| { | |
| "best_metric": 0.9278258085250854, | |
| "best_model_checkpoint": "./outputs/checkpoint-2200", | |
| "epoch": 2.9333333333333336, | |
| "eval_steps": 100, | |
| "global_step": 2200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9997, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.0932432413101196, | |
| "eval_runtime": 721.0711, | |
| "eval_samples_per_second": 2.677, | |
| "eval_steps_per_second": 0.336, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.897, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.0685845613479614, | |
| "eval_runtime": 721.8083, | |
| "eval_samples_per_second": 2.674, | |
| "eval_steps_per_second": 0.335, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8812, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.0530365705490112, | |
| "eval_runtime": 727.1346, | |
| "eval_samples_per_second": 2.654, | |
| "eval_steps_per_second": 0.333, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8694, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.0397064685821533, | |
| "eval_runtime": 725.2926, | |
| "eval_samples_per_second": 2.661, | |
| "eval_steps_per_second": 0.334, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8549, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.02787184715271, | |
| "eval_runtime": 726.5869, | |
| "eval_samples_per_second": 2.656, | |
| "eval_steps_per_second": 0.333, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8498, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.0169517993927002, | |
| "eval_runtime": 729.2685, | |
| "eval_samples_per_second": 2.646, | |
| "eval_steps_per_second": 0.332, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8448, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.011763572692871, | |
| "eval_runtime": 729.6091, | |
| "eval_samples_per_second": 2.645, | |
| "eval_steps_per_second": 0.332, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8276, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.0014097690582275, | |
| "eval_runtime": 726.8878, | |
| "eval_samples_per_second": 2.655, | |
| "eval_steps_per_second": 0.333, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.814, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.9944414496421814, | |
| "eval_runtime": 729.3383, | |
| "eval_samples_per_second": 2.646, | |
| "eval_steps_per_second": 0.332, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8088, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 0.986289381980896, | |
| "eval_runtime": 729.5573, | |
| "eval_samples_per_second": 2.645, | |
| "eval_steps_per_second": 0.332, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8149, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.9808956980705261, | |
| "eval_runtime": 729.1444, | |
| "eval_samples_per_second": 2.647, | |
| "eval_steps_per_second": 0.332, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.805, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.9745151996612549, | |
| "eval_runtime": 728.2022, | |
| "eval_samples_per_second": 2.65, | |
| "eval_steps_per_second": 0.332, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7946, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.9681212902069092, | |
| "eval_runtime": 729.3723, | |
| "eval_samples_per_second": 2.646, | |
| "eval_steps_per_second": 0.332, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7937, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.9620557427406311, | |
| "eval_runtime": 727.4393, | |
| "eval_samples_per_second": 2.653, | |
| "eval_steps_per_second": 0.333, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7863, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.9571696519851685, | |
| "eval_runtime": 726.583, | |
| "eval_samples_per_second": 2.656, | |
| "eval_steps_per_second": 0.333, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.766, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 0.9550056457519531, | |
| "eval_runtime": 729.0402, | |
| "eval_samples_per_second": 2.647, | |
| "eval_steps_per_second": 0.332, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7569, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 0.9508923292160034, | |
| "eval_runtime": 724.9845, | |
| "eval_samples_per_second": 2.662, | |
| "eval_steps_per_second": 0.334, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7573, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.9467226266860962, | |
| "eval_runtime": 729.7266, | |
| "eval_samples_per_second": 2.645, | |
| "eval_steps_per_second": 0.332, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7702, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 0.9409560561180115, | |
| "eval_runtime": 727.6024, | |
| "eval_samples_per_second": 2.653, | |
| "eval_steps_per_second": 0.333, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7577, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 0.9364367723464966, | |
| "eval_runtime": 733.1744, | |
| "eval_samples_per_second": 2.632, | |
| "eval_steps_per_second": 0.33, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7525, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.9320885539054871, | |
| "eval_runtime": 728.1051, | |
| "eval_samples_per_second": 2.651, | |
| "eval_steps_per_second": 0.332, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7485, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 0.9278258085250854, | |
| "eval_runtime": 857.14, | |
| "eval_samples_per_second": 2.252, | |
| "eval_steps_per_second": 0.282, | |
| "step": 2200 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 5.6988624815579136e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |