| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 693, | |
| "global_step": 555, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "eval_f1": 0.6193506281612009, | |
| "eval_fn": 512, | |
| "eval_fp": 1821, | |
| "eval_loss": 0.736859142780304, | |
| "eval_precision": 0.5103522452272116, | |
| "eval_recall": 0.787551867219917, | |
| "eval_runtime": 69.9291, | |
| "eval_samples_per_second": 66.825, | |
| "eval_steps_per_second": 8.366, | |
| "eval_tn": 442, | |
| "eval_tp": 1898, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 0.018026137899954935, | |
| "grad_norm": 32.56014633178711, | |
| "learning_rate": 4.981949458483755e-05, | |
| "loss": 0.8382, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03605227579990987, | |
| "grad_norm": 27.728681564331055, | |
| "learning_rate": 4.963898916967509e-05, | |
| "loss": 0.5565, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054078413699864804, | |
| "grad_norm": 26.70035171508789, | |
| "learning_rate": 4.945848375451264e-05, | |
| "loss": 0.5545, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07210455159981974, | |
| "grad_norm": 23.187734603881836, | |
| "learning_rate": 4.927797833935018e-05, | |
| "loss": 0.6027, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09013068949977468, | |
| "grad_norm": 35.976619720458984, | |
| "learning_rate": 4.909747292418773e-05, | |
| "loss": 0.5741, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10815682739972961, | |
| "grad_norm": 27.495447158813477, | |
| "learning_rate": 4.891696750902527e-05, | |
| "loss": 0.4941, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12618296529968454, | |
| "grad_norm": 25.021883010864258, | |
| "learning_rate": 4.873646209386282e-05, | |
| "loss": 0.457, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14420910319963948, | |
| "grad_norm": 29.016551971435547, | |
| "learning_rate": 4.855595667870036e-05, | |
| "loss": 0.4215, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16223524109959442, | |
| "grad_norm": 25.652786254882812, | |
| "learning_rate": 4.837545126353791e-05, | |
| "loss": 0.4292, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18026137899954936, | |
| "grad_norm": 24.254980087280273, | |
| "learning_rate": 4.819494584837546e-05, | |
| "loss": 0.4559, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19828751689950427, | |
| "grad_norm": 43.745643615722656, | |
| "learning_rate": 4.8014440433213e-05, | |
| "loss": 0.4536, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.21631365479945922, | |
| "grad_norm": 19.265901565551758, | |
| "learning_rate": 4.783393501805055e-05, | |
| "loss": 0.4634, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.23433979269941416, | |
| "grad_norm": 75.13768768310547, | |
| "learning_rate": 4.765342960288809e-05, | |
| "loss": 0.4067, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.25236593059936907, | |
| "grad_norm": 24.337844848632812, | |
| "learning_rate": 4.747292418772563e-05, | |
| "loss": 0.4483, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.270392068499324, | |
| "grad_norm": 27.518775939941406, | |
| "learning_rate": 4.7292418772563177e-05, | |
| "loss": 0.4524, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.28841820639927895, | |
| "grad_norm": 23.281097412109375, | |
| "learning_rate": 4.711191335740072e-05, | |
| "loss": 0.4443, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3064443442992339, | |
| "grad_norm": 12.933683395385742, | |
| "learning_rate": 4.693140794223827e-05, | |
| "loss": 0.472, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.32447048219918884, | |
| "grad_norm": 16.49010467529297, | |
| "learning_rate": 4.675090252707581e-05, | |
| "loss": 0.4549, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3424966200991438, | |
| "grad_norm": 19.209016799926758, | |
| "learning_rate": 4.657039711191336e-05, | |
| "loss": 0.4628, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3605227579990987, | |
| "grad_norm": 19.71845054626465, | |
| "learning_rate": 4.63898916967509e-05, | |
| "loss": 0.4281, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3785488958990536, | |
| "grad_norm": 19.700483322143555, | |
| "learning_rate": 4.620938628158845e-05, | |
| "loss": 0.4427, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.39657503379900855, | |
| "grad_norm": 19.06282615661621, | |
| "learning_rate": 4.602888086642599e-05, | |
| "loss": 0.4214, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4146011716989635, | |
| "grad_norm": 14.681564331054688, | |
| "learning_rate": 4.584837545126354e-05, | |
| "loss": 0.4279, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.43262730959891843, | |
| "grad_norm": 28.783143997192383, | |
| "learning_rate": 4.566787003610109e-05, | |
| "loss": 0.4475, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.45065344749887337, | |
| "grad_norm": 14.686984062194824, | |
| "learning_rate": 4.548736462093863e-05, | |
| "loss": 0.4232, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4686795853988283, | |
| "grad_norm": 15.651535987854004, | |
| "learning_rate": 4.530685920577618e-05, | |
| "loss": 0.4026, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.48670572329878325, | |
| "grad_norm": 17.506153106689453, | |
| "learning_rate": 4.5126353790613716e-05, | |
| "loss": 0.416, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5047318611987381, | |
| "grad_norm": 23.381561279296875, | |
| "learning_rate": 4.494584837545127e-05, | |
| "loss": 0.385, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5227579990986931, | |
| "grad_norm": 18.458227157592773, | |
| "learning_rate": 4.4765342960288806e-05, | |
| "loss": 0.4352, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.540784136998648, | |
| "grad_norm": 16.285743713378906, | |
| "learning_rate": 4.458483754512636e-05, | |
| "loss": 0.4191, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.558810274898603, | |
| "grad_norm": 22.14523696899414, | |
| "learning_rate": 4.44043321299639e-05, | |
| "loss": 0.4525, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5768364127985579, | |
| "grad_norm": 12.94579029083252, | |
| "learning_rate": 4.422382671480145e-05, | |
| "loss": 0.4335, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5948625506985128, | |
| "grad_norm": 29.218290328979492, | |
| "learning_rate": 4.404332129963899e-05, | |
| "loss": 0.4194, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6128886885984678, | |
| "grad_norm": 20.067014694213867, | |
| "learning_rate": 4.386281588447654e-05, | |
| "loss": 0.4016, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6309148264984227, | |
| "grad_norm": 15.315394401550293, | |
| "learning_rate": 4.368231046931408e-05, | |
| "loss": 0.4293, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6489409643983777, | |
| "grad_norm": 28.87151527404785, | |
| "learning_rate": 4.350180505415163e-05, | |
| "loss": 0.3952, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6669671022983326, | |
| "grad_norm": 12.91943645477295, | |
| "learning_rate": 4.332129963898917e-05, | |
| "loss": 0.4276, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6849932401982876, | |
| "grad_norm": 18.917442321777344, | |
| "learning_rate": 4.314079422382672e-05, | |
| "loss": 0.3843, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7030193780982424, | |
| "grad_norm": 16.344675064086914, | |
| "learning_rate": 4.296028880866426e-05, | |
| "loss": 0.4283, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7210455159981974, | |
| "grad_norm": 27.420021057128906, | |
| "learning_rate": 4.277978339350181e-05, | |
| "loss": 0.4663, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7390716538981523, | |
| "grad_norm": 37.13134765625, | |
| "learning_rate": 4.259927797833935e-05, | |
| "loss": 0.4338, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.7570977917981072, | |
| "grad_norm": 23.59578514099121, | |
| "learning_rate": 4.24187725631769e-05, | |
| "loss": 0.3714, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7751239296980622, | |
| "grad_norm": 30.009662628173828, | |
| "learning_rate": 4.223826714801444e-05, | |
| "loss": 0.3775, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7931500675980171, | |
| "grad_norm": 13.575807571411133, | |
| "learning_rate": 4.205776173285199e-05, | |
| "loss": 0.4104, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8111762054979721, | |
| "grad_norm": 18.727609634399414, | |
| "learning_rate": 4.187725631768953e-05, | |
| "loss": 0.3804, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.829202343397927, | |
| "grad_norm": 14.367807388305664, | |
| "learning_rate": 4.169675090252708e-05, | |
| "loss": 0.4124, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.847228481297882, | |
| "grad_norm": 12.945828437805176, | |
| "learning_rate": 4.151624548736462e-05, | |
| "loss": 0.4149, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.8652546191978369, | |
| "grad_norm": 24.02052116394043, | |
| "learning_rate": 4.1335740072202167e-05, | |
| "loss": 0.4093, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8832807570977917, | |
| "grad_norm": 15.609790802001953, | |
| "learning_rate": 4.115523465703972e-05, | |
| "loss": 0.3874, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9013068949977467, | |
| "grad_norm": 25.04174041748047, | |
| "learning_rate": 4.0974729241877256e-05, | |
| "loss": 0.391, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9193330328977016, | |
| "grad_norm": 20.739681243896484, | |
| "learning_rate": 4.079422382671481e-05, | |
| "loss": 0.3939, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.9373591707976566, | |
| "grad_norm": 16.13037872314453, | |
| "learning_rate": 4.0613718411552346e-05, | |
| "loss": 0.4004, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.9553853086976115, | |
| "grad_norm": 21.17761993408203, | |
| "learning_rate": 4.043321299638989e-05, | |
| "loss": 0.3978, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.9734114465975665, | |
| "grad_norm": 27.03806495666504, | |
| "learning_rate": 4.0252707581227436e-05, | |
| "loss": 0.4391, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9914375844975214, | |
| "grad_norm": 15.054065704345703, | |
| "learning_rate": 4.007220216606498e-05, | |
| "loss": 0.4187, | |
| "step": 550 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2770, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 1.929257128088371e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |