| { | |
| "best_metric": 0.35955047607421875, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-2025", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2025, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.93583415597236e-06, | |
| "loss": 0.5941, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.87166831194472e-06, | |
| "loss": 0.5625, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.4807502467917079e-05, | |
| "loss": 0.5233, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.974333662388944e-05, | |
| "loss": 0.443, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.46791707798618e-05, | |
| "loss": 0.4222, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.9615004935834158e-05, | |
| "loss": 0.4242, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.455083909180652e-05, | |
| "loss": 0.4401, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.948667324777888e-05, | |
| "loss": 0.3815, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.4422507403751234e-05, | |
| "loss": 0.3833, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.93583415597236e-05, | |
| "loss": 0.3968, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.952260755048288e-05, | |
| "loss": 0.4156, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.8973880597014924e-05, | |
| "loss": 0.4019, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.842515364354697e-05, | |
| "loss": 0.3999, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.7876426690079015e-05, | |
| "loss": 0.4215, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.7327699736611064e-05, | |
| "loss": 0.3855, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.677897278314311e-05, | |
| "loss": 0.3786, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.6230245829675155e-05, | |
| "loss": 0.415, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.5681518876207204e-05, | |
| "loss": 0.4079, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.5132791922739246e-05, | |
| "loss": 0.4044, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.4584064969271295e-05, | |
| "loss": 0.3671, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.839, | |
| "eval_auc": 0.8849468102956475, | |
| "eval_f1": 0.5477528089887641, | |
| "eval_loss": 0.35955047607421875, | |
| "eval_precision": 0.8986175115207373, | |
| "eval_recall": 0.3939393939393939, | |
| "eval_runtime": 897.0094, | |
| "eval_samples_per_second": 4.459, | |
| "eval_steps_per_second": 0.279, | |
| "step": 2025 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 10125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 1065599774208000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |