| { | |
| "best_metric": 0.6430063247680664, | |
| "best_model_checkpoint": "output/checkpoint-50", | |
| "epoch": 0.9219360657380499, | |
| "eval_steps": 50, | |
| "global_step": 1150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.444444444444445e-07, | |
| "loss": 0.5542, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2e-05, | |
| "loss": 0.554, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.6626865671641791, | |
| "eval_loss": 0.6430063247680664, | |
| "eval_runtime": 61.7692, | |
| "eval_samples_per_second": 5.423, | |
| "eval_steps_per_second": 1.36, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.5957, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.6686567164179105, | |
| "eval_loss": 0.6705919504165649, | |
| "eval_runtime": 60.4388, | |
| "eval_samples_per_second": 5.543, | |
| "eval_steps_per_second": 1.39, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.444444444444446e-05, | |
| "loss": 0.5668, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.6805970149253732, | |
| "eval_loss": 0.7224913835525513, | |
| "eval_runtime": 56.4882, | |
| "eval_samples_per_second": 5.93, | |
| "eval_steps_per_second": 1.487, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 0.5626, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.6746268656716418, | |
| "eval_loss": 0.7115103006362915, | |
| "eval_runtime": 56.506, | |
| "eval_samples_per_second": 5.929, | |
| "eval_steps_per_second": 1.487, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.80430528375734e-05, | |
| "loss": 0.5604, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.6746268656716418, | |
| "eval_loss": 0.700947105884552, | |
| "eval_runtime": 56.4927, | |
| "eval_samples_per_second": 5.93, | |
| "eval_steps_per_second": 1.487, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.315068493150684e-05, | |
| "loss": 0.5675, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.6597014925373135, | |
| "eval_loss": 0.662155032157898, | |
| "eval_runtime": 56.4903, | |
| "eval_samples_per_second": 5.93, | |
| "eval_steps_per_second": 1.487, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.825831702544032e-05, | |
| "loss": 0.5725, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.6567164179104478, | |
| "eval_loss": 0.6746364831924438, | |
| "eval_runtime": 56.482, | |
| "eval_samples_per_second": 5.931, | |
| "eval_steps_per_second": 1.487, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.336594911937378e-05, | |
| "loss": 0.5884, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.6656716417910448, | |
| "eval_loss": 0.7047849893569946, | |
| "eval_runtime": 56.4873, | |
| "eval_samples_per_second": 5.931, | |
| "eval_steps_per_second": 1.487, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.847358121330725e-05, | |
| "loss": 0.5567, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.6477611940298508, | |
| "eval_loss": 0.6832321286201477, | |
| "eval_runtime": 56.4814, | |
| "eval_samples_per_second": 5.931, | |
| "eval_steps_per_second": 1.487, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.35812133072407e-05, | |
| "loss": 0.5723, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.6955223880597015, | |
| "eval_loss": 0.7437570691108704, | |
| "eval_runtime": 56.4677, | |
| "eval_samples_per_second": 5.933, | |
| "eval_steps_per_second": 1.488, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.868884540117417e-05, | |
| "loss": 0.5908, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.6238805970149254, | |
| "eval_loss": 0.6612433791160583, | |
| "eval_runtime": 56.4799, | |
| "eval_samples_per_second": 5.931, | |
| "eval_steps_per_second": 1.487, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.379647749510763e-05, | |
| "loss": 0.5681, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.6507462686567164, | |
| "eval_loss": 0.6833732724189758, | |
| "eval_runtime": 56.4689, | |
| "eval_samples_per_second": 5.932, | |
| "eval_steps_per_second": 1.488, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.89041095890411e-05, | |
| "loss": 0.5782, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.6507462686567164, | |
| "eval_loss": 0.67350834608078, | |
| "eval_runtime": 56.4637, | |
| "eval_samples_per_second": 5.933, | |
| "eval_steps_per_second": 1.488, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.401174168297456e-05, | |
| "loss": 0.569, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.6686567164179105, | |
| "eval_loss": 0.7085319757461548, | |
| "eval_runtime": 56.4627, | |
| "eval_samples_per_second": 5.933, | |
| "eval_steps_per_second": 1.488, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.911937377690802e-05, | |
| "loss": 0.5661, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.6835820895522388, | |
| "eval_loss": 0.7564846277236938, | |
| "eval_runtime": 56.4648, | |
| "eval_samples_per_second": 5.933, | |
| "eval_steps_per_second": 1.488, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.422700587084149e-05, | |
| "loss": 0.5675, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.6417910447761194, | |
| "eval_loss": 0.6759604215621948, | |
| "eval_runtime": 56.4652, | |
| "eval_samples_per_second": 5.933, | |
| "eval_steps_per_second": 1.488, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.933463796477495e-05, | |
| "loss": 0.5611, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.6477611940298508, | |
| "eval_loss": 0.6798116564750671, | |
| "eval_runtime": 56.4714, | |
| "eval_samples_per_second": 5.932, | |
| "eval_steps_per_second": 1.487, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.4442270058708414e-05, | |
| "loss": 0.5664, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.6656716417910448, | |
| "eval_loss": 0.7185413837432861, | |
| "eval_runtime": 56.4811, | |
| "eval_samples_per_second": 5.931, | |
| "eval_steps_per_second": 1.487, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.9549902152641878e-05, | |
| "loss": 0.5765, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.6417910447761194, | |
| "eval_loss": 0.6795146465301514, | |
| "eval_runtime": 56.4589, | |
| "eval_samples_per_second": 5.934, | |
| "eval_steps_per_second": 1.488, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.4657534246575342e-05, | |
| "loss": 0.555, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.6298507462686567, | |
| "eval_loss": 0.677854061126709, | |
| "eval_runtime": 56.4673, | |
| "eval_samples_per_second": 5.933, | |
| "eval_steps_per_second": 1.488, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.9765166340508805e-05, | |
| "loss": 0.5578, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.6507462686567164, | |
| "eval_loss": 0.6885824203491211, | |
| "eval_runtime": 56.4615, | |
| "eval_samples_per_second": 5.933, | |
| "eval_steps_per_second": 1.488, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.4872798434442269e-05, | |
| "loss": 0.5709, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.6447761194029851, | |
| "eval_loss": 0.6935857534408569, | |
| "eval_runtime": 56.4542, | |
| "eval_samples_per_second": 5.934, | |
| "eval_steps_per_second": 1.488, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.980430528375734e-06, | |
| "loss": 0.5711, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.6388059701492538, | |
| "eval_loss": 0.6908484101295471, | |
| "eval_runtime": 56.4666, | |
| "eval_samples_per_second": 5.933, | |
| "eval_steps_per_second": 1.488, | |
| "step": 1150 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1247, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 4.2922784557756416e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |