| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4230118443316413, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008460236886632826, | |
| "grad_norm": 2.4233109951019287, | |
| "learning_rate": 1.9949238578680207e-05, | |
| "loss": 1.3216, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01692047377326565, | |
| "grad_norm": 1.1721662282943726, | |
| "learning_rate": 1.9892836999435986e-05, | |
| "loss": 0.5312, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025380710659898477, | |
| "grad_norm": 0.899889349937439, | |
| "learning_rate": 1.9836435420191765e-05, | |
| "loss": 0.2969, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0338409475465313, | |
| "grad_norm": 0.4674186408519745, | |
| "learning_rate": 1.9780033840947548e-05, | |
| "loss": 0.1564, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04230118443316413, | |
| "grad_norm": 0.9013752937316895, | |
| "learning_rate": 1.972363226170333e-05, | |
| "loss": 0.0966, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.050761421319796954, | |
| "grad_norm": 0.364164799451828, | |
| "learning_rate": 1.966723068245911e-05, | |
| "loss": 0.0516, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05922165820642978, | |
| "grad_norm": 0.22717136144638062, | |
| "learning_rate": 1.9610829103214893e-05, | |
| "loss": 0.0307, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0676818950930626, | |
| "grad_norm": 0.09149003773927689, | |
| "learning_rate": 1.9554427523970672e-05, | |
| "loss": 0.0182, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07614213197969544, | |
| "grad_norm": 0.12942063808441162, | |
| "learning_rate": 1.949802594472645e-05, | |
| "loss": 0.017, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08460236886632826, | |
| "grad_norm": 0.27440059185028076, | |
| "learning_rate": 1.9441624365482234e-05, | |
| "loss": 0.0113, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09306260575296109, | |
| "grad_norm": 0.5005059242248535, | |
| "learning_rate": 1.9385222786238017e-05, | |
| "loss": 0.0082, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.10152284263959391, | |
| "grad_norm": 0.19820384681224823, | |
| "learning_rate": 1.9328821206993796e-05, | |
| "loss": 0.0057, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10998307952622674, | |
| "grad_norm": 0.03431914001703262, | |
| "learning_rate": 1.927241962774958e-05, | |
| "loss": 0.0055, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11844331641285956, | |
| "grad_norm": 0.4414117634296417, | |
| "learning_rate": 1.921601804850536e-05, | |
| "loss": 0.0063, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12690355329949238, | |
| "grad_norm": 0.9055352807044983, | |
| "learning_rate": 1.915961646926114e-05, | |
| "loss": 0.0048, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1353637901861252, | |
| "grad_norm": 0.036724768579006195, | |
| "learning_rate": 1.910321489001692e-05, | |
| "loss": 0.0035, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.14382402707275804, | |
| "grad_norm": 0.0888664722442627, | |
| "learning_rate": 1.9046813310772703e-05, | |
| "loss": 0.0033, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.15228426395939088, | |
| "grad_norm": 0.019098607823252678, | |
| "learning_rate": 1.8990411731528486e-05, | |
| "loss": 0.0029, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.16074450084602368, | |
| "grad_norm": 0.0171552412211895, | |
| "learning_rate": 1.8934010152284265e-05, | |
| "loss": 0.0029, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1692047377326565, | |
| "grad_norm": 0.01885647512972355, | |
| "learning_rate": 1.8877608573040048e-05, | |
| "loss": 0.0028, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17766497461928935, | |
| "grad_norm": 0.01599389687180519, | |
| "learning_rate": 1.8821206993795827e-05, | |
| "loss": 0.0022, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.18612521150592218, | |
| "grad_norm": 0.017242038622498512, | |
| "learning_rate": 1.876480541455161e-05, | |
| "loss": 0.0023, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.19458544839255498, | |
| "grad_norm": 0.5941590666770935, | |
| "learning_rate": 1.870840383530739e-05, | |
| "loss": 0.0031, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.20304568527918782, | |
| "grad_norm": 0.4872148931026459, | |
| "learning_rate": 1.8652002256063172e-05, | |
| "loss": 0.0027, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.21150592216582065, | |
| "grad_norm": 0.014173777773976326, | |
| "learning_rate": 1.859560067681895e-05, | |
| "loss": 0.0021, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.21996615905245348, | |
| "grad_norm": 0.024433018639683723, | |
| "learning_rate": 1.8539199097574734e-05, | |
| "loss": 0.0017, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.22842639593908629, | |
| "grad_norm": 0.017857005819678307, | |
| "learning_rate": 1.8482797518330516e-05, | |
| "loss": 0.0017, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.23688663282571912, | |
| "grad_norm": 0.014704135246574879, | |
| "learning_rate": 1.8426395939086296e-05, | |
| "loss": 0.0021, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.24534686971235195, | |
| "grad_norm": 0.022361995652318, | |
| "learning_rate": 1.8369994359842075e-05, | |
| "loss": 0.0016, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.25380710659898476, | |
| "grad_norm": 0.01112055778503418, | |
| "learning_rate": 1.8313592780597858e-05, | |
| "loss": 0.0015, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2622673434856176, | |
| "grad_norm": 0.010048450902104378, | |
| "learning_rate": 1.825719120135364e-05, | |
| "loss": 0.0015, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.2707275803722504, | |
| "grad_norm": 0.012935510836541653, | |
| "learning_rate": 1.820078962210942e-05, | |
| "loss": 0.0014, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.27918781725888325, | |
| "grad_norm": 0.010541570372879505, | |
| "learning_rate": 1.8144388042865203e-05, | |
| "loss": 0.0013, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.2876480541455161, | |
| "grad_norm": 0.009258048608899117, | |
| "learning_rate": 1.8087986463620982e-05, | |
| "loss": 0.0012, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.2961082910321489, | |
| "grad_norm": 0.009454768151044846, | |
| "learning_rate": 1.8031584884376765e-05, | |
| "loss": 0.0015, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.30456852791878175, | |
| "grad_norm": 0.018366724252700806, | |
| "learning_rate": 1.7975183305132544e-05, | |
| "loss": 0.0012, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3130287648054145, | |
| "grad_norm": 0.009252658113837242, | |
| "learning_rate": 1.7918781725888327e-05, | |
| "loss": 0.0011, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.32148900169204736, | |
| "grad_norm": 0.1430797576904297, | |
| "learning_rate": 1.7862380146644106e-05, | |
| "loss": 0.0018, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3299492385786802, | |
| "grad_norm": 0.009182159788906574, | |
| "learning_rate": 1.780597856739989e-05, | |
| "loss": 0.0018, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.338409475465313, | |
| "grad_norm": 0.00843009352684021, | |
| "learning_rate": 1.774957698815567e-05, | |
| "loss": 0.0017, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.34686971235194586, | |
| "grad_norm": 0.008176930248737335, | |
| "learning_rate": 1.769317540891145e-05, | |
| "loss": 0.0013, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.3553299492385787, | |
| "grad_norm": 0.008539380505681038, | |
| "learning_rate": 1.7636773829667233e-05, | |
| "loss": 0.001, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3637901861252115, | |
| "grad_norm": 0.008693977259099483, | |
| "learning_rate": 1.7580372250423013e-05, | |
| "loss": 0.0014, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.37225042301184436, | |
| "grad_norm": 0.009141940623521805, | |
| "learning_rate": 1.7523970671178795e-05, | |
| "loss": 0.0012, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.38071065989847713, | |
| "grad_norm": 0.009133282117545605, | |
| "learning_rate": 1.7467569091934575e-05, | |
| "loss": 0.0015, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.38917089678510997, | |
| "grad_norm": 0.5799979567527771, | |
| "learning_rate": 1.7411167512690357e-05, | |
| "loss": 0.0013, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.3976311336717428, | |
| "grad_norm": 0.04120843857526779, | |
| "learning_rate": 1.7354765933446137e-05, | |
| "loss": 0.0011, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.40609137055837563, | |
| "grad_norm": 0.01276948768645525, | |
| "learning_rate": 1.729836435420192e-05, | |
| "loss": 0.0012, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.41455160744500846, | |
| "grad_norm": 0.0076572224497795105, | |
| "learning_rate": 1.7241962774957702e-05, | |
| "loss": 0.0014, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.4230118443316413, | |
| "grad_norm": 0.008293437771499157, | |
| "learning_rate": 1.718556119571348e-05, | |
| "loss": 0.0009, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3546, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 149081805091296.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |