| { | |
| "best_metric": 0.45803794264793396, | |
| "best_model_checkpoint": "output/checkpoint-150", | |
| "epoch": 0.9625990173468365, | |
| "eval_steps": 50, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.6453, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.777777777777779e-06, | |
| "loss": 1.3216, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.8057142857142857, | |
| "eval_loss": 0.6264824271202087, | |
| "eval_runtime": 28.8159, | |
| "eval_samples_per_second": 6.073, | |
| "eval_steps_per_second": 1.527, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.088888888888889e-05, | |
| "loss": 0.918, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.7885714285714286, | |
| "eval_loss": 0.49068325757980347, | |
| "eval_runtime": 26.1642, | |
| "eval_samples_per_second": 6.689, | |
| "eval_steps_per_second": 1.682, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.7219, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.7942857142857143, | |
| "eval_loss": 0.45803794264793396, | |
| "eval_runtime": 26.1308, | |
| "eval_samples_per_second": 6.697, | |
| "eval_steps_per_second": 1.684, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.311111111111111e-05, | |
| "loss": 0.6619, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.4676758646965027, | |
| "eval_runtime": 26.1149, | |
| "eval_samples_per_second": 6.701, | |
| "eval_steps_per_second": 1.685, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.906953966699315e-05, | |
| "loss": 0.633, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.8114285714285714, | |
| "eval_loss": 0.4800652265548706, | |
| "eval_runtime": 26.1161, | |
| "eval_samples_per_second": 6.701, | |
| "eval_steps_per_second": 1.685, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.66209598432909e-05, | |
| "loss": 0.6147, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.7657142857142857, | |
| "eval_loss": 0.5112562775611877, | |
| "eval_runtime": 26.1127, | |
| "eval_samples_per_second": 6.702, | |
| "eval_steps_per_second": 1.685, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.4172380019588636e-05, | |
| "loss": 0.6355, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.7828571428571428, | |
| "eval_loss": 0.5210281610488892, | |
| "eval_runtime": 26.1048, | |
| "eval_samples_per_second": 6.704, | |
| "eval_steps_per_second": 1.686, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.1723800195886386e-05, | |
| "loss": 0.593, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.7885714285714286, | |
| "eval_loss": 0.5098910927772522, | |
| "eval_runtime": 26.1072, | |
| "eval_samples_per_second": 6.703, | |
| "eval_steps_per_second": 1.685, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.927522037218414e-05, | |
| "loss": 0.6047, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.7314285714285714, | |
| "eval_loss": 0.5602952837944031, | |
| "eval_runtime": 26.1116, | |
| "eval_samples_per_second": 6.702, | |
| "eval_steps_per_second": 1.685, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.682664054848188e-05, | |
| "loss": 0.5661, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.7542857142857143, | |
| "eval_loss": 0.5670996904373169, | |
| "eval_runtime": 26.1104, | |
| "eval_samples_per_second": 6.702, | |
| "eval_steps_per_second": 1.685, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.437806072477963e-05, | |
| "loss": 0.6111, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.7714285714285715, | |
| "eval_loss": 0.5074692368507385, | |
| "eval_runtime": 26.1037, | |
| "eval_samples_per_second": 6.704, | |
| "eval_steps_per_second": 1.686, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 3.1929480901077375e-05, | |
| "loss": 0.5788, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.7485714285714286, | |
| "eval_loss": 0.6720603108406067, | |
| "eval_runtime": 26.1036, | |
| "eval_samples_per_second": 6.704, | |
| "eval_steps_per_second": 1.686, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.9480901077375122e-05, | |
| "loss": 0.562, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.7942857142857143, | |
| "eval_loss": 0.5063876509666443, | |
| "eval_runtime": 26.1086, | |
| "eval_samples_per_second": 6.703, | |
| "eval_steps_per_second": 1.685, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.7032321253672872e-05, | |
| "loss": 0.5472, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.7371428571428571, | |
| "eval_loss": 0.5650284886360168, | |
| "eval_runtime": 26.1065, | |
| "eval_samples_per_second": 6.703, | |
| "eval_steps_per_second": 1.685, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.458374142997062e-05, | |
| "loss": 0.551, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.5052895545959473, | |
| "eval_runtime": 26.1094, | |
| "eval_samples_per_second": 6.703, | |
| "eval_steps_per_second": 1.685, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.2135161606268366e-05, | |
| "loss": 0.5259, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.7485714285714286, | |
| "eval_loss": 0.5384859442710876, | |
| "eval_runtime": 26.0891, | |
| "eval_samples_per_second": 6.708, | |
| "eval_steps_per_second": 1.687, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.9686581782566114e-05, | |
| "loss": 0.5231, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.7371428571428571, | |
| "eval_loss": 0.5821840763092041, | |
| "eval_runtime": 26.0996, | |
| "eval_samples_per_second": 6.705, | |
| "eval_steps_per_second": 1.686, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.7238001958863857e-05, | |
| "loss": 0.4987, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.5697786211967468, | |
| "eval_runtime": 26.0884, | |
| "eval_samples_per_second": 6.708, | |
| "eval_steps_per_second": 1.687, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.4789422135161608e-05, | |
| "loss": 0.5019, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.7657142857142857, | |
| "eval_loss": 0.5529425740242004, | |
| "eval_runtime": 26.1154, | |
| "eval_samples_per_second": 6.701, | |
| "eval_steps_per_second": 1.685, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2340842311459353e-05, | |
| "loss": 0.515, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.7314285714285714, | |
| "eval_loss": 0.571620762348175, | |
| "eval_runtime": 26.0898, | |
| "eval_samples_per_second": 6.708, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.8922624877571e-06, | |
| "loss": 0.5154, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.7257142857142858, | |
| "eval_loss": 0.5566055774688721, | |
| "eval_runtime": 26.1014, | |
| "eval_samples_per_second": 6.705, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.443682664054849e-06, | |
| "loss": 0.5066, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.6971428571428572, | |
| "eval_loss": 0.5895078778266907, | |
| "eval_runtime": 26.0898, | |
| "eval_samples_per_second": 6.708, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.995102840352596e-06, | |
| "loss": 0.5173, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.6914285714285714, | |
| "eval_loss": 0.5952877402305603, | |
| "eval_runtime": 26.0937, | |
| "eval_samples_per_second": 6.707, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.5465230166503427e-06, | |
| "loss": 0.5043, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.6914285714285714, | |
| "eval_loss": 0.5993438959121704, | |
| "eval_runtime": 26.0968, | |
| "eval_samples_per_second": 6.706, | |
| "eval_steps_per_second": 1.686, | |
| "step": 1200 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1246, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 4.451075398582272e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |