| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0243116756822464, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000121558378411232, | |
| "grad_norm": 1.3522109985351562, | |
| "learning_rate": 2e-05, | |
| "loss": 9.0768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000121558378411232, | |
| "eval_loss": 2.5203659534454346, | |
| "eval_runtime": 130.544, | |
| "eval_samples_per_second": 26.535, | |
| "eval_steps_per_second": 13.268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000243116756822464, | |
| "grad_norm": 0.9176049828529358, | |
| "learning_rate": 4e-05, | |
| "loss": 8.9894, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000364675135233696, | |
| "grad_norm": 1.0146596431732178, | |
| "learning_rate": 6e-05, | |
| "loss": 9.935, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000486233513644928, | |
| "grad_norm": 1.0469788312911987, | |
| "learning_rate": 8e-05, | |
| "loss": 9.3424, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00060779189205616, | |
| "grad_norm": 0.8254321813583374, | |
| "learning_rate": 0.0001, | |
| "loss": 8.339, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000729350270467392, | |
| "grad_norm": 1.032138705253601, | |
| "learning_rate": 0.00012, | |
| "loss": 9.6692, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000850908648878624, | |
| "grad_norm": 1.692064881324768, | |
| "learning_rate": 0.00014, | |
| "loss": 9.8725, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000972467027289856, | |
| "grad_norm": 1.5163041353225708, | |
| "learning_rate": 0.00016, | |
| "loss": 9.3607, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001094025405701088, | |
| "grad_norm": 3.152874231338501, | |
| "learning_rate": 0.00018, | |
| "loss": 9.9624, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00121558378411232, | |
| "grad_norm": 1.7264574766159058, | |
| "learning_rate": 0.0002, | |
| "loss": 10.4001, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013371421625235518, | |
| "grad_norm": 4.396702766418457, | |
| "learning_rate": 0.0001999863304992469, | |
| "loss": 8.8946, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001458700540934784, | |
| "grad_norm": 1.9022140502929688, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 10.3819, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001580258919346016, | |
| "grad_norm": 2.1845006942749023, | |
| "learning_rate": 0.00019987699691483048, | |
| "loss": 9.6356, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001701817297757248, | |
| "grad_norm": 2.10140061378479, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 9.6127, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0018233756761684798, | |
| "grad_norm": 2.068610668182373, | |
| "learning_rate": 0.000199658449300667, | |
| "loss": 11.08, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001944934054579712, | |
| "grad_norm": 3.655803680419922, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 10.0545, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002066492432990944, | |
| "grad_norm": 1.8618426322937012, | |
| "learning_rate": 0.00019933092663536382, | |
| "loss": 9.6545, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002188050811402176, | |
| "grad_norm": 1.8773517608642578, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 7.7819, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002309609189813408, | |
| "grad_norm": 2.198024272918701, | |
| "learning_rate": 0.00019889478706014687, | |
| "loss": 9.8384, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00243116756822464, | |
| "grad_norm": 2.1132476329803467, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 8.5882, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0025527259466358717, | |
| "grad_norm": 2.646947145462036, | |
| "learning_rate": 0.00019835050748723824, | |
| "loss": 9.4244, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0026742843250471037, | |
| "grad_norm": 2.169708728790283, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 8.9, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.002795842703458336, | |
| "grad_norm": 4.217128276824951, | |
| "learning_rate": 0.00019769868307835994, | |
| "loss": 8.5476, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002917401081869568, | |
| "grad_norm": 1.9587572813034058, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 9.5256, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0030389594602808, | |
| "grad_norm": 4.422936916351318, | |
| "learning_rate": 0.00019694002659393305, | |
| "loss": 8.403, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003160517838692032, | |
| "grad_norm": 1.6125566959381104, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 9.2696, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.003282076217103264, | |
| "grad_norm": 1.9092199802398682, | |
| "learning_rate": 0.00019607536761368484, | |
| "loss": 9.0772, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003403634595514496, | |
| "grad_norm": 3.2192418575286865, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 9.7968, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0035251929739257277, | |
| "grad_norm": 2.5830280780792236, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 9.7017, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0036467513523369597, | |
| "grad_norm": 2.7067151069641113, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 10.3412, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0037683097307481916, | |
| "grad_norm": 3.9291067123413086, | |
| "learning_rate": 0.00019403193901161613, | |
| "loss": 9.8539, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.003889868109159424, | |
| "grad_norm": 1.7529088258743286, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 8.7478, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004011426487570656, | |
| "grad_norm": 1.7117114067077637, | |
| "learning_rate": 0.00019285540384897073, | |
| "loss": 8.765, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004132984865981888, | |
| "grad_norm": 1.856972575187683, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 9.777, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00425454324439312, | |
| "grad_norm": 2.3596813678741455, | |
| "learning_rate": 0.00019157733266550575, | |
| "loss": 9.5862, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004376101622804352, | |
| "grad_norm": 2.5083954334259033, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 9.3247, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004497660001215584, | |
| "grad_norm": 1.3706068992614746, | |
| "learning_rate": 0.00019019912301329592, | |
| "loss": 9.3214, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.004619218379626816, | |
| "grad_norm": 1.7020275592803955, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 8.5611, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.004740776758038048, | |
| "grad_norm": 1.8647181987762451, | |
| "learning_rate": 0.0001887222819443612, | |
| "loss": 9.9951, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00486233513644928, | |
| "grad_norm": 2.506580352783203, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 9.6237, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0049838935148605115, | |
| "grad_norm": 1.9629899263381958, | |
| "learning_rate": 0.00018714842436272773, | |
| "loss": 9.371, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0051054518932717435, | |
| "grad_norm": 2.3143656253814697, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 9.235, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005227010271682975, | |
| "grad_norm": 2.5331368446350098, | |
| "learning_rate": 0.0001854792712585539, | |
| "loss": 10.1562, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.005348568650094207, | |
| "grad_norm": 4.555860996246338, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 8.2419, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005470127028505439, | |
| "grad_norm": 1.6661875247955322, | |
| "learning_rate": 0.00018371664782625287, | |
| "loss": 8.2566, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005591685406916672, | |
| "grad_norm": 1.7546186447143555, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 9.1446, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005713243785327904, | |
| "grad_norm": 1.751132845878601, | |
| "learning_rate": 0.00018186248146866927, | |
| "loss": 8.6259, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.005834802163739136, | |
| "grad_norm": 2.203023672103882, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 9.3622, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.005956360542150368, | |
| "grad_norm": 2.7363836765289307, | |
| "learning_rate": 0.0001799187996894925, | |
| "loss": 8.0726, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0060779189205616, | |
| "grad_norm": 2.010042905807495, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 9.8848, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0060779189205616, | |
| "eval_loss": 2.22426700592041, | |
| "eval_runtime": 130.4637, | |
| "eval_samples_per_second": 26.551, | |
| "eval_steps_per_second": 13.276, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006199477298972832, | |
| "grad_norm": 2.2631587982177734, | |
| "learning_rate": 0.00017788772787621126, | |
| "loss": 9.446, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.006321035677384064, | |
| "grad_norm": 4.675655364990234, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 9.3449, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.006442594055795296, | |
| "grad_norm": 1.7152106761932373, | |
| "learning_rate": 0.0001757714869760335, | |
| "loss": 9.475, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.006564152434206528, | |
| "grad_norm": 1.5290554761886597, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 9.117, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.00668571081261776, | |
| "grad_norm": 2.0921902656555176, | |
| "learning_rate": 0.00017357239106731317, | |
| "loss": 9.5546, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.006807269191028992, | |
| "grad_norm": 2.1920764446258545, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 8.953, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0069288275694402235, | |
| "grad_norm": 1.7566354274749756, | |
| "learning_rate": 0.00017129284482913972, | |
| "loss": 9.6787, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0070503859478514555, | |
| "grad_norm": 1.4819419384002686, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 7.3843, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.007171944326262687, | |
| "grad_norm": 1.6789450645446777, | |
| "learning_rate": 0.0001689353409118566, | |
| "loss": 9.802, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.007293502704673919, | |
| "grad_norm": 1.282571792602539, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 7.7288, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.007415061083085151, | |
| "grad_norm": 2.066798448562622, | |
| "learning_rate": 0.0001665024572113848, | |
| "loss": 9.3806, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.007536619461496383, | |
| "grad_norm": 1.7693638801574707, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 9.6393, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.007658177839907615, | |
| "grad_norm": 1.7502071857452393, | |
| "learning_rate": 0.00016399685405033167, | |
| "loss": 8.3708, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.007779736218318848, | |
| "grad_norm": 2.8502800464630127, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 8.8738, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.00790129459673008, | |
| "grad_norm": 2.4103214740753174, | |
| "learning_rate": 0.0001614212712689668, | |
| "loss": 9.5765, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.008022852975141312, | |
| "grad_norm": 1.8917535543441772, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 9.4486, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.008144411353552544, | |
| "grad_norm": 1.5890737771987915, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 8.5677, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.008265969731963776, | |
| "grad_norm": 2.1370444297790527, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 9.4762, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.008387528110375008, | |
| "grad_norm": 1.7275190353393555, | |
| "learning_rate": 0.0001560715057351673, | |
| "loss": 8.829, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.00850908648878624, | |
| "grad_norm": 1.7048512697219849, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 8.8259, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.008630644867197472, | |
| "grad_norm": 1.903066635131836, | |
| "learning_rate": 0.0001533031728727994, | |
| "loss": 9.6929, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.008752203245608704, | |
| "grad_norm": 1.5013515949249268, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 8.1273, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.008873761624019936, | |
| "grad_norm": 1.6483365297317505, | |
| "learning_rate": 0.0001504765537734844, | |
| "loss": 8.8742, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.008995320002431167, | |
| "grad_norm": 1.8312402963638306, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 8.7848, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.0091168783808424, | |
| "grad_norm": 1.3816986083984375, | |
| "learning_rate": 0.00014759473930370736, | |
| "loss": 8.2036, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.009238436759253631, | |
| "grad_norm": 2.2364020347595215, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 10.4628, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.009359995137664863, | |
| "grad_norm": 1.573431134223938, | |
| "learning_rate": 0.00014466088068528068, | |
| "loss": 8.8974, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.009481553516076095, | |
| "grad_norm": 2.187255859375, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 8.5312, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.009603111894487327, | |
| "grad_norm": 2.0174520015716553, | |
| "learning_rate": 0.00014167818604952906, | |
| "loss": 8.829, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.00972467027289856, | |
| "grad_norm": 1.8616173267364502, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 8.3692, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.009846228651309791, | |
| "grad_norm": 1.8460533618927002, | |
| "learning_rate": 0.00013864991692924523, | |
| "loss": 8.6283, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.009967787029721023, | |
| "grad_norm": 2.5459718704223633, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 8.4909, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.010089345408132255, | |
| "grad_norm": 1.9989314079284668, | |
| "learning_rate": 0.00013557938469225167, | |
| "loss": 8.9659, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.010210903786543487, | |
| "grad_norm": 1.3886724710464478, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 9.1106, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.010332462164954719, | |
| "grad_norm": 2.354243040084839, | |
| "learning_rate": 0.00013246994692046836, | |
| "loss": 9.2569, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.01045402054336595, | |
| "grad_norm": 2.085102081298828, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 8.9907, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.010575578921777183, | |
| "grad_norm": 1.2773852348327637, | |
| "learning_rate": 0.0001293250037384465, | |
| "loss": 8.7438, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.010697137300188415, | |
| "grad_norm": 1.6545124053955078, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 8.7085, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.010818695678599647, | |
| "grad_norm": 2.1138100624084473, | |
| "learning_rate": 0.00012614799409538198, | |
| "loss": 8.8577, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.010940254057010879, | |
| "grad_norm": 1.8220653533935547, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 9.198, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.011061812435422112, | |
| "grad_norm": 1.6138783693313599, | |
| "learning_rate": 0.00012294239200467516, | |
| "loss": 8.9333, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.011183370813833344, | |
| "grad_norm": 1.6465097665786743, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 9.123, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.011304929192244576, | |
| "grad_norm": 1.7768160104751587, | |
| "learning_rate": 0.00011971170274514802, | |
| "loss": 8.6597, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.011426487570655808, | |
| "grad_norm": 1.6465460062026978, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 9.841, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.01154804594906704, | |
| "grad_norm": 1.3596290349960327, | |
| "learning_rate": 0.00011645945902807341, | |
| "loss": 8.5273, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.011669604327478272, | |
| "grad_norm": 1.612764596939087, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 8.4275, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.011791162705889504, | |
| "grad_norm": 2.3744266033172607, | |
| "learning_rate": 0.00011318921713420691, | |
| "loss": 9.6372, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.011912721084300736, | |
| "grad_norm": 1.4123613834381104, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 8.4314, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.012034279462711968, | |
| "grad_norm": 1.9357587099075317, | |
| "learning_rate": 0.0001099045530250463, | |
| "loss": 8.7244, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0121558378411232, | |
| "grad_norm": 1.6507443189620972, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 10.0314, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0121558378411232, | |
| "eval_loss": 2.20096755027771, | |
| "eval_runtime": 130.4185, | |
| "eval_samples_per_second": 26.561, | |
| "eval_steps_per_second": 13.28, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.012277396219534432, | |
| "grad_norm": 2.1093552112579346, | |
| "learning_rate": 0.00010660905843256994, | |
| "loss": 10.0093, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.012398954597945664, | |
| "grad_norm": 2.1423592567443848, | |
| "learning_rate": 0.00010495837546732224, | |
| "loss": 9.6464, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.012520512976356896, | |
| "grad_norm": 1.413726568222046, | |
| "learning_rate": 0.00010330633693173082, | |
| "loss": 9.0782, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.012642071354768128, | |
| "grad_norm": 2.7693593502044678, | |
| "learning_rate": 0.00010165339447663587, | |
| "loss": 9.1446, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.01276362973317936, | |
| "grad_norm": 1.9296963214874268, | |
| "learning_rate": 0.0001, | |
| "loss": 8.2252, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.012885188111590591, | |
| "grad_norm": 2.1879448890686035, | |
| "learning_rate": 9.834660552336415e-05, | |
| "loss": 10.2142, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.013006746490001823, | |
| "grad_norm": 1.3834993839263916, | |
| "learning_rate": 9.669366306826919e-05, | |
| "loss": 9.5412, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.013128304868413055, | |
| "grad_norm": 1.5268234014511108, | |
| "learning_rate": 9.504162453267777e-05, | |
| "loss": 8.0744, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.013249863246824287, | |
| "grad_norm": 1.9845620393753052, | |
| "learning_rate": 9.339094156743007e-05, | |
| "loss": 8.4186, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.01337142162523552, | |
| "grad_norm": 1.6854311227798462, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 8.4435, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.013492980003646751, | |
| "grad_norm": 1.5681287050247192, | |
| "learning_rate": 9.009544697495374e-05, | |
| "loss": 8.6079, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.013614538382057983, | |
| "grad_norm": 1.6393003463745117, | |
| "learning_rate": 8.845153630304139e-05, | |
| "loss": 9.3246, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.013736096760469215, | |
| "grad_norm": 1.6968841552734375, | |
| "learning_rate": 8.681078286579311e-05, | |
| "loss": 7.5143, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.013857655138880447, | |
| "grad_norm": 1.4313429594039917, | |
| "learning_rate": 8.517363522881579e-05, | |
| "loss": 9.078, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.013979213517291679, | |
| "grad_norm": 1.592039942741394, | |
| "learning_rate": 8.35405409719266e-05, | |
| "loss": 8.1703, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.014100771895702911, | |
| "grad_norm": 1.4118988513946533, | |
| "learning_rate": 8.191194656678904e-05, | |
| "loss": 8.941, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.014222330274114143, | |
| "grad_norm": 1.3782672882080078, | |
| "learning_rate": 8.028829725485199e-05, | |
| "loss": 8.4541, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.014343888652525375, | |
| "grad_norm": 2.4915947914123535, | |
| "learning_rate": 7.867003692562534e-05, | |
| "loss": 7.8308, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.014465447030936607, | |
| "grad_norm": 1.6528788805007935, | |
| "learning_rate": 7.705760799532485e-05, | |
| "loss": 8.732, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.014587005409347839, | |
| "grad_norm": 2.2975354194641113, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 9.3207, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01470856378775907, | |
| "grad_norm": 2.4572110176086426, | |
| "learning_rate": 7.385200590461803e-05, | |
| "loss": 9.4007, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.014830122166170303, | |
| "grad_norm": 1.338627576828003, | |
| "learning_rate": 7.225970912381556e-05, | |
| "loss": 8.8468, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.014951680544581535, | |
| "grad_norm": 1.862164855003357, | |
| "learning_rate": 7.067499626155354e-05, | |
| "loss": 8.9436, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.015073238922992767, | |
| "grad_norm": 2.2516064643859863, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 8.7996, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.015194797301403998, | |
| "grad_norm": 1.4722728729248047, | |
| "learning_rate": 6.753005307953167e-05, | |
| "loss": 7.7244, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.01531635567981523, | |
| "grad_norm": 2.090157985687256, | |
| "learning_rate": 6.59706825558357e-05, | |
| "loss": 8.5753, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.015437914058226464, | |
| "grad_norm": 1.8846075534820557, | |
| "learning_rate": 6.442061530774834e-05, | |
| "loss": 8.9389, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.015559472436637696, | |
| "grad_norm": 1.606086254119873, | |
| "learning_rate": 6.28802751081779e-05, | |
| "loss": 7.7107, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.015681030815048926, | |
| "grad_norm": 1.6152966022491455, | |
| "learning_rate": 6.135008307075481e-05, | |
| "loss": 9.4444, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.01580258919346016, | |
| "grad_norm": 2.8925600051879883, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 8.2291, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01592414757187139, | |
| "grad_norm": 1.3763501644134521, | |
| "learning_rate": 5.832181395047098e-05, | |
| "loss": 8.9548, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.016045705950282624, | |
| "grad_norm": 1.7891381978988647, | |
| "learning_rate": 5.6824564766150726e-05, | |
| "loss": 8.7198, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.016167264328693854, | |
| "grad_norm": 1.6122995615005493, | |
| "learning_rate": 5.533911931471936e-05, | |
| "loss": 9.8015, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.016288822707105088, | |
| "grad_norm": 2.285371780395508, | |
| "learning_rate": 5.386588370213124e-05, | |
| "loss": 8.8946, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.016410381085516318, | |
| "grad_norm": 2.1016831398010254, | |
| "learning_rate": 5.240526069629265e-05, | |
| "loss": 8.5699, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.01653193946392755, | |
| "grad_norm": 1.6653213500976562, | |
| "learning_rate": 5.095764961694922e-05, | |
| "loss": 8.6184, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.016653497842338782, | |
| "grad_norm": 1.4281337261199951, | |
| "learning_rate": 4.952344622651566e-05, | |
| "loss": 8.0501, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.016775056220750015, | |
| "grad_norm": 1.9814000129699707, | |
| "learning_rate": 4.810304262187852e-05, | |
| "loss": 7.7907, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.016896614599161246, | |
| "grad_norm": 1.6379835605621338, | |
| "learning_rate": 4.669682712720065e-05, | |
| "loss": 8.7783, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.01701817297757248, | |
| "grad_norm": 2.8867030143737793, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 8.2023, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01713973135598371, | |
| "grad_norm": 1.8214524984359741, | |
| "learning_rate": 4.392849426483274e-05, | |
| "loss": 9.0595, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.017261289734394943, | |
| "grad_norm": 1.807656168937683, | |
| "learning_rate": 4.256713373170564e-05, | |
| "loss": 8.4609, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.017382848112806173, | |
| "grad_norm": 1.7904338836669922, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 8.0106, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.017504406491217407, | |
| "grad_norm": 2.073862314224243, | |
| "learning_rate": 3.9891885271697496e-05, | |
| "loss": 8.6199, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.01762596486962864, | |
| "grad_norm": 1.665391445159912, | |
| "learning_rate": 3.857872873103322e-05, | |
| "loss": 9.1573, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.01774752324803987, | |
| "grad_norm": 2.4493348598480225, | |
| "learning_rate": 3.7282364152646297e-05, | |
| "loss": 7.3018, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.017869081626451105, | |
| "grad_norm": 1.4470022916793823, | |
| "learning_rate": 3.600314594966834e-05, | |
| "loss": 8.5612, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.017990640004862335, | |
| "grad_norm": 1.7825874090194702, | |
| "learning_rate": 3.4741423847583134e-05, | |
| "loss": 9.3814, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.01811219838327357, | |
| "grad_norm": 1.5861843824386597, | |
| "learning_rate": 3.349754278861517e-05, | |
| "loss": 9.1074, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.0182337567616848, | |
| "grad_norm": 1.8981313705444336, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 7.7665, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0182337567616848, | |
| "eval_loss": 2.19260835647583, | |
| "eval_runtime": 130.7594, | |
| "eval_samples_per_second": 26.491, | |
| "eval_steps_per_second": 13.246, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.018355315140096033, | |
| "grad_norm": 1.6255931854248047, | |
| "learning_rate": 3.106465908814342e-05, | |
| "loss": 9.076, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.018476873518507263, | |
| "grad_norm": 1.4169337749481201, | |
| "learning_rate": 2.9876321572751144e-05, | |
| "loss": 8.5266, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.018598431896918496, | |
| "grad_norm": 1.3011150360107422, | |
| "learning_rate": 2.87071551708603e-05, | |
| "loss": 8.4848, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.018719990275329727, | |
| "grad_norm": 2.2448577880859375, | |
| "learning_rate": 2.7557479520891104e-05, | |
| "loss": 8.4936, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.01884154865374096, | |
| "grad_norm": 2.336907386779785, | |
| "learning_rate": 2.6427608932686843e-05, | |
| "loss": 10.1081, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.01896310703215219, | |
| "grad_norm": 2.3736586570739746, | |
| "learning_rate": 2.5317852301584643e-05, | |
| "loss": 8.715, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.019084665410563424, | |
| "grad_norm": 2.2278640270233154, | |
| "learning_rate": 2.422851302396655e-05, | |
| "loss": 7.6252, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.019206223788974654, | |
| "grad_norm": 2.075263261795044, | |
| "learning_rate": 2.315988891431412e-05, | |
| "loss": 8.8813, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.019327782167385888, | |
| "grad_norm": 1.630843162536621, | |
| "learning_rate": 2.2112272123788768e-05, | |
| "loss": 9.5883, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.01944934054579712, | |
| "grad_norm": 1.8123506307601929, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 8.3388, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.019570898924208352, | |
| "grad_norm": 1.678495168685913, | |
| "learning_rate": 2.008120031050753e-05, | |
| "loss": 7.75, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.019692457302619582, | |
| "grad_norm": 1.6239267587661743, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 9.6735, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.019814015681030816, | |
| "grad_norm": 1.7330944538116455, | |
| "learning_rate": 1.8137518531330767e-05, | |
| "loss": 8.2531, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.019935574059442046, | |
| "grad_norm": 1.772774338722229, | |
| "learning_rate": 1.7199116885197995e-05, | |
| "loss": 9.5867, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.02005713243785328, | |
| "grad_norm": 2.354120969772339, | |
| "learning_rate": 1.6283352173747145e-05, | |
| "loss": 9.5565, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.02017869081626451, | |
| "grad_norm": 1.7209793329238892, | |
| "learning_rate": 1.5390474757906446e-05, | |
| "loss": 9.5981, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.020300249194675744, | |
| "grad_norm": 1.2247873544692993, | |
| "learning_rate": 1.4520728741446089e-05, | |
| "loss": 8.0355, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.020421807573086974, | |
| "grad_norm": 1.4264851808547974, | |
| "learning_rate": 1.3674351904242611e-05, | |
| "loss": 8.0481, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.020543365951498208, | |
| "grad_norm": 1.3829172849655151, | |
| "learning_rate": 1.2851575637272262e-05, | |
| "loss": 9.0446, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.020664924329909438, | |
| "grad_norm": 1.413722038269043, | |
| "learning_rate": 1.2052624879351104e-05, | |
| "loss": 7.2469, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.02078648270832067, | |
| "grad_norm": 1.6910505294799805, | |
| "learning_rate": 1.1277718055638819e-05, | |
| "loss": 8.2903, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.0209080410867319, | |
| "grad_norm": 1.9138679504394531, | |
| "learning_rate": 1.0527067017923654e-05, | |
| "loss": 9.0652, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.021029599465143135, | |
| "grad_norm": 1.5398927927017212, | |
| "learning_rate": 9.80087698670411e-06, | |
| "loss": 9.4462, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.021151157843554366, | |
| "grad_norm": 2.0731565952301025, | |
| "learning_rate": 9.09934649508375e-06, | |
| "loss": 9.2584, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.0212727162219656, | |
| "grad_norm": 1.8292239904403687, | |
| "learning_rate": 8.422667334494249e-06, | |
| "loss": 8.2206, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.02139427460037683, | |
| "grad_norm": 1.8700852394104004, | |
| "learning_rate": 7.771024502261526e-06, | |
| "loss": 9.4161, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.021515832978788063, | |
| "grad_norm": 2.166424512863159, | |
| "learning_rate": 7.144596151029303e-06, | |
| "loss": 8.0841, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.021637391357199293, | |
| "grad_norm": 1.5074312686920166, | |
| "learning_rate": 6.543553540053926e-06, | |
| "loss": 9.621, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.021758949735610527, | |
| "grad_norm": 1.4082826375961304, | |
| "learning_rate": 5.968060988383883e-06, | |
| "loss": 9.3076, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.021880508114021757, | |
| "grad_norm": 1.45763099193573, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 8.8478, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02200206649243299, | |
| "grad_norm": 2.5203921794891357, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 8.3001, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.022123624870844225, | |
| "grad_norm": 1.9692637920379639, | |
| "learning_rate": 4.3964218465642355e-06, | |
| "loss": 9.1614, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.022245183249255455, | |
| "grad_norm": 1.598758339881897, | |
| "learning_rate": 3.924632386315186e-06, | |
| "loss": 9.3152, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.02236674162766669, | |
| "grad_norm": 1.3611668348312378, | |
| "learning_rate": 3.4791089722651436e-06, | |
| "loss": 8.5055, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.02248830000607792, | |
| "grad_norm": 1.7095437049865723, | |
| "learning_rate": 3.059973406066963e-06, | |
| "loss": 8.6328, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.022609858384489152, | |
| "grad_norm": 1.3015220165252686, | |
| "learning_rate": 2.667340275199426e-06, | |
| "loss": 7.9608, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.022731416762900383, | |
| "grad_norm": 1.7117013931274414, | |
| "learning_rate": 2.3013169216400733e-06, | |
| "loss": 8.2766, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.022852975141311616, | |
| "grad_norm": 1.5060421228408813, | |
| "learning_rate": 1.9620034125190644e-06, | |
| "loss": 10.397, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.022974533519722846, | |
| "grad_norm": 1.8349546194076538, | |
| "learning_rate": 1.6494925127617634e-06, | |
| "loss": 9.6316, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.02309609189813408, | |
| "grad_norm": 2.0943706035614014, | |
| "learning_rate": 1.3638696597277679e-06, | |
| "loss": 7.7704, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.02321765027654531, | |
| "grad_norm": 1.7935388088226318, | |
| "learning_rate": 1.1052129398531507e-06, | |
| "loss": 10.2541, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.023339208654956544, | |
| "grad_norm": 1.8074511289596558, | |
| "learning_rate": 8.735930673024806e-07, | |
| "loss": 9.2515, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.023460767033367774, | |
| "grad_norm": 1.4618196487426758, | |
| "learning_rate": 6.690733646361857e-07, | |
| "loss": 8.3641, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.023582325411779008, | |
| "grad_norm": 2.332951307296753, | |
| "learning_rate": 4.917097454988584e-07, | |
| "loss": 9.805, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.023703883790190238, | |
| "grad_norm": 1.3441449403762817, | |
| "learning_rate": 3.415506993330153e-07, | |
| "loss": 8.7603, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.023825442168601472, | |
| "grad_norm": 1.8775608539581299, | |
| "learning_rate": 2.1863727812254653e-07, | |
| "loss": 9.3356, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.023947000547012702, | |
| "grad_norm": 1.3865495920181274, | |
| "learning_rate": 1.230030851695263e-07, | |
| "loss": 8.5184, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.024068558925423936, | |
| "grad_norm": 2.735950469970703, | |
| "learning_rate": 5.467426590739511e-08, | |
| "loss": 8.6827, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.024190117303835166, | |
| "grad_norm": 1.6667054891586304, | |
| "learning_rate": 1.3669500753099585e-08, | |
| "loss": 9.2634, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.0243116756822464, | |
| "grad_norm": 1.8722801208496094, | |
| "learning_rate": 0.0, | |
| "loss": 8.9515, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0243116756822464, | |
| "eval_loss": 2.1910746097564697, | |
| "eval_runtime": 130.64, | |
| "eval_samples_per_second": 26.516, | |
| "eval_steps_per_second": 13.258, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.762410749113139e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |