| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.049, | |
| "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": 4.2000000000000006e-07, | |
| "loss": 1.1399, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.200000000000001e-07, | |
| "loss": 1.0896, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.42e-06, | |
| "loss": 0.5087, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 0.3005, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.42e-06, | |
| "loss": 0.2431, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.92e-06, | |
| "loss": 0.2133, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.4200000000000007e-06, | |
| "loss": 0.2139, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.920000000000001e-06, | |
| "loss": 0.2167, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.42e-06, | |
| "loss": 0.2431, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.92e-06, | |
| "loss": 0.2238, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5.420000000000001e-06, | |
| "loss": 0.2326, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5.92e-06, | |
| "loss": 0.191, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 6.42e-06, | |
| "loss": 0.2003, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 6.92e-06, | |
| "loss": 0.227, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.420000000000001e-06, | |
| "loss": 0.2297, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.92e-06, | |
| "loss": 0.1586, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 8.42e-06, | |
| "loss": 0.1579, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 8.920000000000001e-06, | |
| "loss": 0.1501, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 9.42e-06, | |
| "loss": 0.1332, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 9.920000000000002e-06, | |
| "loss": 0.1359, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 9.58e-06, | |
| "loss": 0.1483, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 9.080000000000001e-06, | |
| "loss": 0.1512, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 8.580000000000001e-06, | |
| "loss": 0.1344, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 8.08e-06, | |
| "loss": 0.1335, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 7.58e-06, | |
| "loss": 0.1112, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 7.08e-06, | |
| "loss": 0.1223, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.5800000000000005e-06, | |
| "loss": 0.1303, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 6.08e-06, | |
| "loss": 0.1094, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 5.580000000000001e-06, | |
| "loss": 0.0896, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 5.0800000000000005e-06, | |
| "loss": 0.0829, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.58e-06, | |
| "loss": 0.0717, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 4.08e-06, | |
| "loss": 0.0709, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.58e-06, | |
| "loss": 0.0716, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.08e-06, | |
| "loss": 0.0762, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 2.5800000000000003e-06, | |
| "loss": 0.0686, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.08e-06, | |
| "loss": 0.0628, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.5800000000000001e-06, | |
| "loss": 0.0648, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.08e-06, | |
| "loss": 0.0575, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 5.800000000000001e-07, | |
| "loss": 0.0696, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 8e-08, | |
| "loss": 0.0693, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 0.26113396883010864, | |
| "eval_runtime": 1552.6312, | |
| "eval_samples_per_second": 6.533, | |
| "eval_steps_per_second": 0.204, | |
| "eval_wer": 17.210750075918614, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "step": 1000, | |
| "total_flos": 1.844002990964736e+19, | |
| "train_loss": 0.20262496268749236, | |
| "train_runtime": 8345.5759, | |
| "train_samples_per_second": 7.669, | |
| "train_steps_per_second": 0.12 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.844002990964736e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |