| { | |
| "best_metric": 0.47534212470054626, | |
| "best_model_checkpoint": "qa-code-finetune/checkpoint-168", | |
| "epoch": 6.413793103448276, | |
| "eval_steps": 500, | |
| "global_step": 168, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.448275862068966e-06, | |
| "loss": 1.4775, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.896551724137932e-06, | |
| "loss": 1.1041, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.0344827586206897e-05, | |
| "loss": 1.3887, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.3793103448275863e-05, | |
| "loss": 0.8684, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.7241379310344828e-05, | |
| "loss": 1.5696, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.0689655172413793e-05, | |
| "loss": 1.3935, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.413793103448276e-05, | |
| "loss": 1.3506, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.7586206896551727e-05, | |
| "loss": 1.4628, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.103448275862069e-05, | |
| "loss": 1.3917, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.4482758620689657e-05, | |
| "loss": 1.5045, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.793103448275862e-05, | |
| "loss": 1.4222, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.1379310344827587e-05, | |
| "loss": 1.3411, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.482758620689655e-05, | |
| "loss": 1.4104, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.827586206896552e-05, | |
| "loss": 1.2848, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 5.172413793103449e-05, | |
| "loss": 1.3306, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5.517241379310345e-05, | |
| "loss": 1.228, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 5.862068965517241e-05, | |
| "loss": 1.1974, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.206896551724138e-05, | |
| "loss": 1.0348, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.551724137931034e-05, | |
| "loss": 1.14, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.896551724137931e-05, | |
| "loss": 1.2986, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.241379310344828e-05, | |
| "loss": 1.29, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.586206896551724e-05, | |
| "loss": 1.0764, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.931034482758621e-05, | |
| "loss": 1.244, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.275862068965517e-05, | |
| "loss": 1.2264, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.001452922821045, | |
| "eval_runtime": 45.5541, | |
| "eval_samples_per_second": 0.549, | |
| "eval_steps_per_second": 0.154, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 8.620689655172413e-05, | |
| "loss": 1.1878, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 8.96551724137931e-05, | |
| "loss": 1.1258, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.310344827586207e-05, | |
| "loss": 1.199, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.655172413793105e-05, | |
| "loss": 1.0574, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1888, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00010344827586206898, | |
| "loss": 1.1305, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00010689655172413792, | |
| "loss": 0.978, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001103448275862069, | |
| "loss": 1.1873, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00011379310344827588, | |
| "loss": 1.0899, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00011724137931034482, | |
| "loss": 0.9437, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0001206896551724138, | |
| "loss": 1.0896, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00012413793103448277, | |
| "loss": 0.8899, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00012758620689655174, | |
| "loss": 1.0744, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00013103448275862068, | |
| "loss": 0.9309, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00013448275862068965, | |
| "loss": 1.0572, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00013793103448275863, | |
| "loss": 0.94, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0001413793103448276, | |
| "loss": 0.9554, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00014482758620689657, | |
| "loss": 0.863, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00014827586206896554, | |
| "loss": 0.9654, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00015172413793103449, | |
| "loss": 0.9372, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00015517241379310346, | |
| "loss": 0.7731, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00015862068965517243, | |
| "loss": 0.9372, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00016206896551724137, | |
| "loss": 0.7921, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00016551724137931035, | |
| "loss": 0.7756, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 0.7165587544441223, | |
| "eval_runtime": 45.4378, | |
| "eval_samples_per_second": 0.55, | |
| "eval_steps_per_second": 0.154, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00016896551724137932, | |
| "loss": 0.8733, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00017241379310344826, | |
| "loss": 0.7803, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.00017586206896551723, | |
| "loss": 1.0161, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0001793103448275862, | |
| "loss": 0.8577, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.00018275862068965518, | |
| "loss": 0.8049, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00018620689655172415, | |
| "loss": 0.7638, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00018965517241379312, | |
| "loss": 0.7288, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0001931034482758621, | |
| "loss": 0.7548, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.00019655172413793104, | |
| "loss": 0.6096, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9043, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0001996168582375479, | |
| "loss": 0.6023, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0001992337164750958, | |
| "loss": 0.6247, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00019885057471264367, | |
| "loss": 0.7316, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0001984674329501916, | |
| "loss": 0.6398, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00019808429118773948, | |
| "loss": 0.7006, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.00019770114942528738, | |
| "loss": 0.6344, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.00019731800766283525, | |
| "loss": 0.7474, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00019693486590038314, | |
| "loss": 0.5874, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.00019655172413793104, | |
| "loss": 0.6165, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.00019616858237547893, | |
| "loss": 0.7373, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00019578544061302683, | |
| "loss": 0.702, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00019540229885057472, | |
| "loss": 0.7673, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00019501915708812262, | |
| "loss": 0.767, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0001946360153256705, | |
| "loss": 0.712, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.5802827477455139, | |
| "eval_runtime": 45.5609, | |
| "eval_samples_per_second": 0.549, | |
| "eval_steps_per_second": 0.154, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0001942528735632184, | |
| "loss": 0.6086, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.00019386973180076628, | |
| "loss": 0.5534, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.00019348659003831417, | |
| "loss": 0.7017, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0001931034482758621, | |
| "loss": 0.7676, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.00019272030651341, | |
| "loss": 0.6932, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.00019233716475095786, | |
| "loss": 0.5797, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.00019195402298850575, | |
| "loss": 0.5496, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.00019157088122605365, | |
| "loss": 0.5773, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.00019118773946360154, | |
| "loss": 0.6998, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.00019080459770114944, | |
| "loss": 0.5153, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.00019042145593869733, | |
| "loss": 0.5796, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.00019003831417624523, | |
| "loss": 0.528, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.00018965517241379312, | |
| "loss": 0.5977, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.00018927203065134102, | |
| "loss": 0.5815, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.00018888888888888888, | |
| "loss": 0.6144, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.00018850574712643678, | |
| "loss": 0.6932, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 0.0001881226053639847, | |
| "loss": 0.6371, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.0001877394636015326, | |
| "loss": 0.6041, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00018735632183908046, | |
| "loss": 0.5556, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.00018697318007662836, | |
| "loss": 0.5421, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.00018659003831417625, | |
| "loss": 0.7292, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 0.00018620689655172415, | |
| "loss": 0.4931, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 0.00018582375478927202, | |
| "loss": 0.6219, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 0.00018544061302681994, | |
| "loss": 0.6215, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_loss": 0.5279306173324585, | |
| "eval_runtime": 45.1884, | |
| "eval_samples_per_second": 0.553, | |
| "eval_steps_per_second": 0.155, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.00018505747126436783, | |
| "loss": 0.5279, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.00018467432950191573, | |
| "loss": 0.6158, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.0001842911877394636, | |
| "loss": 0.479, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.0001839080459770115, | |
| "loss": 0.6229, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0001835249042145594, | |
| "loss": 0.5331, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.00018314176245210728, | |
| "loss": 0.4522, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.00018275862068965518, | |
| "loss": 0.349, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.00018237547892720307, | |
| "loss": 0.6031, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 0.00018199233716475097, | |
| "loss": 0.5603, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 0.00018160919540229886, | |
| "loss": 0.5386, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.00018122605363984676, | |
| "loss": 0.5133, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.00018084291187739463, | |
| "loss": 0.5644, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.00018045977011494252, | |
| "loss": 0.5141, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 0.00018007662835249044, | |
| "loss": 0.4475, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 0.00017969348659003834, | |
| "loss": 0.4485, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 0.0001793103448275862, | |
| "loss": 0.4857, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.0001789272030651341, | |
| "loss": 0.7387, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 0.000178544061302682, | |
| "loss": 0.5216, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.0001781609195402299, | |
| "loss": 0.4717, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 0.4892, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.00017739463601532568, | |
| "loss": 0.5037, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 0.00017701149425287358, | |
| "loss": 0.5465, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 0.00017662835249042147, | |
| "loss": 0.5272, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.00017624521072796937, | |
| "loss": 0.5952, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "eval_loss": 0.4989665448665619, | |
| "eval_runtime": 45.2351, | |
| "eval_samples_per_second": 0.553, | |
| "eval_steps_per_second": 0.155, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.00017586206896551723, | |
| "loss": 0.4193, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 0.00017547892720306513, | |
| "loss": 0.4954, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.00017509578544061302, | |
| "loss": 0.4177, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.00017471264367816095, | |
| "loss": 0.3927, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.00017432950191570881, | |
| "loss": 0.3624, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 0.0001739463601532567, | |
| "loss": 0.481, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.0001735632183908046, | |
| "loss": 0.4035, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 0.0001731800766283525, | |
| "loss": 0.4724, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.0001727969348659004, | |
| "loss": 0.389, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 0.00017241379310344826, | |
| "loss": 0.5242, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 0.00017203065134099618, | |
| "loss": 0.4476, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 0.00017164750957854408, | |
| "loss": 0.5525, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.00017126436781609197, | |
| "loss": 0.4405, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 0.00017088122605363984, | |
| "loss": 0.4422, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 0.00017049808429118774, | |
| "loss": 0.5116, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 0.00017011494252873563, | |
| "loss": 0.3784, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 0.00016973180076628356, | |
| "loss": 0.5097, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 0.00016934865900383142, | |
| "loss": 0.3885, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.00016896551724137932, | |
| "loss": 0.4608, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 0.0001685823754789272, | |
| "loss": 0.4212, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 0.0001681992337164751, | |
| "loss": 0.4852, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.000167816091954023, | |
| "loss": 0.484, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 0.00016743295019157087, | |
| "loss": 0.5694, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 0.0001670498084291188, | |
| "loss": 0.5575, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_loss": 0.4801803529262543, | |
| "eval_runtime": 45.3478, | |
| "eval_samples_per_second": 0.551, | |
| "eval_steps_per_second": 0.154, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.4301, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 0.00016628352490421458, | |
| "loss": 0.4271, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 0.00016590038314176245, | |
| "loss": 0.4016, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 0.00016551724137931035, | |
| "loss": 0.4963, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 0.00016513409961685824, | |
| "loss": 0.4159, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 0.00016475095785440614, | |
| "loss": 0.3818, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 0.00016436781609195403, | |
| "loss": 0.3326, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 0.00016398467432950193, | |
| "loss": 0.3099, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 0.00016360153256704982, | |
| "loss": 0.3519, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 0.00016321839080459772, | |
| "loss": 0.4866, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 0.0001628352490421456, | |
| "loss": 0.4286, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 0.00016245210727969348, | |
| "loss": 0.3815, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 0.00016206896551724137, | |
| "loss": 0.4642, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.0001616858237547893, | |
| "loss": 0.4076, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.0001613026819923372, | |
| "loss": 0.3396, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 0.00016091954022988506, | |
| "loss": 0.2513, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 0.00016053639846743295, | |
| "loss": 0.3305, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 0.00016015325670498085, | |
| "loss": 0.4355, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 0.00015977011494252874, | |
| "loss": 0.4543, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 0.00015938697318007664, | |
| "loss": 0.3778, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 0.00015900383141762453, | |
| "loss": 0.4365, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 0.00015862068965517243, | |
| "loss": 0.4298, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.00015823754789272032, | |
| "loss": 0.4427, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.00015785440613026822, | |
| "loss": 0.4207, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "eval_loss": 0.47534212470054626, | |
| "eval_runtime": 45.2548, | |
| "eval_samples_per_second": 0.552, | |
| "eval_steps_per_second": 0.155, | |
| "step": 168 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 580, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 2.731509408595968e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |