| { | |
| "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 | |
| } | |