| { | |
| "best_metric": 2.2062222957611084, | |
| "best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-4/checkpoint-258", | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 258, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.017117117117117116, | |
| "eval_f1": 0.0037002775208140612, | |
| "eval_loss": 4.726041316986084, | |
| "eval_precision": 0.002952029520295203, | |
| "eval_recall": 0.004956629491945477, | |
| "eval_runtime": 0.3653, | |
| "eval_samples_per_second": 796.702, | |
| "eval_steps_per_second": 101.299, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.05345345345345345, | |
| "eval_f1": 0.005950770895320531, | |
| "eval_loss": 4.565603733062744, | |
| "eval_precision": 0.00528084493518963, | |
| "eval_recall": 0.006815365551425031, | |
| "eval_runtime": 0.3702, | |
| "eval_samples_per_second": 786.087, | |
| "eval_steps_per_second": 99.949, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.14594594594594595, | |
| "eval_f1": 0.022442244224422443, | |
| "eval_loss": 4.133880138397217, | |
| "eval_precision": 0.02401129943502825, | |
| "eval_recall": 0.021065675340768277, | |
| "eval_runtime": 0.3715, | |
| "eval_samples_per_second": 783.407, | |
| "eval_steps_per_second": 99.608, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3012012012012012, | |
| "eval_f1": 0.08808290155440414, | |
| "eval_loss": 3.4629595279693604, | |
| "eval_precision": 0.109375, | |
| "eval_recall": 0.07372986369268897, | |
| "eval_runtime": 0.361, | |
| "eval_samples_per_second": 805.99, | |
| "eval_steps_per_second": 102.48, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.42372372372372374, | |
| "eval_f1": 0.1667268134247564, | |
| "eval_loss": 2.7417962551116943, | |
| "eval_precision": 0.1996542783059637, | |
| "eval_recall": 0.14312267657992564, | |
| "eval_runtime": 0.3592, | |
| "eval_samples_per_second": 810.024, | |
| "eval_steps_per_second": 102.993, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5027027027027027, | |
| "eval_f1": 0.24229390681003585, | |
| "eval_loss": 2.2062222957611084, | |
| "eval_precision": 0.28741496598639454, | |
| "eval_recall": 0.2094175960346964, | |
| "eval_runtime": 0.3678, | |
| "eval_samples_per_second": 791.169, | |
| "eval_steps_per_second": 100.595, | |
| "step": 258 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 516, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 2.85638715216918e-05, | |
| "num_train_epochs": 12, | |
| "per_device_train_batch_size": 32, | |
| "warmup_steps": 446, | |
| "weight_decay": 0.2979496592454386 | |
| } | |
| } | |