| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 50, |
| "global_step": 114, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13157894736842105, |
| "grad_norm": 18.609325408935547, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 3.100375747680664, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2631578947368421, |
| "grad_norm": 7.61398458480835, |
| "learning_rate": 4.990486745229364e-05, |
| "loss": 0.7916615962982178, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.39473684210526316, |
| "grad_norm": 21.08771324157715, |
| "learning_rate": 4.9326121764495596e-05, |
| "loss": 0.2971171855926514, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.5263157894736842, |
| "grad_norm": 3.2525250911712646, |
| "learning_rate": 4.823368810567056e-05, |
| "loss": 0.20022857189178467, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.6578947368421053, |
| "grad_norm": 2.770566463470459, |
| "learning_rate": 4.665063509461097e-05, |
| "loss": 0.1185336947441101, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.7894736842105263, |
| "grad_norm": 0.9369506239891052, |
| "learning_rate": 4.4610391622989396e-05, |
| "loss": 0.05945125222206116, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.9210526315789473, |
| "grad_norm": 0.7369817495346069, |
| "learning_rate": 4.215604094671835e-05, |
| "loss": 0.04002172350883484, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.0526315789473684, |
| "grad_norm": 0.9492254257202148, |
| "learning_rate": 3.933941090877615e-05, |
| "loss": 0.020497632026672364, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.1842105263157894, |
| "grad_norm": 0.3728443682193756, |
| "learning_rate": 3.621997950501156e-05, |
| "loss": 0.012034893035888672, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.3157894736842106, |
| "grad_norm": 0.010420924983918667, |
| "learning_rate": 3.2863618903790346e-05, |
| "loss": 0.0003852380206808448, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.3157894736842106, |
| "eval_loss": 8.908205199986696e-05, |
| "eval_runtime": 0.2398, |
| "eval_samples_per_second": 1042.674, |
| "eval_steps_per_second": 33.366, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.4473684210526316, |
| "grad_norm": 0.0057847267016768456, |
| "learning_rate": 2.9341204441673266e-05, |
| "loss": 6.551978876814246e-05, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.5789473684210527, |
| "grad_norm": 0.004835825879126787, |
| "learning_rate": 2.5727117968577784e-05, |
| "loss": 4.137617652304471e-05, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.7105263157894737, |
| "grad_norm": 0.00434767734259367, |
| "learning_rate": 2.2097677146869242e-05, |
| "loss": 3.404428716748953e-05, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.8421052631578947, |
| "grad_norm": 0.004089520312845707, |
| "learning_rate": 1.852952387243698e-05, |
| "loss": 3.0071102082729338e-05, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.973684210526316, |
| "grad_norm": 0.0039205304346978664, |
| "learning_rate": 1.509800584902108e-05, |
| "loss": 2.7886469615623356e-05, |
| "step": 75 |
| }, |
| { |
| "epoch": 2.1052631578947367, |
| "grad_norm": 0.003841632977128029, |
| "learning_rate": 1.1875585491636e-05, |
| "loss": 2.677349839359522e-05, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.236842105263158, |
| "grad_norm": 0.0037360202986747026, |
| "learning_rate": 8.930309757836517e-06, |
| "loss": 2.9993365751579403e-05, |
| "step": 85 |
| }, |
| { |
| "epoch": 2.3684210526315788, |
| "grad_norm": 0.003737943945452571, |
| "learning_rate": 6.324373218975105e-06, |
| "loss": 2.560944703873247e-05, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.003710727905854583, |
| "learning_rate": 4.112804714676594e-06, |
| "loss": 2.5494518922641873e-05, |
| "step": 95 |
| }, |
| { |
| "epoch": 2.6315789473684212, |
| "grad_norm": 0.0036761967930942774, |
| "learning_rate": 2.3423053240837515e-06, |
| "loss": 2.499283873476088e-05, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.6315789473684212, |
| "eval_loss": 2.4945922632468864e-05, |
| "eval_runtime": 0.2256, |
| "eval_samples_per_second": 1108.295, |
| "eval_steps_per_second": 35.465, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.763157894736842, |
| "grad_norm": 0.0036698589101433754, |
| "learning_rate": 1.0502621921127776e-06, |
| "loss": 2.4992326507344843e-05, |
| "step": 105 |
| }, |
| { |
| "epoch": 2.8947368421052633, |
| "grad_norm": 0.0036843419075012207, |
| "learning_rate": 2.6395903547638825e-07, |
| "loss": 2.493572246748954e-05, |
| "step": 110 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 2.4861023121047765e-05, |
| "eval_runtime": 0.2248, |
| "eval_samples_per_second": 1112.214, |
| "eval_steps_per_second": 35.591, |
| "step": 114 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 114, |
| "total_flos": 1.743788665995264e+16, |
| "train_loss": 0.2035398631068937, |
| "train_runtime": 208.2933, |
| "train_samples_per_second": 68.413, |
| "train_steps_per_second": 0.547 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 114, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.743788665995264e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
