| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.7934532165527344, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3404, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.5168005228042603, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0804, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 1.047807216644287, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9184, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.041599988937378, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0393, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.8074644804000854, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1779, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.7784727811813354, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1583, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.8535248637199402, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0766, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.8507911562919617, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1175, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.8497746586799622, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1156, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.9205197691917419, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1782, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1.2332911491394043, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0536, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 1.3457396030426025, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2186, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.6494730114936829, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8011, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.6363134980201721, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8819, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.7927612662315369, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8845, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.7082176804542542, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8748, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.861709713935852, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8777, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.7901681661605835, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8811, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.7719288468360901, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8898, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.027469277381897, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0089, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.9486727714538574, | |
| "learning_rate": 0.0002, | |
| "loss": 1.968, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.9629890322685242, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0568, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 1.033793568611145, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8401, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.3298218250274658, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9165, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.6936089396476746, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6614, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.6136096119880676, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8167, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.6043046712875366, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7217, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.6395452618598938, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7353, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.6829009056091309, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7708, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.8561712503433228, | |
| "learning_rate": 0.0002, | |
| "loss": 1.774, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.7594190239906311, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8788, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.867341160774231, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8708, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.9393973350524902, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9839, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 1.0540133714675903, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7637, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 1.2020256519317627, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9187, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 1.7588919401168823, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5851, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.9404975175857544, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7903, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.7744253873825073, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7476, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.7260447144508362, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5547, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.9214150905609131, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6342, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.834932267665863, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6577, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.8663449883460999, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7133, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.9534509181976318, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7999, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 1.058899164199829, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5964, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 1.1835004091262817, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7596, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 1.2041128873825073, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6529, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 1.5300588607788086, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7852, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.6037429571151733, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6873, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.6437931656837463, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5729, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.1996123790740967, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5609, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.6186010837554932, | |
| "eval_runtime": 565.3333, | |
| "eval_samples_per_second": 0.708, | |
| "eval_steps_per_second": 0.177, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.6480159163475037, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5754, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.8269457817077637, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4743, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 1.1054280996322632, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3447, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.9144314527511597, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3652, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.8429620862007141, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4696, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 1.3091776371002197, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3109, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.1400000000000001, | |
| "grad_norm": 1.2086460590362549, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3424, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 1.1823766231536865, | |
| "learning_rate": 0.0002, | |
| "loss": 1.213, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 1.817803144454956, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2911, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 1.2870073318481445, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2712, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 1.2424544095993042, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2292, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 1.4258471727371216, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0814, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 1.1297271251678467, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5303, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.8728504776954651, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4354, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.7809789776802063, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4398, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.844166100025177, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2171, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.8636218905448914, | |
| "learning_rate": 0.0002, | |
| "loss": 1.23, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 0.9831591248512268, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2496, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 1.4268325567245483, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2354, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 1.6133723258972168, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2123, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 1.5462720394134521, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0258, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 1.1962395906448364, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0858, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 1.413921594619751, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0169, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 1.442657470703125, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9553, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.9919085502624512, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2394, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.988468587398529, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3642, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.9793186187744141, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2818, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.7799855470657349, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1705, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.8288784027099609, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0484, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.064773440361023, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1608, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 1.0099600553512573, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1873, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 1.9040124416351318, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9739, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.6600000000000001, | |
| "grad_norm": 1.2448644638061523, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9418, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 1.2129086256027222, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8821, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 1.6727265119552612, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9965, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 1.6569440364837646, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9182, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.8596146702766418, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3188, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.8928490281105042, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3601, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.7409713268280029, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1212, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.8979334831237793, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4162, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.8199999999999998, | |
| "grad_norm": 0.979978621006012, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1969, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 0.9733594059944153, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0468, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.8599999999999999, | |
| "grad_norm": 0.9226842522621155, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1807, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 1.1638745069503784, | |
| "learning_rate": 0.0002, | |
| "loss": 1.139, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 1.5604937076568604, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1872, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 1.3674428462982178, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1865, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 1.8469598293304443, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0469, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 1.3148952722549438, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9915, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 1.599141001701355, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2296, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.3382114171981812, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1813, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.409305453300476, | |
| "eval_runtime": 565.9517, | |
| "eval_samples_per_second": 0.707, | |
| "eval_steps_per_second": 0.177, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 1.0162380933761597, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1481, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 0.7402092814445496, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0086, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 0.8824872970581055, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0588, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 0.7582442760467529, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8181, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 1.0200812816619873, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9041, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 1.08174467086792, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8479, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 1.01225745677948, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7659, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 1.2194840908050537, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7926, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "grad_norm": 1.0519524812698364, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6604, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 1.2860150337219238, | |
| "learning_rate": 0.0002, | |
| "loss": 0.663, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 1.5521994829177856, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7791, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 1.455283284187317, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5112, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "grad_norm": 1.7097278833389282, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2219, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 2.2800000000000002, | |
| "grad_norm": 1.5385531187057495, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1261, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 1.0525436401367188, | |
| "learning_rate": 0.0002, | |
| "loss": 0.86, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 1.0388120412826538, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9022, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "grad_norm": 1.060497760772705, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9265, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 1.0629950761795044, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7222, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "grad_norm": 1.2574018239974976, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7952, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 1.0951610803604126, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6647, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "grad_norm": 1.46285879611969, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7845, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 1.3611388206481934, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7084, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "grad_norm": 1.6670907735824585, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6594, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 2.1525955200195312, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6401, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 2.5126793384552, | |
| "learning_rate": 0.0002, | |
| "loss": 0.926, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 1.800521969795227, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0936, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 1.0617576837539673, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8052, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 1.0823312997817993, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9443, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "grad_norm": 1.2193264961242676, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7955, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 1.0502954721450806, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8365, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "grad_norm": 1.1898560523986816, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9706, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 1.1076680421829224, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7529, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "grad_norm": 1.3826709985733032, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7474, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "grad_norm": 1.2504832744598389, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7086, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 1.6292765140533447, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6305, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 1.9603074789047241, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6834, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "grad_norm": 2.202030897140503, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1712, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 1.6344685554504395, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0772, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.7800000000000002, | |
| "grad_norm": 1.3579537868499756, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8803, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 1.0554553270339966, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9222, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "grad_norm": 0.9431642889976501, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8031, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 1.0826098918914795, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8259, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "grad_norm": 1.24959135055542, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7957, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 1.1057368516921997, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7079, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 1.144061803817749, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7165, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "grad_norm": 1.0690631866455078, | |
| "learning_rate": 0.0002, | |
| "loss": 0.601, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "grad_norm": 1.292758584022522, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7191, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 1.729408860206604, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5851, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "grad_norm": 2.078197717666626, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8942, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.0007128715515137, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7139, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.4874461889266968, | |
| "eval_runtime": 566.1506, | |
| "eval_samples_per_second": 0.707, | |
| "eval_steps_per_second": 0.177, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "grad_norm": 1.024670958518982, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8969, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "grad_norm": 0.9738882184028625, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9056, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "grad_norm": 0.9969688653945923, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6676, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "grad_norm": 1.12136971950531, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5916, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "grad_norm": 1.3517699241638184, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5908, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "grad_norm": 1.5965360403060913, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6148, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "grad_norm": 1.3009252548217773, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4902, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "grad_norm": 1.2742400169372559, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4515, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "grad_norm": 1.2994771003723145, | |
| "learning_rate": 0.0002, | |
| "loss": 0.416, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 1.3306324481964111, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4144, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "grad_norm": 1.5406475067138672, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4256, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "grad_norm": 1.584506630897522, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4511, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "grad_norm": 1.6618622541427612, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8865, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 3.2800000000000002, | |
| "grad_norm": 1.6019847393035889, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7339, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "grad_norm": 1.1740251779556274, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6945, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "grad_norm": 1.1268410682678223, | |
| "learning_rate": 0.0002, | |
| "loss": 0.579, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "grad_norm": 1.3038002252578735, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5217, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "grad_norm": 1.112185001373291, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4766, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "grad_norm": 1.3828542232513428, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4781, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "grad_norm": 1.1456600427627563, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4056, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "grad_norm": 1.2479093074798584, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4447, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "grad_norm": 1.4044010639190674, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3814, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "grad_norm": 1.565138339996338, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3982, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "grad_norm": 1.4442418813705444, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4262, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 1.1203701496124268, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8025, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "grad_norm": 1.3620504140853882, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9045, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "grad_norm": 1.5145343542099, | |
| "learning_rate": 0.0002, | |
| "loss": 0.703, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "grad_norm": 1.333682656288147, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6285, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "grad_norm": 1.4228661060333252, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6004, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "grad_norm": 1.2111386060714722, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4754, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "grad_norm": 1.410719394683838, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5324, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "grad_norm": 1.4157259464263916, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4556, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "grad_norm": 1.3982216119766235, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4465, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "grad_norm": 1.4364334344863892, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4313, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "grad_norm": 1.5408861637115479, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4108, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 3.7199999999999998, | |
| "grad_norm": 1.5500551462173462, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4664, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "grad_norm": 1.1150060892105103, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8951, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "grad_norm": 1.0168464183807373, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8619, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 3.7800000000000002, | |
| "grad_norm": 1.2093026638031006, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5782, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "grad_norm": 1.3905984163284302, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6929, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "grad_norm": 1.3665902614593506, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5701, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "grad_norm": 1.1478445529937744, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4515, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "grad_norm": 1.2758458852767944, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5819, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "grad_norm": 1.0731329917907715, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4448, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "grad_norm": 1.20659339427948, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4295, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "grad_norm": 1.3976835012435913, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4566, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "grad_norm": 1.617711067199707, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4303, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "grad_norm": 1.707471489906311, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4539, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "grad_norm": 1.2962028980255127, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5971, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.8809109926223755, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4973, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.5414550304412842, | |
| "eval_runtime": 565.7272, | |
| "eval_samples_per_second": 0.707, | |
| "eval_steps_per_second": 0.177, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 300, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.545659449265357e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |