| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.93048128342246, | |
| "eval_steps": 500, | |
| "global_step": 93, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03208556149732621, | |
| "grad_norm": 0.20311123132705688, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.0142, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06417112299465241, | |
| "grad_norm": 0.19597311317920685, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.0111, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0962566844919786, | |
| "grad_norm": 0.19070063531398773, | |
| "learning_rate": 3e-06, | |
| "loss": 1.0203, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": 0.19738665223121643, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.9815, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16042780748663102, | |
| "grad_norm": 0.1658538281917572, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9497, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1925133689839572, | |
| "grad_norm": 0.13552631437778473, | |
| "learning_rate": 6e-06, | |
| "loss": 0.9655, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22459893048128343, | |
| "grad_norm": 0.12660366296768188, | |
| "learning_rate": 7e-06, | |
| "loss": 1.0031, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25668449197860965, | |
| "grad_norm": 0.13044770061969757, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.8836, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2887700534759358, | |
| "grad_norm": 0.133613720536232, | |
| "learning_rate": 9e-06, | |
| "loss": 0.904, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.32085561497326204, | |
| "grad_norm": 0.13057634234428406, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8347, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.15763278305530548, | |
| "learning_rate": 9.996418774081658e-06, | |
| "loss": 0.8767, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3850267379679144, | |
| "grad_norm": 0.13350480794906616, | |
| "learning_rate": 9.985680226398261e-06, | |
| "loss": 0.8649, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41711229946524064, | |
| "grad_norm": 0.11397632211446762, | |
| "learning_rate": 9.967799739815925e-06, | |
| "loss": 0.8318, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.44919786096256686, | |
| "grad_norm": 0.09967950731515884, | |
| "learning_rate": 9.942802927959444e-06, | |
| "loss": 0.8099, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.48128342245989303, | |
| "grad_norm": 0.09817608445882797, | |
| "learning_rate": 9.910725598521014e-06, | |
| "loss": 0.7997, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5133689839572193, | |
| "grad_norm": 0.09854481369256973, | |
| "learning_rate": 9.871613701966067e-06, | |
| "loss": 0.8052, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.09840090572834015, | |
| "learning_rate": 9.825523265709667e-06, | |
| "loss": 0.8383, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5775401069518716, | |
| "grad_norm": 0.08703222870826721, | |
| "learning_rate": 9.772520313857777e-06, | |
| "loss": 0.8014, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6096256684491979, | |
| "grad_norm": 0.07054264843463898, | |
| "learning_rate": 9.712680772628365e-06, | |
| "loss": 0.7716, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6417112299465241, | |
| "grad_norm": 0.07254040986299515, | |
| "learning_rate": 9.646090361587828e-06, | |
| "loss": 0.7857, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6737967914438503, | |
| "grad_norm": 0.06903552263975143, | |
| "learning_rate": 9.572844470858537e-06, | |
| "loss": 0.7589, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.08053260296583176, | |
| "learning_rate": 9.493048024473413e-06, | |
| "loss": 0.7776, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7379679144385026, | |
| "grad_norm": 0.07109075039625168, | |
| "learning_rate": 9.406815330073244e-06, | |
| "loss": 0.7594, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7700534759358288, | |
| "grad_norm": 0.06771097332239151, | |
| "learning_rate": 9.314269915162115e-06, | |
| "loss": 0.7548, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8021390374331551, | |
| "grad_norm": 0.06824363768100739, | |
| "learning_rate": 9.215544350155423e-06, | |
| "loss": 0.7432, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8342245989304813, | |
| "grad_norm": 0.06845725327730179, | |
| "learning_rate": 9.110780058474052e-06, | |
| "loss": 0.7391, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8663101604278075, | |
| "grad_norm": 0.06926020979881287, | |
| "learning_rate": 9.000127113956673e-06, | |
| "loss": 0.7673, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8983957219251337, | |
| "grad_norm": 0.06381599605083466, | |
| "learning_rate": 8.883744025880429e-06, | |
| "loss": 0.747, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.93048128342246, | |
| "grad_norm": 0.06366810202598572, | |
| "learning_rate": 8.761797511897907e-06, | |
| "loss": 0.7633, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9625668449197861, | |
| "grad_norm": 0.05870290845632553, | |
| "learning_rate": 8.634462259215719e-06, | |
| "loss": 0.7426, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9946524064171123, | |
| "grad_norm": 0.06190042197704315, | |
| "learning_rate": 8.501920674356755e-06, | |
| "loss": 0.7761, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.06190042197704315, | |
| "learning_rate": 8.364362621864595e-06, | |
| "loss": 0.7086, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.032085561497326, | |
| "grad_norm": 0.1603803187608719, | |
| "learning_rate": 8.221985152324385e-06, | |
| "loss": 0.6956, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0641711229946524, | |
| "grad_norm": 0.06225842982530594, | |
| "learning_rate": 8.07499222008977e-06, | |
| "loss": 0.6742, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0962566844919786, | |
| "grad_norm": 0.055793747305870056, | |
| "learning_rate": 7.923594391120237e-06, | |
| "loss": 0.6592, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1283422459893049, | |
| "grad_norm": 0.05490822345018387, | |
| "learning_rate": 7.768008541347423e-06, | |
| "loss": 0.6395, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.160427807486631, | |
| "grad_norm": 0.05545506253838539, | |
| "learning_rate": 7.608457546002423e-06, | |
| "loss": 0.6601, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.192513368983957, | |
| "grad_norm": 0.05865738168358803, | |
| "learning_rate": 7.445169960349167e-06, | |
| "loss": 0.6438, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2245989304812834, | |
| "grad_norm": 0.05824247747659683, | |
| "learning_rate": 7.278379692281209e-06, | |
| "loss": 0.7292, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2566844919786098, | |
| "grad_norm": 0.055361997336149216, | |
| "learning_rate": 7.10832566725092e-06, | |
| "loss": 0.6213, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2887700534759359, | |
| "grad_norm": 0.0581163614988327, | |
| "learning_rate": 6.9352514860110876e-06, | |
| "loss": 0.6631, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.320855614973262, | |
| "grad_norm": 0.05861780047416687, | |
| "learning_rate": 6.759405075659165e-06, | |
| "loss": 0.6472, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.3529411764705883, | |
| "grad_norm": 0.06006443873047829, | |
| "learning_rate": 6.58103833448412e-06, | |
| "loss": 0.661, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.3850267379679144, | |
| "grad_norm": 0.05911916866898537, | |
| "learning_rate": 6.4004067711245366e-06, | |
| "loss": 0.6537, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4171122994652405, | |
| "grad_norm": 0.05767710879445076, | |
| "learning_rate": 6.2177691385549595e-06, | |
| "loss": 0.6372, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4491978609625669, | |
| "grad_norm": 0.06271807849407196, | |
| "learning_rate": 6.033387063424765e-06, | |
| "loss": 0.6449, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.481283422459893, | |
| "grad_norm": 0.05773553252220154, | |
| "learning_rate": 5.8475246712804845e-06, | |
| "loss": 0.6532, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5133689839572193, | |
| "grad_norm": 0.05972479656338692, | |
| "learning_rate": 5.660448208208513e-06, | |
| "loss": 0.639, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5454545454545454, | |
| "grad_norm": 0.060490116477012634, | |
| "learning_rate": 5.472425659440157e-06, | |
| "loss": 0.6427, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5775401069518717, | |
| "grad_norm": 0.056138068437576294, | |
| "learning_rate": 5.2837263654653715e-06, | |
| "loss": 0.6328, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6096256684491979, | |
| "grad_norm": 0.057874809950590134, | |
| "learning_rate": 5.094620636205096e-06, | |
| "loss": 0.6267, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.641711229946524, | |
| "grad_norm": 0.1051662415266037, | |
| "learning_rate": 4.905379363794907e-06, | |
| "loss": 0.5955, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.6737967914438503, | |
| "grad_norm": 0.05756345018744469, | |
| "learning_rate": 4.71627363453463e-06, | |
| "loss": 0.6069, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.7058823529411766, | |
| "grad_norm": 0.059037283062934875, | |
| "learning_rate": 4.527574340559844e-06, | |
| "loss": 0.6352, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.7379679144385025, | |
| "grad_norm": 0.06045999750494957, | |
| "learning_rate": 4.33955179179149e-06, | |
| "loss": 0.6434, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.7700534759358288, | |
| "grad_norm": 0.05958287790417671, | |
| "learning_rate": 4.152475328719517e-06, | |
| "loss": 0.6803, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.8021390374331552, | |
| "grad_norm": 0.05772184208035469, | |
| "learning_rate": 3.966612936575235e-06, | |
| "loss": 0.5837, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.8342245989304813, | |
| "grad_norm": 0.05690668150782585, | |
| "learning_rate": 3.782230861445041e-06, | |
| "loss": 0.6416, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.8663101604278074, | |
| "grad_norm": 0.055760458111763, | |
| "learning_rate": 3.5995932288754655e-06, | |
| "loss": 0.594, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.8983957219251337, | |
| "grad_norm": 0.060565654188394547, | |
| "learning_rate": 3.4189616655158803e-06, | |
| "loss": 0.613, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.93048128342246, | |
| "grad_norm": 0.0587182492017746, | |
| "learning_rate": 3.240594924340835e-06, | |
| "loss": 0.6263, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.962566844919786, | |
| "grad_norm": 0.06040377542376518, | |
| "learning_rate": 3.0647485139889145e-06, | |
| "loss": 0.6344, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.9946524064171123, | |
| "grad_norm": 0.05578358843922615, | |
| "learning_rate": 2.89167433274908e-06, | |
| "loss": 0.5962, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.05578358843922615, | |
| "learning_rate": 2.721620307718793e-06, | |
| "loss": 0.6669, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.0320855614973263, | |
| "grad_norm": 0.1518927663564682, | |
| "learning_rate": 2.554830039650834e-06, | |
| "loss": 0.5842, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.064171122994652, | |
| "grad_norm": 0.05603505298495293, | |
| "learning_rate": 2.391542453997578e-06, | |
| "loss": 0.6017, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.0962566844919786, | |
| "grad_norm": 0.0569174662232399, | |
| "learning_rate": 2.2319914586525776e-06, | |
| "loss": 0.5905, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.128342245989305, | |
| "grad_norm": 0.05474628135561943, | |
| "learning_rate": 2.0764056088797646e-06, | |
| "loss": 0.5657, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.160427807486631, | |
| "grad_norm": 0.05412266403436661, | |
| "learning_rate": 1.9250077799102323e-06, | |
| "loss": 0.5692, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.192513368983957, | |
| "grad_norm": 0.05691121146082878, | |
| "learning_rate": 1.7780148476756148e-06, | |
| "loss": 0.5528, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.2245989304812834, | |
| "grad_norm": 0.0541236586868763, | |
| "learning_rate": 1.6356373781354058e-06, | |
| "loss": 0.5426, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.2566844919786098, | |
| "grad_norm": 0.054437655955553055, | |
| "learning_rate": 1.4980793256432474e-06, | |
| "loss": 0.5578, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.2887700534759357, | |
| "grad_norm": 0.0597856268286705, | |
| "learning_rate": 1.3655377407842813e-06, | |
| "loss": 0.5612, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.320855614973262, | |
| "grad_norm": 0.060152262449264526, | |
| "learning_rate": 1.2382024881020937e-06, | |
| "loss": 0.5616, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.05507192015647888, | |
| "learning_rate": 1.1162559741195733e-06, | |
| "loss": 0.5736, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.385026737967914, | |
| "grad_norm": 0.0576910674571991, | |
| "learning_rate": 9.998728860433277e-07, | |
| "loss": 0.5565, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.4171122994652405, | |
| "grad_norm": 0.056697096675634384, | |
| "learning_rate": 8.892199415259501e-07, | |
| "loss": 0.5509, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.449197860962567, | |
| "grad_norm": 0.05489673465490341, | |
| "learning_rate": 7.844556498445788e-07, | |
| "loss": 0.5783, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.481283422459893, | |
| "grad_norm": 0.05427519232034683, | |
| "learning_rate": 6.857300848378857e-07, | |
| "loss": 0.553, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.5133689839572195, | |
| "grad_norm": 0.05728753283619881, | |
| "learning_rate": 5.931846699267558e-07, | |
| "loss": 0.5956, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.5454545454545454, | |
| "grad_norm": 0.05481986328959465, | |
| "learning_rate": 5.0695197552659e-07, | |
| "loss": 0.564, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.5775401069518717, | |
| "grad_norm": 0.05629381909966469, | |
| "learning_rate": 4.271555291414636e-07, | |
| "loss": 0.5545, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.6096256684491976, | |
| "grad_norm": 0.057915519922971725, | |
| "learning_rate": 3.539096384121743e-07, | |
| "loss": 0.5994, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.641711229946524, | |
| "grad_norm": 0.05390770733356476, | |
| "learning_rate": 2.873192273716369e-07, | |
| "loss": 0.5615, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.6737967914438503, | |
| "grad_norm": 0.056489136070013046, | |
| "learning_rate": 2.274796861422246e-07, | |
| "loss": 0.5494, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.05273538455367088, | |
| "learning_rate": 1.7447673429033361e-07, | |
| "loss": 0.5975, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.7379679144385025, | |
| "grad_norm": 0.05448044836521149, | |
| "learning_rate": 1.2838629803393343e-07, | |
| "loss": 0.5877, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 2.770053475935829, | |
| "grad_norm": 0.05841987207531929, | |
| "learning_rate": 8.927440147898703e-08, | |
| "loss": 0.5497, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.802139037433155, | |
| "grad_norm": 0.053782325237989426, | |
| "learning_rate": 5.7197072040557356e-08, | |
| "loss": 0.552, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 2.834224598930481, | |
| "grad_norm": 0.05557689070701599, | |
| "learning_rate": 3.220026018407541e-08, | |
| "loss": 0.5543, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.8663101604278074, | |
| "grad_norm": 0.055889178067445755, | |
| "learning_rate": 1.431977360173975e-08, | |
| "loss": 0.5606, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 2.8983957219251337, | |
| "grad_norm": 0.058224692940711975, | |
| "learning_rate": 3.5812259183426457e-09, | |
| "loss": 0.5859, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.93048128342246, | |
| "grad_norm": 0.06218594312667847, | |
| "learning_rate": 0.0, | |
| "loss": 0.5555, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 2.93048128342246, | |
| "step": 93, | |
| "total_flos": 9.35169742560297e+16, | |
| "train_loss": 0.0, | |
| "train_runtime": 1.09, | |
| "train_samples_per_second": 4109.216, | |
| "train_steps_per_second": 85.322 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 93, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.35169742560297e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |