | |
| "learning_rate": 1.529067643515495e-05, | |
| "loss": 1.7934, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 1.6481387047424785, | |
| "grad_norm": 0.31931138038635254, | |
| "learning_rate": 1.5118999209546559e-05, | |
| "loss": 1.5801, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 1.6501784803671598, | |
| "grad_norm": 0.31838297843933105, | |
| "learning_rate": 1.4948212345471491e-05, | |
| "loss": 1.7495, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 1.652218255991841, | |
| "grad_norm": 0.3544289767742157, | |
| "learning_rate": 1.4778317634403083e-05, | |
| "loss": 1.6048, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.6542580316165223, | |
| "grad_norm": 0.3429974317550659, | |
| "learning_rate": 1.460931685845649e-05, | |
| "loss": 1.6734, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 1.6562978072412036, | |
| "grad_norm": 0.3236132562160492, | |
| "learning_rate": 1.444121179036989e-05, | |
| "loss": 1.5718, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 1.6583375828658848, | |
| "grad_norm": 0.3145132064819336, | |
| "learning_rate": 1.427400419348588e-05, | |
| "loss": 1.504, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 1.6603773584905661, | |
| "grad_norm": 0.35008659958839417, | |
| "learning_rate": 1.4107695821733025e-05, | |
| "loss": 1.513, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 1.6624171341152474, | |
| "grad_norm": 0.36491960287094116, | |
| "learning_rate": 1.3942288419607475e-05, | |
| "loss": 1.5571, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 1.6644569097399287, | |
| "grad_norm": 0.34494370222091675, | |
| "learning_rate": 1.3777783722154603e-05, | |
| "loss": 1.598, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 1.66649668536461, | |
| "grad_norm": 0.3233909010887146, | |
| "learning_rate": 1.3614183454950824e-05, | |
| "loss": 1.7063, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 1.6685364609892912, | |
| "grad_norm": 0.31574997305870056, | |
| "learning_rate": 1.3451489334085554e-05, | |
| "loss": 1.5871, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 1.6705762366139725, | |
| "grad_norm": 0.36086753010749817, | |
| "learning_rate": 1.3289703066143111e-05, | |
| "loss": 1.5401, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 1.6726160122386537, | |
| "grad_norm": 0.35289233922958374, | |
| "learning_rate": 1.3128826348184887e-05, | |
| "loss": 1.5204, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.674655787863335, | |
| "grad_norm": 0.3321409821510315, | |
| "learning_rate": 1.2968860867731569e-05, | |
| "loss": 1.647, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 1.6766955634880163, | |
| "grad_norm": 0.3479863405227661, | |
| "learning_rate": 1.2809808302745297e-05, | |
| "loss": 1.6429, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 1.6787353391126976, | |
| "grad_norm": 0.3064015209674835, | |
| "learning_rate": 1.2651670321612263e-05, | |
| "loss": 1.349, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 1.6807751147373788, | |
| "grad_norm": 0.34040096402168274, | |
| "learning_rate": 1.2494448583125018e-05, | |
| "loss": 1.5489, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 1.6828148903620601, | |
| "grad_norm": 0.3219228982925415, | |
| "learning_rate": 1.233814473646524e-05, | |
| "loss": 1.5782, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.6848546659867414, | |
| "grad_norm": 0.3284182846546173, | |
| "learning_rate": 1.218276042118629e-05, | |
| "loss": 1.7502, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 1.6868944416114227, | |
| "grad_norm": 0.3325609862804413, | |
| "learning_rate": 1.202829726719611e-05, | |
| "loss": 1.6647, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 1.688934217236104, | |
| "grad_norm": 0.3373055160045624, | |
| "learning_rate": 1.1874756894740135e-05, | |
| "loss": 1.6314, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 1.6909739928607852, | |
| "grad_norm": 0.3512837886810303, | |
| "learning_rate": 1.172214091438416e-05, | |
| "loss": 1.595, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 1.6930137684854665, | |
| "grad_norm": 0.32167279720306396, | |
| "learning_rate": 1.1570450926997655e-05, | |
| "loss": 1.5507, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.6950535441101477, | |
| "grad_norm": 0.37384939193725586, | |
| "learning_rate": 1.141968852373676e-05, | |
| "loss": 1.7151, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 1.697093319734829, | |
| "grad_norm": 0.3775462806224823, | |
| "learning_rate": 1.1269855286027797e-05, | |
| "loss": 1.6552, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 1.6991330953595103, | |
| "grad_norm": 0.3442714512348175, | |
| "learning_rate": 1.1120952785550476e-05, | |
| "loss": 1.416, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 1.7011728709841918, | |
| "grad_norm": 0.3268585205078125, | |
| "learning_rate": 1.0972982584221592e-05, | |
| "loss": 1.5926, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 1.703212646608873, | |
| "grad_norm": 0.33221572637557983, | |
| "learning_rate": 1.0825946234178574e-05, | |
| "loss": 1.5878, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 1.7052524222335543, | |
| "grad_norm": 0.32683464884757996, | |
| "learning_rate": 1.067984527776309e-05, | |
| "loss": 1.5254, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 1.7072921978582356, | |
| "grad_norm": 0.34125399589538574, | |
| "learning_rate": 1.0534681247505106e-05, | |
| "loss": 1.701, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 1.7093319734829169, | |
| "grad_norm": 0.33410507440567017, | |
| "learning_rate": 1.0390455666106547e-05, | |
| "loss": 1.5889, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 1.7113717491075982, | |
| "grad_norm": 0.3767413794994354, | |
| "learning_rate": 1.024717004642557e-05, | |
| "loss": 1.7098, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 1.7134115247322794, | |
| "grad_norm": 0.32880616188049316, | |
| "learning_rate": 1.010482589146048e-05, | |
| "loss": 1.6303, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.7154513003569607, | |
| "grad_norm": 0.3286539316177368, | |
| "learning_rate": 9.963424694334122e-06, | |
| "loss": 1.7356, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 1.717491075981642, | |
| "grad_norm": 0.3123774528503418, | |
| "learning_rate": 9.822967938278171e-06, | |
| "loss": 1.6089, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 1.7195308516063235, | |
| "grad_norm": 0.32634440064430237, | |
| "learning_rate": 9.683457096617488e-06, | |
| "loss": 1.5619, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 1.7215706272310047, | |
| "grad_norm": 0.33105430006980896, | |
| "learning_rate": 9.544893632754814e-06, | |
| "loss": 1.5669, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 1.723610402855686, | |
| "grad_norm": 0.3234579563140869, | |
| "learning_rate": 9.407279000155312e-06, | |
| "loss": 1.4746, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 1.7256501784803673, | |
| "grad_norm": 0.3418089747428894, | |
| "learning_rate": 9.270614642331376e-06, | |
| "loss": 1.4701, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 1.7276899541050486, | |
| "grad_norm": 0.2889448404312134, | |
| "learning_rate": 9.134901992827427e-06, | |
| "loss": 1.6088, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 1.7297297297297298, | |
| "grad_norm": 0.33682364225387573, | |
| "learning_rate": 9.000142475204964e-06, | |
| "loss": 1.7242, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 1.731769505354411, | |
| "grad_norm": 0.3277648389339447, | |
| "learning_rate": 8.866337503027522e-06, | |
| "loss": 1.4125, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 1.7338092809790924, | |
| "grad_norm": 0.3308608829975128, | |
| "learning_rate": 8.733488479845997e-06, | |
| "loss": 1.5832, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.7358490566037736, | |
| "grad_norm": 0.3282967209815979, | |
| "learning_rate": 8.60159679918372e-06, | |
| "loss": 1.5004, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 1.737888832228455, | |
| "grad_norm": 0.31315362453460693, | |
| "learning_rate": 8.470663844522052e-06, | |
| "loss": 1.6842, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 1.7399286078531362, | |
| "grad_norm": 0.3475480377674103, | |
| "learning_rate": 8.340690989285726e-06, | |
| "loss": 1.8289, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 1.7419683834778175, | |
| "grad_norm": 0.31732621788978577, | |
| "learning_rate": 8.21167959682848e-06, | |
| "loss": 1.531, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 1.7440081591024987, | |
| "grad_norm": 0.3633415102958679, | |
| "learning_rate": 8.083631020418791e-06, | |
| "loss": 1.4785, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 1.74604793472718, | |
| "grad_norm": 0.3418223559856415, | |
| "learning_rate": 7.956546603225601e-06, | |
| "loss": 1.6414, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 1.7480877103518613, | |
| "grad_norm": 0.3294214904308319, | |
| "learning_rate": 7.830427678304353e-06, | |
| "loss": 1.5571, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 1.7501274859765426, | |
| "grad_norm": 0.3359309732913971, | |
| "learning_rate": 7.705275568582848e-06, | |
| "loss": 1.5797, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 1.7521672616012238, | |
| "grad_norm": 0.3166341781616211, | |
| "learning_rate": 7.581091586847522e-06, | |
| "loss": 1.5041, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 1.754207037225905, | |
| "grad_norm": 0.34301674365997314, | |
| "learning_rate": 7.457877035729588e-06, | |
| "loss": 1.6699, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.7562468128505864, | |
| "grad_norm": 0.3607090413570404, | |
| "learning_rate": 7.335633207691361e-06, | |
| "loss": 1.6225, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 1.7582865884752676, | |
| "grad_norm": 0.3538651764392853, | |
| "learning_rate": 7.21436138501278e-06, | |
| "loss": 1.7165, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 1.760326364099949, | |
| "grad_norm": 0.335679292678833, | |
| "learning_rate": 7.094062839777837e-06, | |
| "loss": 1.4925, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 1.7623661397246302, | |
| "grad_norm": 0.36252662539482117, | |
| "learning_rate": 6.974738833861383e-06, | |
| "loss": 1.4831, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 1.7644059153493115, | |
| "grad_norm": 0.34220951795578003, | |
| "learning_rate": 6.856390618915775e-06, | |
| "loss": 1.6031, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 1.7664456909739927, | |
| "grad_norm": 0.32884883880615234, | |
| "learning_rate": 6.739019436357774e-06, | |
| "loss": 1.6789, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 1.768485466598674, | |
| "grad_norm": 0.32627391815185547, | |
| "learning_rate": 6.622626517355557e-06, | |
| "loss": 1.517, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 1.7705252422233553, | |
| "grad_norm": 0.3443872928619385, | |
| "learning_rate": 6.507213082815744e-06, | |
| "loss": 1.7773, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 1.7725650178480366, | |
| "grad_norm": 0.3367038369178772, | |
| "learning_rate": 6.392780343370686e-06, | |
| "loss": 1.5157, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 1.774604793472718, | |
| "grad_norm": 0.34665989875793457, | |
| "learning_rate": 6.2793294993656494e-06, | |
| "loss": 1.5797, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.7766445690973993, | |
| "grad_norm": 0.37426507472991943, | |
| "learning_rate": 6.166861740846297e-06, | |
| "loss": 1.6184, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 1.7786843447220806, | |
| "grad_norm": 0.3536684811115265, | |
| "learning_rate": 6.055378247546218e-06, | |
| "loss": 1.5539, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 1.7807241203467619, | |
| "grad_norm": 0.3466222584247589, | |
| "learning_rate": 5.9448801888744795e-06, | |
| "loss": 1.6129, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 1.7827638959714431, | |
| "grad_norm": 0.33310428261756897, | |
| "learning_rate": 5.835368723903456e-06, | |
| "loss": 1.591, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 1.7848036715961244, | |
| "grad_norm": 0.37535133957862854, | |
| "learning_rate": 5.726845001356573e-06, | |
| "loss": 1.6924, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.7868434472208057, | |
| "grad_norm": 0.3487565517425537, | |
| "learning_rate": 5.6193101595963585e-06, | |
| "loss": 1.6721, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 1.788883222845487, | |
| "grad_norm": 0.3542119562625885, | |
| "learning_rate": 5.512765326612379e-06, | |
| "loss": 1.5829, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 1.7909229984701684, | |
| "grad_norm": 0.37221917510032654, | |
| "learning_rate": 5.407211620009544e-06, | |
| "loss": 1.5421, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 1.7929627740948497, | |
| "grad_norm": 0.31831902265548706, | |
| "learning_rate": 5.30265014699628e-06, | |
| "loss": 1.6259, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 1.795002549719531, | |
| "grad_norm": 0.33141520619392395, | |
| "learning_rate": 5.199082004372957e-06, | |
| "loss": 1.4876, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.7970423253442123, | |
| "grad_norm": 0.37575435638427734, | |
| "learning_rate": 5.096508278520384e-06, | |
| "loss": 1.8337, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 1.7990821009688935, | |
| "grad_norm": 0.3518213927745819, | |
| "learning_rate": 4.994930045388413e-06, | |
| "loss": 1.3687, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 1.8011218765935748, | |
| "grad_norm": 0.3328496217727661, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 1.6246, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 1.803161652218256, | |
| "grad_norm": 0.3764415383338928, | |
| "learning_rate": 4.794764308863242e-06, | |
| "loss": 1.901, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 1.8052014278429374, | |
| "grad_norm": 0.352507621049881, | |
| "learning_rate": 4.6961789051139124e-06, | |
| "loss": 1.5077, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 1.8072412034676186, | |
| "grad_norm": 0.3292696475982666, | |
| "learning_rate": 4.5985931933508754e-06, | |
| "loss": 1.4446, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 1.8092809790923, | |
| "grad_norm": 0.37563368678092957, | |
| "learning_rate": 4.502008197202068e-06, | |
| "loss": 1.6857, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 1.8113207547169812, | |
| "grad_norm": 0.3451184928417206, | |
| "learning_rate": 4.406424929798403e-06, | |
| "loss": 1.4763, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 1.8133605303416624, | |
| "grad_norm": 0.33383306860923767, | |
| "learning_rate": 4.311844393763109e-06, | |
| "loss": 1.4001, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 1.8154003059663437, | |
| "grad_norm": 0.32124102115631104, | |
| "learning_rate": 4.2182675812012965e-06, | |
| "loss": 1.5507, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.817440081591025, | |
| "grad_norm": 0.3836451768875122, | |
| "learning_rate": 4.125695473689406e-06, | |
| "loss": 1.571, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 1.8194798572157063, | |
| "grad_norm": 0.33983170986175537, | |
| "learning_rate": 4.034129042265066e-06, | |
| "loss": 1.6818, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 1.8215196328403875, | |
| "grad_norm": 0.3245023488998413, | |
| "learning_rate": 3.943569247416801e-06, | |
| "loss": 1.3421, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 1.8235594084650688, | |
| "grad_norm": 0.3230661451816559, | |
| "learning_rate": 3.854017039074009e-06, | |
| "loss": 1.4876, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 1.82559918408975, | |
| "grad_norm": 0.3374238610267639, | |
| "learning_rate": 3.7654733565969826e-06, | |
| "loss": 1.7574, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 1.8276389597144314, | |
| "grad_norm": 0.3538075089454651, | |
| "learning_rate": 3.6779391287670494e-06, | |
| "loss": 1.5753, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 1.8296787353391126, | |
| "grad_norm": 0.3529132008552551, | |
| "learning_rate": 3.591415273776855e-06, | |
| "loss": 1.5352, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 1.831718510963794, | |
| "grad_norm": 0.33535516262054443, | |
| "learning_rate": 3.5059026992206647e-06, | |
| "loss": 1.4236, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 1.8337582865884752, | |
| "grad_norm": 0.32166826725006104, | |
| "learning_rate": 3.421402302084953e-06, | |
| "loss": 1.5437, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 1.8357980622131564, | |
| "grad_norm": 0.35232868790626526, | |
| "learning_rate": 3.3379149687388867e-06, | |
| "loss": 1.5435, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.8378378378378377, | |
| "grad_norm": 0.3278467059135437, | |
| "learning_rate": 3.2554415749250888e-06, | |
| "loss": 1.5345, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 1.839877613462519, | |
| "grad_norm": 0.33369168639183044, | |
| "learning_rate": 3.1739829857504234e-06, | |
| "loss": 1.5248, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 1.8419173890872003, | |
| "grad_norm": 0.35533764958381653, | |
| "learning_rate": 3.093540055676958e-06, | |
| "loss": 1.7297, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 1.8439571647118815, | |
| "grad_norm": 0.3504745364189148, | |
| "learning_rate": 3.014113628512982e-06, | |
| "loss": 1.6832, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 1.845996940336563, | |
| "grad_norm": 0.33277443051338196, | |
| "learning_rate": 2.9357045374040825e-06, | |
| "loss": 1.514, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 1.8480367159612443, | |
| "grad_norm": 0.3157265782356262, | |
| "learning_rate": 2.8583136048245697e-06, | |
| "loss": 1.5827, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 1.8500764915859256, | |
| "grad_norm": 0.3428395986557007, | |
| "learning_rate": 2.781941642568686e-06, | |
| "loss": 1.5938, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 1.8521162672106068, | |
| "grad_norm": 0.3374231159687042, | |
| "learning_rate": 2.706589451742181e-06, | |
| "loss": 1.4763, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 1.8541560428352881, | |
| "grad_norm": 0.3595046401023865, | |
| "learning_rate": 2.632257822753881e-06, | |
| "loss": 1.4746, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 1.8561958184599694, | |
| "grad_norm": 0.3170601725578308, | |
| "learning_rate": 2.5589475353073988e-06, | |
| "loss": 1.4764, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.8582355940846507, | |
| "grad_norm": 0.34321513772010803, | |
| "learning_rate": 2.486659358392951e-06, | |
| "loss": 1.6465, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 1.860275369709332, | |
| "grad_norm": 0.3204958736896515, | |
| "learning_rate": 2.415394050279318e-06, | |
| "loss": 1.7065, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 1.8623151453340132, | |
| "grad_norm": 0.3391380310058594, | |
| "learning_rate": 2.3451523585058754e-06, | |
| "loss": 1.5181, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 1.8643549209586947, | |
| "grad_norm": 0.3181851804256439, | |
| "learning_rate": 2.2759350198746976e-06, | |
| "loss": 1.5589, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 1.866394696583376, | |
| "grad_norm": 0.3439972996711731, | |
| "learning_rate": 2.2077427604429433e-06, | |
| "loss": 1.4837, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 1.8684344722080573, | |
| "grad_norm": 0.33056753873825073, | |
| "learning_rate": 2.1405762955151176e-06, | |
| "loss": 1.4456, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 1.8704742478327385, | |
| "grad_norm": 0.3104906976222992, | |
| "learning_rate": 2.074436329635687e-06, | |
| "loss": 1.6013, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 1.8725140234574198, | |
| "grad_norm": 0.35013991594314575, | |
| "learning_rate": 2.009323556581566e-06, | |
| "loss": 1.6274, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 1.874553799082101, | |
| "grad_norm": 0.33168038725852966, | |
| "learning_rate": 1.945238659354953e-06, | |
| "loss": 1.5064, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 1.8765935747067823, | |
| "grad_norm": 0.3438383936882019, | |
| "learning_rate": 1.882182310176095e-06, | |
| "loss": 1.5561, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.8786333503314636, | |
| "grad_norm": 0.33750832080841064, | |
| "learning_rate": 1.8201551704762453e-06, | |
| "loss": 1.5402, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 1.8806731259561449, | |
| "grad_norm": 0.3846586346626282, | |
| "learning_rate": 1.7591578908907724e-06, | |
| "loss": 1.7503, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 1.8827129015808262, | |
| "grad_norm": 0.36325526237487793, | |
| "learning_rate": 1.6991911112522407e-06, | |
| "loss": 1.5359, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 1.8847526772055074, | |
| "grad_norm": 0.3386278748512268, | |
| "learning_rate": 1.6402554605838172e-06, | |
| "loss": 1.4694, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 1.8867924528301887, | |
| "grad_norm": 0.3506017327308655, | |
| "learning_rate": 1.5823515570925763e-06, | |
| "loss": 1.7565, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.88883222845487, | |
| "grad_norm": 0.30699026584625244, | |
| "learning_rate": 1.5254800081630826e-06, | |
| "loss": 1.4995, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 1.8908720040795512, | |
| "grad_norm": 0.32542306184768677, | |
| "learning_rate": 1.4696414103509636e-06, | |
| "loss": 1.6048, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 1.8929117797042325, | |
| "grad_norm": 0.3201080560684204, | |
| "learning_rate": 1.4148363493766802e-06, | |
| "loss": 1.6548, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 1.8949515553289138, | |
| "grad_norm": 0.35210901498794556, | |
| "learning_rate": 1.361065400119399e-06, | |
| "loss": 1.5078, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 1.896991330953595, | |
| "grad_norm": 0.3742671012878418, | |
| "learning_rate": 1.30832912661093e-06, | |
| "loss": 1.411, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.8990311065782763, | |
| "grad_norm": 0.31074491143226624, | |
| "learning_rate": 1.2566280820298426e-06, | |
| "loss": 1.3539, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 1.9010708822029576, | |
| "grad_norm": 0.33461233973503113, | |
| "learning_rate": 1.2059628086956044e-06, | |
| "loss": 1.6129, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 1.9031106578276389, | |
| "grad_norm": 0.3572944700717926, | |
| "learning_rate": 1.1563338380629618e-06, | |
| "loss": 1.4976, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 1.9051504334523202, | |
| "grad_norm": 0.34117141366004944, | |
| "learning_rate": 1.1077416907163574e-06, | |
| "loss": 1.4853, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 1.9071902090770014, | |
| "grad_norm": 0.34180155396461487, | |
| "learning_rate": 1.0601868763643996e-06, | |
| "loss": 1.6407, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 1.9092299847016827, | |
| "grad_norm": 0.3573477864265442, | |
| "learning_rate": 1.0136698938346011e-06, | |
| "loss": 1.6081, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 1.911269760326364, | |
| "grad_norm": 0.35802096128463745, | |
| "learning_rate": 9.68191231068083e-07, | |
| "loss": 1.7181, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 1.9133095359510452, | |
| "grad_norm": 0.336832731962204, | |
| "learning_rate": 9.237513651145225e-07, | |
| "loss": 1.3533, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 1.9153493115757265, | |
| "grad_norm": 0.3149198293685913, | |
| "learning_rate": 8.803507621270579e-07, | |
| "loss": 1.352, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 1.9173890872004078, | |
| "grad_norm": 0.3341595232486725, | |
| "learning_rate": 8.379898773574924e-07, | |
| "loss": 1.5971, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.9194288628250893, | |
| "grad_norm": 0.34054580330848694, | |
| "learning_rate": 7.966691551514527e-07, | |
| "loss": 1.6251, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 1.9214686384497706, | |
| "grad_norm": 0.3276701271533966, | |
| "learning_rate": 7.563890289437825e-07, | |
| "loss": 1.598, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 1.9235084140744518, | |
| "grad_norm": 0.3295578062534332, | |
| "learning_rate": 7.171499212539123e-07, | |
| "loss": 1.6034, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 1.925548189699133, | |
| "grad_norm": 0.3124001920223236, | |
| "learning_rate": 6.78952243681541e-07, | |
| "loss": 1.4692, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 1.9275879653238144, | |
| "grad_norm": 0.35024166107177734, | |
| "learning_rate": 6.41796396902239e-07, | |
| "loss": 1.532, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 1.9296277409484957, | |
| "grad_norm": 0.34173583984375, | |
| "learning_rate": 6.056827706632185e-07, | |
| "loss": 1.6586, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 1.931667516573177, | |
| "grad_norm": 0.3405357003211975, | |
| "learning_rate": 5.706117437793701e-07, | |
| "loss": 1.6072, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 1.9337072921978582, | |
| "grad_norm": 0.31896910071372986, | |
| "learning_rate": 5.365836841291438e-07, | |
| "loss": 1.5897, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 1.9357470678225395, | |
| "grad_norm": 0.3417130410671234, | |
| "learning_rate": 5.035989486508075e-07, | |
| "loss": 1.6046, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 1.937786843447221, | |
| "grad_norm": 0.3479056656360626, | |
| "learning_rate": 4.7165788333860536e-07, | |
| "loss": 1.6084, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.9398266190719022, | |
| "grad_norm": 0.34046056866645813, | |
| "learning_rate": 4.4076082323920576e-07, | |
| "loss": 1.4111, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 1.9418663946965835, | |
| "grad_norm": 0.3575671315193176, | |
| "learning_rate": 4.1090809244814785e-07, | |
| "loss": 1.4932, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 1.9439061703212648, | |
| "grad_norm": 0.35397884249687195, | |
| "learning_rate": 3.82100004106456e-07, | |
| "loss": 1.7126, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 1.945945945945946, | |
| "grad_norm": 0.33311253786087036, | |
| "learning_rate": 3.543368603973529e-07, | |
| "loss": 1.6558, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 1.9479857215706273, | |
| "grad_norm": 0.35361233353614807, | |
| "learning_rate": 3.2761895254306287e-07, | |
| "loss": 1.7049, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 1.9500254971953086, | |
| "grad_norm": 0.35136890411376953, | |
| "learning_rate": 3.019465608018024e-07, | |
| "loss": 1.4853, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 1.9520652728199899, | |
| "grad_norm": 0.32909440994262695, | |
| "learning_rate": 2.773199544648164e-07, | |
| "loss": 1.534, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 1.9541050484446711, | |
| "grad_norm": 0.3327445387840271, | |
| "learning_rate": 2.537393918535358e-07, | |
| "loss": 1.4084, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 1.9561448240693524, | |
| "grad_norm": 0.3465093672275543, | |
| "learning_rate": 2.312051203169352e-07, | |
| "loss": 1.5575, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 1.9581845996940337, | |
| "grad_norm": 0.31249111890792847, | |
| "learning_rate": 2.0971737622883515e-07, | |
| "loss": 1.6387, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.960224375318715, | |
| "grad_norm": 0.32050248980522156, | |
| "learning_rate": 1.8927638498551502e-07, | |
| "loss": 1.6431, | |
| "step": 961 | |
| }, | |
| { | |
| "epoch": 1.9622641509433962, | |
| "grad_norm": 0.31345027685165405, | |
| "learning_rate": 1.6988236100329292e-07, | |
| "loss": 1.5125, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 1.9643039265680775, | |
| "grad_norm": 0.32769250869750977, | |
| "learning_rate": 1.5153550771630498e-07, | |
| "loss": 1.5726, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 1.9663437021927588, | |
| "grad_norm": 0.32842305302619934, | |
| "learning_rate": 1.3423601757436287e-07, | |
| "loss": 1.5826, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 1.96838347781744, | |
| "grad_norm": 0.34551113843917847, | |
| "learning_rate": 1.179840720409331e-07, | |
| "loss": 1.6897, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 1.9704232534421213, | |
| "grad_norm": 0.35393452644348145, | |
| "learning_rate": 1.0277984159122733e-07, | |
| "loss": 1.6387, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 1.9724630290668026, | |
| "grad_norm": 0.3255729377269745, | |
| "learning_rate": 8.862348571043733e-08, | |
| "loss": 1.5134, | |
| "step": 967 | |
| }, | |
| { | |
| "epoch": 1.9745028046914839, | |
| "grad_norm": 0.334995836019516, | |
| "learning_rate": 7.551515289203615e-08, | |
| "loss": 1.4714, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 1.9765425803161651, | |
| "grad_norm": 0.3348861634731293, | |
| "learning_rate": 6.34549806362239e-08, | |
| "loss": 1.4172, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 1.9785823559408464, | |
| "grad_norm": 0.34796562790870667, | |
| "learning_rate": 5.2443095448506674e-08, | |
| "loss": 1.3779, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.9806221315655277, | |
| "grad_norm": 0.36725080013275146, | |
| "learning_rate": 4.247961283835311e-08, | |
| "loss": 1.4744, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 1.982661907190209, | |
| "grad_norm": 0.349135160446167, | |
| "learning_rate": 3.356463731798432e-08, | |
| "loss": 1.6751, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 1.9847016828148902, | |
| "grad_norm": 0.34291085600852966, | |
| "learning_rate": 2.5698262401263605e-08, | |
| "loss": 1.5718, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 1.9867414584395715, | |
| "grad_norm": 0.3310767710208893, | |
| "learning_rate": 1.888057060274173e-08, | |
| "loss": 1.6042, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 1.9887812340642528, | |
| "grad_norm": 0.3502123951911926, | |
| "learning_rate": 1.3111633436779791e-08, | |
| "loss": 1.6323, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.990821009688934, | |
| "grad_norm": 0.34913215041160583, | |
| "learning_rate": 8.391511416816489e-09, | |
| "loss": 1.5433, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 1.9928607853136155, | |
| "grad_norm": 0.3260555863380432, | |
| "learning_rate": 4.720254054679796e-09, | |
| "loss": 1.5161, | |
| "step": 977 | |
| }, | |
| { | |
| "epoch": 1.9949005609382968, | |
| "grad_norm": 0.3483281433582306, | |
| "learning_rate": 2.0978998601206556e-09, | |
| "loss": 1.5955, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 1.996940336562978, | |
| "grad_norm": 0.33206477761268616, | |
| "learning_rate": 5.244763404133046e-10, | |
| "loss": 1.6749, | |
| "step": 979 | |
| }, | |
| { | |
| "epoch": 1.9989801121876594, | |
| "grad_norm": 0.34603679180145264, | |
| "learning_rate": 0.0, | |
| "loss": 1.6485, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.9989801121876594, | |
| "eval_loss": 1.6838241815567017, | |
| "eval_runtime": 49.2126, | |
| "eval_samples_per_second": 16.784, | |
| "eval_steps_per_second": 2.113, | |
| "step": 980 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 980, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 490, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.465388413369713e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |