| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3337505214851898, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008343763037129746, | |
| "grad_norm": 0.7562159895896912, | |
| "learning_rate": 0.0001951951951951952, | |
| "loss": 1.9181, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016687526074259492, | |
| "grad_norm": 0.8098325133323669, | |
| "learning_rate": 0.0001901901901901902, | |
| "loss": 1.1849, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.025031289111389236, | |
| "grad_norm": 0.3777216374874115, | |
| "learning_rate": 0.0001851851851851852, | |
| "loss": 1.6916, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.033375052148518984, | |
| "grad_norm": 0.5206697583198547, | |
| "learning_rate": 0.00018018018018018018, | |
| "loss": 1.1422, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.041718815185648725, | |
| "grad_norm": 0.38817787170410156, | |
| "learning_rate": 0.0001751751751751752, | |
| "loss": 1.6667, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.05006257822277847, | |
| "grad_norm": 0.6388385891914368, | |
| "learning_rate": 0.0001701701701701702, | |
| "loss": 1.2033, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05840634125990822, | |
| "grad_norm": 0.4120958149433136, | |
| "learning_rate": 0.00016516516516516518, | |
| "loss": 1.725, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.06675010429703797, | |
| "grad_norm": 0.46837368607521057, | |
| "learning_rate": 0.00016016016016016018, | |
| "loss": 1.065, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07509386733416772, | |
| "grad_norm": 0.4679395854473114, | |
| "learning_rate": 0.00015515515515515516, | |
| "loss": 1.7601, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.08343763037129745, | |
| "grad_norm": 0.380135178565979, | |
| "learning_rate": 0.00015015015015015014, | |
| "loss": 1.0251, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0917813934084272, | |
| "grad_norm": 0.3675175905227661, | |
| "learning_rate": 0.00014514514514514515, | |
| "loss": 1.6459, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.10012515644555695, | |
| "grad_norm": 0.48725131154060364, | |
| "learning_rate": 0.00014014014014014013, | |
| "loss": 1.0373, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1084689194826867, | |
| "grad_norm": 0.42459967732429504, | |
| "learning_rate": 0.00013513513513513514, | |
| "loss": 1.6939, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.11681268251981644, | |
| "grad_norm": 0.44615626335144043, | |
| "learning_rate": 0.00013013013013013014, | |
| "loss": 1.1265, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1251564455569462, | |
| "grad_norm": 0.3729555904865265, | |
| "learning_rate": 0.00012512512512512512, | |
| "loss": 1.7411, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.13350020859407594, | |
| "grad_norm": 0.42633363604545593, | |
| "learning_rate": 0.00012012012012012013, | |
| "loss": 1.1436, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.14184397163120568, | |
| "grad_norm": 0.4313684105873108, | |
| "learning_rate": 0.00011511511511511512, | |
| "loss": 1.6521, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.15018773466833543, | |
| "grad_norm": 0.3195270597934723, | |
| "learning_rate": 0.00011011011011011012, | |
| "loss": 0.984, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.15853149770546515, | |
| "grad_norm": 0.279301255941391, | |
| "learning_rate": 0.00010510510510510511, | |
| "loss": 1.6523, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.1668752607425949, | |
| "grad_norm": 0.32661929726600647, | |
| "learning_rate": 0.00010010010010010012, | |
| "loss": 1.0151, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1668752607425949, | |
| "eval_loss": 1.5524340867996216, | |
| "eval_runtime": 511.702, | |
| "eval_samples_per_second": 2.931, | |
| "eval_steps_per_second": 0.367, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.17521902377972465, | |
| "grad_norm": 0.27320751547813416, | |
| "learning_rate": 9.50950950950951e-05, | |
| "loss": 1.6524, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.1835627868168544, | |
| "grad_norm": 0.393206387758255, | |
| "learning_rate": 9.009009009009009e-05, | |
| "loss": 0.9658, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.19190654985398414, | |
| "grad_norm": 0.29037702083587646, | |
| "learning_rate": 8.50850850850851e-05, | |
| "loss": 1.6467, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.2002503128911139, | |
| "grad_norm": 0.3599018156528473, | |
| "learning_rate": 8.008008008008009e-05, | |
| "loss": 1.0368, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.20859407592824364, | |
| "grad_norm": 0.397064208984375, | |
| "learning_rate": 7.507507507507507e-05, | |
| "loss": 1.7412, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.2169378389653734, | |
| "grad_norm": 0.3856523334980011, | |
| "learning_rate": 7.007007007007007e-05, | |
| "loss": 1.1053, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.22528160200250313, | |
| "grad_norm": 0.30977582931518555, | |
| "learning_rate": 6.506506506506507e-05, | |
| "loss": 1.7623, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.23362536503963288, | |
| "grad_norm": 0.4029249846935272, | |
| "learning_rate": 6.0060060060060066e-05, | |
| "loss": 1.1681, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.24196912807676263, | |
| "grad_norm": 0.3093183636665344, | |
| "learning_rate": 5.505505505505506e-05, | |
| "loss": 1.7267, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.2503128911138924, | |
| "grad_norm": 0.45136523246765137, | |
| "learning_rate": 5.005005005005006e-05, | |
| "loss": 1.1256, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.2586566541510221, | |
| "grad_norm": 0.2787851393222809, | |
| "learning_rate": 4.5045045045045046e-05, | |
| "loss": 1.7174, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.2670004171881519, | |
| "grad_norm": 0.33277878165245056, | |
| "learning_rate": 4.0040040040040046e-05, | |
| "loss": 0.9848, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.2753441802252816, | |
| "grad_norm": 0.3014131784439087, | |
| "learning_rate": 3.503503503503503e-05, | |
| "loss": 1.6547, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.28368794326241137, | |
| "grad_norm": 0.27079567313194275, | |
| "learning_rate": 3.0030030030030033e-05, | |
| "loss": 1.1372, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.2920317062995411, | |
| "grad_norm": 0.2874036729335785, | |
| "learning_rate": 2.502502502502503e-05, | |
| "loss": 1.7384, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.30037546933667086, | |
| "grad_norm": 0.38741400837898254, | |
| "learning_rate": 2.0020020020020023e-05, | |
| "loss": 1.0731, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3087192323738006, | |
| "grad_norm": 0.3522486090660095, | |
| "learning_rate": 1.5015015015015016e-05, | |
| "loss": 1.6537, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.3170629954109303, | |
| "grad_norm": 0.41225603222846985, | |
| "learning_rate": 1.0010010010010011e-05, | |
| "loss": 1.0646, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.32540675844806005, | |
| "grad_norm": 0.33286789059638977, | |
| "learning_rate": 5.005005005005006e-06, | |
| "loss": 1.6279, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.3337505214851898, | |
| "grad_norm": 0.405441552400589, | |
| "learning_rate": 0.0, | |
| "loss": 1.0594, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3337505214851898, | |
| "eval_loss": 1.5415141582489014, | |
| "eval_runtime": 511.169, | |
| "eval_samples_per_second": 2.934, | |
| "eval_steps_per_second": 0.368, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.341797200653312e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |