| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 185, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005405405405405406, | |
| "grad_norm": 61.001103964725324, | |
| "learning_rate": 1.0526315789473685e-06, | |
| "loss": 1.9097, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02702702702702703, | |
| "grad_norm": 35.97997402423919, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 1.7102, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 30.10156193198182, | |
| "learning_rate": 1.0526315789473684e-05, | |
| "loss": 1.5516, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08108108108108109, | |
| "grad_norm": 6.532111146208257, | |
| "learning_rate": 1.578947368421053e-05, | |
| "loss": 1.4536, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 4.983904851506608, | |
| "learning_rate": 1.999820922669738e-05, | |
| "loss": 1.4112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13513513513513514, | |
| "grad_norm": 3.8732866550483545, | |
| "learning_rate": 1.993559947963185e-05, | |
| "loss": 1.4056, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16216216216216217, | |
| "grad_norm": 3.0620367608079846, | |
| "learning_rate": 1.9784091409455728e-05, | |
| "loss": 1.4016, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1891891891891892, | |
| "grad_norm": 3.2352358324557167, | |
| "learning_rate": 1.9545040627715554e-05, | |
| "loss": 1.4128, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 3.022703286965415, | |
| "learning_rate": 1.9220586030376135e-05, | |
| "loss": 1.4148, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24324324324324326, | |
| "grad_norm": 2.8955611484982033, | |
| "learning_rate": 1.881363066014649e-05, | |
| "loss": 1.4159, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 2.8660620524615688, | |
| "learning_rate": 1.8327815731637612e-05, | |
| "loss": 1.42, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2972972972972973, | |
| "grad_norm": 2.632475843797219, | |
| "learning_rate": 1.7767488051760858e-05, | |
| "loss": 1.4078, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.32432432432432434, | |
| "grad_norm": 2.5436272914892872, | |
| "learning_rate": 1.713766112687139e-05, | |
| "loss": 1.4015, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.35135135135135137, | |
| "grad_norm": 2.431239149211266, | |
| "learning_rate": 1.644397030464877e-05, | |
| "loss": 1.3807, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3783783783783784, | |
| "grad_norm": 2.328539582829742, | |
| "learning_rate": 1.5692622352080662e-05, | |
| "loss": 1.3639, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.40540540540540543, | |
| "grad_norm": 2.708625235728292, | |
| "learning_rate": 1.4890339920698334e-05, | |
| "loss": 1.3836, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 2.4202434897618317, | |
| "learning_rate": 1.404430139595877e-05, | |
| "loss": 1.3823, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4594594594594595, | |
| "grad_norm": 2.243346482513894, | |
| "learning_rate": 1.316207666896824e-05, | |
| "loss": 1.3538, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4864864864864865, | |
| "grad_norm": 2.4109049967489433, | |
| "learning_rate": 1.2251559405226943e-05, | |
| "loss": 1.3503, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5135135135135135, | |
| "grad_norm": 2.242883116591874, | |
| "learning_rate": 1.1320896416417026e-05, | |
| "loss": 1.3562, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 2.1959662600808203, | |
| "learning_rate": 1.0378414767176706e-05, | |
| "loss": 1.3447, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5675675675675675, | |
| "grad_norm": 2.2348646553535714, | |
| "learning_rate": 9.43254726906926e-06, | |
| "loss": 1.3398, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.5945945945945946, | |
| "grad_norm": 2.21405256524929, | |
| "learning_rate": 8.491757028386262e-06, | |
| "loss": 1.3383, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6216216216216216, | |
| "grad_norm": 2.1710850419967263, | |
| "learning_rate": 7.564461722890082e-06, | |
| "loss": 1.3271, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.6486486486486487, | |
| "grad_norm": 2.1752417729097338, | |
| "learning_rate": 6.6589582850261025e-06, | |
| "loss": 1.3176, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6756756756756757, | |
| "grad_norm": 2.1322248363189686, | |
| "learning_rate": 5.78334866549816e-06, | |
| "loss": 1.321, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7027027027027027, | |
| "grad_norm": 2.1516864548066525, | |
| "learning_rate": 4.9454673414341945e-06, | |
| "loss": 1.3074, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7297297297297297, | |
| "grad_norm": 2.04797883118049, | |
| "learning_rate": 4.152811217759529e-06, | |
| "loss": 1.3123, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7567567567567568, | |
| "grad_norm": 2.1202023783270367, | |
| "learning_rate": 3.4124725489820643e-06, | |
| "loss": 1.3026, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7837837837837838, | |
| "grad_norm": 2.1203746539007158, | |
| "learning_rate": 2.7310754815685627e-06, | |
| "loss": 1.2838, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8108108108108109, | |
| "grad_norm": 2.058016060238832, | |
| "learning_rate": 2.114716784696342e-06, | |
| "loss": 1.2805, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8378378378378378, | |
| "grad_norm": 2.072702697896577, | |
| "learning_rate": 1.5689112996891576e-06, | |
| "loss": 1.276, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 2.070358297476048, | |
| "learning_rate": 1.0985425962260342e-06, | |
| "loss": 1.2768, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8918918918918919, | |
| "grad_norm": 1.993421902652665, | |
| "learning_rate": 7.078192768243486e-07, | |
| "loss": 1.2755, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.918918918918919, | |
| "grad_norm": 2.02321205406663, | |
| "learning_rate": 4.0023732056077235e-07, | |
| "loss": 1.276, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9459459459459459, | |
| "grad_norm": 2.0216958269361154, | |
| "learning_rate": 1.7854880295797406e-07, | |
| "loss": 1.2694, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.972972972972973, | |
| "grad_norm": 2.0002791761840157, | |
| "learning_rate": 4.473727191441124e-08, | |
| "loss": 1.2669, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.9847900492979156, | |
| "learning_rate": 0.0, | |
| "loss": 1.2583, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.2626361846923828, | |
| "eval_runtime": 57.4547, | |
| "eval_samples_per_second": 11.47, | |
| "eval_steps_per_second": 0.366, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 185, | |
| "total_flos": 19367618150400.0, | |
| "train_loss": 1.3619260220914273, | |
| "train_runtime": 1878.7186, | |
| "train_samples_per_second": 3.148, | |
| "train_steps_per_second": 0.098 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 185, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 800, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 19367618150400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |