| { | |
| "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": 0.29335439463795626, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 1.0993, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05921539600296077, | |
| "grad_norm": 0.24974276882783836, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.0434, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08882309400444116, | |
| "grad_norm": 0.13249460225804482, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.9668, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11843079200592153, | |
| "grad_norm": 0.09803049524347336, | |
| "learning_rate": 1.9980527694749952e-05, | |
| "loss": 0.9077, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14803849000740193, | |
| "grad_norm": 0.07618540921622716, | |
| "learning_rate": 1.986180478852149e-05, | |
| "loss": 0.8708, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17764618800888232, | |
| "grad_norm": 0.06017940731234282, | |
| "learning_rate": 1.963645895935632e-05, | |
| "loss": 0.8417, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20725388601036268, | |
| "grad_norm": 0.05030045847341557, | |
| "learning_rate": 1.930692657985482e-05, | |
| "loss": 0.8355, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23686158401184307, | |
| "grad_norm": 0.04490192945997187, | |
| "learning_rate": 1.887677045685188e-05, | |
| "loss": 0.8342, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2664692820133235, | |
| "grad_norm": 0.04289421891660055, | |
| "learning_rate": 1.8350641311400813e-05, | |
| "loss": 0.8182, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.29607698001480387, | |
| "grad_norm": 0.042583173233877836, | |
| "learning_rate": 1.773422749654988e-05, | |
| "loss": 0.8081, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32568467801628426, | |
| "grad_norm": 0.042418491223949785, | |
| "learning_rate": 1.7034193496547903e-05, | |
| "loss": 0.7974, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.35529237601776464, | |
| "grad_norm": 0.04318659192859987, | |
| "learning_rate": 1.6258107872407376e-05, | |
| "loss": 0.8074, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38490007401924503, | |
| "grad_norm": 0.04186212190455867, | |
| "learning_rate": 1.5414361432856475e-05, | |
| "loss": 0.7811, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.41450777202072536, | |
| "grad_norm": 0.03891429842772997, | |
| "learning_rate": 1.4512076515391375e-05, | |
| "loss": 0.7829, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.44411547002220575, | |
| "grad_norm": 0.043245677806225846, | |
| "learning_rate": 1.356100835825547e-05, | |
| "loss": 0.7939, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.47372316802368614, | |
| "grad_norm": 0.0417510435796824, | |
| "learning_rate": 1.257143962968246e-05, | |
| "loss": 0.7752, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5033308660251665, | |
| "grad_norm": 0.04184839517393442, | |
| "learning_rate": 1.155406925472205e-05, | |
| "loss": 0.7791, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.532938564026647, | |
| "grad_norm": 0.04114645929545094, | |
| "learning_rate": 1.0519896741619803e-05, | |
| "loss": 0.7783, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5625462620281273, | |
| "grad_norm": 0.041770371505857336, | |
| "learning_rate": 9.480103258380198e-06, | |
| "loss": 0.7855, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5921539600296077, | |
| "grad_norm": 0.04114281633366516, | |
| "learning_rate": 8.445930745277953e-06, | |
| "loss": 0.7612, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5921539600296077, | |
| "eval_loss": 0.7964568138122559, | |
| "eval_runtime": 1.3496, | |
| "eval_samples_per_second": 94.841, | |
| "eval_steps_per_second": 2.964, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6217616580310881, | |
| "grad_norm": 0.040839116887339516, | |
| "learning_rate": 7.428560370317542e-06, | |
| "loss": 0.7651, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6513693560325685, | |
| "grad_norm": 0.0398495836348172, | |
| "learning_rate": 6.438991641744531e-06, | |
| "loss": 0.7763, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6809770540340488, | |
| "grad_norm": 0.03775265832702839, | |
| "learning_rate": 5.487923484608629e-06, | |
| "loss": 0.7708, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7105847520355293, | |
| "grad_norm": 0.03691773787087903, | |
| "learning_rate": 4.5856385671435285e-06, | |
| "loss": 0.7598, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7401924500370096, | |
| "grad_norm": 0.0393036985818084, | |
| "learning_rate": 3.7418921275926245e-06, | |
| "loss": 0.7622, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7698001480384901, | |
| "grad_norm": 0.037994882364357475, | |
| "learning_rate": 2.965806503452098e-06, | |
| "loss": 0.7638, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7994078460399704, | |
| "grad_norm": 0.04067457252715543, | |
| "learning_rate": 2.265772503450122e-06, | |
| "loss": 0.7669, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8290155440414507, | |
| "grad_norm": 0.03761393898606893, | |
| "learning_rate": 1.6493586885991908e-06, | |
| "loss": 0.7583, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8586232420429312, | |
| "grad_norm": 0.03804818743072382, | |
| "learning_rate": 1.1232295431481222e-06, | |
| "loss": 0.7651, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8882309400444115, | |
| "grad_norm": 0.03722689725275752, | |
| "learning_rate": 6.930734201451817e-07, | |
| "loss": 0.7751, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9178386380458919, | |
| "grad_norm": 0.03700633814993851, | |
| "learning_rate": 3.635410406436857e-07, | |
| "loss": 0.7699, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9474463360473723, | |
| "grad_norm": 0.035679947322838766, | |
| "learning_rate": 1.3819521147851122e-07, | |
| "loss": 0.7691, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9770540340488527, | |
| "grad_norm": 0.03450691947549809, | |
| "learning_rate": 1.947230525005006e-08, | |
| "loss": 0.753, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9948186528497409, | |
| "step": 168, | |
| "total_flos": 76517996494848.0, | |
| "train_loss": 0.8114972341628301, | |
| "train_runtime": 720.0182, | |
| "train_samples_per_second": 30.013, | |
| "train_steps_per_second": 0.233 | |
| } | |
| ], | |
| "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 | |
| } | |