| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 19, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.062219502243982046, | |
| "eval_loss": 2.654296875, | |
| "eval_runtime": 2.3869, | |
| "eval_samples_per_second": 23.881, | |
| "eval_steps_per_second": 1.676, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6914, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.062219502243982046, | |
| "eval_loss": 2.654296875, | |
| "eval_runtime": 3.2001, | |
| "eval_samples_per_second": 17.812, | |
| "eval_steps_per_second": 1.25, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.9795419551040836e-05, | |
| "loss": 2.6003, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.06265016546534294, | |
| "eval_loss": 2.6015625, | |
| "eval_runtime": 3.1764, | |
| "eval_samples_per_second": 17.945, | |
| "eval_steps_per_second": 1.259, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.9187258625509518e-05, | |
| "loss": 2.5603, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.06260483249467337, | |
| "eval_loss": 2.5703125, | |
| "eval_runtime": 2.9857, | |
| "eval_samples_per_second": 19.091, | |
| "eval_steps_per_second": 1.34, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.8192106268097336e-05, | |
| "loss": 2.606, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.06292216328936036, | |
| "eval_loss": 2.55078125, | |
| "eval_runtime": 2.5694, | |
| "eval_samples_per_second": 22.184, | |
| "eval_steps_per_second": 1.557, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.6837107640945904e-05, | |
| "loss": 2.5439, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.06292216328936036, | |
| "eval_loss": 2.544921875, | |
| "eval_runtime": 3.1779, | |
| "eval_samples_per_second": 17.937, | |
| "eval_steps_per_second": 1.259, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.5159223574386117e-05, | |
| "loss": 2.4449, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.06287683031869079, | |
| "eval_loss": 2.546875, | |
| "eval_runtime": 2.3628, | |
| "eval_samples_per_second": 24.124, | |
| "eval_steps_per_second": 1.693, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.320422237183641e-05, | |
| "loss": 2.5422, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.0629901627453647, | |
| "eval_loss": 2.546875, | |
| "eval_runtime": 3.1712, | |
| "eval_samples_per_second": 17.974, | |
| "eval_steps_per_second": 1.261, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.1025431369794546e-05, | |
| "loss": 2.6101, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.06319416111337776, | |
| "eval_loss": 2.541015625, | |
| "eval_runtime": 2.3922, | |
| "eval_samples_per_second": 23.827, | |
| "eval_steps_per_second": 1.672, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.8682282307111988e-05, | |
| "loss": 2.4482, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.0629901627453647, | |
| "eval_loss": 2.53515625, | |
| "eval_runtime": 2.3705, | |
| "eval_samples_per_second": 24.045, | |
| "eval_steps_per_second": 1.687, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.623869018208499e-05, | |
| "loss": 2.501, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.0631261616573734, | |
| "eval_loss": 2.529296875, | |
| "eval_runtime": 2.7727, | |
| "eval_samples_per_second": 20.558, | |
| "eval_steps_per_second": 1.443, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.3761309817915017e-05, | |
| "loss": 2.5967, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.06337549299605603, | |
| "eval_loss": 2.521484375, | |
| "eval_runtime": 2.168, | |
| "eval_samples_per_second": 26.292, | |
| "eval_steps_per_second": 1.845, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.1317717692888014e-05, | |
| "loss": 2.4998, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.06346615893739517, | |
| "eval_loss": 2.513671875, | |
| "eval_runtime": 3.1858, | |
| "eval_samples_per_second": 17.892, | |
| "eval_steps_per_second": 1.256, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.974568630205462e-06, | |
| "loss": 2.5957, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.06364749082007344, | |
| "eval_loss": 2.509765625, | |
| "eval_runtime": 2.1678, | |
| "eval_samples_per_second": 26.294, | |
| "eval_steps_per_second": 1.845, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.795777628163599e-06, | |
| "loss": 2.5967, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.06387415567342128, | |
| "eval_loss": 2.50390625, | |
| "eval_runtime": 3.188, | |
| "eval_samples_per_second": 17.879, | |
| "eval_steps_per_second": 1.255, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.840776425613887e-06, | |
| "loss": 2.5022, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.06373815676141258, | |
| "eval_loss": 2.5, | |
| "eval_runtime": 3.178, | |
| "eval_samples_per_second": 17.936, | |
| "eval_steps_per_second": 1.259, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.162892359054098e-06, | |
| "loss": 2.4314, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.06371549027607779, | |
| "eval_loss": 2.498046875, | |
| "eval_runtime": 2.968, | |
| "eval_samples_per_second": 19.205, | |
| "eval_steps_per_second": 1.348, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.8078937319026655e-06, | |
| "loss": 2.6279, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.06362482433473865, | |
| "eval_loss": 2.49609375, | |
| "eval_runtime": 3.1736, | |
| "eval_samples_per_second": 17.961, | |
| "eval_steps_per_second": 1.26, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 8.127413744904805e-07, | |
| "loss": 2.571, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.06357949136406908, | |
| "eval_loss": 2.49609375, | |
| "eval_runtime": 2.9674, | |
| "eval_samples_per_second": 19.208, | |
| "eval_steps_per_second": 1.348, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 19, | |
| "total_flos": 1001216802816.0, | |
| "train_loss": 2.5612600226151314, | |
| "train_runtime": 437.2347, | |
| "train_samples_per_second": 0.693, | |
| "train_steps_per_second": 0.043 | |
| } | |
| ], | |
| "max_steps": 19, | |
| "num_train_epochs": 1, | |
| "total_flos": 1001216802816.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |