| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 285, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 6.543553342182306, | |
| "learning_rate": 3.448275862068966e-06, | |
| "loss": 1.8558, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 3.5154288610740023, | |
| "learning_rate": 6.896551724137932e-06, | |
| "loss": 1.4458, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 2.778543537236469, | |
| "learning_rate": 9.999623509195724e-06, | |
| "loss": 1.2409, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 2.5059789149316045, | |
| "learning_rate": 9.9545131771389e-06, | |
| "loss": 1.1153, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 2.33426924896289, | |
| "learning_rate": 9.834882355224261e-06, | |
| "loss": 1.0284, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 2.238033736817208, | |
| "learning_rate": 9.64253040236608e-06, | |
| "loss": 0.9903, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24561403508771928, | |
| "grad_norm": 2.172103858227053, | |
| "learning_rate": 9.380350470977033e-06, | |
| "loss": 0.9464, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 2.0775067726943957, | |
| "learning_rate": 9.052285991262975e-06, | |
| "loss": 0.9232, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 2.036467828021783, | |
| "learning_rate": 8.663271358362064e-06, | |
| "loss": 0.8927, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 2.092139892865783, | |
| "learning_rate": 8.219157714448957e-06, | |
| "loss": 0.8748, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.38596491228070173, | |
| "grad_norm": 2.354936030454241, | |
| "learning_rate": 7.726624942110233e-06, | |
| "loss": 0.8712, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 2.4480552576537313, | |
| "learning_rate": 7.193081192692639e-06, | |
| "loss": 0.8413, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.45614035087719296, | |
| "grad_norm": 2.225961040994733, | |
| "learning_rate": 6.626551460811316e-06, | |
| "loss": 0.8245, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.49122807017543857, | |
| "grad_norm": 2.2280118933835227, | |
| "learning_rate": 6.035556880961093e-06, | |
| "loss": 0.7995, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 2.1092585894132694, | |
| "learning_rate": 5.4289865617222005e-06, | |
| "loss": 0.7919, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 2.2317869413724947, | |
| "learning_rate": 4.815963885293206e-06, | |
| "loss": 0.794, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5964912280701754, | |
| "grad_norm": 2.1555810331504976, | |
| "learning_rate": 4.205709283330694e-06, | |
| "loss": 0.7713, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 2.0442009159494785, | |
| "learning_rate": 3.6074015530747354e-06, | |
| "loss": 0.7775, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 2.113365321780909, | |
| "learning_rate": 3.0300397996947604e-06, | |
| "loss": 0.7515, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 2.1674953587420838, | |
| "learning_rate": 2.482308081371413e-06, | |
| "loss": 0.765, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 2.2304080548395917, | |
| "learning_rate": 1.972444792978373e-06, | |
| "loss": 0.7528, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7719298245614035, | |
| "grad_norm": 2.40752310761597, | |
| "learning_rate": 1.508118752955136e-06, | |
| "loss": 0.7396, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8070175438596491, | |
| "grad_norm": 2.117568701663915, | |
| "learning_rate": 1.0963138571395277e-06, | |
| "loss": 0.7408, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 2.919503306825211, | |
| "learning_rate": 7.43224034473674e-07, | |
| "loss": 0.7486, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8771929824561403, | |
| "grad_norm": 2.125280125804679, | |
| "learning_rate": 4.5416008454738813e-07, | |
| "loss": 0.7359, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9122807017543859, | |
| "grad_norm": 2.066124288511879, | |
| "learning_rate": 2.3346979822903071e-07, | |
| "loss": 0.7375, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 1.9772889405004763, | |
| "learning_rate": 8.447256284391858e-08, | |
| "loss": 0.7245, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "grad_norm": 1.9570228116416033, | |
| "learning_rate": 9.409435499254105e-09, | |
| "loss": 0.7378, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 285, | |
| "total_flos": 1.4819175628485427e+17, | |
| "train_loss": 0.8990087810315583, | |
| "train_runtime": 350.8438, | |
| "train_samples_per_second": 103.861, | |
| "train_steps_per_second": 0.812 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 285, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1.4819175628485427e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |