| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.996832101372756, | |
| "eval_steps": 500, | |
| "global_step": 177, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.028159098908834918, | |
| "grad_norm": 19.6645688545719, | |
| "learning_rate": 7.551296174514496e-06, | |
| "loss": 1.772, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.056318197817669835, | |
| "grad_norm": 4.727027394780319, | |
| "learning_rate": 1.0803462419947182e-05, | |
| "loss": 0.1847, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08447729672650475, | |
| "grad_norm": 19.711230344682384, | |
| "learning_rate": 1.2705857719636416e-05, | |
| "loss": 0.0731, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11263639563533967, | |
| "grad_norm": 120.55146168999882, | |
| "learning_rate": 1.4055628665379864e-05, | |
| "loss": 0.1351, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1407954945441746, | |
| "grad_norm": 1.4221918091023358, | |
| "learning_rate": 1.5102592349028992e-05, | |
| "loss": 0.6003, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1689545934530095, | |
| "grad_norm": 93.16203439540969, | |
| "learning_rate": 1.59580239650691e-05, | |
| "loss": 0.1643, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19711369236184442, | |
| "grad_norm": 1.4802141559756252, | |
| "learning_rate": 1.6681281090979538e-05, | |
| "loss": 0.0388, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22527279127067934, | |
| "grad_norm": 0.5497965991231408, | |
| "learning_rate": 1.7307794910812547e-05, | |
| "loss": 0.041, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25343189017951423, | |
| "grad_norm": 0.809671175331064, | |
| "learning_rate": 1.7860419264758336e-05, | |
| "loss": 0.0226, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2815909890883492, | |
| "grad_norm": 0.5726493910943911, | |
| "learning_rate": 1.8354758594461676e-05, | |
| "loss": 0.0125, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.30975008799718406, | |
| "grad_norm": 2.152125865226535, | |
| "learning_rate": 1.8801942913029267e-05, | |
| "loss": 0.0288, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.337909186906019, | |
| "grad_norm": 1.7715340956034473, | |
| "learning_rate": 1.9210190210501782e-05, | |
| "loss": 0.0747, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3660682858148539, | |
| "grad_norm": 0.7929555878733779, | |
| "learning_rate": 1.958574131911139e-05, | |
| "loss": 0.032, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.39422738472368885, | |
| "grad_norm": 0.4312710941467189, | |
| "learning_rate": 1.9933447336412223e-05, | |
| "loss": 0.0134, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42238648363252373, | |
| "grad_norm": 0.42440254982809505, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0085, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4505455825413587, | |
| "grad_norm": 6.717903145975225, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0852, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47870468145019357, | |
| "grad_norm": 0.2616911994136381, | |
| "learning_rate": 2e-05, | |
| "loss": 0.019, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5068637803590285, | |
| "grad_norm": 0.8929028186175655, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0182, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5350228792678634, | |
| "grad_norm": 0.7663707991929901, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0121, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5631819781766984, | |
| "grad_norm": 0.2751891648435824, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0102, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5913410770855333, | |
| "grad_norm": 0.430346596578061, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0108, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6195001759943681, | |
| "grad_norm": 1.4084539796481979, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0101, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6476592749032031, | |
| "grad_norm": 0.4526307765811631, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0097, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.675818373812038, | |
| "grad_norm": 0.8195970452263144, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0056, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.703977472720873, | |
| "grad_norm": 0.33201877895047494, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0159, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7321365716297078, | |
| "grad_norm": 0.11072814422450454, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0098, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7602956705385427, | |
| "grad_norm": 0.24416225262702998, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0074, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7884547694473777, | |
| "grad_norm": 0.3324109610233922, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0077, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8166138683562126, | |
| "grad_norm": 0.38309506546184624, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0075, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8447729672650475, | |
| "grad_norm": 0.4132780671494754, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0086, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8729320661738824, | |
| "grad_norm": 0.6511569066773779, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0068, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9010911650827174, | |
| "grad_norm": 0.510007207472237, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0061, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9292502639915523, | |
| "grad_norm": 0.6855848058318451, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0051, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9574093629003871, | |
| "grad_norm": 0.5746575155652519, | |
| "learning_rate": 2e-05, | |
| "loss": 0.009, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9855684618092221, | |
| "grad_norm": 0.07311127035672031, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0065, | |
| "step": 175 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 708, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 18127515828224.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |