| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9900990099009901, | |
| "eval_steps": 20, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.5e-06, | |
| "loss": 2.0407, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.3e-05, | |
| "loss": 2.3107, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9499999999999996e-05, | |
| "loss": 2.1613, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.6e-05, | |
| "loss": 2.0444, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.25e-05, | |
| "loss": 2.2512, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.899999999999999e-05, | |
| "loss": 2.0516, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.5499999999999995e-05, | |
| "loss": 2.2006, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5.2e-05, | |
| "loss": 2.1229, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 5.85e-05, | |
| "loss": 2.2498, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 6.5e-05, | |
| "loss": 2.0293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 6.499564948206075e-05, | |
| "loss": 2.1316, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.498259909298188e-05, | |
| "loss": 2.1274, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 6.49608523266681e-05, | |
| "loss": 2.1129, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 6.493041500525461e-05, | |
| "loss": 2.1517, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 6.489129527754836e-05, | |
| "loss": 2.1078, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 6.484350361684639e-05, | |
| "loss": 2.0362, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 6.478705281813194e-05, | |
| "loss": 2.0553, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 6.472195799464884e-05, | |
| "loss": 2.1223, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 6.464823657385538e-05, | |
| "loss": 2.0326, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 6.456590829275857e-05, | |
| "loss": 2.1802, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 2.012301445007324, | |
| "eval_runtime": 1.4855, | |
| "eval_samples_per_second": 5.385, | |
| "eval_steps_per_second": 0.673, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6.447499519263001e-05, | |
| "loss": 2.0665, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 6.437552161310498e-05, | |
| "loss": 2.0354, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 6.426751418566609e-05, | |
| "loss": 2.1289, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 6.415100182651334e-05, | |
| "loss": 2.0742, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 6.402601572882268e-05, | |
| "loss": 2.0412, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 6.38925893543947e-05, | |
| "loss": 2.1974, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 6.375075842469626e-05, | |
| "loss": 2.196, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 6.360056091129678e-05, | |
| "loss": 2.0775, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 6.344203702570254e-05, | |
| "loss": 2.0366, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 6.327522920859093e-05, | |
| "loss": 2.1438, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.310018211844817e-05, | |
| "loss": 2.0639, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.291694261961308e-05, | |
| "loss": 2.1794, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.272555976973039e-05, | |
| "loss": 2.0592, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.252608480661681e-05, | |
| "loss": 2.1628, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.231857113454346e-05, | |
| "loss": 2.1851, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.21030743099382e-05, | |
| "loss": 2.0531, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.18796520265119e-05, | |
| "loss": 2.0284, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.164836409981237e-05, | |
| "loss": 2.2359, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.140927245121032e-05, | |
| "loss": 1.8967, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.116244109132153e-05, | |
| "loss": 2.0275, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.9861761331558228, | |
| "eval_runtime": 1.4896, | |
| "eval_samples_per_second": 5.37, | |
| "eval_steps_per_second": 0.671, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.0907936102869656e-05, | |
| "loss": 2.0316, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.0645825622994254e-05, | |
| "loss": 2.0768, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.037617982500884e-05, | |
| "loss": 2.0058, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.009907089961381e-05, | |
| "loss": 2.2319, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.981457303556923e-05, | |
| "loss": 2.1693, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.9522762399832716e-05, | |
| "loss": 2.0858, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.922371711716768e-05, | |
| "loss": 2.0576, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.891751724922749e-05, | |
| "loss": 1.9946, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.860424477312095e-05, | |
| "loss": 2.0166, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.828398355946514e-05, | |
| "loss": 2.1482, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.795681934993113e-05, | |
| "loss": 2.0698, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.7622839734288945e-05, | |
| "loss": 1.9317, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.728213412695761e-05, | |
| "loss": 2.1399, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.693479374306676e-05, | |
| "loss": 2.1637, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.658091157403617e-05, | |
| "loss": 2.0557, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.622058236267965e-05, | |
| "loss": 1.926, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.585390257784018e-05, | |
| "loss": 2.0984, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.548097038856279e-05, | |
| "loss": 2.0428, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.5101885637812374e-05, | |
| "loss": 1.9624, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 5.4716749815743304e-05, | |
| "loss": 1.913, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.97765052318573, | |
| "eval_runtime": 1.4886, | |
| "eval_samples_per_second": 5.374, | |
| "eval_steps_per_second": 0.672, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.432566603252809e-05, | |
| "loss": 2.0125, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.3928738990752234e-05, | |
| "loss": 2.0721, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5.3526074957382866e-05, | |
| "loss": 2.1046, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 5.311778173531847e-05, | |
| "loss": 2.0074, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.2703968634527514e-05, | |
| "loss": 2.1667, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.2284746442783414e-05, | |
| "loss": 2.0677, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.186022739600408e-05, | |
| "loss": 2.1798, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.143052514820357e-05, | |
| "loss": 2.105, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.099575474106419e-05, | |
| "loss": 2.118, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5.055603257313707e-05, | |
| "loss": 2.0791, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 5.011147636867943e-05, | |
| "loss": 2.032, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.9662205146136955e-05, | |
| "loss": 1.9331, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.92083391862797e-05, | |
| "loss": 2.0077, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.874999999999999e-05, | |
| "loss": 2.0253, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.828731029578105e-05, | |
| "loss": 1.9922, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.7820393946844926e-05, | |
| "loss": 2.0295, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.734937595798867e-05, | |
| "loss": 1.9514, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.687438243211754e-05, | |
| "loss": 2.1018, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.639554053648416e-05, | |
| "loss": 2.1032, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.5912978468642824e-05, | |
| "loss": 2.1258, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.972991704940796, | |
| "eval_runtime": 1.494, | |
| "eval_samples_per_second": 5.355, | |
| "eval_steps_per_second": 0.669, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.542682542212785e-05, | |
| "loss": 2.0353, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.4937211551865415e-05, | |
| "loss": 1.9987, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.444426793932787e-05, | |
| "loss": 1.8856, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.3948126557440085e-05, | |
| "loss": 2.0904, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.344892023524714e-05, | |
| "loss": 2.0685, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.2946782622352746e-05, | |
| "loss": 2.1, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.244184815313799e-05, | |
| "loss": 1.9322, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.193425201077002e-05, | |
| "loss": 2.194, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.14241300910103e-05, | |
| "loss": 2.0455, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.091161896583192e-05, | |
| "loss": 2.1239, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.0396855846856076e-05, | |
| "loss": 2.142, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.9879978548617125e-05, | |
| "loss": 2.2304, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.936112545166636e-05, | |
| "loss": 1.925, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.884043546552417e-05, | |
| "loss": 2.1547, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.831804799149057e-05, | |
| "loss": 2.0439, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.779410288532413e-05, | |
| "loss": 1.9763, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.726874041979925e-05, | |
| "loss": 2.114, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.674210124715168e-05, | |
| "loss": 2.0293, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.621432636142251e-05, | |
| "loss": 2.0833, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.5685557060710726e-05, | |
| "loss": 2.0452, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.9682413339614868, | |
| "eval_runtime": 1.4934, | |
| "eval_samples_per_second": 5.357, | |
| "eval_steps_per_second": 0.67, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 202, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "total_flos": 8.359599153348608e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |