| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.945945945945946, | |
| "eval_steps": 500, | |
| "global_step": 460, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 0.00019976687691905393, | |
| "loss": 0.7107, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 0.235595703125, | |
| "learning_rate": 0.00019906859460363307, | |
| "loss": 0.6952, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6486486486486487, | |
| "grad_norm": 0.423583984375, | |
| "learning_rate": 0.00019790840876823232, | |
| "loss": 0.6967, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.3974609375, | |
| "learning_rate": 0.00019629172873477995, | |
| "loss": 0.7649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 0.327880859375, | |
| "learning_rate": 0.00019422609221188207, | |
| "loss": 0.7627, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2972972972972974, | |
| "grad_norm": 0.31689453125, | |
| "learning_rate": 0.00019172113015054532, | |
| "loss": 0.7527, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.5135135135135136, | |
| "grad_norm": 0.4111328125, | |
| "learning_rate": 0.0001887885218402375, | |
| "loss": 0.7536, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.7297297297297298, | |
| "grad_norm": 1.376953125, | |
| "learning_rate": 0.00018544194045464886, | |
| "loss": 0.7241, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.945945945945946, | |
| "grad_norm": 0.387939453125, | |
| "learning_rate": 0.0001816969893010442, | |
| "loss": 0.757, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "grad_norm": 0.366455078125, | |
| "learning_rate": 0.000177571129070442, | |
| "loss": 0.7339, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.3783783783783785, | |
| "grad_norm": 0.419677734375, | |
| "learning_rate": 0.00017308359642781242, | |
| "loss": 0.7005, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.5945945945945947, | |
| "grad_norm": 0.38818359375, | |
| "learning_rate": 0.00016825531432186543, | |
| "loss": 0.7167, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.810810810810811, | |
| "grad_norm": 0.452880859375, | |
| "learning_rate": 0.00016310879443260528, | |
| "loss": 0.7403, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.027027027027027, | |
| "grad_norm": 0.412841796875, | |
| "learning_rate": 0.00015766803221148673, | |
| "loss": 0.7248, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.2432432432432434, | |
| "grad_norm": 0.410400390625, | |
| "learning_rate": 0.00015195839500354335, | |
| "loss": 0.7208, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.4594594594594597, | |
| "grad_norm": 0.484619140625, | |
| "learning_rate": 0.00014600650377311522, | |
| "loss": 0.7079, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.6756756756756754, | |
| "grad_norm": 0.429443359375, | |
| "learning_rate": 0.00013984010898462416, | |
| "loss": 0.6847, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.891891891891892, | |
| "grad_norm": 0.437744140625, | |
| "learning_rate": 0.00013348796121709862, | |
| "loss": 0.7104, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.108108108108108, | |
| "grad_norm": 0.4140625, | |
| "learning_rate": 0.00012697967711570242, | |
| "loss": 0.682, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.324324324324325, | |
| "grad_norm": 0.484130859375, | |
| "learning_rate": 0.0001203456013052634, | |
| "loss": 0.6754, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.54054054054054, | |
| "grad_norm": 0.474853515625, | |
| "learning_rate": 0.00011361666490962468, | |
| "loss": 0.6671, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.756756756756757, | |
| "grad_norm": 0.474365234375, | |
| "learning_rate": 0.0001068242413364671, | |
| "loss": 0.6956, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.972972972972973, | |
| "grad_norm": 0.484130859375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6679, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 5.1891891891891895, | |
| "grad_norm": 0.47265625, | |
| "learning_rate": 9.317575866353292e-05, | |
| "loss": 0.6496, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.405405405405405, | |
| "grad_norm": 0.44482421875, | |
| "learning_rate": 8.638333509037536e-05, | |
| "loss": 0.6547, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.621621621621622, | |
| "grad_norm": 0.488037109375, | |
| "learning_rate": 7.965439869473664e-05, | |
| "loss": 0.6739, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.837837837837838, | |
| "grad_norm": 0.4658203125, | |
| "learning_rate": 7.302032288429756e-05, | |
| "loss": 0.6501, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.054054054054054, | |
| "grad_norm": 0.48974609375, | |
| "learning_rate": 6.651203878290139e-05, | |
| "loss": 0.6773, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 6.27027027027027, | |
| "grad_norm": 0.4775390625, | |
| "learning_rate": 6.015989101537586e-05, | |
| "loss": 0.6298, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 6.486486486486487, | |
| "grad_norm": 0.521484375, | |
| "learning_rate": 5.399349622688479e-05, | |
| "loss": 0.6464, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.702702702702703, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 4.804160499645667e-05, | |
| "loss": 0.6369, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 6.918918918918919, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 4.2331967788513295e-05, | |
| "loss": 0.6734, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 7.135135135135135, | |
| "grad_norm": 0.54736328125, | |
| "learning_rate": 3.689120556739475e-05, | |
| "loss": 0.6321, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 7.351351351351352, | |
| "grad_norm": 0.57080078125, | |
| "learning_rate": 3.174468567813461e-05, | |
| "loss": 0.6261, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 7.5675675675675675, | |
| "grad_norm": 0.47705078125, | |
| "learning_rate": 2.691640357218759e-05, | |
| "loss": 0.6196, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 7.783783783783784, | |
| "grad_norm": 0.5712890625, | |
| "learning_rate": 2.242887092955801e-05, | |
| "loss": 0.6505, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.50732421875, | |
| "learning_rate": 1.8303010698955804e-05, | |
| "loss": 0.6331, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 8.216216216216216, | |
| "grad_norm": 0.48046875, | |
| "learning_rate": 1.4558059545351143e-05, | |
| "loss": 0.6366, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 8.432432432432432, | |
| "grad_norm": 0.49951171875, | |
| "learning_rate": 1.1211478159762478e-05, | |
| "loss": 0.641, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 8.64864864864865, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 8.278869849454718e-06, | |
| "loss": 0.6233, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.864864864864865, | |
| "grad_norm": 0.50634765625, | |
| "learning_rate": 5.77390778811796e-06, | |
| "loss": 0.6185, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 9.08108108108108, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 3.7082712652200867e-06, | |
| "loss": 0.6224, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 9.297297297297296, | |
| "grad_norm": 0.487548828125, | |
| "learning_rate": 2.091591231767709e-06, | |
| "loss": 0.6054, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 9.513513513513514, | |
| "grad_norm": 0.5166015625, | |
| "learning_rate": 9.314053963669245e-07, | |
| "loss": 0.6299, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 9.72972972972973, | |
| "grad_norm": 0.4990234375, | |
| "learning_rate": 2.3312308094607382e-07, | |
| "loss": 0.6193, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 9.945945945945946, | |
| "grad_norm": 0.53271484375, | |
| "learning_rate": 0.0, | |
| "loss": 0.6231, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 9.945945945945946, | |
| "step": 460, | |
| "total_flos": 2.244679865204736e+16, | |
| "train_loss": 0.6764944273492565, | |
| "train_runtime": 411.2593, | |
| "train_samples_per_second": 4.498, | |
| "train_steps_per_second": 1.119 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 460, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 2.244679865204736e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |