| { | |
| "best_metric": 0.38998281955718994, | |
| "best_model_checkpoint": "output_pipe/0/origin/checkpoint-200", | |
| "epoch": 4.0, | |
| "eval_steps": 200, | |
| "global_step": 408, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9803921568627451, | |
| "grad_norm": 4.097352981567383, | |
| "learning_rate": 2.5893854748603352e-05, | |
| "loss": 0.547, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.9607843137254903, | |
| "grad_norm": 3.9965834617614746, | |
| "learning_rate": 1.7513966480446926e-05, | |
| "loss": 0.322, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.9607843137254903, | |
| "eval_accuracy": 0.837037037037037, | |
| "eval_f1": 0.8369734266075469, | |
| "eval_loss": 0.38998281955718994, | |
| "eval_matthews_correlation": 0.6739877047317809, | |
| "eval_precision": 0.8369280866399575, | |
| "eval_recall": 0.8370596309287784, | |
| "eval_runtime": 0.212, | |
| "eval_samples_per_second": 3820.954, | |
| "eval_steps_per_second": 61.324, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 6.0555243492126465, | |
| "learning_rate": 9.217877094972067e-06, | |
| "loss": 0.1597, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.9215686274509802, | |
| "grad_norm": 0.1700039803981781, | |
| "learning_rate": 8.379888268156424e-07, | |
| "loss": 0.0536, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.9215686274509802, | |
| "eval_accuracy": 0.8469135802469135, | |
| "eval_f1": 0.8467304323410385, | |
| "eval_loss": 0.6194068193435669, | |
| "eval_matthews_correlation": 0.6936264310968385, | |
| "eval_precision": 0.847050415086041, | |
| "eval_recall": 0.8465761781302426, | |
| "eval_runtime": 0.2105, | |
| "eval_samples_per_second": 3848.264, | |
| "eval_steps_per_second": 61.762, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 408, | |
| "total_flos": 1744413390456720.0, | |
| "train_loss": 0.2661988531403682, | |
| "train_runtime": 40.6489, | |
| "train_samples_per_second": 637.459, | |
| "train_steps_per_second": 10.037 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 408, | |
| "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": 1744413390456720.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |