| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.03, | |
| "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": 4.4e-06, | |
| "loss": 0.9569, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.4e-06, | |
| "loss": 0.3894, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2687, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2337, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2489, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2167, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2061, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2224, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2625, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2468, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2173, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2145, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2131, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2189, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1924, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2072, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2229, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2295, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2471, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2184, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-05, | |
| "loss": 0.211, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2061, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2067, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2136, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2185, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2203, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2007, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1924, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1802, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2249, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1922, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2316, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2101, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2112, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2152, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2356, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2237, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2122, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.257, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3281, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.24993625283241272, | |
| "eval_runtime": 4077.3451, | |
| "eval_samples_per_second": 3.806, | |
| "eval_steps_per_second": 0.238, | |
| "eval_wer": 9.736370251026454, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "step": 1000, | |
| "total_flos": 9.23473281024e+18, | |
| "train_loss": 0.24561575746536254, | |
| "train_runtime": 7682.7325, | |
| "train_samples_per_second": 4.165, | |
| "train_steps_per_second": 0.13 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 9.23473281024e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |