| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8387342737323675, | |
| "eval_steps": 500, | |
| "global_step": 275, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": false, | |
| "is_world_process_zero": false, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 26.258708272339597, | |
| "learning_rate": 0.0001, | |
| "loss": 6.0469, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 20.031528084144362, | |
| "learning_rate": 0.0002, | |
| "loss": 6.0524, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 9.323112879274246, | |
| "learning_rate": 0.0003, | |
| "loss": 6.0052, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 4.147754138762137, | |
| "learning_rate": 0.0004, | |
| "loss": 5.7581, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.4117904450662409, | |
| "learning_rate": 0.0005, | |
| "loss": 5.5959, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.450165632053372, | |
| "learning_rate": 0.0006, | |
| "loss": 5.3926, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.3379034522061206, | |
| "learning_rate": 0.0007, | |
| "loss": 5.2432, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.3149419664848485, | |
| "learning_rate": 0.0008, | |
| "loss": 4.9048, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.5265629850853388, | |
| "learning_rate": 0.0009000000000000001, | |
| "loss": 4.8456, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.2248009557702129, | |
| "learning_rate": 0.001, | |
| "loss": 4.4037, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.5753342093655753, | |
| "learning_rate": 0.0009999754462587395, | |
| "loss": 3.7762, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.0959671581261972, | |
| "learning_rate": 0.0009999017874465026, | |
| "loss": 3.5411, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.8383646382276924, | |
| "learning_rate": 0.0009997790307976872, | |
| "loss": 3.4374, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.6879126623626883, | |
| "learning_rate": 0.0009996071883688333, | |
| "loss": 3.3495, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.48057277440632934, | |
| "learning_rate": 0.000999386277037439, | |
| "loss": 3.3236, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.5193770648047042, | |
| "learning_rate": 0.0009991163185003027, | |
| "loss": 3.194, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.34046016814570407, | |
| "learning_rate": 0.0009987973392713932, | |
| "loss": 3.008, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.2969743503479429, | |
| "learning_rate": 0.0009984293706792437, | |
| "loss": 3.0682, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.22754131045377113, | |
| "learning_rate": 0.0009980124488638772, | |
| "loss": 2.92, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.15880784203685044, | |
| "learning_rate": 0.000997546614773255, | |
| "loss": 2.881, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.10804346892890891, | |
| "learning_rate": 0.0009970319141592559, | |
| "loss": 2.8386, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.0789962600177391, | |
| "learning_rate": 0.0009964683975731828, | |
| "loss": 2.8704, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.0678766718481922, | |
| "learning_rate": 0.0009958561203607973, | |
| "loss": 2.8326, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.15129601777209895, | |
| "learning_rate": 0.000995195142656885, | |
| "loss": 2.8444, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.23876681297628152, | |
| "learning_rate": 0.0009944855293793475, | |
| "loss": 2.8809, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.2458680275413572, | |
| "learning_rate": 0.0009937273502228282, | |
| "loss": 2.8308, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.2646415320413548, | |
| "learning_rate": 0.0009929206796518663, | |
| "loss": 2.8296, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.1855177204894958, | |
| "learning_rate": 0.0009920655968935837, | |
| "loss": 2.8302, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.1692458314027983, | |
| "learning_rate": 0.0009911621859299041, | |
| "loss": 2.7798, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.0887107703024984, | |
| "learning_rate": 0.000990210535489303, | |
| "loss": 2.8246, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.05971709937694414, | |
| "learning_rate": 0.0009892107390380958, | |
| "loss": 2.777, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.04203098841999937, | |
| "learning_rate": 0.0009881628947712555, | |
| "loss": 2.7673, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.03708904853213128, | |
| "learning_rate": 0.0009870671056027706, | |
| "loss": 2.7486, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.03528212659332326, | |
| "learning_rate": 0.0009859234791555354, | |
| "loss": 2.7886, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.03018922862288316, | |
| "learning_rate": 0.000984732127750782, | |
| "loss": 2.7327, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.03686815342528168, | |
| "learning_rate": 0.0009834931683970467, | |
| "loss": 2.7474, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.033172131047386, | |
| "learning_rate": 0.0009822067227786794, | |
| "loss": 2.7345, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.0373016703958135, | |
| "learning_rate": 0.000980872917243891, | |
| "loss": 2.7655, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.03688389598963858, | |
| "learning_rate": 0.0009794918827923458, | |
| "loss": 2.7393, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.038870114526809094, | |
| "learning_rate": 0.000978063755062294, | |
| "loss": 2.7611, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.04038306990198406, | |
| "learning_rate": 0.0009765886743172511, | |
| "loss": 2.7386, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.036670767168349196, | |
| "learning_rate": 0.0009750667854322206, | |
| "loss": 2.6912, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.03291379266422108, | |
| "learning_rate": 0.0009734982378794661, | |
| "loss": 2.7719, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.03542095069122837, | |
| "learning_rate": 0.0009718831857138308, | |
| "loss": 2.7095, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.03556844983258325, | |
| "learning_rate": 0.0009702217875576068, | |
| "loss": 2.7435, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.03705512589107, | |
| "learning_rate": 0.0009685142065849555, | |
| "loss": 2.713, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.027028911527830556, | |
| "learning_rate": 0.0009667606105058828, | |
| "loss": 2.6472, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.028600789964649966, | |
| "learning_rate": 0.0009649611715497661, | |
| "loss": 2.6931, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.029116613327395607, | |
| "learning_rate": 0.0009631160664484398, | |
| "loss": 2.7082, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.02557746875550266, | |
| "learning_rate": 0.0009612254764188368, | |
| "loss": 2.6707, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.0256723041758138, | |
| "learning_rate": 0.0009592895871451908, | |
| "loss": 2.6608, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.02295300029667766, | |
| "learning_rate": 0.000957308588760799, | |
| "loss": 2.6942, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.02203986352323152, | |
| "learning_rate": 0.0009552826758293487, | |
| "loss": 2.6441, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.02299784546740539, | |
| "learning_rate": 0.0009532120473258075, | |
| "loss": 2.6728, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.023913877734993542, | |
| "learning_rate": 0.0009510969066168813, | |
| "loss": 2.6924, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.020131800174103105, | |
| "learning_rate": 0.0009489374614410414, | |
| "loss": 2.6151, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.02106884604663375, | |
| "learning_rate": 0.0009467339238881198, | |
| "loss": 2.6413, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.02440845171243592, | |
| "learning_rate": 0.0009444865103784803, | |
| "loss": 2.6663, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.019024075041881073, | |
| "learning_rate": 0.0009421954416417624, | |
| "loss": 2.6063, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.019667612528268406, | |
| "learning_rate": 0.0009398609426952018, | |
| "loss": 2.6697, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.020324139148677475, | |
| "learning_rate": 0.0009374832428215309, | |
| "loss": 2.6739, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.02049609873784361, | |
| "learning_rate": 0.00093506257554646, | |
| "loss": 2.6115, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.022068793706639576, | |
| "learning_rate": 0.0009325991786157404, | |
| "loss": 2.6537, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.02119215165943166, | |
| "learning_rate": 0.0009300932939718159, | |
| "loss": 2.6668, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.020470851870879974, | |
| "learning_rate": 0.000927545167730059, | |
| "loss": 2.6495, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.020239015102427586, | |
| "learning_rate": 0.0009249550501545996, | |
| "loss": 2.6229, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.02006561036060577, | |
| "learning_rate": 0.000922323195633745, | |
| "loss": 2.6541, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.020517458730459407, | |
| "learning_rate": 0.0009196498626549943, | |
| "loss": 2.6263, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.020546751672942867, | |
| "learning_rate": 0.0009169353137796533, | |
| "loss": 2.6868, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.020795862822058586, | |
| "learning_rate": 0.0009141798156170446, | |
| "loss": 2.6376, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.023603442107788076, | |
| "learning_rate": 0.0009113836387983239, | |
| "loss": 2.6679, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.020593236730693215, | |
| "learning_rate": 0.0009085470579498995, | |
| "loss": 2.628, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.0185506077207348, | |
| "learning_rate": 0.0009056703516664606, | |
| "loss": 2.6315, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.02046637689680032, | |
| "learning_rate": 0.0009027538024836141, | |
| "loss": 2.6227, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.018026412977487194, | |
| "learning_rate": 0.0008997976968501361, | |
| "loss": 2.6062, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.017993838807838707, | |
| "learning_rate": 0.000896802325099838, | |
| "loss": 2.5869, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.01897876413125471, | |
| "learning_rate": 0.0008937679814230517, | |
| "loss": 2.6046, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.019221228785349705, | |
| "learning_rate": 0.000890694963837735, | |
| "loss": 2.6163, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.01999062056670978, | |
| "learning_rate": 0.0008875835741602029, | |
| "loss": 2.6624, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.01688098771768354, | |
| "learning_rate": 0.0008844341179754839, | |
| "loss": 2.597, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.021679649830905732, | |
| "learning_rate": 0.0008812469046073068, | |
| "loss": 2.6252, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.01976703829526433, | |
| "learning_rate": 0.0008780222470877213, | |
| "loss": 2.6547, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.01721216059701167, | |
| "learning_rate": 0.000874760462126353, | |
| "loss": 2.5894, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.017796757505650348, | |
| "learning_rate": 0.0008714618700792976, | |
| "loss": 2.6428, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.017516085193709605, | |
| "learning_rate": 0.0008681267949176579, | |
| "loss": 2.6267, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.019752354059471497, | |
| "learning_rate": 0.0008647555641957244, | |
| "loss": 2.6172, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.01942107114850748, | |
| "learning_rate": 0.0008613485090188043, | |
| "loss": 2.6469, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.021049275004733702, | |
| "learning_rate": 0.000857905964010703, | |
| "loss": 2.6337, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.017375996512513512, | |
| "learning_rate": 0.0008544282672808579, | |
| "loss": 2.6066, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.020054221841685173, | |
| "learning_rate": 0.0008509157603911319, | |
| "loss": 2.6293, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.016754816692027007, | |
| "learning_rate": 0.0008473687883222664, | |
| "loss": 2.553, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.018264517242335677, | |
| "learning_rate": 0.0008437876994399991, | |
| "loss": 2.582, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.01738231752273472, | |
| "learning_rate": 0.0008401728454608494, | |
| "loss": 2.6246, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.017582673986843284, | |
| "learning_rate": 0.0008365245814175744, | |
| "loss": 2.5377, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.01841568278108112, | |
| "learning_rate": 0.0008328432656242997, | |
| "loss": 2.6107, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.01806489585852763, | |
| "learning_rate": 0.0008291292596413272, | |
| "loss": 2.5388, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.01910768409990766, | |
| "learning_rate": 0.0008253829282396245, | |
| "loss": 2.6252, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.019034711943532324, | |
| "learning_rate": 0.0008216046393649996, | |
| "loss": 2.6193, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.020284737834854932, | |
| "learning_rate": 0.0008177947641019621, | |
| "loss": 2.6149, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.05158744985589759, | |
| "learning_rate": 0.0008139536766372775, | |
| "loss": 2.6072, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.018922120101005344, | |
| "learning_rate": 0.0008100817542232173, | |
| "loss": 2.6032, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.019044369144979888, | |
| "learning_rate": 0.000806179377140506, | |
| "loss": 2.5879, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.017582902915047, | |
| "learning_rate": 0.000802246928660972, | |
| "loss": 2.6069, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.019578808618249007, | |
| "learning_rate": 0.0007982847950099055, | |
| "loss": 2.5965, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.018236739907291074, | |
| "learning_rate": 0.0007942933653281245, | |
| "loss": 2.5707, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.018258178535900983, | |
| "learning_rate": 0.0007902730316337556, | |
| "loss": 2.5382, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.022391092471974905, | |
| "learning_rate": 0.0007862241887837322, | |
| "loss": 2.6118, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.016821289155497087, | |
| "learning_rate": 0.0007821472344350131, | |
| "loss": 2.5829, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.019386550472160386, | |
| "learning_rate": 0.0007780425690055274, | |
| "loss": 2.6255, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.1772374509222317, | |
| "learning_rate": 0.0007739105956348464, | |
| "loss": 2.5617, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.020123188408530047, | |
| "learning_rate": 0.0007697517201445905, | |
| "loss": 2.6127, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.0217268258079, | |
| "learning_rate": 0.0007655663509985707, | |
| "loss": 2.5991, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.018981113976254002, | |
| "learning_rate": 0.0007613548992626711, | |
| "loss": 2.6047, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.01878803361275613, | |
| "learning_rate": 0.0007571177785644766, | |
| "loss": 2.5482, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.018908774218863146, | |
| "learning_rate": 0.0007528554050526488, | |
| "loss": 2.6141, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.019547294966543106, | |
| "learning_rate": 0.0007485681973560532, | |
| "loss": 2.5407, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.018739519276120584, | |
| "learning_rate": 0.0007442565765426436, | |
| "loss": 2.6212, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.018979109952080055, | |
| "learning_rate": 0.0007399209660781074, | |
| "loss": 2.5721, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.0175358024051344, | |
| "learning_rate": 0.0007355617917842751, | |
| "loss": 2.577, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.018692342003597935, | |
| "learning_rate": 0.0007311794817972975, | |
| "loss": 2.5944, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.019650294357122313, | |
| "learning_rate": 0.0007267744665255965, | |
| "loss": 2.608, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.01787007786983172, | |
| "learning_rate": 0.0007223471786075934, | |
| "loss": 2.5898, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.018327854729029175, | |
| "learning_rate": 0.0007178980528692161, | |
| "loss": 2.5641, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.01819571331500734, | |
| "learning_rate": 0.0007134275262811934, | |
| "loss": 2.5724, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.016879527517399177, | |
| "learning_rate": 0.0007089360379161381, | |
| "loss": 2.6016, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.018893461615821387, | |
| "learning_rate": 0.0007044240289054227, | |
| "loss": 2.5726, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.018652185039036564, | |
| "learning_rate": 0.0006998919423958547, | |
| "loss": 2.5559, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.020673958617829544, | |
| "learning_rate": 0.0006953402235061519, | |
| "loss": 2.634, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.01939109964021446, | |
| "learning_rate": 0.0006907693192832263, | |
| "loss": 2.568, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.018062900613076246, | |
| "learning_rate": 0.0006861796786582761, | |
| "loss": 2.554, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.018609687828424634, | |
| "learning_rate": 0.0006815717524026949, | |
| "loss": 2.5842, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.019554131820221306, | |
| "learning_rate": 0.0006769459930837989, | |
| "loss": 2.632, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.017713236616086883, | |
| "learning_rate": 0.0006723028550203778, | |
| "loss": 2.5547, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.019353124709199913, | |
| "learning_rate": 0.000667642794238074, | |
| "loss": 2.6321, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.01984763650797756, | |
| "learning_rate": 0.0006629662684245948, | |
| "loss": 2.5521, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.0194768410660429, | |
| "learning_rate": 0.0006582737368847592, | |
| "loss": 2.564, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.02008541514106773, | |
| "learning_rate": 0.0006535656604953884, | |
| "loss": 2.6406, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.019023120632534838, | |
| "learning_rate": 0.0006488425016600402, | |
| "loss": 2.5492, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.019894786782134775, | |
| "learning_rate": 0.0006441047242635947, | |
| "loss": 2.598, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.02011873025218978, | |
| "learning_rate": 0.0006393527936266933, | |
| "loss": 2.5729, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.019172173916513022, | |
| "learning_rate": 0.0006345871764600374, | |
| "loss": 2.5594, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.019721366832981004, | |
| "learning_rate": 0.0006298083408185502, | |
| "loss": 2.5915, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.020228287976845075, | |
| "learning_rate": 0.0006250167560554076, | |
| "loss": 2.5898, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.020882340174208855, | |
| "learning_rate": 0.0006202128927759391, | |
| "loss": 2.6273, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.02081451600660678, | |
| "learning_rate": 0.0006153972227914089, | |
| "loss": 2.595, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.01941546346347613, | |
| "learning_rate": 0.0006105702190726764, | |
| "loss": 2.5732, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.02166634263027907, | |
| "learning_rate": 0.000605732355703743, | |
| "loss": 2.5453, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.019573148109730217, | |
| "learning_rate": 0.0006008841078351903, | |
| "loss": 2.5429, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.01903540723775177, | |
| "learning_rate": 0.0005960259516375134, | |
| "loss": 2.5388, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.02051218709860799, | |
| "learning_rate": 0.0005911583642543531, | |
| "loss": 2.5793, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.02101151521755854, | |
| "learning_rate": 0.0005862818237556344, | |
| "loss": 2.5677, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.02162618990843192, | |
| "learning_rate": 0.0005813968090906116, | |
| "loss": 2.5635, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.018935934203135756, | |
| "learning_rate": 0.0005765038000408295, | |
| "loss": 2.5174, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.021177497387846266, | |
| "learning_rate": 0.0005716032771730008, | |
| "loss": 2.5266, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.019633074877257486, | |
| "learning_rate": 0.0005666957217918076, | |
| "loss": 2.5909, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.020321617227441156, | |
| "learning_rate": 0.0005617816158926302, | |
| "loss": 2.5727, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.02171314000863455, | |
| "learning_rate": 0.0005568614421142077, | |
| "loss": 2.5728, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.02036197464612551, | |
| "learning_rate": 0.0005519356836912357, | |
| "loss": 2.5546, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.021214591076630044, | |
| "learning_rate": 0.0005470048244069055, | |
| "loss": 2.6089, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.021380356809754895, | |
| "learning_rate": 0.0005420693485453892, | |
| "loss": 2.5701, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.020301144411914027, | |
| "learning_rate": 0.0005371297408442765, | |
| "loss": 2.5783, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.02317064813036681, | |
| "learning_rate": 0.0005321864864469646, | |
| "loss": 2.5787, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.020981576388978553, | |
| "learning_rate": 0.0005272400708550113, | |
| "loss": 2.5657, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.01972062092753295, | |
| "learning_rate": 0.0005222909798804515, | |
| "loss": 2.5941, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.022818553102453083, | |
| "learning_rate": 0.0005173396995980818, | |
| "loss": 2.5567, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.021333416992185616, | |
| "learning_rate": 0.0005123867162977224, | |
| "loss": 2.5552, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.020142143404330078, | |
| "learning_rate": 0.0005074325164364548, | |
| "loss": 2.5305, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.022025222387284903, | |
| "learning_rate": 0.0005024775865908451, | |
| "loss": 2.59, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.020907939242901075, | |
| "learning_rate": 0.000497522413409155, | |
| "loss": 2.5452, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.022927802322477854, | |
| "learning_rate": 0.0004925674835635454, | |
| "loss": 2.5792, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.020657968617921074, | |
| "learning_rate": 0.00048761328370227773, | |
| "loss": 2.5099, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.020110997895501886, | |
| "learning_rate": 0.0004826603004019182, | |
| "loss": 2.5163, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.021049174068166514, | |
| "learning_rate": 0.0004777090201195486, | |
| "loss": 2.5372, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.02117182813897076, | |
| "learning_rate": 0.00047275992914498865, | |
| "loss": 2.5022, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.020475434729428973, | |
| "learning_rate": 0.0004678135135530355, | |
| "loss": 2.5626, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.01948270633034859, | |
| "learning_rate": 0.0004628702591557237, | |
| "loss": 2.5286, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.020212144683261414, | |
| "learning_rate": 0.00045793065145461064, | |
| "loss": 2.5305, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.020337213413087113, | |
| "learning_rate": 0.00045299517559309457, | |
| "loss": 2.5624, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.02101629597235714, | |
| "learning_rate": 0.00044806431630876436, | |
| "loss": 2.5109, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.02099914834706713, | |
| "learning_rate": 0.00044313855788579234, | |
| "loss": 2.5702, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.020635070288327804, | |
| "learning_rate": 0.0004382183841073698, | |
| "loss": 2.5483, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.019941103414359743, | |
| "learning_rate": 0.00043330427820819256, | |
| "loss": 2.5722, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.032674916215766084, | |
| "learning_rate": 0.0004283967228269992, | |
| "loss": 2.5775, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.021496384704403824, | |
| "learning_rate": 0.00042349619995917057, | |
| "loss": 2.5856, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.030321207463772364, | |
| "learning_rate": 0.0004186031909093884, | |
| "loss": 2.5618, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.02175980169134122, | |
| "learning_rate": 0.00041371817624436577, | |
| "loss": 2.5437, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.020391275857096873, | |
| "learning_rate": 0.0004088416357456471, | |
| "loss": 2.5338, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.022437463329837284, | |
| "learning_rate": 0.00040397404836248684, | |
| "loss": 2.5812, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.02129701651167051, | |
| "learning_rate": 0.0003991158921648096, | |
| "loss": 2.5453, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.0238633278616985, | |
| "learning_rate": 0.00039426764429625693, | |
| "loss": 2.5233, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.02998116183042863, | |
| "learning_rate": 0.0003894297809273237, | |
| "loss": 2.5646, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.022238039030238917, | |
| "learning_rate": 0.00038460277720859116, | |
| "loss": 2.5242, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.0231977730809198, | |
| "learning_rate": 0.00037978710722406115, | |
| "loss": 2.5681, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 1.3831873669660701, | |
| "learning_rate": 0.0003749832439445925, | |
| "loss": 2.6152, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.024837482288635006, | |
| "learning_rate": 0.0003701916591814497, | |
| "loss": 2.5305, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.02460819770267967, | |
| "learning_rate": 0.00036541282353996275, | |
| "loss": 2.5512, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.021382499301954485, | |
| "learning_rate": 0.0003606472063733067, | |
| "loss": 2.5726, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.022843480204416112, | |
| "learning_rate": 0.00035589527573640534, | |
| "loss": 2.5911, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.0217433912155617, | |
| "learning_rate": 0.0003511574983399599, | |
| "loss": 2.5437, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.022341313083280037, | |
| "learning_rate": 0.0003464343395046117, | |
| "loss": 2.5565, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.023326386453843787, | |
| "learning_rate": 0.0003417262631152409, | |
| "loss": 2.5862, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.022197350352034496, | |
| "learning_rate": 0.0003370337315754052, | |
| "loss": 2.514, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.022582353309783542, | |
| "learning_rate": 0.000332357205761926, | |
| "loss": 2.5331, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.022070023826541343, | |
| "learning_rate": 0.00032769714497962233, | |
| "loss": 2.5413, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.02402408808891166, | |
| "learning_rate": 0.00032305400691620125, | |
| "loss": 2.5431, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.022714950946985384, | |
| "learning_rate": 0.0003184282475973052, | |
| "loss": 2.5615, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.02424470988882824, | |
| "learning_rate": 0.00031382032134172393, | |
| "loss": 2.5785, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.02175217108726291, | |
| "learning_rate": 0.00030923068071677377, | |
| "loss": 2.5665, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.022606633086133584, | |
| "learning_rate": 0.00030465977649384815, | |
| "loss": 2.5634, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.021011727388658842, | |
| "learning_rate": 0.00030010805760414546, | |
| "loss": 2.5054, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.021639315653958227, | |
| "learning_rate": 0.00029557597109457727, | |
| "loss": 2.4963, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.022615720963103284, | |
| "learning_rate": 0.0002910639620838619, | |
| "loss": 2.5688, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.02342914831258654, | |
| "learning_rate": 0.00028657247371880666, | |
| "loss": 2.5139, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.021794224872284197, | |
| "learning_rate": 0.00028210194713078405, | |
| "loss": 2.566, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.02372720731132013, | |
| "learning_rate": 0.00027765282139240676, | |
| "loss": 2.5438, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.02308128114302715, | |
| "learning_rate": 0.00027322553347440364, | |
| "loss": 2.4794, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.021725513095176348, | |
| "learning_rate": 0.0002688205182027026, | |
| "loss": 2.5699, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.020065121737088774, | |
| "learning_rate": 0.00026443820821572497, | |
| "loss": 2.4926, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.022790401677010647, | |
| "learning_rate": 0.00026007903392189256, | |
| "loss": 2.4887, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.022412544948915192, | |
| "learning_rate": 0.00025574342345735654, | |
| "loss": 2.4844, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.024482726567851745, | |
| "learning_rate": 0.0002514318026439469, | |
| "loss": 2.5568, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.0239324452654226, | |
| "learning_rate": 0.0002471445949473512, | |
| "loss": 2.5034, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.02099692498226099, | |
| "learning_rate": 0.00024288222143552346, | |
| "loss": 2.5125, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.0235532129320808, | |
| "learning_rate": 0.00023864510073732915, | |
| "loss": 2.5117, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.02514350938291889, | |
| "learning_rate": 0.00023443364900142949, | |
| "loss": 2.5651, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.02429410977297701, | |
| "learning_rate": 0.00023024827985540958, | |
| "loss": 2.5001, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.02368660244630603, | |
| "learning_rate": 0.00022608940436515368, | |
| "loss": 2.5307, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.024787276626786165, | |
| "learning_rate": 0.00022195743099447256, | |
| "loss": 2.5478, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.02513065999138821, | |
| "learning_rate": 0.0002178527655649868, | |
| "loss": 2.5136, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.023180635989223257, | |
| "learning_rate": 0.00021377581121626778, | |
| "loss": 2.51, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.02696456869362307, | |
| "learning_rate": 0.00020972696836624437, | |
| "loss": 2.5263, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.022578451161665822, | |
| "learning_rate": 0.00020570663467187555, | |
| "loss": 2.4869, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.0224881916816771, | |
| "learning_rate": 0.00020171520499009455, | |
| "loss": 2.4786, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.025839833730156827, | |
| "learning_rate": 0.00019775307133902808, | |
| "loss": 2.5469, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.02365555522712872, | |
| "learning_rate": 0.00019382062285949414, | |
| "loss": 2.5435, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.023382640821847607, | |
| "learning_rate": 0.00018991824577678268, | |
| "loss": 2.4635, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.02191815592839163, | |
| "learning_rate": 0.0001860463233627225, | |
| "loss": 2.5639, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.02310077430861472, | |
| "learning_rate": 0.00018220523589803806, | |
| "loss": 2.4839, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.02494213141918476, | |
| "learning_rate": 0.00017839536063500052, | |
| "loss": 2.5139, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.025239258961502305, | |
| "learning_rate": 0.00017461707176037546, | |
| "loss": 2.5078, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.02267677070954696, | |
| "learning_rate": 0.00017087074035867283, | |
| "loss": 2.5254, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.024599189724574425, | |
| "learning_rate": 0.00016715673437570034, | |
| "loss": 2.5807, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.023216034005314606, | |
| "learning_rate": 0.0001634754185824256, | |
| "loss": 2.5371, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.02414260114722159, | |
| "learning_rate": 0.00015982715453915082, | |
| "loss": 2.5373, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.02443242612238601, | |
| "learning_rate": 0.0001562123005600009, | |
| "loss": 2.5237, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.02324926523813888, | |
| "learning_rate": 0.00015263121167773358, | |
| "loss": 2.5025, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.02441320875098146, | |
| "learning_rate": 0.00014908423960886808, | |
| "loss": 2.581, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.025546181244876925, | |
| "learning_rate": 0.00014557173271914213, | |
| "loss": 2.5928, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.023743543298364814, | |
| "learning_rate": 0.0001420940359892971, | |
| "loss": 2.5503, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.02346770448694418, | |
| "learning_rate": 0.00013865149098119577, | |
| "loss": 2.5245, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.023286036875758236, | |
| "learning_rate": 0.00013524443580427564, | |
| "loss": 2.5717, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.024579865623865476, | |
| "learning_rate": 0.00013187320508234208, | |
| "loss": 2.5259, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.022907935808609867, | |
| "learning_rate": 0.00012853812992070257, | |
| "loss": 2.4928, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.022534504070165762, | |
| "learning_rate": 0.00012523953787364723, | |
| "loss": 2.526, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.02356875451883086, | |
| "learning_rate": 0.00012197775291227886, | |
| "loss": 2.4895, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.025208951025856796, | |
| "learning_rate": 0.0001187530953926933, | |
| "loss": 2.5507, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.02218054070579941, | |
| "learning_rate": 0.00011556588202451612, | |
| "loss": 2.4625, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.02395294608850655, | |
| "learning_rate": 0.000112416425839797, | |
| "loss": 2.5639, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.021823638739782776, | |
| "learning_rate": 0.00010930503616226495, | |
| "loss": 2.5266, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.026597868541136594, | |
| "learning_rate": 0.00010623201857694837, | |
| "loss": 2.4885, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.023249159762519452, | |
| "learning_rate": 0.00010319767490016197, | |
| "loss": 2.5496, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.023962061282550982, | |
| "learning_rate": 0.00010020230314986395, | |
| "loss": 2.5455, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.026815554632171338, | |
| "learning_rate": 9.724619751638597e-05, | |
| "loss": 2.5542, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.02519451505343548, | |
| "learning_rate": 9.432964833353947e-05, | |
| "loss": 2.5337, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.02636032377682285, | |
| "learning_rate": 9.145294205010057e-05, | |
| "loss": 2.5442, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.02381095096499113, | |
| "learning_rate": 8.861636120167632e-05, | |
| "loss": 2.5356, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.025026865092621895, | |
| "learning_rate": 8.582018438295552e-05, | |
| "loss": 2.518, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 1.000001217827216, | |
| "learning_rate": 8.306468622034664e-05, | |
| "loss": 2.5153, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 1.4142135623730951, | |
| "learning_rate": 8.035013734500557e-05, | |
| "loss": 0.0, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 1.4142135623730951, | |
| "learning_rate": 7.767680436625513e-05, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 1.4142135623730951, | |
| "learning_rate": 7.504494984540034e-05, | |
| "loss": 0.0, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 1.4142135623730951, | |
| "learning_rate": 7.245483226994093e-05, | |
| "loss": 0.0, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 1.4142135623730951, | |
| "learning_rate": 6.990670602818411e-05, | |
| "loss": 0.0, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 1.4142135623730951, | |
| "learning_rate": 6.740082138425962e-05, | |
| "loss": 0.0, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 1.4142135623730951, | |
| "learning_rate": 6.493742445354011e-05, | |
| "loss": 0.0, | |
| "step": 275 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 327, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "total_flos": 4.881335385730318e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |