| { |
| "best_metric": 0.8675475120544434, |
| "best_model_checkpoint": "./lora-out/checkpoint-60", |
| "epoch": 93.33333333333333, |
| "eval_steps": 10, |
| "global_step": 140, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 2e-05, |
| "loss": 1.9263, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 4e-05, |
| "loss": 0.6362, |
| "step": 2 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 6e-05, |
| "loss": 1.2827, |
| "step": 3 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 8e-05, |
| "loss": 1.271, |
| "step": 4 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 0.0001, |
| "loss": 0.634, |
| "step": 5 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 0.00012, |
| "loss": 1.8734, |
| "step": 6 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 0.00014, |
| "loss": 1.815, |
| "step": 7 |
| }, |
| { |
| "epoch": 5.33, |
| "learning_rate": 0.00016, |
| "loss": 0.5571, |
| "step": 8 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 0.00018, |
| "loss": 1.0428, |
| "step": 9 |
| }, |
| { |
| "epoch": 6.67, |
| "learning_rate": 0.0002, |
| "loss": 0.953, |
| "step": 10 |
| }, |
| { |
| "epoch": 6.67, |
| "eval_loss": 1.6378157138824463, |
| "eval_runtime": 0.8713, |
| "eval_samples_per_second": 6.886, |
| "eval_steps_per_second": 3.443, |
| "step": 10 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 0.00019997482349425066, |
| "loss": 0.4287, |
| "step": 11 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 0.00019989930665413147, |
| "loss": 1.2133, |
| "step": 12 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 0.0001997734875046456, |
| "loss": 1.1351, |
| "step": 13 |
| }, |
| { |
| "epoch": 9.33, |
| "learning_rate": 0.00019959742939952392, |
| "loss": 0.355, |
| "step": 14 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 0.00019937122098932428, |
| "loss": 0.68, |
| "step": 15 |
| }, |
| { |
| "epoch": 10.67, |
| "learning_rate": 0.00019909497617679348, |
| "loss": 0.6661, |
| "step": 16 |
| }, |
| { |
| "epoch": 11.0, |
| "learning_rate": 0.00019876883405951377, |
| "loss": 0.3162, |
| "step": 17 |
| }, |
| { |
| "epoch": 12.0, |
| "learning_rate": 0.00019839295885986296, |
| "loss": 0.9141, |
| "step": 18 |
| }, |
| { |
| "epoch": 13.0, |
| "learning_rate": 0.00019796753984232358, |
| "loss": 0.8809, |
| "step": 19 |
| }, |
| { |
| "epoch": 13.33, |
| "learning_rate": 0.00019749279121818235, |
| "loss": 0.2831, |
| "step": 20 |
| }, |
| { |
| "epoch": 13.33, |
| "eval_loss": 1.0763869285583496, |
| "eval_runtime": 0.8722, |
| "eval_samples_per_second": 6.879, |
| "eval_steps_per_second": 3.44, |
| "step": 20 |
| }, |
| { |
| "epoch": 14.0, |
| "learning_rate": 0.0001969689520376687, |
| "loss": 0.5415, |
| "step": 21 |
| }, |
| { |
| "epoch": 14.67, |
| "learning_rate": 0.00019639628606958533, |
| "loss": 0.5414, |
| "step": 22 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 0.00019577508166849304, |
| "loss": 0.2592, |
| "step": 23 |
| }, |
| { |
| "epoch": 16.0, |
| "learning_rate": 0.00019510565162951537, |
| "loss": 0.7754, |
| "step": 24 |
| }, |
| { |
| "epoch": 17.0, |
| "learning_rate": 0.00019438833303083678, |
| "loss": 0.7689, |
| "step": 25 |
| }, |
| { |
| "epoch": 17.33, |
| "learning_rate": 0.00019362348706397373, |
| "loss": 0.2523, |
| "step": 26 |
| }, |
| { |
| "epoch": 18.0, |
| "learning_rate": 0.0001928114988519039, |
| "loss": 0.5015, |
| "step": 27 |
| }, |
| { |
| "epoch": 18.67, |
| "learning_rate": 0.0001919527772551451, |
| "loss": 0.5023, |
| "step": 28 |
| }, |
| { |
| "epoch": 19.0, |
| "learning_rate": 0.00019104775466588161, |
| "loss": 0.2493, |
| "step": 29 |
| }, |
| { |
| "epoch": 20.0, |
| "learning_rate": 0.0001900968867902419, |
| "loss": 0.74, |
| "step": 30 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 1.0189049243927002, |
| "eval_runtime": 0.8726, |
| "eval_samples_per_second": 6.876, |
| "eval_steps_per_second": 3.438, |
| "step": 30 |
| }, |
| { |
| "epoch": 21.0, |
| "learning_rate": 0.0001891006524188368, |
| "loss": 0.7203, |
| "step": 31 |
| }, |
| { |
| "epoch": 21.33, |
| "learning_rate": 0.0001880595531856738, |
| "loss": 0.2385, |
| "step": 32 |
| }, |
| { |
| "epoch": 22.0, |
| "learning_rate": 0.00018697411331556956, |
| "loss": 0.4841, |
| "step": 33 |
| }, |
| { |
| "epoch": 22.67, |
| "learning_rate": 0.00018584487936018661, |
| "loss": 0.4746, |
| "step": 34 |
| }, |
| { |
| "epoch": 23.0, |
| "learning_rate": 0.00018467241992282843, |
| "loss": 0.2257, |
| "step": 35 |
| }, |
| { |
| "epoch": 24.0, |
| "learning_rate": 0.00018345732537213027, |
| "loss": 0.6933, |
| "step": 36 |
| }, |
| { |
| "epoch": 25.0, |
| "learning_rate": 0.00018220020754479102, |
| "loss": 0.6819, |
| "step": 37 |
| }, |
| { |
| "epoch": 25.33, |
| "learning_rate": 0.00018090169943749476, |
| "loss": 0.2184, |
| "step": 38 |
| }, |
| { |
| "epoch": 26.0, |
| "learning_rate": 0.00017956245488817812, |
| "loss": 0.4415, |
| "step": 39 |
| }, |
| { |
| "epoch": 26.67, |
| "learning_rate": 0.000178183148246803, |
| "loss": 0.4336, |
| "step": 40 |
| }, |
| { |
| "epoch": 26.67, |
| "eval_loss": 0.9619529843330383, |
| "eval_runtime": 0.874, |
| "eval_samples_per_second": 6.865, |
| "eval_steps_per_second": 3.433, |
| "step": 40 |
| }, |
| { |
| "epoch": 27.0, |
| "learning_rate": 0.0001767644740358011, |
| "loss": 0.2187, |
| "step": 41 |
| }, |
| { |
| "epoch": 28.0, |
| "learning_rate": 0.00017530714660036112, |
| "loss": 0.642, |
| "step": 42 |
| }, |
| { |
| "epoch": 29.0, |
| "learning_rate": 0.00017381189974873407, |
| "loss": 0.6302, |
| "step": 43 |
| }, |
| { |
| "epoch": 29.33, |
| "learning_rate": 0.00017227948638273916, |
| "loss": 0.2054, |
| "step": 44 |
| }, |
| { |
| "epoch": 30.0, |
| "learning_rate": 0.00017071067811865476, |
| "loss": 0.4056, |
| "step": 45 |
| }, |
| { |
| "epoch": 30.67, |
| "learning_rate": 0.00016910626489868649, |
| "loss": 0.3933, |
| "step": 46 |
| }, |
| { |
| "epoch": 31.0, |
| "learning_rate": 0.00016746705459320745, |
| "loss": 0.1891, |
| "step": 47 |
| }, |
| { |
| "epoch": 32.0, |
| "learning_rate": 0.00016579387259397127, |
| "loss": 0.5689, |
| "step": 48 |
| }, |
| { |
| "epoch": 33.0, |
| "learning_rate": 0.0001640875613985024, |
| "loss": 0.5574, |
| "step": 49 |
| }, |
| { |
| "epoch": 33.33, |
| "learning_rate": 0.00016234898018587337, |
| "loss": 0.1827, |
| "step": 50 |
| }, |
| { |
| "epoch": 33.33, |
| "eval_loss": 0.8636454939842224, |
| "eval_runtime": 0.8737, |
| "eval_samples_per_second": 6.867, |
| "eval_steps_per_second": 3.434, |
| "step": 50 |
| }, |
| { |
| "epoch": 34.0, |
| "learning_rate": 0.000160579004384082, |
| "loss": 0.3592, |
| "step": 51 |
| }, |
| { |
| "epoch": 34.67, |
| "learning_rate": 0.00015877852522924732, |
| "loss": 0.3602, |
| "step": 52 |
| }, |
| { |
| "epoch": 35.0, |
| "learning_rate": 0.0001569484493168452, |
| "loss": 0.1678, |
| "step": 53 |
| }, |
| { |
| "epoch": 36.0, |
| "learning_rate": 0.00015508969814521025, |
| "loss": 0.5046, |
| "step": 54 |
| }, |
| { |
| "epoch": 37.0, |
| "learning_rate": 0.00015320320765153367, |
| "loss": 0.5016, |
| "step": 55 |
| }, |
| { |
| "epoch": 37.33, |
| "learning_rate": 0.00015128992774059063, |
| "loss": 0.1718, |
| "step": 56 |
| }, |
| { |
| "epoch": 38.0, |
| "learning_rate": 0.0001493508218064347, |
| "loss": 0.3245, |
| "step": 57 |
| }, |
| { |
| "epoch": 38.67, |
| "learning_rate": 0.00014738686624729986, |
| "loss": 0.3233, |
| "step": 58 |
| }, |
| { |
| "epoch": 39.0, |
| "learning_rate": 0.00014539904997395468, |
| "loss": 0.1573, |
| "step": 59 |
| }, |
| { |
| "epoch": 40.0, |
| "learning_rate": 0.00014338837391175582, |
| "loss": 0.4726, |
| "step": 60 |
| }, |
| { |
| "epoch": 40.0, |
| "eval_loss": 0.8675475120544434, |
| "eval_runtime": 0.8737, |
| "eval_samples_per_second": 6.867, |
| "eval_steps_per_second": 3.434, |
| "step": 60 |
| }, |
| { |
| "epoch": 41.0, |
| "learning_rate": 0.00014135585049665207, |
| "loss": 0.4665, |
| "step": 61 |
| }, |
| { |
| "epoch": 41.33, |
| "learning_rate": 0.00013930250316539238, |
| "loss": 0.1493, |
| "step": 62 |
| }, |
| { |
| "epoch": 42.0, |
| "learning_rate": 0.00013722936584019453, |
| "loss": 0.3025, |
| "step": 63 |
| }, |
| { |
| "epoch": 42.67, |
| "learning_rate": 0.0001351374824081343, |
| "loss": 0.2971, |
| "step": 64 |
| }, |
| { |
| "epoch": 43.0, |
| "learning_rate": 0.00013302790619551674, |
| "loss": 0.1348, |
| "step": 65 |
| }, |
| { |
| "epoch": 44.0, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 0.4268, |
| "step": 66 |
| }, |
| { |
| "epoch": 45.0, |
| "learning_rate": 0.00012875993274320173, |
| "loss": 0.4176, |
| "step": 67 |
| }, |
| { |
| "epoch": 45.33, |
| "learning_rate": 0.00012660368455666752, |
| "loss": 0.1309, |
| "step": 68 |
| }, |
| { |
| "epoch": 46.0, |
| "learning_rate": 0.0001244340406137894, |
| "loss": 0.2693, |
| "step": 69 |
| }, |
| { |
| "epoch": 46.67, |
| "learning_rate": 0.00012225209339563145, |
| "loss": 0.2564, |
| "step": 70 |
| }, |
| { |
| "epoch": 46.67, |
| "eval_loss": 0.9176617860794067, |
| "eval_runtime": 0.8733, |
| "eval_samples_per_second": 6.871, |
| "eval_steps_per_second": 3.435, |
| "step": 70 |
| }, |
| { |
| "epoch": 47.0, |
| "learning_rate": 0.00012005894157832729, |
| "loss": 0.1313, |
| "step": 71 |
| }, |
| { |
| "epoch": 48.0, |
| "learning_rate": 0.00011785568947986367, |
| "loss": 0.3761, |
| "step": 72 |
| }, |
| { |
| "epoch": 49.0, |
| "learning_rate": 0.0001156434465040231, |
| "loss": 0.3719, |
| "step": 73 |
| }, |
| { |
| "epoch": 49.33, |
| "learning_rate": 0.00011342332658176555, |
| "loss": 0.1238, |
| "step": 74 |
| }, |
| { |
| "epoch": 50.0, |
| "learning_rate": 0.00011119644761033078, |
| "loss": 0.2303, |
| "step": 75 |
| }, |
| { |
| "epoch": 50.67, |
| "learning_rate": 0.00010896393089034336, |
| "loss": 0.2324, |
| "step": 76 |
| }, |
| { |
| "epoch": 51.0, |
| "learning_rate": 0.00010672690056120399, |
| "loss": 0.1158, |
| "step": 77 |
| }, |
| { |
| "epoch": 52.0, |
| "learning_rate": 0.00010448648303505151, |
| "loss": 0.3286, |
| "step": 78 |
| }, |
| { |
| "epoch": 53.0, |
| "learning_rate": 0.00010224380642958052, |
| "loss": 0.3256, |
| "step": 79 |
| }, |
| { |
| "epoch": 53.33, |
| "learning_rate": 0.0001, |
| "loss": 0.1031, |
| "step": 80 |
| }, |
| { |
| "epoch": 53.33, |
| "eval_loss": 0.9727662205696106, |
| "eval_runtime": 0.8715, |
| "eval_samples_per_second": 6.884, |
| "eval_steps_per_second": 3.442, |
| "step": 80 |
| }, |
| { |
| "epoch": 54.0, |
| "learning_rate": 9.775619357041952e-05, |
| "loss": 0.2059, |
| "step": 81 |
| }, |
| { |
| "epoch": 54.67, |
| "learning_rate": 9.551351696494854e-05, |
| "loss": 0.2032, |
| "step": 82 |
| }, |
| { |
| "epoch": 55.0, |
| "learning_rate": 9.327309943879604e-05, |
| "loss": 0.0924, |
| "step": 83 |
| }, |
| { |
| "epoch": 56.0, |
| "learning_rate": 9.103606910965666e-05, |
| "loss": 0.2809, |
| "step": 84 |
| }, |
| { |
| "epoch": 57.0, |
| "learning_rate": 8.880355238966923e-05, |
| "loss": 0.2757, |
| "step": 85 |
| }, |
| { |
| "epoch": 57.33, |
| "learning_rate": 8.657667341823448e-05, |
| "loss": 0.088, |
| "step": 86 |
| }, |
| { |
| "epoch": 58.0, |
| "learning_rate": 8.435655349597689e-05, |
| "loss": 0.1725, |
| "step": 87 |
| }, |
| { |
| "epoch": 58.67, |
| "learning_rate": 8.214431052013634e-05, |
| "loss": 0.1654, |
| "step": 88 |
| }, |
| { |
| "epoch": 59.0, |
| "learning_rate": 7.994105842167273e-05, |
| "loss": 0.0806, |
| "step": 89 |
| }, |
| { |
| "epoch": 60.0, |
| "learning_rate": 7.774790660436858e-05, |
| "loss": 0.2316, |
| "step": 90 |
| }, |
| { |
| "epoch": 60.0, |
| "eval_loss": 1.0534545183181763, |
| "eval_runtime": 0.8706, |
| "eval_samples_per_second": 6.892, |
| "eval_steps_per_second": 3.446, |
| "step": 90 |
| }, |
| { |
| "epoch": 61.0, |
| "learning_rate": 7.556595938621058e-05, |
| "loss": 0.2254, |
| "step": 91 |
| }, |
| { |
| "epoch": 61.33, |
| "learning_rate": 7.339631544333249e-05, |
| "loss": 0.0724, |
| "step": 92 |
| }, |
| { |
| "epoch": 62.0, |
| "learning_rate": 7.124006725679828e-05, |
| "loss": 0.1469, |
| "step": 93 |
| }, |
| { |
| "epoch": 62.67, |
| "learning_rate": 6.909830056250527e-05, |
| "loss": 0.1392, |
| "step": 94 |
| }, |
| { |
| "epoch": 63.0, |
| "learning_rate": 6.697209380448333e-05, |
| "loss": 0.0677, |
| "step": 95 |
| }, |
| { |
| "epoch": 64.0, |
| "learning_rate": 6.486251759186572e-05, |
| "loss": 0.1941, |
| "step": 96 |
| }, |
| { |
| "epoch": 65.0, |
| "learning_rate": 6.277063415980549e-05, |
| "loss": 0.1933, |
| "step": 97 |
| }, |
| { |
| "epoch": 65.33, |
| "learning_rate": 6.069749683460765e-05, |
| "loss": 0.0599, |
| "step": 98 |
| }, |
| { |
| "epoch": 66.0, |
| "learning_rate": 5.864414950334796e-05, |
| "loss": 0.1258, |
| "step": 99 |
| }, |
| { |
| "epoch": 66.67, |
| "learning_rate": 5.6611626088244194e-05, |
| "loss": 0.1146, |
| "step": 100 |
| }, |
| { |
| "epoch": 66.67, |
| "eval_loss": 1.147660493850708, |
| "eval_runtime": 0.8723, |
| "eval_samples_per_second": 6.878, |
| "eval_steps_per_second": 3.439, |
| "step": 100 |
| }, |
| { |
| "epoch": 67.0, |
| "learning_rate": 5.4600950026045326e-05, |
| "loss": 0.0585, |
| "step": 101 |
| }, |
| { |
| "epoch": 68.0, |
| "learning_rate": 5.261313375270014e-05, |
| "loss": 0.1722, |
| "step": 102 |
| }, |
| { |
| "epoch": 69.0, |
| "learning_rate": 5.0649178193565314e-05, |
| "loss": 0.1656, |
| "step": 103 |
| }, |
| { |
| "epoch": 69.33, |
| "learning_rate": 4.87100722594094e-05, |
| "loss": 0.0534, |
| "step": 104 |
| }, |
| { |
| "epoch": 70.0, |
| "learning_rate": 4.6796792348466356e-05, |
| "loss": 0.1112, |
| "step": 105 |
| }, |
| { |
| "epoch": 70.67, |
| "learning_rate": 4.491030185478976e-05, |
| "loss": 0.107, |
| "step": 106 |
| }, |
| { |
| "epoch": 71.0, |
| "learning_rate": 4.305155068315481e-05, |
| "loss": 0.0502, |
| "step": 107 |
| }, |
| { |
| "epoch": 72.0, |
| "learning_rate": 4.12214747707527e-05, |
| "loss": 0.1502, |
| "step": 108 |
| }, |
| { |
| "epoch": 73.0, |
| "learning_rate": 3.942099561591802e-05, |
| "loss": 0.1472, |
| "step": 109 |
| }, |
| { |
| "epoch": 73.33, |
| "learning_rate": 3.7651019814126654e-05, |
| "loss": 0.0463, |
| "step": 110 |
| }, |
| { |
| "epoch": 73.33, |
| "eval_loss": 1.2258118391036987, |
| "eval_runtime": 0.871, |
| "eval_samples_per_second": 6.888, |
| "eval_steps_per_second": 3.444, |
| "step": 110 |
| }, |
| { |
| "epoch": 74.0, |
| "learning_rate": 3.591243860149759e-05, |
| "loss": 0.0995, |
| "step": 111 |
| }, |
| { |
| "epoch": 74.67, |
| "learning_rate": 3.4206127406028745e-05, |
| "loss": 0.093, |
| "step": 112 |
| }, |
| { |
| "epoch": 75.0, |
| "learning_rate": 3.253294540679257e-05, |
| "loss": 0.0489, |
| "step": 113 |
| }, |
| { |
| "epoch": 76.0, |
| "learning_rate": 3.089373510131354e-05, |
| "loss": 0.1373, |
| "step": 114 |
| }, |
| { |
| "epoch": 77.0, |
| "learning_rate": 2.9289321881345254e-05, |
| "loss": 0.1337, |
| "step": 115 |
| }, |
| { |
| "epoch": 77.33, |
| "learning_rate": 2.7720513617260856e-05, |
| "loss": 0.0413, |
| "step": 116 |
| }, |
| { |
| "epoch": 78.0, |
| "learning_rate": 2.6188100251265945e-05, |
| "loss": 0.0911, |
| "step": 117 |
| }, |
| { |
| "epoch": 78.67, |
| "learning_rate": 2.4692853399638917e-05, |
| "loss": 0.0871, |
| "step": 118 |
| }, |
| { |
| "epoch": 79.0, |
| "learning_rate": 2.323552596419889e-05, |
| "loss": 0.0424, |
| "step": 119 |
| }, |
| { |
| "epoch": 80.0, |
| "learning_rate": 2.181685175319702e-05, |
| "loss": 0.127, |
| "step": 120 |
| }, |
| { |
| "epoch": 80.0, |
| "eval_loss": 1.2826638221740723, |
| "eval_runtime": 0.8716, |
| "eval_samples_per_second": 6.884, |
| "eval_steps_per_second": 3.442, |
| "step": 120 |
| }, |
| { |
| "epoch": 81.0, |
| "learning_rate": 2.043754511182191e-05, |
| "loss": 0.124, |
| "step": 121 |
| }, |
| { |
| "epoch": 81.33, |
| "learning_rate": 1.9098300562505266e-05, |
| "loss": 0.0409, |
| "step": 122 |
| }, |
| { |
| "epoch": 82.0, |
| "learning_rate": 1.7799792455209018e-05, |
| "loss": 0.0819, |
| "step": 123 |
| }, |
| { |
| "epoch": 82.67, |
| "learning_rate": 1.6542674627869737e-05, |
| "loss": 0.0816, |
| "step": 124 |
| }, |
| { |
| "epoch": 83.0, |
| "learning_rate": 1.5327580077171587e-05, |
| "loss": 0.0397, |
| "step": 125 |
| }, |
| { |
| "epoch": 84.0, |
| "learning_rate": 1.415512063981339e-05, |
| "loss": 0.1216, |
| "step": 126 |
| }, |
| { |
| "epoch": 85.0, |
| "learning_rate": 1.3025886684430467e-05, |
| "loss": 0.1204, |
| "step": 127 |
| }, |
| { |
| "epoch": 85.33, |
| "learning_rate": 1.19404468143262e-05, |
| "loss": 0.041, |
| "step": 128 |
| }, |
| { |
| "epoch": 86.0, |
| "learning_rate": 1.0899347581163221e-05, |
| "loss": 0.0772, |
| "step": 129 |
| }, |
| { |
| "epoch": 86.67, |
| "learning_rate": 9.903113209758096e-06, |
| "loss": 0.0779, |
| "step": 130 |
| }, |
| { |
| "epoch": 86.67, |
| "eval_loss": 1.3157517910003662, |
| "eval_runtime": 0.8712, |
| "eval_samples_per_second": 6.887, |
| "eval_steps_per_second": 3.444, |
| "step": 130 |
| }, |
| { |
| "epoch": 87.0, |
| "learning_rate": 8.952245334118414e-06, |
| "loss": 0.0401, |
| "step": 131 |
| }, |
| { |
| "epoch": 88.0, |
| "learning_rate": 8.047222744854943e-06, |
| "loss": 0.1173, |
| "step": 132 |
| }, |
| { |
| "epoch": 89.0, |
| "learning_rate": 7.1885011480961164e-06, |
| "loss": 0.1178, |
| "step": 133 |
| }, |
| { |
| "epoch": 89.33, |
| "learning_rate": 6.37651293602628e-06, |
| "loss": 0.0397, |
| "step": 134 |
| }, |
| { |
| "epoch": 90.0, |
| "learning_rate": 5.611666969163243e-06, |
| "loss": 0.079, |
| "step": 135 |
| }, |
| { |
| "epoch": 90.67, |
| "learning_rate": 4.8943483704846475e-06, |
| "loss": 0.0766, |
| "step": 136 |
| }, |
| { |
| "epoch": 91.0, |
| "learning_rate": 4.224918331506955e-06, |
| "loss": 0.0397, |
| "step": 137 |
| }, |
| { |
| "epoch": 92.0, |
| "learning_rate": 3.6037139304146762e-06, |
| "loss": 0.1141, |
| "step": 138 |
| }, |
| { |
| "epoch": 93.0, |
| "learning_rate": 3.0310479623313127e-06, |
| "loss": 0.1184, |
| "step": 139 |
| }, |
| { |
| "epoch": 93.33, |
| "learning_rate": 2.5072087818176382e-06, |
| "loss": 0.0386, |
| "step": 140 |
| }, |
| { |
| "epoch": 93.33, |
| "eval_loss": 1.331322431564331, |
| "eval_runtime": 0.873, |
| "eval_samples_per_second": 6.873, |
| "eval_steps_per_second": 3.436, |
| "step": 140 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 150, |
| "num_train_epochs": 150, |
| "save_steps": 20, |
| "total_flos": 9.203523552018432e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
