| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6666666666666666, | |
| "eval_steps": 106, | |
| "global_step": 702, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000949667616334283, | |
| "eval_loss": 1.59001886844635, | |
| "eval_runtime": 241.2886, | |
| "eval_samples_per_second": 4.849, | |
| "eval_steps_per_second": 2.424, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00949667616334283, | |
| "grad_norm": 1.056609034538269, | |
| "learning_rate": 4e-08, | |
| "loss": 1.4438, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01899335232668566, | |
| "grad_norm": 0.9450796246528625, | |
| "learning_rate": 8e-08, | |
| "loss": 1.49, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02849002849002849, | |
| "grad_norm": 0.991963803768158, | |
| "learning_rate": 1.2e-07, | |
| "loss": 1.488, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03798670465337132, | |
| "grad_norm": 0.8748257160186768, | |
| "learning_rate": 1.6e-07, | |
| "loss": 1.4817, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04748338081671415, | |
| "grad_norm": 0.9113293290138245, | |
| "learning_rate": 2e-07, | |
| "loss": 1.4838, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05698005698005698, | |
| "grad_norm": 0.9806835651397705, | |
| "learning_rate": 2.4e-07, | |
| "loss": 1.4866, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06647673314339982, | |
| "grad_norm": 0.8570646643638611, | |
| "learning_rate": 2.8e-07, | |
| "loss": 1.4502, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07597340930674264, | |
| "grad_norm": 0.8111629486083984, | |
| "learning_rate": 3.2e-07, | |
| "loss": 1.4681, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 0.7242903709411621, | |
| "learning_rate": 3.6e-07, | |
| "loss": 1.5103, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0949667616334283, | |
| "grad_norm": 0.9140864014625549, | |
| "learning_rate": 4e-07, | |
| "loss": 1.4756, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.100664767331434, | |
| "eval_loss": 1.588047742843628, | |
| "eval_runtime": 241.8249, | |
| "eval_samples_per_second": 4.838, | |
| "eval_steps_per_second": 2.419, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.10446343779677113, | |
| "grad_norm": 0.766789436340332, | |
| "learning_rate": 4.3999999999999997e-07, | |
| "loss": 1.4455, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 1.0300992727279663, | |
| "learning_rate": 4.8e-07, | |
| "loss": 1.4651, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12345679012345678, | |
| "grad_norm": 0.8080026507377625, | |
| "learning_rate": 5.2e-07, | |
| "loss": 1.5405, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.13295346628679963, | |
| "grad_norm": 0.8535659909248352, | |
| "learning_rate": 5.6e-07, | |
| "loss": 1.5043, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14245014245014245, | |
| "grad_norm": 1.1608635187149048, | |
| "learning_rate": 6e-07, | |
| "loss": 1.4763, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15194681861348527, | |
| "grad_norm": 1.0252463817596436, | |
| "learning_rate": 6.4e-07, | |
| "loss": 1.4542, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16144349477682812, | |
| "grad_norm": 1.242639183998108, | |
| "learning_rate": 6.800000000000001e-07, | |
| "loss": 1.4663, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 0.9343454241752625, | |
| "learning_rate": 7.2e-07, | |
| "loss": 1.4858, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.18043684710351376, | |
| "grad_norm": 1.0508811473846436, | |
| "learning_rate": 7.599999999999999e-07, | |
| "loss": 1.4917, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1899335232668566, | |
| "grad_norm": 1.4828695058822632, | |
| "learning_rate": 8e-07, | |
| "loss": 1.4477, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19943019943019943, | |
| "grad_norm": 1.3482277393341064, | |
| "learning_rate": 8.399999999999999e-07, | |
| "loss": 1.4972, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.201329534662868, | |
| "eval_loss": 1.5654927492141724, | |
| "eval_runtime": 241.4855, | |
| "eval_samples_per_second": 4.845, | |
| "eval_steps_per_second": 2.423, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.20892687559354226, | |
| "grad_norm": 0.8324021697044373, | |
| "learning_rate": 8.799999999999999e-07, | |
| "loss": 1.4831, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2184235517568851, | |
| "grad_norm": 0.8362078070640564, | |
| "learning_rate": 9.2e-07, | |
| "loss": 1.4395, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 0.9072378873825073, | |
| "learning_rate": 9.6e-07, | |
| "loss": 1.4402, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.23741690408357075, | |
| "grad_norm": 0.9287540912628174, | |
| "learning_rate": 1e-06, | |
| "loss": 1.4659, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.24691358024691357, | |
| "grad_norm": 0.8501766920089722, | |
| "learning_rate": 1.04e-06, | |
| "loss": 1.4708, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 0.5359634160995483, | |
| "learning_rate": 1.08e-06, | |
| "loss": 1.4748, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.26590693257359926, | |
| "grad_norm": 0.6378765106201172, | |
| "learning_rate": 1.12e-06, | |
| "loss": 1.4286, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2754036087369421, | |
| "grad_norm": 0.6789595484733582, | |
| "learning_rate": 1.16e-06, | |
| "loss": 1.4212, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2849002849002849, | |
| "grad_norm": 0.6995547413825989, | |
| "learning_rate": 1.2e-06, | |
| "loss": 1.4406, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2943969610636277, | |
| "grad_norm": 0.7261990904808044, | |
| "learning_rate": 1.24e-06, | |
| "loss": 1.4563, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.301994301994302, | |
| "eval_loss": 1.5017595291137695, | |
| "eval_runtime": 241.2449, | |
| "eval_samples_per_second": 4.85, | |
| "eval_steps_per_second": 2.425, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.30389363722697055, | |
| "grad_norm": 0.6617552042007446, | |
| "learning_rate": 1.28e-06, | |
| "loss": 1.3913, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.31339031339031337, | |
| "grad_norm": 0.5867168307304382, | |
| "learning_rate": 1.32e-06, | |
| "loss": 1.3892, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.32288698955365625, | |
| "grad_norm": 0.6030348539352417, | |
| "learning_rate": 1.3600000000000001e-06, | |
| "loss": 1.39, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.33238366571699907, | |
| "grad_norm": 0.5722991228103638, | |
| "learning_rate": 1.4e-06, | |
| "loss": 1.3744, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.5842142105102539, | |
| "learning_rate": 1.44e-06, | |
| "loss": 1.3968, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3513770180436847, | |
| "grad_norm": 0.8536161184310913, | |
| "learning_rate": 1.48e-06, | |
| "loss": 1.4192, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.36087369420702753, | |
| "grad_norm": 0.6988087296485901, | |
| "learning_rate": 1.5199999999999998e-06, | |
| "loss": 1.3769, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 0.5693365931510925, | |
| "learning_rate": 1.5599999999999999e-06, | |
| "loss": 1.3986, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.3798670465337132, | |
| "grad_norm": 0.6898847818374634, | |
| "learning_rate": 1.6e-06, | |
| "loss": 1.3774, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.38936372269705605, | |
| "grad_norm": 0.6398094892501831, | |
| "learning_rate": 1.6399999999999998e-06, | |
| "loss": 1.4069, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.39886039886039887, | |
| "grad_norm": 0.5179505944252014, | |
| "learning_rate": 1.6799999999999998e-06, | |
| "loss": 1.3754, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.402659069325736, | |
| "eval_loss": 1.4127401113510132, | |
| "eval_runtime": 242.04, | |
| "eval_samples_per_second": 4.834, | |
| "eval_steps_per_second": 2.417, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.4083570750237417, | |
| "grad_norm": 0.691733717918396, | |
| "learning_rate": 1.7199999999999998e-06, | |
| "loss": 1.3288, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.4178537511870845, | |
| "grad_norm": 0.684332013130188, | |
| "learning_rate": 1.7599999999999999e-06, | |
| "loss": 1.3613, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.42735042735042733, | |
| "grad_norm": 0.7648876309394836, | |
| "learning_rate": 1.8e-06, | |
| "loss": 1.3232, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4368471035137702, | |
| "grad_norm": 0.8008069396018982, | |
| "learning_rate": 1.84e-06, | |
| "loss": 1.346, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.44634377967711303, | |
| "grad_norm": 0.7102649211883545, | |
| "learning_rate": 1.8799999999999998e-06, | |
| "loss": 1.325, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 0.6222986578941345, | |
| "learning_rate": 1.92e-06, | |
| "loss": 1.2948, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.46533713200379867, | |
| "grad_norm": 0.8117070198059082, | |
| "learning_rate": 1.96e-06, | |
| "loss": 1.3221, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.4748338081671415, | |
| "grad_norm": 0.7963566780090332, | |
| "learning_rate": 2e-06, | |
| "loss": 1.2908, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4843304843304843, | |
| "grad_norm": 0.7263100147247314, | |
| "learning_rate": 1.998386746257178e-06, | |
| "loss": 1.3097, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.49382716049382713, | |
| "grad_norm": 1.0555329322814941, | |
| "learning_rate": 1.993552190203991e-06, | |
| "loss": 1.2671, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.50332383665717, | |
| "grad_norm": 0.9024184346199036, | |
| "learning_rate": 1.985511930571733e-06, | |
| "loss": 1.271, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.50332383665717, | |
| "eval_loss": 1.3055741786956787, | |
| "eval_runtime": 241.4921, | |
| "eval_samples_per_second": 4.845, | |
| "eval_steps_per_second": 2.422, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 0.9171520471572876, | |
| "learning_rate": 1.9742919093182947e-06, | |
| "loss": 1.3002, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5223171889838556, | |
| "grad_norm": 1.1000499725341797, | |
| "learning_rate": 1.959928327926239e-06, | |
| "loss": 1.2513, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5318138651471985, | |
| "grad_norm": 0.9843473434448242, | |
| "learning_rate": 1.942467530598449e-06, | |
| "loss": 1.2669, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.5413105413105413, | |
| "grad_norm": 0.9255275726318359, | |
| "learning_rate": 1.9219658547282065e-06, | |
| "loss": 1.2479, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5508072174738842, | |
| "grad_norm": 0.9032674431800842, | |
| "learning_rate": 1.8984894491261762e-06, | |
| "loss": 1.2133, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.560303893637227, | |
| "grad_norm": 1.0691276788711548, | |
| "learning_rate": 1.872114060590769e-06, | |
| "loss": 1.185, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 1.0371201038360596, | |
| "learning_rate": 1.842924789510531e-06, | |
| "loss": 1.2179, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5792972459639126, | |
| "grad_norm": 1.1502381563186646, | |
| "learning_rate": 1.8110158152871029e-06, | |
| "loss": 1.2306, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.5887939221272555, | |
| "grad_norm": 0.9843053817749023, | |
| "learning_rate": 1.776490092464676e-06, | |
| "loss": 1.1823, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.5982905982905983, | |
| "grad_norm": 1.2571120262145996, | |
| "learning_rate": 1.7394590185463837e-06, | |
| "loss": 1.2054, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.603988603988604, | |
| "eval_loss": 1.200851559638977, | |
| "eval_runtime": 241.2048, | |
| "eval_samples_per_second": 4.851, | |
| "eval_steps_per_second": 2.425, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.6077872744539411, | |
| "grad_norm": 1.0591609477996826, | |
| "learning_rate": 1.7000420745694253e-06, | |
| "loss": 1.1656, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6172839506172839, | |
| "grad_norm": 1.0051286220550537, | |
| "learning_rate": 1.6583664395986035e-06, | |
| "loss": 1.1572, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6267806267806267, | |
| "grad_norm": 1.3040874004364014, | |
| "learning_rate": 1.61456658038212e-06, | |
| "loss": 1.1662, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.6362773029439696, | |
| "grad_norm": 1.066710352897644, | |
| "learning_rate": 1.5687838174936082e-06, | |
| "loss": 1.1534, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.6457739791073125, | |
| "grad_norm": 1.009498953819275, | |
| "learning_rate": 1.5211658693602396e-06, | |
| "loss": 1.1528, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.6552706552706553, | |
| "grad_norm": 1.3166037797927856, | |
| "learning_rate": 1.471866375648119e-06, | |
| "loss": 1.1289, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.6647673314339981, | |
| "grad_norm": 1.092807412147522, | |
| "learning_rate": 1.4210444015427466e-06, | |
| "loss": 1.1494, | |
| "step": 700 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1053, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 351, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2971277740408832e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |