| { | |
| "best_metric": 0.8727797865867615, | |
| "best_model_checkpoint": "autotrain-rqsu1-nelrs/checkpoint-6000", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.222222222222223e-06, | |
| "loss": 2.2551, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.65e-05, | |
| "loss": 1.533, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.4833333333333335e-05, | |
| "loss": 1.3785, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.316666666666667e-05, | |
| "loss": 1.2836, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.15e-05, | |
| "loss": 1.2161, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.9833333333333336e-05, | |
| "loss": 1.1853, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.9092592592592595e-05, | |
| "loss": 1.1863, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.8166666666666674e-05, | |
| "loss": 1.1578, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.724074074074074e-05, | |
| "loss": 1.1281, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.631481481481481e-05, | |
| "loss": 1.0885, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.538888888888889e-05, | |
| "loss": 1.0728, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.4462962962962966e-05, | |
| "loss": 1.0805, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.353703703703704e-05, | |
| "loss": 1.0485, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.261111111111111e-05, | |
| "loss": 1.0415, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.168518518518519e-05, | |
| "loss": 0.9634, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.0759259259259264e-05, | |
| "loss": 0.9934, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.9839506172839506e-05, | |
| "loss": 0.9743, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.8913580246913585e-05, | |
| "loss": 1.0402, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.798765432098765e-05, | |
| "loss": 0.9291, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.706172839506173e-05, | |
| "loss": 0.999, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6781666666666667, | |
| "eval_f1_macro": 0.417421299699202, | |
| "eval_f1_micro": 0.6781666666666667, | |
| "eval_f1_weighted": 0.6526203782124326, | |
| "eval_loss": 0.9398497939109802, | |
| "eval_precision_macro": 0.53233579791898, | |
| "eval_precision_micro": 0.6781666666666667, | |
| "eval_precision_weighted": 0.6686669761134056, | |
| "eval_recall_macro": 0.37103282997495, | |
| "eval_recall_micro": 0.6781666666666667, | |
| "eval_recall_weighted": 0.6781666666666667, | |
| "eval_runtime": 13.8601, | |
| "eval_samples_per_second": 432.897, | |
| "eval_steps_per_second": 27.056, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.6135802469135804e-05, | |
| "loss": 0.8418, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.520987654320988e-05, | |
| "loss": 0.7844, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.428395061728395e-05, | |
| "loss": 0.853, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.335802469135802e-05, | |
| "loss": 0.8219, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.24320987654321e-05, | |
| "loss": 0.8721, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.1506172839506175e-05, | |
| "loss": 0.7844, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.058024691358025e-05, | |
| "loss": 0.8645, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.965432098765432e-05, | |
| "loss": 0.7823, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.8728395061728397e-05, | |
| "loss": 0.7494, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.7802469135802474e-05, | |
| "loss": 0.8125, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.6876543209876543e-05, | |
| "loss": 0.7879, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.595061728395062e-05, | |
| "loss": 0.8092, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.5024691358024692e-05, | |
| "loss": 0.7535, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.4098765432098765e-05, | |
| "loss": 0.7787, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.317283950617284e-05, | |
| "loss": 0.8109, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.2246913580246914e-05, | |
| "loss": 0.7853, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.132098765432099e-05, | |
| "loss": 0.7999, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.0395061728395064e-05, | |
| "loss": 0.7545, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.9469135802469137e-05, | |
| "loss": 0.7805, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.854320987654321e-05, | |
| "loss": 0.741, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7148333333333333, | |
| "eval_f1_macro": 0.4743843561639563, | |
| "eval_f1_micro": 0.7148333333333333, | |
| "eval_f1_weighted": 0.6973841930196186, | |
| "eval_loss": 0.8727797865867615, | |
| "eval_precision_macro": 0.689196184834718, | |
| "eval_precision_micro": 0.7148333333333333, | |
| "eval_precision_weighted": 0.7078896728033317, | |
| "eval_recall_macro": 0.41641019062275997, | |
| "eval_recall_micro": 0.7148333333333333, | |
| "eval_recall_weighted": 0.7148333333333333, | |
| "eval_runtime": 13.8166, | |
| "eval_samples_per_second": 434.26, | |
| "eval_steps_per_second": 27.141, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 150, | |
| "max_steps": 9000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3157587800064000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |