| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 555, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018026137899954935, | |
| "grad_norm": 37.54188919067383, | |
| "learning_rate": 4.981949458483755e-05, | |
| "loss": 0.8911, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03605227579990987, | |
| "grad_norm": 15.440231323242188, | |
| "learning_rate": 4.963898916967509e-05, | |
| "loss": 0.6165, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054078413699864804, | |
| "grad_norm": 226.8269500732422, | |
| "learning_rate": 4.945848375451264e-05, | |
| "loss": 0.5151, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07210455159981974, | |
| "grad_norm": 21.70491600036621, | |
| "learning_rate": 4.927797833935018e-05, | |
| "loss": 0.5669, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09013068949977468, | |
| "grad_norm": 79.27781677246094, | |
| "learning_rate": 4.909747292418773e-05, | |
| "loss": 0.5119, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10815682739972961, | |
| "grad_norm": 15.314950942993164, | |
| "learning_rate": 4.891696750902527e-05, | |
| "loss": 0.474, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12618296529968454, | |
| "grad_norm": 25.575763702392578, | |
| "learning_rate": 4.873646209386282e-05, | |
| "loss": 0.478, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14420910319963948, | |
| "grad_norm": 27.453636169433594, | |
| "learning_rate": 4.855595667870036e-05, | |
| "loss": 0.4285, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16223524109959442, | |
| "grad_norm": 34.88062286376953, | |
| "learning_rate": 4.837545126353791e-05, | |
| "loss": 0.4317, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18026137899954936, | |
| "grad_norm": 46.823577880859375, | |
| "learning_rate": 4.819494584837546e-05, | |
| "loss": 0.4899, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19828751689950427, | |
| "grad_norm": 36.73914337158203, | |
| "learning_rate": 4.8014440433213e-05, | |
| "loss": 0.4839, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.21631365479945922, | |
| "grad_norm": 102.61051940917969, | |
| "learning_rate": 4.783393501805055e-05, | |
| "loss": 0.4795, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.23433979269941416, | |
| "grad_norm": 24.9108829498291, | |
| "learning_rate": 4.765342960288809e-05, | |
| "loss": 0.4332, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.25236593059936907, | |
| "grad_norm": 14.366719245910645, | |
| "learning_rate": 4.747292418772563e-05, | |
| "loss": 0.4811, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.270392068499324, | |
| "grad_norm": 19.95521354675293, | |
| "learning_rate": 4.7292418772563177e-05, | |
| "loss": 0.4544, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.28841820639927895, | |
| "grad_norm": 20.914020538330078, | |
| "learning_rate": 4.711191335740072e-05, | |
| "loss": 0.4646, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3064443442992339, | |
| "grad_norm": 154.6277313232422, | |
| "learning_rate": 4.693140794223827e-05, | |
| "loss": 0.47, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.32447048219918884, | |
| "grad_norm": 30.73076820373535, | |
| "learning_rate": 4.675090252707581e-05, | |
| "loss": 0.4341, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3424966200991438, | |
| "grad_norm": 14.621489524841309, | |
| "learning_rate": 4.657039711191336e-05, | |
| "loss": 0.5163, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3605227579990987, | |
| "grad_norm": 25.546030044555664, | |
| "learning_rate": 4.63898916967509e-05, | |
| "loss": 0.4601, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3785488958990536, | |
| "grad_norm": 18.222177505493164, | |
| "learning_rate": 4.620938628158845e-05, | |
| "loss": 0.4398, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.39657503379900855, | |
| "grad_norm": 20.1109676361084, | |
| "learning_rate": 4.602888086642599e-05, | |
| "loss": 0.432, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4146011716989635, | |
| "grad_norm": 13.729535102844238, | |
| "learning_rate": 4.584837545126354e-05, | |
| "loss": 0.4327, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.43262730959891843, | |
| "grad_norm": 32.50856018066406, | |
| "learning_rate": 4.566787003610109e-05, | |
| "loss": 0.4208, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.45065344749887337, | |
| "grad_norm": 15.05933666229248, | |
| "learning_rate": 4.548736462093863e-05, | |
| "loss": 0.4451, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4686795853988283, | |
| "grad_norm": 31.787078857421875, | |
| "learning_rate": 4.530685920577618e-05, | |
| "loss": 0.4376, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.48670572329878325, | |
| "grad_norm": 25.446210861206055, | |
| "learning_rate": 4.5126353790613716e-05, | |
| "loss": 0.4131, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5047318611987381, | |
| "grad_norm": 31.328969955444336, | |
| "learning_rate": 4.494584837545127e-05, | |
| "loss": 0.4194, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5227579990986931, | |
| "grad_norm": 255.53672790527344, | |
| "learning_rate": 4.4765342960288806e-05, | |
| "loss": 0.4984, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.540784136998648, | |
| "grad_norm": 14.31953239440918, | |
| "learning_rate": 4.458483754512636e-05, | |
| "loss": 0.4417, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.558810274898603, | |
| "grad_norm": 26.942129135131836, | |
| "learning_rate": 4.44043321299639e-05, | |
| "loss": 0.4527, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5768364127985579, | |
| "grad_norm": 36.217586517333984, | |
| "learning_rate": 4.422382671480145e-05, | |
| "loss": 0.4485, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5948625506985128, | |
| "grad_norm": 38.54646682739258, | |
| "learning_rate": 4.404332129963899e-05, | |
| "loss": 0.4579, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6128886885984678, | |
| "grad_norm": 21.504106521606445, | |
| "learning_rate": 4.386281588447654e-05, | |
| "loss": 0.4117, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6309148264984227, | |
| "grad_norm": 16.283788681030273, | |
| "learning_rate": 4.368231046931408e-05, | |
| "loss": 0.438, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6489409643983777, | |
| "grad_norm": 33.57164001464844, | |
| "learning_rate": 4.350180505415163e-05, | |
| "loss": 0.4043, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6669671022983326, | |
| "grad_norm": 12.821700096130371, | |
| "learning_rate": 4.332129963898917e-05, | |
| "loss": 0.4119, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6849932401982876, | |
| "grad_norm": 23.477996826171875, | |
| "learning_rate": 4.314079422382672e-05, | |
| "loss": 0.3783, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7030193780982424, | |
| "grad_norm": 18.2862548828125, | |
| "learning_rate": 4.296028880866426e-05, | |
| "loss": 0.4023, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7210455159981974, | |
| "grad_norm": 19.799530029296875, | |
| "learning_rate": 4.277978339350181e-05, | |
| "loss": 0.419, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7390716538981523, | |
| "grad_norm": 17.081830978393555, | |
| "learning_rate": 4.259927797833935e-05, | |
| "loss": 0.467, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.7570977917981072, | |
| "grad_norm": 24.008344650268555, | |
| "learning_rate": 4.24187725631769e-05, | |
| "loss": 0.4302, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7751239296980622, | |
| "grad_norm": 40.07936477661133, | |
| "learning_rate": 4.223826714801444e-05, | |
| "loss": 0.3622, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7931500675980171, | |
| "grad_norm": 19.614171981811523, | |
| "learning_rate": 4.205776173285199e-05, | |
| "loss": 0.4645, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8111762054979721, | |
| "grad_norm": 32.0594596862793, | |
| "learning_rate": 4.187725631768953e-05, | |
| "loss": 0.3755, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.829202343397927, | |
| "grad_norm": 15.177023887634277, | |
| "learning_rate": 4.169675090252708e-05, | |
| "loss": 0.4275, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.847228481297882, | |
| "grad_norm": 11.258400917053223, | |
| "learning_rate": 4.151624548736462e-05, | |
| "loss": 0.4137, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.8652546191978369, | |
| "grad_norm": 13.211421012878418, | |
| "learning_rate": 4.1335740072202167e-05, | |
| "loss": 0.4337, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8832807570977917, | |
| "grad_norm": 14.50296401977539, | |
| "learning_rate": 4.115523465703972e-05, | |
| "loss": 0.4318, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9013068949977467, | |
| "grad_norm": 21.239362716674805, | |
| "learning_rate": 4.0974729241877256e-05, | |
| "loss": 0.3939, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9193330328977016, | |
| "grad_norm": 18.6204891204834, | |
| "learning_rate": 4.079422382671481e-05, | |
| "loss": 0.3838, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.9373591707976566, | |
| "grad_norm": 21.722551345825195, | |
| "learning_rate": 4.0613718411552346e-05, | |
| "loss": 0.4236, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.9553853086976115, | |
| "grad_norm": 23.824357986450195, | |
| "learning_rate": 4.043321299638989e-05, | |
| "loss": 0.4062, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.9734114465975665, | |
| "grad_norm": 18.93727684020996, | |
| "learning_rate": 4.0252707581227436e-05, | |
| "loss": 0.4412, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9914375844975214, | |
| "grad_norm": 16.050817489624023, | |
| "learning_rate": 4.007220216606498e-05, | |
| "loss": 0.4142, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.8390086641144469, | |
| "eval_fn": 205, | |
| "eval_fp": 594, | |
| "eval_loss": 0.3744712173938751, | |
| "eval_precision": 0.7780269058295964, | |
| "eval_recall": 0.910362920857018, | |
| "eval_runtime": 73.1391, | |
| "eval_samples_per_second": 63.892, | |
| "eval_steps_per_second": 7.998, | |
| "eval_tn": 1792, | |
| "eval_tp": 2082, | |
| "step": 555 | |
| } | |
| ], | |
| "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 | |
| } | |