| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.04, | |
| "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": 2.6357, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.4e-06, | |
| "loss": 1.1709, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5833, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4675, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4283, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3938, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3441, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3245, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3231, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2487, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1887, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1e-05, | |
| "loss": 0.194, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1661, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1686, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1446, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1445, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1493, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1011, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0859, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.087, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0787, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0723, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0663, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0732, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0634, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0461, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0442, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0395, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0371, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0357, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0344, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0374, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0328, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0228, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0239, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0205, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0204, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0211, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0201, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0212, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "eval_loss": 0.4091407060623169, | |
| "eval_runtime": 2023.4771, | |
| "eval_samples_per_second": 2.532, | |
| "eval_steps_per_second": 0.159, | |
| "eval_wer": 33.104473386183464, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "step": 1000, | |
| "total_flos": 9.205874270208e+18, | |
| "train_loss": 0.22901735782623292, | |
| "train_runtime": 5468.9251, | |
| "train_samples_per_second": 5.851, | |
| "train_steps_per_second": 0.183 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 9.205874270208e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |