| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13508949679162446, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006754474839581223, | |
| "grad_norm": 0.32079648971557617, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006754474839581223, | |
| "eval_loss": 10.850319862365723, | |
| "eval_runtime": 2.6665, | |
| "eval_samples_per_second": 234.019, | |
| "eval_steps_per_second": 117.009, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013508949679162446, | |
| "grad_norm": 0.32938364148139954, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8557, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002026342451874367, | |
| "grad_norm": 0.3332866430282593, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8487, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002701789935832489, | |
| "grad_norm": 0.3259293735027313, | |
| "learning_rate": 8e-05, | |
| "loss": 10.8485, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003377237419790611, | |
| "grad_norm": 0.33600881695747375, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8459, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004052684903748734, | |
| "grad_norm": 0.3575391173362732, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8517, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004728132387706856, | |
| "grad_norm": 0.33056777715682983, | |
| "learning_rate": 0.00014, | |
| "loss": 10.8459, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005403579871664978, | |
| "grad_norm": 0.35549676418304443, | |
| "learning_rate": 0.00016, | |
| "loss": 10.8443, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0060790273556231, | |
| "grad_norm": 0.34090492129325867, | |
| "learning_rate": 0.00018, | |
| "loss": 10.8468, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006754474839581222, | |
| "grad_norm": 0.34161046147346497, | |
| "learning_rate": 0.0002, | |
| "loss": 10.8432, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007429922323539345, | |
| "grad_norm": 0.3733224868774414, | |
| "learning_rate": 0.0001999863304992469, | |
| "loss": 10.8395, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008105369807497468, | |
| "grad_norm": 0.37448549270629883, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 10.8345, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008780817291455589, | |
| "grad_norm": 0.39854905009269714, | |
| "learning_rate": 0.00019987699691483048, | |
| "loss": 10.8358, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009456264775413711, | |
| "grad_norm": 0.4029870629310608, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 10.8312, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010131712259371834, | |
| "grad_norm": 0.3861730396747589, | |
| "learning_rate": 0.000199658449300667, | |
| "loss": 10.827, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010807159743329957, | |
| "grad_norm": 0.4259829819202423, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 10.8214, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011482607227288078, | |
| "grad_norm": 0.4038204252719879, | |
| "learning_rate": 0.00019933092663536382, | |
| "loss": 10.8221, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0121580547112462, | |
| "grad_norm": 0.4385932385921478, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 10.8208, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012833502195204323, | |
| "grad_norm": 0.4669629633426666, | |
| "learning_rate": 0.00019889478706014687, | |
| "loss": 10.8162, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013508949679162444, | |
| "grad_norm": 0.45796719193458557, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 10.8103, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014184397163120567, | |
| "grad_norm": 0.46000435948371887, | |
| "learning_rate": 0.00019835050748723824, | |
| "loss": 10.8013, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01485984464707869, | |
| "grad_norm": 0.4528140425682068, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 10.7983, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.015535292131036813, | |
| "grad_norm": 0.5075253248214722, | |
| "learning_rate": 0.00019769868307835994, | |
| "loss": 10.7945, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.016210739614994935, | |
| "grad_norm": 0.49094441533088684, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 10.7873, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016886187098953058, | |
| "grad_norm": 0.4418376684188843, | |
| "learning_rate": 0.00019694002659393305, | |
| "loss": 10.7869, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017561634582911177, | |
| "grad_norm": 0.4543623924255371, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 10.7771, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0182370820668693, | |
| "grad_norm": 0.514811098575592, | |
| "learning_rate": 0.00019607536761368484, | |
| "loss": 10.7833, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018912529550827423, | |
| "grad_norm": 0.5044733881950378, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 10.7702, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.019587977034785545, | |
| "grad_norm": 0.5136566162109375, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.7711, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.020263424518743668, | |
| "grad_norm": 0.5506525039672852, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 10.7634, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02093887200270179, | |
| "grad_norm": 0.5305942893028259, | |
| "learning_rate": 0.00019403193901161613, | |
| "loss": 10.7524, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.021614319486659914, | |
| "grad_norm": 0.5339845418930054, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 10.7551, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.022289766970618033, | |
| "grad_norm": 0.5734214186668396, | |
| "learning_rate": 0.00019285540384897073, | |
| "loss": 10.7459, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.022965214454576156, | |
| "grad_norm": 0.5622735023498535, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 10.7351, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02364066193853428, | |
| "grad_norm": 0.5738793015480042, | |
| "learning_rate": 0.00019157733266550575, | |
| "loss": 10.7313, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0243161094224924, | |
| "grad_norm": 0.560500979423523, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 10.7251, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.024991556906450524, | |
| "grad_norm": 0.5471153259277344, | |
| "learning_rate": 0.00019019912301329592, | |
| "loss": 10.7093, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.025667004390408647, | |
| "grad_norm": 0.5753123760223389, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 10.7115, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02634245187436677, | |
| "grad_norm": 0.5051413774490356, | |
| "learning_rate": 0.0001887222819443612, | |
| "loss": 10.7161, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02701789935832489, | |
| "grad_norm": 0.5438815355300903, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 10.6966, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02769334684228301, | |
| "grad_norm": 0.5222083330154419, | |
| "learning_rate": 0.00018714842436272773, | |
| "loss": 10.6916, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.028368794326241134, | |
| "grad_norm": 0.4598117172718048, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 10.7039, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.029044241810199257, | |
| "grad_norm": 0.517598032951355, | |
| "learning_rate": 0.0001854792712585539, | |
| "loss": 10.6926, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02971968929415738, | |
| "grad_norm": 0.5157806873321533, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 10.685, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.030395136778115502, | |
| "grad_norm": 0.4841625690460205, | |
| "learning_rate": 0.00018371664782625287, | |
| "loss": 10.6855, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.031070584262073625, | |
| "grad_norm": 0.47345930337905884, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 10.6667, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.031746031746031744, | |
| "grad_norm": 0.3876435458660126, | |
| "learning_rate": 0.00018186248146866927, | |
| "loss": 10.699, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03242147922998987, | |
| "grad_norm": 0.43177780508995056, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 10.6633, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03309692671394799, | |
| "grad_norm": 0.4080864489078522, | |
| "learning_rate": 0.0001799187996894925, | |
| "loss": 10.6654, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.033772374197906116, | |
| "grad_norm": 0.40777599811553955, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 10.659, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.033772374197906116, | |
| "eval_loss": 10.658723831176758, | |
| "eval_runtime": 2.2172, | |
| "eval_samples_per_second": 281.442, | |
| "eval_steps_per_second": 140.721, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.034447821681864235, | |
| "grad_norm": 0.37587037682533264, | |
| "learning_rate": 0.00017788772787621126, | |
| "loss": 10.6597, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.035123269165822354, | |
| "grad_norm": 0.35869449377059937, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 10.6479, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.03579871664978048, | |
| "grad_norm": 0.3892292380332947, | |
| "learning_rate": 0.0001757714869760335, | |
| "loss": 10.651, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0364741641337386, | |
| "grad_norm": 0.372700572013855, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 10.6507, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.037149611617696726, | |
| "grad_norm": 0.3261224329471588, | |
| "learning_rate": 0.00017357239106731317, | |
| "loss": 10.6657, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.037825059101654845, | |
| "grad_norm": 0.3149575889110565, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 10.6366, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.03850050658561297, | |
| "grad_norm": 0.3464124798774719, | |
| "learning_rate": 0.00017129284482913972, | |
| "loss": 10.6405, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.03917595406957109, | |
| "grad_norm": 0.291887491941452, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 10.6374, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03985140155352921, | |
| "grad_norm": 0.2717147767543793, | |
| "learning_rate": 0.0001689353409118566, | |
| "loss": 10.6367, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.040526849037487336, | |
| "grad_norm": 0.27471521496772766, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 10.6394, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.041202296521445456, | |
| "grad_norm": 0.26729482412338257, | |
| "learning_rate": 0.0001665024572113848, | |
| "loss": 10.6301, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.04187774400540358, | |
| "grad_norm": 0.25519606471061707, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 10.6343, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0425531914893617, | |
| "grad_norm": 0.25052082538604736, | |
| "learning_rate": 0.00016399685405033167, | |
| "loss": 10.6282, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.04322863897331983, | |
| "grad_norm": 0.24196283519268036, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 10.6253, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.04390408645727795, | |
| "grad_norm": 0.24466153979301453, | |
| "learning_rate": 0.0001614212712689668, | |
| "loss": 10.6304, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.044579533941236066, | |
| "grad_norm": 0.21384331583976746, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 10.6279, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.04525498142519419, | |
| "grad_norm": 0.23176230490207672, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 10.6254, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.04593042890915231, | |
| "grad_norm": 0.21549372375011444, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 10.6254, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.04660587639311044, | |
| "grad_norm": 0.21212856471538544, | |
| "learning_rate": 0.0001560715057351673, | |
| "loss": 10.6306, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.04728132387706856, | |
| "grad_norm": 0.2017771154642105, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 10.6216, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04795677136102668, | |
| "grad_norm": 0.21862851083278656, | |
| "learning_rate": 0.0001533031728727994, | |
| "loss": 10.6099, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0486322188449848, | |
| "grad_norm": 0.1980670690536499, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 10.6245, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.04930766632894292, | |
| "grad_norm": 0.2036397010087967, | |
| "learning_rate": 0.0001504765537734844, | |
| "loss": 10.6232, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.04998311381290105, | |
| "grad_norm": 0.17732380330562592, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 10.6244, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.05065856129685917, | |
| "grad_norm": 0.19181127846240997, | |
| "learning_rate": 0.00014759473930370736, | |
| "loss": 10.6222, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.05133400878081729, | |
| "grad_norm": 0.1601181924343109, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 10.6218, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.05200945626477541, | |
| "grad_norm": 0.18116536736488342, | |
| "learning_rate": 0.00014466088068528068, | |
| "loss": 10.625, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.05268490374873354, | |
| "grad_norm": 0.14323946833610535, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 10.6489, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.05336035123269166, | |
| "grad_norm": 0.1809110790491104, | |
| "learning_rate": 0.00014167818604952906, | |
| "loss": 10.6282, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.05403579871664978, | |
| "grad_norm": 0.13735494017601013, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 10.6169, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0547112462006079, | |
| "grad_norm": 0.15906408429145813, | |
| "learning_rate": 0.00013864991692924523, | |
| "loss": 10.6212, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.05538669368456602, | |
| "grad_norm": 0.17548221349716187, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 10.6171, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.05606214116852415, | |
| "grad_norm": 0.12418357282876968, | |
| "learning_rate": 0.00013557938469225167, | |
| "loss": 10.6143, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.05673758865248227, | |
| "grad_norm": 0.1521899700164795, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 10.6199, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.057413036136440394, | |
| "grad_norm": 0.14142099022865295, | |
| "learning_rate": 0.00013246994692046836, | |
| "loss": 10.6131, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.058088483620398514, | |
| "grad_norm": 0.13722097873687744, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.6153, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.05876393110435663, | |
| "grad_norm": 0.14299722015857697, | |
| "learning_rate": 0.0001293250037384465, | |
| "loss": 10.6094, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.05943937858831476, | |
| "grad_norm": 0.13671687245368958, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 10.6242, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.06011482607227288, | |
| "grad_norm": 0.12905743718147278, | |
| "learning_rate": 0.00012614799409538198, | |
| "loss": 10.6116, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.060790273556231005, | |
| "grad_norm": 0.13734190165996552, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 10.6142, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.061465721040189124, | |
| "grad_norm": 0.13106867671012878, | |
| "learning_rate": 0.00012294239200467516, | |
| "loss": 10.6176, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.06214116852414725, | |
| "grad_norm": 0.1443423628807068, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 10.6369, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.06281661600810537, | |
| "grad_norm": 0.11222351342439651, | |
| "learning_rate": 0.00011971170274514802, | |
| "loss": 10.6164, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.06349206349206349, | |
| "grad_norm": 0.11618170142173767, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 10.6057, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.06416751097602161, | |
| "grad_norm": 0.11936385929584503, | |
| "learning_rate": 0.00011645945902807341, | |
| "loss": 10.6146, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.06484295845997974, | |
| "grad_norm": 0.12773548066616058, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 10.6161, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.06551840594393786, | |
| "grad_norm": 0.1389545202255249, | |
| "learning_rate": 0.00011318921713420691, | |
| "loss": 10.6053, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.06619385342789598, | |
| "grad_norm": 0.13642248511314392, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 10.6153, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0668693009118541, | |
| "grad_norm": 0.11348054558038712, | |
| "learning_rate": 0.0001099045530250463, | |
| "loss": 10.6132, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.06754474839581223, | |
| "grad_norm": 0.1491929590702057, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 10.6309, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06754474839581223, | |
| "eval_loss": 10.612899780273438, | |
| "eval_runtime": 2.3146, | |
| "eval_samples_per_second": 269.593, | |
| "eval_steps_per_second": 134.797, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06822019587977035, | |
| "grad_norm": 0.11731832474470139, | |
| "learning_rate": 0.00010660905843256994, | |
| "loss": 10.6064, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.06889564336372847, | |
| "grad_norm": 0.1060105562210083, | |
| "learning_rate": 0.00010495837546732224, | |
| "loss": 10.6059, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.06957109084768659, | |
| "grad_norm": 0.12271567434072495, | |
| "learning_rate": 0.00010330633693173082, | |
| "loss": 10.6046, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.07024653833164471, | |
| "grad_norm": 0.1422068178653717, | |
| "learning_rate": 0.00010165339447663587, | |
| "loss": 10.6122, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.07092198581560284, | |
| "grad_norm": 0.123976930975914, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6086, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.07159743329956096, | |
| "grad_norm": 0.11725173145532608, | |
| "learning_rate": 9.834660552336415e-05, | |
| "loss": 10.6312, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.07227288078351908, | |
| "grad_norm": 0.13431864976882935, | |
| "learning_rate": 9.669366306826919e-05, | |
| "loss": 10.6129, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.0729483282674772, | |
| "grad_norm": 0.10811913758516312, | |
| "learning_rate": 9.504162453267777e-05, | |
| "loss": 10.6102, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.07362377575143532, | |
| "grad_norm": 0.1448288857936859, | |
| "learning_rate": 9.339094156743007e-05, | |
| "loss": 10.6097, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.07429922323539345, | |
| "grad_norm": 0.14231544733047485, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 10.6149, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07497467071935157, | |
| "grad_norm": 0.11350355297327042, | |
| "learning_rate": 9.009544697495374e-05, | |
| "loss": 10.6123, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.07565011820330969, | |
| "grad_norm": 0.11213658004999161, | |
| "learning_rate": 8.845153630304139e-05, | |
| "loss": 10.6059, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.07632556568726781, | |
| "grad_norm": 0.12278730422258377, | |
| "learning_rate": 8.681078286579311e-05, | |
| "loss": 10.6049, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.07700101317122594, | |
| "grad_norm": 0.15146122872829437, | |
| "learning_rate": 8.517363522881579e-05, | |
| "loss": 10.6104, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.07767646065518406, | |
| "grad_norm": 0.11578516662120819, | |
| "learning_rate": 8.35405409719266e-05, | |
| "loss": 10.6276, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.07835190813914218, | |
| "grad_norm": 0.13298995792865753, | |
| "learning_rate": 8.191194656678904e-05, | |
| "loss": 10.6115, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.0790273556231003, | |
| "grad_norm": 0.13557101786136627, | |
| "learning_rate": 8.028829725485199e-05, | |
| "loss": 10.6083, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.07970280310705842, | |
| "grad_norm": 0.12159471958875656, | |
| "learning_rate": 7.867003692562534e-05, | |
| "loss": 10.6037, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.08037825059101655, | |
| "grad_norm": 0.12765274941921234, | |
| "learning_rate": 7.705760799532485e-05, | |
| "loss": 10.6016, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.08105369807497467, | |
| "grad_norm": 0.11235444992780685, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 10.6065, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08172914555893279, | |
| "grad_norm": 0.14903466403484344, | |
| "learning_rate": 7.385200590461803e-05, | |
| "loss": 10.5995, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.08240459304289091, | |
| "grad_norm": 0.10130941867828369, | |
| "learning_rate": 7.225970912381556e-05, | |
| "loss": 10.6095, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.08308004052684904, | |
| "grad_norm": 0.1442113071680069, | |
| "learning_rate": 7.067499626155354e-05, | |
| "loss": 10.6024, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.08375548801080716, | |
| "grad_norm": 0.14047802984714508, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 10.6104, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.08443093549476528, | |
| "grad_norm": 0.1147422268986702, | |
| "learning_rate": 6.753005307953167e-05, | |
| "loss": 10.6125, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 0.11507318913936615, | |
| "learning_rate": 6.59706825558357e-05, | |
| "loss": 10.6038, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.08578183046268152, | |
| "grad_norm": 0.13589414954185486, | |
| "learning_rate": 6.442061530774834e-05, | |
| "loss": 10.6044, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.08645727794663965, | |
| "grad_norm": 0.13625499606132507, | |
| "learning_rate": 6.28802751081779e-05, | |
| "loss": 10.6058, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.08713272543059777, | |
| "grad_norm": 0.12005976587533951, | |
| "learning_rate": 6.135008307075481e-05, | |
| "loss": 10.62, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.0878081729145559, | |
| "grad_norm": 0.11311294883489609, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 10.6092, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.08848362039851401, | |
| "grad_norm": 0.13194864988327026, | |
| "learning_rate": 5.832181395047098e-05, | |
| "loss": 10.5994, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.08915906788247213, | |
| "grad_norm": 0.12505017220973969, | |
| "learning_rate": 5.6824564766150726e-05, | |
| "loss": 10.6069, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.08983451536643026, | |
| "grad_norm": 0.13057582080364227, | |
| "learning_rate": 5.533911931471936e-05, | |
| "loss": 10.5994, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.09050996285038838, | |
| "grad_norm": 0.17442747950553894, | |
| "learning_rate": 5.386588370213124e-05, | |
| "loss": 10.6025, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.0911854103343465, | |
| "grad_norm": 0.12355850636959076, | |
| "learning_rate": 5.240526069629265e-05, | |
| "loss": 10.6065, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.09186085781830462, | |
| "grad_norm": 0.13733559846878052, | |
| "learning_rate": 5.095764961694922e-05, | |
| "loss": 10.5974, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.09253630530226276, | |
| "grad_norm": 0.14686278998851776, | |
| "learning_rate": 4.952344622651566e-05, | |
| "loss": 10.5941, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.09321175278622088, | |
| "grad_norm": 0.13458283245563507, | |
| "learning_rate": 4.810304262187852e-05, | |
| "loss": 10.5959, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.093887200270179, | |
| "grad_norm": 0.1384890228509903, | |
| "learning_rate": 4.669682712720065e-05, | |
| "loss": 10.6081, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.09456264775413711, | |
| "grad_norm": 0.15113620460033417, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 10.6194, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 0.14613160490989685, | |
| "learning_rate": 4.392849426483274e-05, | |
| "loss": 10.6113, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.09591354272205337, | |
| "grad_norm": 0.12903277575969696, | |
| "learning_rate": 4.256713373170564e-05, | |
| "loss": 10.6009, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.09658899020601149, | |
| "grad_norm": 0.15327778458595276, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.5978, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.0972644376899696, | |
| "grad_norm": 0.14414553344249725, | |
| "learning_rate": 3.9891885271697496e-05, | |
| "loss": 10.5922, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.09793988517392772, | |
| "grad_norm": 0.15006524324417114, | |
| "learning_rate": 3.857872873103322e-05, | |
| "loss": 10.6253, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.09861533265788584, | |
| "grad_norm": 0.14634265005588531, | |
| "learning_rate": 3.7282364152646297e-05, | |
| "loss": 10.6011, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.09929078014184398, | |
| "grad_norm": 0.14320406317710876, | |
| "learning_rate": 3.600314594966834e-05, | |
| "loss": 10.5892, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.0999662276258021, | |
| "grad_norm": 0.14602705836296082, | |
| "learning_rate": 3.4741423847583134e-05, | |
| "loss": 10.5927, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.10064167510976021, | |
| "grad_norm": 0.14189378917217255, | |
| "learning_rate": 3.349754278861517e-05, | |
| "loss": 10.5985, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.10131712259371833, | |
| "grad_norm": 0.15539740025997162, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 10.5968, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10131712259371833, | |
| "eval_loss": 10.599814414978027, | |
| "eval_runtime": 2.2579, | |
| "eval_samples_per_second": 276.357, | |
| "eval_steps_per_second": 138.179, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10199257007767647, | |
| "grad_norm": 0.1630678027868271, | |
| "learning_rate": 3.106465908814342e-05, | |
| "loss": 10.6025, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.10266801756163459, | |
| "grad_norm": 0.15854433178901672, | |
| "learning_rate": 2.9876321572751144e-05, | |
| "loss": 10.589, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.1033434650455927, | |
| "grad_norm": 0.15652941167354584, | |
| "learning_rate": 2.87071551708603e-05, | |
| "loss": 10.6022, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.10401891252955082, | |
| "grad_norm": 0.14386983215808868, | |
| "learning_rate": 2.7557479520891104e-05, | |
| "loss": 10.5974, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.10469436001350894, | |
| "grad_norm": 0.17749740183353424, | |
| "learning_rate": 2.6427608932686843e-05, | |
| "loss": 10.6112, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.10536980749746708, | |
| "grad_norm": 0.1529720574617386, | |
| "learning_rate": 2.5317852301584643e-05, | |
| "loss": 10.6075, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.1060452549814252, | |
| "grad_norm": 0.16465173661708832, | |
| "learning_rate": 2.422851302396655e-05, | |
| "loss": 10.5917, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.10672070246538332, | |
| "grad_norm": 0.148993581533432, | |
| "learning_rate": 2.315988891431412e-05, | |
| "loss": 10.5951, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.10739614994934144, | |
| "grad_norm": 0.17219752073287964, | |
| "learning_rate": 2.2112272123788768e-05, | |
| "loss": 10.5877, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.10807159743329955, | |
| "grad_norm": 0.17853744328022003, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 10.5945, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.10874704491725769, | |
| "grad_norm": 0.16907915472984314, | |
| "learning_rate": 2.008120031050753e-05, | |
| "loss": 10.5967, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.1094224924012158, | |
| "grad_norm": 0.18723782896995544, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 10.5955, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.11009793988517393, | |
| "grad_norm": 0.18115279078483582, | |
| "learning_rate": 1.8137518531330767e-05, | |
| "loss": 10.6003, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.11077338736913205, | |
| "grad_norm": 0.14582610130310059, | |
| "learning_rate": 1.7199116885197995e-05, | |
| "loss": 10.6084, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.11144883485309018, | |
| "grad_norm": 0.16853328049182892, | |
| "learning_rate": 1.6283352173747145e-05, | |
| "loss": 10.6109, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.1121242823370483, | |
| "grad_norm": 0.16580811142921448, | |
| "learning_rate": 1.5390474757906446e-05, | |
| "loss": 10.6031, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.11279972982100642, | |
| "grad_norm": 0.1782258301973343, | |
| "learning_rate": 1.4520728741446089e-05, | |
| "loss": 10.5978, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.11347517730496454, | |
| "grad_norm": 0.16206084191799164, | |
| "learning_rate": 1.3674351904242611e-05, | |
| "loss": 10.5997, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.11415062478892266, | |
| "grad_norm": 0.1567702740430832, | |
| "learning_rate": 1.2851575637272262e-05, | |
| "loss": 10.6037, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.11482607227288079, | |
| "grad_norm": 0.174870565533638, | |
| "learning_rate": 1.2052624879351104e-05, | |
| "loss": 10.5948, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11550151975683891, | |
| "grad_norm": 0.15422426164150238, | |
| "learning_rate": 1.1277718055638819e-05, | |
| "loss": 10.5984, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.11617696724079703, | |
| "grad_norm": 0.17559370398521423, | |
| "learning_rate": 1.0527067017923654e-05, | |
| "loss": 10.5945, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.11685241472475515, | |
| "grad_norm": 0.1844927966594696, | |
| "learning_rate": 9.80087698670411e-06, | |
| "loss": 10.5987, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.11752786220871327, | |
| "grad_norm": 0.16079100966453552, | |
| "learning_rate": 9.09934649508375e-06, | |
| "loss": 10.6051, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.1182033096926714, | |
| "grad_norm": 0.16014216840267181, | |
| "learning_rate": 8.422667334494249e-06, | |
| "loss": 10.596, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.11887875717662952, | |
| "grad_norm": 0.16521821916103363, | |
| "learning_rate": 7.771024502261526e-06, | |
| "loss": 10.6092, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.11955420466058764, | |
| "grad_norm": 0.1629599630832672, | |
| "learning_rate": 7.144596151029303e-06, | |
| "loss": 10.5984, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.12022965214454576, | |
| "grad_norm": 0.16382640600204468, | |
| "learning_rate": 6.543553540053926e-06, | |
| "loss": 10.5851, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.12090509962850389, | |
| "grad_norm": 0.15883676707744598, | |
| "learning_rate": 5.968060988383883e-06, | |
| "loss": 10.5956, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.12158054711246201, | |
| "grad_norm": 0.184475377202034, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 10.589, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12225599459642013, | |
| "grad_norm": 0.19880411028862, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 10.581, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.12293144208037825, | |
| "grad_norm": 0.16972365975379944, | |
| "learning_rate": 4.3964218465642355e-06, | |
| "loss": 10.5909, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.12360688956433637, | |
| "grad_norm": 0.17554166913032532, | |
| "learning_rate": 3.924632386315186e-06, | |
| "loss": 10.5855, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.1242823370482945, | |
| "grad_norm": 0.15895400941371918, | |
| "learning_rate": 3.4791089722651436e-06, | |
| "loss": 10.6027, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.12495778453225262, | |
| "grad_norm": 0.15381865203380585, | |
| "learning_rate": 3.059973406066963e-06, | |
| "loss": 10.6043, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.12563323201621074, | |
| "grad_norm": 0.1588447093963623, | |
| "learning_rate": 2.667340275199426e-06, | |
| "loss": 10.5858, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.12630867950016886, | |
| "grad_norm": 0.170160710811615, | |
| "learning_rate": 2.3013169216400733e-06, | |
| "loss": 10.5963, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.12698412698412698, | |
| "grad_norm": 0.19386546313762665, | |
| "learning_rate": 1.9620034125190644e-06, | |
| "loss": 10.5906, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "grad_norm": 0.15733763575553894, | |
| "learning_rate": 1.6494925127617634e-06, | |
| "loss": 10.5984, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.12833502195204322, | |
| "grad_norm": 0.1530665159225464, | |
| "learning_rate": 1.3638696597277679e-06, | |
| "loss": 10.5911, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.12901046943600136, | |
| "grad_norm": 0.1876905858516693, | |
| "learning_rate": 1.1052129398531507e-06, | |
| "loss": 10.6023, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.12968591691995948, | |
| "grad_norm": 0.1700376272201538, | |
| "learning_rate": 8.735930673024806e-07, | |
| "loss": 10.5979, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.1303613644039176, | |
| "grad_norm": 0.18517427146434784, | |
| "learning_rate": 6.690733646361857e-07, | |
| "loss": 10.5894, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.13103681188787572, | |
| "grad_norm": 0.16964897513389587, | |
| "learning_rate": 4.917097454988584e-07, | |
| "loss": 10.5996, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.13171225937183384, | |
| "grad_norm": 0.1931840479373932, | |
| "learning_rate": 3.415506993330153e-07, | |
| "loss": 10.5854, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.13238770685579196, | |
| "grad_norm": 0.15033087134361267, | |
| "learning_rate": 2.1863727812254653e-07, | |
| "loss": 10.6238, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.13306315433975008, | |
| "grad_norm": 0.1763419657945633, | |
| "learning_rate": 1.230030851695263e-07, | |
| "loss": 10.5943, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.1337386018237082, | |
| "grad_norm": 0.17355754971504211, | |
| "learning_rate": 5.467426590739511e-08, | |
| "loss": 10.5912, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.13441404930766632, | |
| "grad_norm": 0.1702238917350769, | |
| "learning_rate": 1.3669500753099585e-08, | |
| "loss": 10.6278, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.13508949679162446, | |
| "grad_norm": 0.15678980946540833, | |
| "learning_rate": 0.0, | |
| "loss": 10.5993, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13508949679162446, | |
| "eval_loss": 10.595317840576172, | |
| "eval_runtime": 2.2488, | |
| "eval_samples_per_second": 277.475, | |
| "eval_steps_per_second": 138.738, | |
| "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": 32811830476800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |