| { | |
| "best_metric": 0.03708931431174278, | |
| "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-11000", | |
| "epoch": 5.424063116370808, | |
| "eval_steps": 1000, | |
| "global_step": 11000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2465483234714004, | |
| "grad_norm": 0.3815906345844269, | |
| "learning_rate": 1.9950690335305722e-05, | |
| "loss": 0.1667, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4930966469428008, | |
| "grad_norm": 0.36234650015830994, | |
| "learning_rate": 1.9901380670611442e-05, | |
| "loss": 0.0923, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4930966469428008, | |
| "eval_accuracy": 0.9814660487265615, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.08645907044410706, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 11.8049, | |
| "eval_samples_per_second": 687.004, | |
| "eval_steps_per_second": 2.711, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7396449704142012, | |
| "grad_norm": 0.39963558316230774, | |
| "learning_rate": 1.9852071005917162e-05, | |
| "loss": 0.084, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9861932938856016, | |
| "grad_norm": 0.37207868695259094, | |
| "learning_rate": 1.980276134122288e-05, | |
| "loss": 0.0734, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9861932938856016, | |
| "eval_accuracy": 0.9814660487265615, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.0668005496263504, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 11.8932, | |
| "eval_samples_per_second": 681.903, | |
| "eval_steps_per_second": 2.691, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.232741617357002, | |
| "grad_norm": 0.39202699065208435, | |
| "learning_rate": 1.9753451676528602e-05, | |
| "loss": 0.0653, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.4792899408284024, | |
| "grad_norm": 0.3334597647190094, | |
| "learning_rate": 1.9704142011834322e-05, | |
| "loss": 0.0606, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.4792899408284024, | |
| "eval_accuracy": 0.9823617784202843, | |
| "eval_f1": 0.12648276830209867, | |
| "eval_loss": 0.05524122714996338, | |
| "eval_precision": 0.7700854700854701, | |
| "eval_recall": 0.06889959470826643, | |
| "eval_runtime": 14.1698, | |
| "eval_samples_per_second": 572.346, | |
| "eval_steps_per_second": 2.258, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.725838264299803, | |
| "grad_norm": 0.3517291843891144, | |
| "learning_rate": 1.965483234714004e-05, | |
| "loss": 0.055, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.972386587771203, | |
| "grad_norm": 0.43956857919692993, | |
| "learning_rate": 1.9605522682445763e-05, | |
| "loss": 0.0532, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.972386587771203, | |
| "eval_accuracy": 0.9840511926527489, | |
| "eval_f1": 0.2943500344892456, | |
| "eval_loss": 0.0491451695561409, | |
| "eval_precision": 0.8177700348432055, | |
| "eval_recall": 0.1794754148505009, | |
| "eval_runtime": 14.1385, | |
| "eval_samples_per_second": 573.612, | |
| "eval_steps_per_second": 2.263, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.2189349112426036, | |
| "grad_norm": 0.33584991097450256, | |
| "learning_rate": 1.9556213017751483e-05, | |
| "loss": 0.0483, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.465483234714004, | |
| "grad_norm": 0.35681256651878357, | |
| "learning_rate": 1.95069033530572e-05, | |
| "loss": 0.0466, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.465483234714004, | |
| "eval_accuracy": 0.9850886517283898, | |
| "eval_f1": 0.43230993363189985, | |
| "eval_loss": 0.04674109071493149, | |
| "eval_precision": 0.7342375366568915, | |
| "eval_recall": 0.3063393744742678, | |
| "eval_runtime": 14.36, | |
| "eval_samples_per_second": 564.763, | |
| "eval_steps_per_second": 2.228, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.712031558185404, | |
| "grad_norm": 0.36567422747612, | |
| "learning_rate": 1.9457593688362923e-05, | |
| "loss": 0.0449, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.9585798816568047, | |
| "grad_norm": 0.4769591689109802, | |
| "learning_rate": 1.940828402366864e-05, | |
| "loss": 0.0433, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.9585798816568047, | |
| "eval_accuracy": 0.9859475317828139, | |
| "eval_f1": 0.484694142716075, | |
| "eval_loss": 0.042755745351314545, | |
| "eval_precision": 0.7564892926670993, | |
| "eval_recall": 0.3565802554102623, | |
| "eval_runtime": 14.1095, | |
| "eval_samples_per_second": 574.791, | |
| "eval_steps_per_second": 2.268, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.2051282051282053, | |
| "grad_norm": 0.4941834807395935, | |
| "learning_rate": 1.935897435897436e-05, | |
| "loss": 0.0405, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.4516765285996054, | |
| "grad_norm": 0.39021360874176025, | |
| "learning_rate": 1.930966469428008e-05, | |
| "loss": 0.0391, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.4516765285996054, | |
| "eval_accuracy": 0.9866122425840101, | |
| "eval_f1": 0.5389046177877574, | |
| "eval_loss": 0.04075852409005165, | |
| "eval_precision": 0.7450398164394655, | |
| "eval_recall": 0.4221151640284469, | |
| "eval_runtime": 14.2258, | |
| "eval_samples_per_second": 570.09, | |
| "eval_steps_per_second": 2.249, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.698224852071006, | |
| "grad_norm": 0.45788881182670593, | |
| "learning_rate": 1.92603550295858e-05, | |
| "loss": 0.0381, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.9447731755424065, | |
| "grad_norm": 0.3994843363761902, | |
| "learning_rate": 1.921104536489152e-05, | |
| "loss": 0.0378, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.9447731755424065, | |
| "eval_accuracy": 0.9867312952648214, | |
| "eval_f1": 0.5526994744386049, | |
| "eval_loss": 0.03952678292989731, | |
| "eval_precision": 0.7365338087355151, | |
| "eval_recall": 0.4423032805689378, | |
| "eval_runtime": 14.2307, | |
| "eval_samples_per_second": 569.894, | |
| "eval_steps_per_second": 2.249, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.191321499013807, | |
| "grad_norm": 0.40335726737976074, | |
| "learning_rate": 1.916173570019724e-05, | |
| "loss": 0.0349, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.437869822485207, | |
| "grad_norm": 0.43202295899391174, | |
| "learning_rate": 1.911242603550296e-05, | |
| "loss": 0.0338, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.437869822485207, | |
| "eval_accuracy": 0.986986408152274, | |
| "eval_f1": 0.5843744341843201, | |
| "eval_loss": 0.03873027116060257, | |
| "eval_precision": 0.7160288408208542, | |
| "eval_recall": 0.49361474344268563, | |
| "eval_runtime": 14.0731, | |
| "eval_samples_per_second": 576.277, | |
| "eval_steps_per_second": 2.274, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.684418145956608, | |
| "grad_norm": 0.3353199064731598, | |
| "learning_rate": 1.906311637080868e-05, | |
| "loss": 0.034, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.930966469428008, | |
| "grad_norm": 0.3929939270019531, | |
| "learning_rate": 1.90138067061144e-05, | |
| "loss": 0.0333, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.930966469428008, | |
| "eval_accuracy": 0.9870771149567017, | |
| "eval_f1": 0.5952951620062139, | |
| "eval_loss": 0.037975214421749115, | |
| "eval_precision": 0.7094044218766529, | |
| "eval_recall": 0.5128087481838343, | |
| "eval_runtime": 14.136, | |
| "eval_samples_per_second": 573.711, | |
| "eval_steps_per_second": 2.264, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.177514792899408, | |
| "grad_norm": 0.2832840085029602, | |
| "learning_rate": 1.896459566074951e-05, | |
| "loss": 0.0303, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.424063116370808, | |
| "grad_norm": 0.43404069542884827, | |
| "learning_rate": 1.891528599605523e-05, | |
| "loss": 0.0301, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 5.424063116370808, | |
| "eval_accuracy": 0.9875660813243193, | |
| "eval_f1": 0.6041958041958042, | |
| "eval_loss": 0.03708931431174278, | |
| "eval_precision": 0.7367957746478874, | |
| "eval_recall": 0.5120440467997247, | |
| "eval_runtime": 14.265, | |
| "eval_samples_per_second": 568.525, | |
| "eval_steps_per_second": 2.243, | |
| "step": 11000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 202800, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 248019064848396.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |