| { | |
| "best_global_step": 252, | |
| "best_metric": 0.7365710735321045, | |
| "best_model_checkpoint": "./multitask_model2/checkpoint-252", | |
| "epoch": 12.0, | |
| "eval_steps": 500, | |
| "global_step": 252, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.7021834254264832, | |
| "learning_rate": 1.904761904761905e-05, | |
| "loss": 0.7665, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_dis_accuracy": 0.6524822695035462, | |
| "eval_dis_f1": 0.0, | |
| "eval_dis_precision": 0.0, | |
| "eval_dis_recall": 0.0, | |
| "eval_loss": 0.755448579788208, | |
| "eval_runtime": 0.4506, | |
| "eval_samples_per_second": 312.894, | |
| "eval_steps_per_second": 11.096, | |
| "eval_target_accuracy": 0.5957446808510638, | |
| "eval_target_f1": 0.37333333333333335, | |
| "eval_target_precision": 0.2978723404255319, | |
| "eval_target_recall": 0.5, | |
| "eval_target_soft_ce": 0.680282711982727, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.5450627207756042, | |
| "learning_rate": 1.804761904761905e-05, | |
| "loss": 0.7636, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_dis_accuracy": 0.6524822695035462, | |
| "eval_dis_f1": 0.0, | |
| "eval_dis_precision": 0.0, | |
| "eval_dis_recall": 0.0, | |
| "eval_loss": 0.7531750202178955, | |
| "eval_runtime": 0.3837, | |
| "eval_samples_per_second": 367.514, | |
| "eval_steps_per_second": 13.032, | |
| "eval_target_accuracy": 0.5957446808510638, | |
| "eval_target_f1": 0.37333333333333335, | |
| "eval_target_precision": 0.2978723404255319, | |
| "eval_target_recall": 0.5, | |
| "eval_target_soft_ce": 0.678588330745697, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.9124093651771545, | |
| "learning_rate": 1.704761904761905e-05, | |
| "loss": 0.7657, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_dis_accuracy": 0.6524822695035462, | |
| "eval_dis_f1": 0.0, | |
| "eval_dis_precision": 0.0, | |
| "eval_dis_recall": 0.0, | |
| "eval_loss": 0.7538319826126099, | |
| "eval_runtime": 0.4379, | |
| "eval_samples_per_second": 321.999, | |
| "eval_steps_per_second": 11.418, | |
| "eval_target_accuracy": 0.5957446808510638, | |
| "eval_target_f1": 0.37333333333333335, | |
| "eval_target_precision": 0.2978723404255319, | |
| "eval_target_recall": 0.5, | |
| "eval_target_soft_ce": 0.6760473847389221, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.8770959377288818, | |
| "learning_rate": 1.604761904761905e-05, | |
| "loss": 0.7601, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_dis_accuracy": 0.6524822695035462, | |
| "eval_dis_f1": 0.0, | |
| "eval_dis_precision": 0.0, | |
| "eval_dis_recall": 0.0, | |
| "eval_loss": 0.7534122467041016, | |
| "eval_runtime": 0.4598, | |
| "eval_samples_per_second": 306.631, | |
| "eval_steps_per_second": 10.873, | |
| "eval_target_accuracy": 0.5957446808510638, | |
| "eval_target_f1": 0.37333333333333335, | |
| "eval_target_precision": 0.2978723404255319, | |
| "eval_target_recall": 0.5, | |
| "eval_target_soft_ce": 0.6773362159729004, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.3157461881637573, | |
| "learning_rate": 1.5047619047619049e-05, | |
| "loss": 0.7586, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_dis_accuracy": 0.6524822695035462, | |
| "eval_dis_f1": 0.0, | |
| "eval_dis_precision": 0.0, | |
| "eval_dis_recall": 0.0, | |
| "eval_loss": 0.7500014305114746, | |
| "eval_runtime": 0.4435, | |
| "eval_samples_per_second": 317.923, | |
| "eval_steps_per_second": 11.274, | |
| "eval_target_accuracy": 0.5957446808510638, | |
| "eval_target_f1": 0.37333333333333335, | |
| "eval_target_precision": 0.2978723404255319, | |
| "eval_target_recall": 0.5, | |
| "eval_target_soft_ce": 0.6725690960884094, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 1.533734679222107, | |
| "learning_rate": 1.4047619047619048e-05, | |
| "loss": 0.7467, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_dis_accuracy": 0.6666666666666666, | |
| "eval_dis_f1": 0.14545454545454545, | |
| "eval_dis_precision": 0.6666666666666666, | |
| "eval_dis_recall": 0.08163265306122448, | |
| "eval_loss": 0.745786190032959, | |
| "eval_runtime": 0.466, | |
| "eval_samples_per_second": 302.556, | |
| "eval_steps_per_second": 10.729, | |
| "eval_target_accuracy": 0.5886524822695035, | |
| "eval_target_f1": 0.38603603603603603, | |
| "eval_target_precision": 0.46376811594202894, | |
| "eval_target_recall": 0.49686716791979946, | |
| "eval_target_soft_ce": 0.6714953184127808, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 2.0812835693359375, | |
| "learning_rate": 1.304761904761905e-05, | |
| "loss": 0.7387, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_dis_accuracy": 0.6524822695035462, | |
| "eval_dis_f1": 0.0, | |
| "eval_dis_precision": 0.0, | |
| "eval_dis_recall": 0.0, | |
| "eval_loss": 0.7480353116989136, | |
| "eval_runtime": 0.4471, | |
| "eval_samples_per_second": 315.367, | |
| "eval_steps_per_second": 11.183, | |
| "eval_target_accuracy": 0.5957446808510638, | |
| "eval_target_f1": 0.37333333333333335, | |
| "eval_target_precision": 0.2978723404255319, | |
| "eval_target_recall": 0.5, | |
| "eval_target_soft_ce": 0.6714373826980591, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 4.809630870819092, | |
| "learning_rate": 1.2047619047619049e-05, | |
| "loss": 0.74, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_dis_accuracy": 0.5177304964539007, | |
| "eval_dis_f1": 0.40350877192982454, | |
| "eval_dis_precision": 0.35384615384615387, | |
| "eval_dis_recall": 0.46938775510204084, | |
| "eval_loss": 0.7411231994628906, | |
| "eval_runtime": 0.4289, | |
| "eval_samples_per_second": 328.731, | |
| "eval_steps_per_second": 11.657, | |
| "eval_target_accuracy": 0.574468085106383, | |
| "eval_target_f1": 0.4683257918552036, | |
| "eval_target_precision": 0.5142857142857142, | |
| "eval_target_recall": 0.5075187969924811, | |
| "eval_target_soft_ce": 0.6614766120910645, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 7.420032024383545, | |
| "learning_rate": 1.104761904761905e-05, | |
| "loss": 0.7288, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_dis_accuracy": 0.6382978723404256, | |
| "eval_dis_f1": 0.2153846153846154, | |
| "eval_dis_precision": 0.4375, | |
| "eval_dis_recall": 0.14285714285714285, | |
| "eval_loss": 0.7409353852272034, | |
| "eval_runtime": 0.4589, | |
| "eval_samples_per_second": 307.224, | |
| "eval_steps_per_second": 10.894, | |
| "eval_target_accuracy": 0.5886524822695035, | |
| "eval_target_f1": 0.44892183288409704, | |
| "eval_target_precision": 0.5315504807692308, | |
| "eval_target_recall": 0.5109649122807017, | |
| "eval_target_soft_ce": 0.6628619432449341, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 3.0795819759368896, | |
| "learning_rate": 1.0047619047619048e-05, | |
| "loss": 0.7314, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_dis_accuracy": 0.5886524822695035, | |
| "eval_dis_f1": 0.21621621621621623, | |
| "eval_dis_precision": 0.32, | |
| "eval_dis_recall": 0.16326530612244897, | |
| "eval_loss": 0.743432879447937, | |
| "eval_runtime": 0.429, | |
| "eval_samples_per_second": 328.682, | |
| "eval_steps_per_second": 11.655, | |
| "eval_target_accuracy": 0.5886524822695035, | |
| "eval_target_f1": 0.48604826546003016, | |
| "eval_target_precision": 0.5422619047619047, | |
| "eval_target_recall": 0.5222431077694236, | |
| "eval_target_soft_ce": 0.6649101972579956, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 5.447195053100586, | |
| "learning_rate": 9.047619047619049e-06, | |
| "loss": 0.7192, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_dis_accuracy": 0.6382978723404256, | |
| "eval_dis_f1": 0.23880597014925373, | |
| "eval_dis_precision": 0.4444444444444444, | |
| "eval_dis_recall": 0.16326530612244897, | |
| "eval_loss": 0.7414493560791016, | |
| "eval_runtime": 0.4442, | |
| "eval_samples_per_second": 317.394, | |
| "eval_steps_per_second": 11.255, | |
| "eval_target_accuracy": 0.6099290780141844, | |
| "eval_target_f1": 0.4723412941416616, | |
| "eval_target_precision": 0.5978682170542635, | |
| "eval_target_recall": 0.531641604010025, | |
| "eval_target_soft_ce": 0.6644006371498108, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 2.391383647918701, | |
| "learning_rate": 8.047619047619048e-06, | |
| "loss": 0.7218, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_dis_accuracy": 0.5957446808510638, | |
| "eval_dis_f1": 0.27848101265822783, | |
| "eval_dis_precision": 0.36666666666666664, | |
| "eval_dis_recall": 0.22448979591836735, | |
| "eval_loss": 0.7365710735321045, | |
| "eval_runtime": 0.4606, | |
| "eval_samples_per_second": 306.148, | |
| "eval_steps_per_second": 10.856, | |
| "eval_target_accuracy": 0.6028368794326241, | |
| "eval_target_f1": 0.487006237006237, | |
| "eval_target_precision": 0.571157495256167, | |
| "eval_target_recall": 0.531328320802005, | |
| "eval_target_soft_ce": 0.6578279137611389, | |
| "step": 252 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 420, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "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": 0.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |