| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 64, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03125, | |
| "grad_norm": 0.02201350385433546, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 0.1659, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 0.017631106732118082, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.1412, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 0.024585057808428103, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.177, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 0.020959913317261634, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.162, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "grad_norm": 0.03942590872310735, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.1743, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 0.02429143191363862, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.1559, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21875, | |
| "grad_norm": 0.0273889533006628, | |
| "learning_rate": 5e-05, | |
| "loss": 0.172, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.02818102247404862, | |
| "learning_rate": 4.996203791083291e-05, | |
| "loss": 0.1581, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.28125, | |
| "grad_norm": 0.026890304317485954, | |
| "learning_rate": 4.984826693294874e-05, | |
| "loss": 0.1446, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 0.024124645018285425, | |
| "learning_rate": 4.965903258506806e-05, | |
| "loss": 0.1285, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34375, | |
| "grad_norm": 0.02714853375981395, | |
| "learning_rate": 4.9394909565685894e-05, | |
| "loss": 0.1268, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 0.023663489752588116, | |
| "learning_rate": 4.905670000773126e-05, | |
| "loss": 0.1162, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.40625, | |
| "grad_norm": 0.021188305364377307, | |
| "learning_rate": 4.864543104251587e-05, | |
| "loss": 0.0981, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4375, | |
| "grad_norm": 0.0194658709087334, | |
| "learning_rate": 4.8162351680370044e-05, | |
| "loss": 0.0931, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.46875, | |
| "grad_norm": 0.027887400760197377, | |
| "learning_rate": 4.760892901743944e-05, | |
| "loss": 0.1164, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.020592628860903846, | |
| "learning_rate": 4.698684378016222e-05, | |
| "loss": 0.0909, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.53125, | |
| "grad_norm": 0.023118079355411377, | |
| "learning_rate": 4.629798522095818e-05, | |
| "loss": 0.0982, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 0.021631048551424618, | |
| "learning_rate": 4.554444538063113e-05, | |
| "loss": 0.0914, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.59375, | |
| "grad_norm": 0.02197341722144493, | |
| "learning_rate": 4.4728512734909844e-05, | |
| "loss": 0.0877, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.02513334409511662, | |
| "learning_rate": 4.385266524442241e-05, | |
| "loss": 0.0844, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.65625, | |
| "grad_norm": 0.019504354913408805, | |
| "learning_rate": 4.2919562829211283e-05, | |
| "loss": 0.0697, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6875, | |
| "grad_norm": 0.02450011364794352, | |
| "learning_rate": 4.193203929064353e-05, | |
| "loss": 0.0809, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.71875, | |
| "grad_norm": 0.016983510438394432, | |
| "learning_rate": 4.089309370524921e-05, | |
| "loss": 0.0687, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.018949190562219987, | |
| "learning_rate": 3.9805881316624506e-05, | |
| "loss": 0.0635, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.78125, | |
| "grad_norm": 0.02287205018712244, | |
| "learning_rate": 3.867370395306068e-05, | |
| "loss": 0.0612, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8125, | |
| "grad_norm": 0.020819928479040052, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0546, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.84375, | |
| "grad_norm": 0.020433744518841782, | |
| "learning_rate": 3.628833395777224e-05, | |
| "loss": 0.0568, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.875, | |
| "grad_norm": 0.02452466104170243, | |
| "learning_rate": 3.504238561632424e-05, | |
| "loss": 0.0589, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.90625, | |
| "grad_norm": 0.020359458235425835, | |
| "learning_rate": 3.376593887981887e-05, | |
| "loss": 0.0537, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 0.02138342331508777, | |
| "learning_rate": 3.246287027504237e-05, | |
| "loss": 0.0518, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.96875, | |
| "grad_norm": 0.02719350877019731, | |
| "learning_rate": 3.1137137178519985e-05, | |
| "loss": 0.0541, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.021133830371054575, | |
| "learning_rate": 2.9792765798093465e-05, | |
| "loss": 0.0498, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.03125, | |
| "grad_norm": 0.021463434498612006, | |
| "learning_rate": 2.8433838945460205e-05, | |
| "loss": 0.0471, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0625, | |
| "grad_norm": 0.021298232872446428, | |
| "learning_rate": 2.7064483636808313e-05, | |
| "loss": 0.0456, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.09375, | |
| "grad_norm": 0.018723821222198695, | |
| "learning_rate": 2.5688858559204053e-05, | |
| "loss": 0.0418, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.125, | |
| "grad_norm": 0.021776653322658348, | |
| "learning_rate": 2.4311141440795953e-05, | |
| "loss": 0.0447, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.15625, | |
| "grad_norm": 0.02142676692573012, | |
| "learning_rate": 2.2935516363191693e-05, | |
| "loss": 0.0379, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1875, | |
| "grad_norm": 0.021725917876407617, | |
| "learning_rate": 2.1566161054539798e-05, | |
| "loss": 0.0385, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.21875, | |
| "grad_norm": 0.026038084021492873, | |
| "learning_rate": 2.0207234201906547e-05, | |
| "loss": 0.0393, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.020403365339063353, | |
| "learning_rate": 1.8862862821480025e-05, | |
| "loss": 0.0334, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.28125, | |
| "grad_norm": 0.022595431121427985, | |
| "learning_rate": 1.7537129724957642e-05, | |
| "loss": 0.0349, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3125, | |
| "grad_norm": 0.020209556742957525, | |
| "learning_rate": 1.6234061120181142e-05, | |
| "loss": 0.0337, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.34375, | |
| "grad_norm": 0.01852736319071734, | |
| "learning_rate": 1.495761438367577e-05, | |
| "loss": 0.0327, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.375, | |
| "grad_norm": 0.028150371453568402, | |
| "learning_rate": 1.3711666042227772e-05, | |
| "loss": 0.036, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.40625, | |
| "grad_norm": 0.01893692320014887, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.0323, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4375, | |
| "grad_norm": 0.02388777329620401, | |
| "learning_rate": 1.1326296046939333e-05, | |
| "loss": 0.0327, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.46875, | |
| "grad_norm": 0.0162514110913781, | |
| "learning_rate": 1.0194118683375503e-05, | |
| "loss": 0.0297, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.01783274996153917, | |
| "learning_rate": 9.106906294750805e-06, | |
| "loss": 0.0276, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.53125, | |
| "grad_norm": 0.018240197689883848, | |
| "learning_rate": 8.067960709356478e-06, | |
| "loss": 0.0272, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "grad_norm": 0.022294167468922533, | |
| "learning_rate": 7.080437170788723e-06, | |
| "loss": 0.0272, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.59375, | |
| "grad_norm": 0.021538953724365907, | |
| "learning_rate": 6.147334755577596e-06, | |
| "loss": 0.0283, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.625, | |
| "grad_norm": 0.01940459958267202, | |
| "learning_rate": 5.271487265090163e-06, | |
| "loss": 0.0295, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.65625, | |
| "grad_norm": 0.02542383499082452, | |
| "learning_rate": 4.4555546193688735e-06, | |
| "loss": 0.0305, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.6875, | |
| "grad_norm": 0.015956943402349977, | |
| "learning_rate": 3.7020147790418263e-06, | |
| "loss": 0.0285, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.71875, | |
| "grad_norm": 0.015680054037671243, | |
| "learning_rate": 3.013156219837776e-06, | |
| "loss": 0.0257, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.01565972558143856, | |
| "learning_rate": 2.391070982560564e-06, | |
| "loss": 0.0258, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.78125, | |
| "grad_norm": 0.015976607813594494, | |
| "learning_rate": 1.837648319629956e-06, | |
| "loss": 0.03, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.8125, | |
| "grad_norm": 0.017413020744993825, | |
| "learning_rate": 1.3545689574841342e-06, | |
| "loss": 0.0237, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.84375, | |
| "grad_norm": 0.013556961343305363, | |
| "learning_rate": 9.432999922687396e-07, | |
| "loss": 0.0277, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 0.016214572350486636, | |
| "learning_rate": 6.050904343141095e-07, | |
| "loss": 0.0295, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.90625, | |
| "grad_norm": 0.018417588061946103, | |
| "learning_rate": 3.4096741493194197e-07, | |
| "loss": 0.0291, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.9375, | |
| "grad_norm": 0.016665497738754777, | |
| "learning_rate": 1.517330670512629e-07, | |
| "loss": 0.0225, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.96875, | |
| "grad_norm": 0.01680460892573064, | |
| "learning_rate": 3.796208916709565e-08, | |
| "loss": 0.0268, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.022852104476789446, | |
| "learning_rate": 0.0, | |
| "loss": 0.0283, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 64, | |
| "total_flos": 80354865971200.0, | |
| "train_loss": 0.0, | |
| "train_runtime": 1.2832, | |
| "train_samples_per_second": 389.65, | |
| "train_steps_per_second": 49.875 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 64, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 80354865971200.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |