| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.984771573604061, | |
| "eval_steps": 500, | |
| "global_step": 294, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10152284263959391, | |
| "grad_norm": 0.2823072373867035, | |
| "learning_rate": 3.9948625730435075e-05, | |
| "loss": 2.8273, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.20304568527918782, | |
| "grad_norm": 0.2618003189563751, | |
| "learning_rate": 3.969770236712935e-05, | |
| "loss": 2.6708, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.30456852791878175, | |
| "grad_norm": 0.24902400374412537, | |
| "learning_rate": 3.9240711835383766e-05, | |
| "loss": 2.495, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.40609137055837563, | |
| "grad_norm": 0.21406474709510803, | |
| "learning_rate": 3.858297520699212e-05, | |
| "loss": 2.3206, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5076142131979695, | |
| "grad_norm": 0.24804013967514038, | |
| "learning_rate": 3.7732150985966965e-05, | |
| "loss": 2.1775, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6091370558375635, | |
| "grad_norm": 0.28641432523727417, | |
| "learning_rate": 3.6698145935029794e-05, | |
| "loss": 1.9521, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7106598984771574, | |
| "grad_norm": 0.3936513066291809, | |
| "learning_rate": 3.5492999723996456e-05, | |
| "loss": 1.7139, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8121827411167513, | |
| "grad_norm": 0.2143162190914154, | |
| "learning_rate": 3.41307447431802e-05, | |
| "loss": 1.4854, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9137055837563451, | |
| "grad_norm": 0.08941923081874847, | |
| "learning_rate": 3.262724271410661e-05, | |
| "loss": 1.3727, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.015228426395939, | |
| "grad_norm": 0.08629459887742996, | |
| "learning_rate": 3.1e-05, | |
| "loss": 1.3856, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.116751269035533, | |
| "grad_norm": 0.07598450779914856, | |
| "learning_rate": 2.9267963766515236e-05, | |
| "loss": 1.3676, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.218274111675127, | |
| "grad_norm": 0.08433938026428223, | |
| "learning_rate": 2.7451301366163116e-05, | |
| "loss": 1.3437, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3197969543147208, | |
| "grad_norm": 0.06350907683372498, | |
| "learning_rate": 2.557116551521642e-05, | |
| "loss": 1.3879, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4213197969543148, | |
| "grad_norm": 0.07121391594409943, | |
| "learning_rate": 2.364944799731179e-05, | |
| "loss": 1.3591, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.5228426395939088, | |
| "grad_norm": 0.0733482763171196, | |
| "learning_rate": 2.1708524761554973e-05, | |
| "loss": 1.3315, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.6243654822335025, | |
| "grad_norm": 0.08874043822288513, | |
| "learning_rate": 1.9770995383136862e-05, | |
| "loss": 1.3264, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.7258883248730963, | |
| "grad_norm": 0.07142503559589386, | |
| "learning_rate": 1.7859419920108888e-05, | |
| "loss": 1.3342, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.8274111675126905, | |
| "grad_norm": 0.07405081391334534, | |
| "learning_rate": 1.5996056230285237e-05, | |
| "loss": 1.325, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.9289340101522843, | |
| "grad_norm": 0.07454005628824234, | |
| "learning_rate": 1.420260080688125e-05, | |
| "loss": 1.3448, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.030456852791878, | |
| "grad_norm": 0.07932838797569275, | |
| "learning_rate": 1.2499936150526519e-05, | |
| "loss": 1.3212, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.1319796954314723, | |
| "grad_norm": 0.07376272976398468, | |
| "learning_rate": 1.0907887619183308e-05, | |
| "loss": 1.3232, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.233502538071066, | |
| "grad_norm": 0.06934653967618942, | |
| "learning_rate": 9.444992587142751e-06, | |
| "loss": 1.3523, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.33502538071066, | |
| "grad_norm": 0.09688505530357361, | |
| "learning_rate": 8.128284600947997e-06, | |
| "loss": 1.3456, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.436548223350254, | |
| "grad_norm": 0.06206211820244789, | |
| "learning_rate": 6.973095045473124e-06, | |
| "loss": 1.2987, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.5380710659898478, | |
| "grad_norm": 0.08122861385345459, | |
| "learning_rate": 5.992874629503358e-06, | |
| "loss": 1.3153, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.6395939086294415, | |
| "grad_norm": 0.07479345053434372, | |
| "learning_rate": 5.199036769389357e-06, | |
| "loss": 1.2851, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.7411167512690353, | |
| "grad_norm": 0.07279635220766068, | |
| "learning_rate": 4.600824694373e-06, | |
| "loss": 1.322, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.8426395939086295, | |
| "grad_norm": 0.08008701354265213, | |
| "learning_rate": 4.205203820973785e-06, | |
| "loss": 1.2833, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.9441624365482233, | |
| "grad_norm": 0.08546874672174454, | |
| "learning_rate": 4.016780649598707e-06, | |
| "loss": 1.294, | |
| "step": 290 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 294, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.4706848609050624e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |