| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9948186528497409, | |
| "eval_steps": 100, | |
| "global_step": 168, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029607698001480384, | |
| "grad_norm": 2.3427891450842355, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 1.0993, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05921539600296077, | |
| "grad_norm": 1.638241993747605, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.0402, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08882309400444116, | |
| "grad_norm": 0.8970481588482149, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.9533, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11843079200592153, | |
| "grad_norm": 0.6126224631372397, | |
| "learning_rate": 1.9980527694749952e-05, | |
| "loss": 0.8922, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14803849000740193, | |
| "grad_norm": 0.5491637741037821, | |
| "learning_rate": 1.986180478852149e-05, | |
| "loss": 0.8551, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17764618800888232, | |
| "grad_norm": 0.4357332212949219, | |
| "learning_rate": 1.963645895935632e-05, | |
| "loss": 0.8282, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20725388601036268, | |
| "grad_norm": 0.3870290405518921, | |
| "learning_rate": 1.930692657985482e-05, | |
| "loss": 0.8229, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23686158401184307, | |
| "grad_norm": 0.41071978450812635, | |
| "learning_rate": 1.887677045685188e-05, | |
| "loss": 0.8225, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2664692820133235, | |
| "grad_norm": 0.35511835037971484, | |
| "learning_rate": 1.8350641311400813e-05, | |
| "loss": 0.8073, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.29607698001480387, | |
| "grad_norm": 0.34562914008715157, | |
| "learning_rate": 1.773422749654988e-05, | |
| "loss": 0.7977, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32568467801628426, | |
| "grad_norm": 0.38429745030506335, | |
| "learning_rate": 1.7034193496547903e-05, | |
| "loss": 0.7877, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.35529237601776464, | |
| "grad_norm": 0.38450100811350485, | |
| "learning_rate": 1.6258107872407376e-05, | |
| "loss": 0.7982, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38490007401924503, | |
| "grad_norm": 0.3508167601846127, | |
| "learning_rate": 1.5414361432856475e-05, | |
| "loss": 0.7722, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.41450777202072536, | |
| "grad_norm": 0.354273236485806, | |
| "learning_rate": 1.4512076515391375e-05, | |
| "loss": 0.7741, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.44411547002220575, | |
| "grad_norm": 0.3435732479373877, | |
| "learning_rate": 1.356100835825547e-05, | |
| "loss": 0.7852, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.47372316802368614, | |
| "grad_norm": 0.3554552572459275, | |
| "learning_rate": 1.257143962968246e-05, | |
| "loss": 0.7667, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5033308660251665, | |
| "grad_norm": 0.37807154489345807, | |
| "learning_rate": 1.155406925472205e-05, | |
| "loss": 0.7707, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.532938564026647, | |
| "grad_norm": 0.3667445569072502, | |
| "learning_rate": 1.0519896741619803e-05, | |
| "loss": 0.7701, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5625462620281273, | |
| "grad_norm": 0.3813236840767762, | |
| "learning_rate": 9.480103258380198e-06, | |
| "loss": 0.7772, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5921539600296077, | |
| "grad_norm": 0.34559010442801097, | |
| "learning_rate": 8.445930745277953e-06, | |
| "loss": 0.7531, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5921539600296077, | |
| "eval_loss": 0.7882063388824463, | |
| "eval_runtime": 1.6572, | |
| "eval_samples_per_second": 77.237, | |
| "eval_steps_per_second": 2.414, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6217616580310881, | |
| "grad_norm": 0.341364069372392, | |
| "learning_rate": 7.428560370317542e-06, | |
| "loss": 0.7571, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6513693560325685, | |
| "grad_norm": 0.3559969343392935, | |
| "learning_rate": 6.438991641744531e-06, | |
| "loss": 0.7682, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6809770540340488, | |
| "grad_norm": 0.3161514819141605, | |
| "learning_rate": 5.487923484608629e-06, | |
| "loss": 0.7625, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7105847520355293, | |
| "grad_norm": 0.30339451601959244, | |
| "learning_rate": 4.5856385671435285e-06, | |
| "loss": 0.7515, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7401924500370096, | |
| "grad_norm": 0.35261640845743664, | |
| "learning_rate": 3.7418921275926245e-06, | |
| "loss": 0.7539, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7698001480384901, | |
| "grad_norm": 0.3193239804674359, | |
| "learning_rate": 2.965806503452098e-06, | |
| "loss": 0.7556, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7994078460399704, | |
| "grad_norm": 0.32912058451560244, | |
| "learning_rate": 2.265772503450122e-06, | |
| "loss": 0.7586, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8290155440414507, | |
| "grad_norm": 0.303685802235117, | |
| "learning_rate": 1.6493586885991908e-06, | |
| "loss": 0.75, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8586232420429312, | |
| "grad_norm": 0.3173990670917867, | |
| "learning_rate": 1.1232295431481222e-06, | |
| "loss": 0.7568, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8882309400444115, | |
| "grad_norm": 0.3010954114203951, | |
| "learning_rate": 6.930734201451817e-07, | |
| "loss": 0.7668, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9178386380458919, | |
| "grad_norm": 0.30232823482832394, | |
| "learning_rate": 3.635410406436857e-07, | |
| "loss": 0.7616, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9474463360473723, | |
| "grad_norm": 0.28964694770453414, | |
| "learning_rate": 1.3819521147851122e-07, | |
| "loss": 0.7609, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9770540340488527, | |
| "grad_norm": 0.28146626492833826, | |
| "learning_rate": 1.947230525005006e-08, | |
| "loss": 0.7448, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9948186528497409, | |
| "step": 168, | |
| "total_flos": 76517996494848.0, | |
| "train_loss": 0.8023917121546609, | |
| "train_runtime": 1111.3885, | |
| "train_samples_per_second": 19.444, | |
| "train_steps_per_second": 0.151 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 168, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 76517996494848.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |