| { | |
| "best_metric": 0.1366359144449234, | |
| "best_model_checkpoint": "output_pipe/prom_300_notata/origin/checkpoint-200", | |
| "epoch": 4.0, | |
| "eval_steps": 200, | |
| "global_step": 664, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6024096385542169, | |
| "grad_norm": 370419.0, | |
| "learning_rate": 2.755700325732899e-05, | |
| "loss": 0.338, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2048192771084336, | |
| "grad_norm": 99553.453125, | |
| "learning_rate": 2.267100977198697e-05, | |
| "loss": 0.1179, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2048192771084336, | |
| "eval_accuracy": 0.9468626342566422, | |
| "eval_f1": 0.9467472789614293, | |
| "eval_loss": 0.1366359144449234, | |
| "eval_matthews_correlation": 0.8959866993928602, | |
| "eval_precision": 0.9495098730394707, | |
| "eval_recall": 0.9464819426882866, | |
| "eval_runtime": 2.8715, | |
| "eval_samples_per_second": 1848.18, | |
| "eval_steps_per_second": 7.313, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8072289156626506, | |
| "grad_norm": 85286.71875, | |
| "learning_rate": 1.7785016286644952e-05, | |
| "loss": 0.0683, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.4096385542168672, | |
| "grad_norm": 463375.1875, | |
| "learning_rate": 1.2899022801302933e-05, | |
| "loss": 0.0309, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.4096385542168672, | |
| "eval_accuracy": 0.9532692670058414, | |
| "eval_f1": 0.9532690662391536, | |
| "eval_loss": 0.24670438468456268, | |
| "eval_matthews_correlation": 0.9068330536890357, | |
| "eval_precision": 0.9534399069262655, | |
| "eval_recall": 0.9533931479682843, | |
| "eval_runtime": 2.8154, | |
| "eval_samples_per_second": 1884.958, | |
| "eval_steps_per_second": 7.459, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.0120481927710845, | |
| "grad_norm": 7877.89013671875, | |
| "learning_rate": 8.013029315960913e-06, | |
| "loss": 0.0229, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.6144578313253013, | |
| "grad_norm": 0.0274798683822155, | |
| "learning_rate": 3.1270358306188927e-06, | |
| "loss": 0.0096, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.6144578313253013, | |
| "eval_accuracy": 0.9626907857546636, | |
| "eval_f1": 0.9626767267039005, | |
| "eval_loss": 0.5383982062339783, | |
| "eval_matthews_correlation": 0.9255110879000064, | |
| "eval_precision": 0.9629181128135269, | |
| "eval_recall": 0.9625930321778626, | |
| "eval_runtime": 2.7968, | |
| "eval_samples_per_second": 1897.499, | |
| "eval_steps_per_second": 7.508, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 664, | |
| "total_flos": 2.752165101007325e+16, | |
| "train_loss": 0.08948779276695597, | |
| "train_runtime": 313.4379, | |
| "train_samples_per_second": 541.76, | |
| "train_steps_per_second": 2.118 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 664, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.752165101007325e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } |