| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.2650000000000001, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 0.6617, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.3705, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3011, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2511, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2239, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2173, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2469, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2689, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2081, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2004, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1881, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2395, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1981, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1862, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1541, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.196, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1792, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1691, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1604, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1711, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1676, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1676, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1537, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1436, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2618, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3308, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2803, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2438, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2396, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2878, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2063, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1593, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1342, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1209, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1221, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1355, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1503, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1393, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1271, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1057, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.23630358278751373, | |
| "eval_runtime": 6814.4877, | |
| "eval_samples_per_second": 1.734, | |
| "eval_steps_per_second": 0.108, | |
| "eval_wer": 12.525534846157502, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "step": 1000, | |
| "total_flos": 9.23357846863872e+18, | |
| "train_loss": 0.2117276496887207, | |
| "train_runtime": 10543.3397, | |
| "train_samples_per_second": 3.035, | |
| "train_steps_per_second": 0.095 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 9.23357846863872e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |