| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 1932, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "step": 276, | |
| "train_eval_accuracy": 0.6987528344671202, | |
| "train_eval_f1": 0.6755183421371805, | |
| "train_eval_loss": 1.2385817766189575, | |
| "train_eval_precision": 0.7371331169153404, | |
| "train_eval_recall": 0.700062751383177, | |
| "train_loss": 1.2385817766189575, | |
| "train_runtime": 259.0959, | |
| "train_samples_per_second": 34.041, | |
| "train_steps_per_second": 1.065 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6833333333333333, | |
| "eval_f1": 0.6547321354719501, | |
| "eval_loss": 1.2707617282867432, | |
| "eval_precision": 0.7152277887972227, | |
| "eval_recall": 0.6807604737331212, | |
| "eval_runtime": 110.9236, | |
| "eval_samples_per_second": 34.078, | |
| "eval_steps_per_second": 1.073, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 552, | |
| "train_eval_accuracy": 0.9099773242630386, | |
| "train_eval_f1": 0.9092824086512392, | |
| "train_eval_loss": 0.39961349964141846, | |
| "train_eval_precision": 0.9126506135478565, | |
| "train_eval_recall": 0.909610330961518, | |
| "train_loss": 0.39961352944374084, | |
| "train_runtime": 259.0099, | |
| "train_samples_per_second": 34.053, | |
| "train_steps_per_second": 1.066 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8843915343915344, | |
| "eval_f1": 0.8845088728896672, | |
| "eval_loss": 0.49980613589286804, | |
| "eval_precision": 0.8892030673846649, | |
| "eval_recall": 0.8861504544427677, | |
| "eval_runtime": 111.0942, | |
| "eval_samples_per_second": 34.025, | |
| "eval_steps_per_second": 1.071, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 828, | |
| "train_eval_accuracy": 0.9325396825396826, | |
| "train_eval_f1": 0.9319133039039142, | |
| "train_eval_loss": 0.27389460802078247, | |
| "train_eval_precision": 0.934170610859209, | |
| "train_eval_recall": 0.9324433400664413, | |
| "train_loss": 0.27389463782310486, | |
| "train_runtime": 258.8663, | |
| "train_samples_per_second": 34.072, | |
| "train_steps_per_second": 1.066 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8981481481481481, | |
| "eval_f1": 0.8983790808910544, | |
| "eval_loss": 0.4277746081352234, | |
| "eval_precision": 0.9018452269248401, | |
| "eval_recall": 0.8993916560895983, | |
| "eval_runtime": 111.0843, | |
| "eval_samples_per_second": 34.028, | |
| "eval_steps_per_second": 1.071, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1104, | |
| "train_eval_accuracy": 0.9470521541950113, | |
| "train_eval_f1": 0.9467599019967656, | |
| "train_eval_loss": 0.20678994059562683, | |
| "train_eval_precision": 0.9485244133482296, | |
| "train_eval_recall": 0.9470018597626247, | |
| "train_loss": 0.20678995549678802, | |
| "train_runtime": 258.8456, | |
| "train_samples_per_second": 34.074, | |
| "train_steps_per_second": 1.066 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8973544973544973, | |
| "eval_f1": 0.8979176810370734, | |
| "eval_loss": 0.39539220929145813, | |
| "eval_precision": 0.9018417578163312, | |
| "eval_recall": 0.8984604158679782, | |
| "eval_runtime": 111.0135, | |
| "eval_samples_per_second": 34.05, | |
| "eval_steps_per_second": 1.072, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1380, | |
| "train_eval_accuracy": 0.9561224489795919, | |
| "train_eval_f1": 0.9558613640362872, | |
| "train_eval_loss": 0.16801320016384125, | |
| "train_eval_precision": 0.956385049537581, | |
| "train_eval_recall": 0.9560588471737465, | |
| "train_loss": 0.16801321506500244, | |
| "train_runtime": 258.896, | |
| "train_samples_per_second": 34.068, | |
| "train_steps_per_second": 1.066 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9034391534391535, | |
| "eval_f1": 0.9040125697548127, | |
| "eval_loss": 0.4033404588699341, | |
| "eval_precision": 0.9052728311936364, | |
| "eval_recall": 0.9046585790514887, | |
| "eval_runtime": 110.9029, | |
| "eval_samples_per_second": 34.084, | |
| "eval_steps_per_second": 1.073, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 1656, | |
| "train_eval_accuracy": 0.9645124716553288, | |
| "train_eval_f1": 0.9643703596173855, | |
| "train_eval_loss": 0.13308991491794586, | |
| "train_eval_precision": 0.964791623196822, | |
| "train_eval_recall": 0.9644331346757402, | |
| "train_loss": 0.13308990001678467, | |
| "train_runtime": 258.612, | |
| "train_samples_per_second": 34.105, | |
| "train_steps_per_second": 1.067 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.903968253968254, | |
| "eval_f1": 0.9045126462342287, | |
| "eval_loss": 0.4025459587574005, | |
| "eval_precision": 0.9070552370106681, | |
| "eval_recall": 0.9050900149375409, | |
| "eval_runtime": 110.9248, | |
| "eval_samples_per_second": 34.077, | |
| "eval_steps_per_second": 1.073, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "step": 1932, | |
| "train_eval_accuracy": 0.9687074829931973, | |
| "train_eval_f1": 0.9684965457139353, | |
| "train_eval_loss": 0.11909189075231552, | |
| "train_eval_precision": 0.9696149844869657, | |
| "train_eval_recall": 0.9685670790376533, | |
| "train_loss": 0.11909190565347672, | |
| "train_runtime": 258.6816, | |
| "train_samples_per_second": 34.096, | |
| "train_steps_per_second": 1.067 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8957671957671958, | |
| "eval_f1": 0.8957969434045191, | |
| "eval_loss": 0.4326554834842682, | |
| "eval_precision": 0.8981578919986064, | |
| "eval_recall": 0.8970552202896507, | |
| "eval_runtime": 111.0014, | |
| "eval_samples_per_second": 34.054, | |
| "eval_steps_per_second": 1.072, | |
| "step": 1932 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "step": 1932, | |
| "total_flos": 1.62503106619392e+16, | |
| "train_loss": 0.6677281476449275, | |
| "train_runtime": 8398.7851, | |
| "train_samples_per_second": 21.003, | |
| "train_steps_per_second": 0.657 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8957671957671958, | |
| "eval_f1": 0.8957969434045191, | |
| "eval_loss": 0.4326554834842682, | |
| "eval_precision": 0.8981578919986064, | |
| "eval_recall": 0.8970552202896507, | |
| "eval_runtime": 111.1885, | |
| "eval_samples_per_second": 33.996, | |
| "eval_steps_per_second": 1.07, | |
| "step": 1932 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "step": 1932, | |
| "train_en_eval_accuracy": 0.9687074829931973, | |
| "train_en_eval_f1": 0.9684965457139353, | |
| "train_en_eval_loss": 0.11909189075231552, | |
| "train_en_eval_precision": 0.9696149844869657, | |
| "train_en_eval_recall": 0.9685670790376533, | |
| "train_en_loss": 0.11909190565347672, | |
| "train_en_runtime": 258.9019, | |
| "train_en_samples_per_second": 34.067, | |
| "train_en_steps_per_second": 1.066 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "step": 1932, | |
| "test_en_eval_accuracy": 0.8957671957671958, | |
| "test_en_eval_f1": 0.8957969434045191, | |
| "test_en_eval_loss": 0.43265554308891296, | |
| "test_en_eval_precision": 0.8981578919986064, | |
| "test_en_eval_recall": 0.8970552202896507, | |
| "test_en_loss": 0.4326554834842682, | |
| "test_en_runtime": 110.7536, | |
| "test_en_samples_per_second": 34.13, | |
| "test_en_steps_per_second": 1.074 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5520, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.62503106619392e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |