| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.984709480122324, | |
| "eval_steps": 500, | |
| "global_step": 366, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08154943934760449, | |
| "grad_norm": 0.660578191280365, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 0.7127, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16309887869520898, | |
| "grad_norm": 0.7271870374679565, | |
| "learning_rate": 5.405405405405406e-05, | |
| "loss": 0.7168, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24464831804281345, | |
| "grad_norm": 0.7715198993682861, | |
| "learning_rate": 8.108108108108109e-05, | |
| "loss": 0.5257, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32619775739041795, | |
| "grad_norm": 0.5615158081054688, | |
| "learning_rate": 9.997948550797227e-05, | |
| "loss": 0.4019, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4077471967380224, | |
| "grad_norm": 0.4358239769935608, | |
| "learning_rate": 9.961525153583327e-05, | |
| "loss": 0.3371, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4892966360856269, | |
| "grad_norm": 0.5554934740066528, | |
| "learning_rate": 9.879896064123961e-05, | |
| "loss": 0.4258, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5708460754332314, | |
| "grad_norm": 0.5321815609931946, | |
| "learning_rate": 9.753805025397779e-05, | |
| "loss": 0.375, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6523955147808359, | |
| "grad_norm": 0.42357194423675537, | |
| "learning_rate": 9.584400884284545e-05, | |
| "loss": 0.368, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "grad_norm": 0.502548098564148, | |
| "learning_rate": 9.373227124134888e-05, | |
| "loss": 0.365, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8154943934760448, | |
| "grad_norm": 1.1985193490982056, | |
| "learning_rate": 9.122207801708802e-05, | |
| "loss": 0.4522, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8970438328236493, | |
| "grad_norm": 0.5025231242179871, | |
| "learning_rate": 8.833630016614976e-05, | |
| "loss": 0.3663, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9785932721712538, | |
| "grad_norm": 0.3899594247341156, | |
| "learning_rate": 8.510123072976239e-05, | |
| "loss": 0.3597, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0601427115188584, | |
| "grad_norm": 0.4278734028339386, | |
| "learning_rate": 8.154634523184388e-05, | |
| "loss": 0.3343, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.1416921508664628, | |
| "grad_norm": 0.5638087391853333, | |
| "learning_rate": 7.770403312015721e-05, | |
| "loss": 0.3215, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2232415902140672, | |
| "grad_norm": 0.5326379537582397, | |
| "learning_rate": 7.360930265797935e-05, | |
| "loss": 0.3058, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.3047910295616718, | |
| "grad_norm": 0.5562155842781067, | |
| "learning_rate": 6.929946195508932e-05, | |
| "loss": 0.3273, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3863404689092762, | |
| "grad_norm": 0.6649357080459595, | |
| "learning_rate": 6.481377904428171e-05, | |
| "loss": 0.3461, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.4678899082568808, | |
| "grad_norm": 0.5380542278289795, | |
| "learning_rate": 6.019312410053286e-05, | |
| "loss": 0.3111, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.5494393476044852, | |
| "grad_norm": 0.6011327505111694, | |
| "learning_rate": 5.547959706265068e-05, | |
| "loss": 0.287, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6309887869520896, | |
| "grad_norm": 0.5643779635429382, | |
| "learning_rate": 5.0716144050239375e-05, | |
| "loss": 0.3202, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.7125382262996942, | |
| "grad_norm": 0.5761425495147705, | |
| "learning_rate": 4.594616607090028e-05, | |
| "loss": 0.3272, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.7940876656472988, | |
| "grad_norm": 0.7082852125167847, | |
| "learning_rate": 4.121312358283463e-05, | |
| "loss": 0.3277, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.8756371049949032, | |
| "grad_norm": 0.41143250465393066, | |
| "learning_rate": 3.656014051577713e-05, | |
| "loss": 0.3057, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.9571865443425076, | |
| "grad_norm": 0.408113569021225, | |
| "learning_rate": 3.202961135812437e-05, | |
| "loss": 0.3117, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.038735983690112, | |
| "grad_norm": 0.47071775794029236, | |
| "learning_rate": 2.7662814890184818e-05, | |
| "loss": 0.3175, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.120285423037717, | |
| "grad_norm": 0.592940092086792, | |
| "learning_rate": 2.3499538082923606e-05, | |
| "loss": 0.2854, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.2018348623853212, | |
| "grad_norm": 0.569543182849884, | |
| "learning_rate": 1.9577713588953795e-05, | |
| "loss": 0.254, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.2833843017329256, | |
| "grad_norm": 0.6796756982803345, | |
| "learning_rate": 1.5933074128684332e-05, | |
| "loss": 0.2637, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.36493374108053, | |
| "grad_norm": 0.5621957182884216, | |
| "learning_rate": 1.2598826920598772e-05, | |
| "loss": 0.2521, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.4464831804281344, | |
| "grad_norm": 0.708060085773468, | |
| "learning_rate": 9.605351122011309e-06, | |
| "loss": 0.2497, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.528032619775739, | |
| "grad_norm": 0.583659827709198, | |
| "learning_rate": 6.979921036993042e-06, | |
| "loss": 0.2822, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.6095820591233436, | |
| "grad_norm": 0.6250892281532288, | |
| "learning_rate": 4.746457613389904e-06, | |
| "loss": 0.2675, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.691131498470948, | |
| "grad_norm": 0.6775749325752258, | |
| "learning_rate": 2.925310493105099e-06, | |
| "loss": 0.2996, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.7726809378185524, | |
| "grad_norm": 0.8949369192123413, | |
| "learning_rate": 1.5330726014397668e-06, | |
| "loss": 0.3064, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.8542303771661572, | |
| "grad_norm": 0.6756715178489685, | |
| "learning_rate": 5.824289648152126e-07, | |
| "loss": 0.2577, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.9357798165137616, | |
| "grad_norm": 0.4671032130718231, | |
| "learning_rate": 8.204113433559201e-08, | |
| "loss": 0.2614, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.984709480122324, | |
| "step": 366, | |
| "total_flos": 8710805828812800.0, | |
| "train_loss": 0.3467143246384918, | |
| "train_runtime": 5692.8921, | |
| "train_samples_per_second": 0.517, | |
| "train_steps_per_second": 0.064 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 366, | |
| "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": 8710805828812800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |