| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.999600585807483, | |
| "global_step": 11262, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8712499999999997e-05, | |
| "loss": 6.2099, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 3.41253662109375, | |
| "eval_runtime": 1358.074, | |
| "eval_samples_per_second": 14.868, | |
| "eval_steps_per_second": 0.465, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.7462499999999996e-05, | |
| "loss": 2.9961, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 2.9223873615264893, | |
| "eval_runtime": 1361.8836, | |
| "eval_samples_per_second": 14.827, | |
| "eval_steps_per_second": 0.463, | |
| "eval_wer": 1.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 5.62125e-05, | |
| "loss": 2.2147, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.6520791053771973, | |
| "eval_runtime": 1355.9385, | |
| "eval_samples_per_second": 14.892, | |
| "eval_steps_per_second": 0.465, | |
| "eval_wer": 0.5567824255052013, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.49625e-05, | |
| "loss": 1.3017, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.31525641679763794, | |
| "eval_runtime": 1371.0684, | |
| "eval_samples_per_second": 14.727, | |
| "eval_steps_per_second": 0.46, | |
| "eval_wer": 0.27607269814249236, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 7.431581352833637e-05, | |
| "loss": 1.1196, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.24444133043289185, | |
| "eval_runtime": 1363.4869, | |
| "eval_samples_per_second": 14.809, | |
| "eval_steps_per_second": 0.463, | |
| "eval_wer": 0.23673497683411066, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 7.363162705667275e-05, | |
| "loss": 1.0712, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.23236490786075592, | |
| "eval_runtime": 1368.4487, | |
| "eval_samples_per_second": 14.755, | |
| "eval_steps_per_second": 0.461, | |
| "eval_wer": 0.21321861436015543, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.294606946983546e-05, | |
| "loss": 1.052, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.21734564006328583, | |
| "eval_runtime": 1358.6503, | |
| "eval_samples_per_second": 14.862, | |
| "eval_steps_per_second": 0.464, | |
| "eval_wer": 0.20317428528513493, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 3.375103277334068e-05, | |
| "loss": 1.2813, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 0.332599401473999, | |
| "eval_runtime": 393.989, | |
| "eval_samples_per_second": 10.906, | |
| "eval_steps_per_second": 0.343, | |
| "eval_wer": 0.20989847979467358, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.3423299366565682e-05, | |
| "loss": 1.2365, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.3223731815814972, | |
| "eval_runtime": 391.7507, | |
| "eval_samples_per_second": 10.969, | |
| "eval_steps_per_second": 0.345, | |
| "eval_wer": 0.2003283560376986, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 1.309556595979069e-05, | |
| "loss": 1.2193, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 0.31981074810028076, | |
| "eval_runtime": 402.4439, | |
| "eval_samples_per_second": 10.677, | |
| "eval_steps_per_second": 0.335, | |
| "eval_wer": 0.19565239980464894, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 2.767832553015698e-06, | |
| "loss": 1.2072, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 0.3063456118106842, | |
| "eval_runtime": 396.6525, | |
| "eval_samples_per_second": 10.833, | |
| "eval_steps_per_second": 0.34, | |
| "eval_wer": 0.19327285763271923, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.263388037141005e-05, | |
| "loss": 1.213, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 0.3051116168498993, | |
| "eval_runtime": 371.5477, | |
| "eval_samples_per_second": 11.565, | |
| "eval_steps_per_second": 0.363, | |
| "eval_wer": 0.19797998690732255, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 3.8585078816670256e-05, | |
| "loss": 1.2074, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "eval_loss": 0.3011966645717621, | |
| "eval_runtime": 372.0587, | |
| "eval_samples_per_second": 11.549, | |
| "eval_steps_per_second": 0.363, | |
| "eval_wer": 0.18792148549934018, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 3.4536277261930465e-05, | |
| "loss": 1.1918, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "eval_loss": 0.29471954703330994, | |
| "eval_runtime": 372.8767, | |
| "eval_samples_per_second": 11.524, | |
| "eval_steps_per_second": 0.362, | |
| "eval_wer": 0.18287145276764655, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.0487475707190668e-05, | |
| "loss": 1.1893, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.28953900933265686, | |
| "eval_runtime": 372.4558, | |
| "eval_samples_per_second": 11.537, | |
| "eval_steps_per_second": 0.362, | |
| "eval_wer": 0.1807205129004437, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 2.643867415245087e-05, | |
| "loss": 1.1751, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "eval_loss": 0.2877567410469055, | |
| "eval_runtime": 371.9244, | |
| "eval_samples_per_second": 11.553, | |
| "eval_steps_per_second": 0.363, | |
| "eval_wer": 0.17759281773122604, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 2.2389872597711073e-05, | |
| "loss": 1.1628, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "eval_loss": 0.28352275490760803, | |
| "eval_runtime": 373.4388, | |
| "eval_samples_per_second": 11.507, | |
| "eval_steps_per_second": 0.362, | |
| "eval_wer": 0.1730727267059447, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 1.834107104297128e-05, | |
| "loss": 1.1577, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "eval_loss": 0.28156954050064087, | |
| "eval_runtime": 371.5997, | |
| "eval_samples_per_second": 11.564, | |
| "eval_steps_per_second": 0.363, | |
| "eval_wer": 0.17605494768124527, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 1.4300367091340963e-05, | |
| "loss": 1.1448, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "eval_loss": 0.2757455110549927, | |
| "eval_runtime": 373.7148, | |
| "eval_samples_per_second": 11.498, | |
| "eval_steps_per_second": 0.361, | |
| "eval_wer": 0.17397674491100096, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 1.0251565536601165e-05, | |
| "loss": 1.1407, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "eval_loss": 0.2768358588218689, | |
| "eval_runtime": 373.2273, | |
| "eval_samples_per_second": 11.513, | |
| "eval_steps_per_second": 0.362, | |
| "eval_wer": 0.17976453962613131, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 6.202763981861369e-06, | |
| "loss": 1.1401, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "eval_loss": 0.2780420780181885, | |
| "eval_runtime": 375.3753, | |
| "eval_samples_per_second": 11.447, | |
| "eval_steps_per_second": 0.36, | |
| "eval_wer": 0.18160374907779753, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 2.153962427121572e-06, | |
| "loss": 1.1333, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "eval_loss": 0.2748132646083832, | |
| "eval_runtime": 371.6352, | |
| "eval_samples_per_second": 11.562, | |
| "eval_steps_per_second": 0.363, | |
| "eval_wer": 0.17495350021301578, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 11262, | |
| "total_flos": 3.063803468240281e+20, | |
| "train_loss": 0.5975231319014925, | |
| "train_runtime": 88923.2167, | |
| "train_samples_per_second": 16.216, | |
| "train_steps_per_second": 0.127 | |
| } | |
| ], | |
| "max_steps": 11262, | |
| "num_train_epochs": 6, | |
| "total_flos": 3.063803468240281e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |