| { | |
| "best_metric": 0.8090804377039739, | |
| "best_model_checkpoint": "./models/entities/test_v6/checkpoint-7000", | |
| "epoch": 19.997926744989634, | |
| "eval_steps": 7000, | |
| "global_step": 7220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.3842432619212164, | |
| "grad_norm": 7.1875, | |
| "learning_rate": 0.0002, | |
| "loss": 8.369, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.7684865238424328, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 0.00018511904761904765, | |
| "loss": 1.059, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.1548030407740155, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 0.00017023809523809523, | |
| "loss": 0.6034, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.5390463026952315, | |
| "grad_norm": 3.90625, | |
| "learning_rate": 0.00015535714285714287, | |
| "loss": 0.3745, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.923289564616448, | |
| "grad_norm": 3.515625, | |
| "learning_rate": 0.00014047619047619049, | |
| "loss": 0.2708, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.309606081548031, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 0.0001255952380952381, | |
| "loss": 0.1967, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.693849343469246, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 0.00011071428571428572, | |
| "loss": 0.1566, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 11.080165860400829, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 9.583333333333334e-05, | |
| "loss": 0.1318, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 12.464409122322046, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 8.095238095238096e-05, | |
| "loss": 0.1131, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 13.848652384243263, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 6.607142857142857e-05, | |
| "loss": 0.1041, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 15.234968901174845, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 5.119047619047619e-05, | |
| "loss": 0.0986, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 16.619212163096062, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 3.630952380952381e-05, | |
| "loss": 0.0951, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 18.005528680027645, | |
| "grad_norm": 3.53125, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.0921, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 19.389771941948858, | |
| "grad_norm": 1.671875, | |
| "learning_rate": 6.547619047619048e-06, | |
| "loss": 0.0925, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 19.389771941948858, | |
| "eval_accuracy": 0.9699217442249749, | |
| "eval_f1": 0.8090804377039739, | |
| "eval_loss": 0.15359356999397278, | |
| "eval_precision": 0.7678083439606486, | |
| "eval_recall": 0.8550415905863258, | |
| "eval_runtime": 169.5033, | |
| "eval_samples_per_second": 29.262, | |
| "eval_steps_per_second": 29.262, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 19.997926744989634, | |
| "step": 7220, | |
| "total_flos": 6132708568035504.0, | |
| "train_loss": 0.8169754918592458, | |
| "train_runtime": 915.3849, | |
| "train_samples_per_second": 505.754, | |
| "train_steps_per_second": 7.887 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 7220, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 7000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6132708568035504.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |