| { | |
| "best_metric": 1.069016456604004, | |
| "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": 1.2967, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.1820014715194702, | |
| "eval_runtime": 212.2382, | |
| "eval_samples_per_second": 9.094, | |
| "eval_steps_per_second": 1.14, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0116, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.1465147733688354, | |
| "eval_runtime": 185.6672, | |
| "eval_samples_per_second": 10.395, | |
| "eval_steps_per_second": 1.303, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9916, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.1323238611221313, | |
| "eval_runtime": 186.616, | |
| "eval_samples_per_second": 10.342, | |
| "eval_steps_per_second": 1.297, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9798, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.1225333213806152, | |
| "eval_runtime": 187.7396, | |
| "eval_samples_per_second": 10.28, | |
| "eval_steps_per_second": 1.289, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9658, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.1167433261871338, | |
| "eval_runtime": 186.8716, | |
| "eval_samples_per_second": 10.328, | |
| "eval_steps_per_second": 1.295, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9675, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.1117215156555176, | |
| "eval_runtime": 187.1986, | |
| "eval_samples_per_second": 10.31, | |
| "eval_steps_per_second": 1.293, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9639, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.107673168182373, | |
| "eval_runtime": 238.8707, | |
| "eval_samples_per_second": 8.08, | |
| "eval_steps_per_second": 1.013, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9532, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.103180170059204, | |
| "eval_runtime": 531.86, | |
| "eval_samples_per_second": 3.629, | |
| "eval_steps_per_second": 0.455, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9517, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.1001368761062622, | |
| "eval_runtime": 467.265, | |
| "eval_samples_per_second": 4.13, | |
| "eval_steps_per_second": 0.518, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.949, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.097861647605896, | |
| "eval_runtime": 187.1864, | |
| "eval_samples_per_second": 10.311, | |
| "eval_steps_per_second": 1.293, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9446, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.0939323902130127, | |
| "eval_runtime": 187.3718, | |
| "eval_samples_per_second": 10.3, | |
| "eval_steps_per_second": 1.292, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9365, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.0908570289611816, | |
| "eval_runtime": 187.4782, | |
| "eval_samples_per_second": 10.295, | |
| "eval_steps_per_second": 1.291, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.941, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.0867445468902588, | |
| "eval_runtime": 187.5842, | |
| "eval_samples_per_second": 10.289, | |
| "eval_steps_per_second": 1.29, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9422, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.0860801935195923, | |
| "eval_runtime": 244.4477, | |
| "eval_samples_per_second": 7.895, | |
| "eval_steps_per_second": 0.99, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9353, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.0852444171905518, | |
| "eval_runtime": 187.7805, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.289, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.933, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.0824370384216309, | |
| "eval_runtime": 187.7567, | |
| "eval_samples_per_second": 10.279, | |
| "eval_steps_per_second": 1.289, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9305, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.0762122869491577, | |
| "eval_runtime": 205.0639, | |
| "eval_samples_per_second": 9.412, | |
| "eval_steps_per_second": 1.18, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9245, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.077301263809204, | |
| "eval_runtime": 356.8145, | |
| "eval_samples_per_second": 5.409, | |
| "eval_steps_per_second": 0.678, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9215, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.0724916458129883, | |
| "eval_runtime": 235.9181, | |
| "eval_samples_per_second": 8.181, | |
| "eval_steps_per_second": 1.026, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9308, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.072939395904541, | |
| "eval_runtime": 188.2681, | |
| "eval_samples_per_second": 10.251, | |
| "eval_steps_per_second": 1.285, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9262, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 1.0696160793304443, | |
| "eval_runtime": 192.1089, | |
| "eval_samples_per_second": 10.046, | |
| "eval_steps_per_second": 1.26, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9177, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 1.069016456604004, | |
| "eval_runtime": 197.4097, | |
| "eval_samples_per_second": 9.777, | |
| "eval_steps_per_second": 1.226, | |
| "step": 2200 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 3.110307163440169e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |