| { | |
| "best_metric": 8.99256706237793, | |
| "best_model_checkpoint": "wav2vec2-large-xlsr-coraa-exp-11/checkpoint-168", | |
| "epoch": 32.0, | |
| "global_step": 448, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3e-05, | |
| "loss": 38.5161, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_cer": 0.9510100090991811, | |
| "eval_loss": 34.24892807006836, | |
| "eval_runtime": 52.8709, | |
| "eval_samples_per_second": 10.251, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 1.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_cer": 0.9510464058234759, | |
| "eval_loss": 23.386924743652344, | |
| "eval_runtime": 52.734, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 1.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_cer": 0.9510464058234759, | |
| "eval_loss": 19.672130584716797, | |
| "eval_runtime": 53.3907, | |
| "eval_samples_per_second": 10.152, | |
| "eval_steps_per_second": 1.274, | |
| "eval_wer": 1.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_cer": 0.9510464058234759, | |
| "eval_loss": 18.373493194580078, | |
| "eval_runtime": 52.736, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 1.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_cer": 0.9495905368516834, | |
| "eval_loss": 17.55065155029297, | |
| "eval_runtime": 52.7319, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0026412027631044, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_cer": 0.9688080072793449, | |
| "eval_loss": 16.934043884277344, | |
| "eval_runtime": 52.6762, | |
| "eval_samples_per_second": 10.289, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 1.0737505079236083, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_cer": 0.9511191992720656, | |
| "eval_loss": 17.322906494140625, | |
| "eval_runtime": 52.7337, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 1.0004063388866316, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 2.8614285714285714e-05, | |
| "loss": 17.5323, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_cer": 0.9313921747042766, | |
| "eval_loss": 16.459413528442383, | |
| "eval_runtime": 52.7143, | |
| "eval_samples_per_second": 10.282, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0156440471353108, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_cer": 0.935213830755232, | |
| "eval_loss": 12.445086479187012, | |
| "eval_runtime": 52.7004, | |
| "eval_samples_per_second": 10.285, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0298659081674115, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_cer": 0.9618562329390354, | |
| "eval_loss": 10.092220306396484, | |
| "eval_runtime": 52.7354, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 1.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_cer": 0.9617834394904459, | |
| "eval_loss": 9.518609046936035, | |
| "eval_runtime": 53.2311, | |
| "eval_samples_per_second": 10.182, | |
| "eval_steps_per_second": 1.277, | |
| "eval_wer": 0.9997968305566842, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_cer": 0.932302092811647, | |
| "eval_loss": 8.99256706237793, | |
| "eval_runtime": 52.6632, | |
| "eval_samples_per_second": 10.292, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.9865908167411621, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_cer": 0.9166515013648772, | |
| "eval_loss": 9.018474578857422, | |
| "eval_runtime": 52.7545, | |
| "eval_samples_per_second": 10.274, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.9839496139780577, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_cer": 0.9216378525932666, | |
| "eval_loss": 9.124226570129395, | |
| "eval_runtime": 53.3159, | |
| "eval_samples_per_second": 10.166, | |
| "eval_steps_per_second": 1.275, | |
| "eval_wer": 0.983746444534742, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 2.7185714285714287e-05, | |
| "loss": 6.6506, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_cer": 0.8844404003639672, | |
| "eval_loss": 9.050068855285645, | |
| "eval_runtime": 52.6837, | |
| "eval_samples_per_second": 10.288, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.9880130028443722, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_cer": 0.902238398544131, | |
| "eval_loss": 9.189239501953125, | |
| "eval_runtime": 52.7185, | |
| "eval_samples_per_second": 10.281, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.9776513612352702, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_cer": 0.8847315741583257, | |
| "eval_loss": 9.173331260681152, | |
| "eval_runtime": 52.733, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.9798862251117432, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_cer": 0.8733393994540491, | |
| "eval_loss": 9.303343772888184, | |
| "eval_runtime": 52.7609, | |
| "eval_samples_per_second": 10.273, | |
| "eval_steps_per_second": 1.289, | |
| "eval_wer": 0.9798862251117432, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_cer": 0.8989626933575978, | |
| "eval_loss": 9.28529167175293, | |
| "eval_runtime": 52.7177, | |
| "eval_samples_per_second": 10.281, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.9746038195855343, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_cer": 0.9086442220200182, | |
| "eval_loss": 9.438006401062012, | |
| "eval_runtime": 52.8014, | |
| "eval_samples_per_second": 10.265, | |
| "eval_steps_per_second": 1.288, | |
| "eval_wer": 0.9748069890288501, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_cer": 0.8900090991810737, | |
| "eval_loss": 9.513178825378418, | |
| "eval_runtime": 52.7023, | |
| "eval_samples_per_second": 10.284, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.9750101584721658, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 2.5757142857142857e-05, | |
| "loss": 3.6568, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_cer": 0.8811282984531392, | |
| "eval_loss": 9.6267728805542, | |
| "eval_runtime": 53.0646, | |
| "eval_samples_per_second": 10.214, | |
| "eval_steps_per_second": 1.281, | |
| "eval_wer": 0.9817147501015847, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_cer": 0.8846587807097361, | |
| "eval_loss": 9.698858261108398, | |
| "eval_runtime": 52.7263, | |
| "eval_samples_per_second": 10.28, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 1.0042665583096302, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_cer": 0.8963057324840764, | |
| "eval_loss": 9.611275672912598, | |
| "eval_runtime": 52.7167, | |
| "eval_samples_per_second": 10.281, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.9788703778951645, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_cer": 0.8923748862602365, | |
| "eval_loss": 9.794692039489746, | |
| "eval_runtime": 52.8702, | |
| "eval_samples_per_second": 10.252, | |
| "eval_steps_per_second": 1.286, | |
| "eval_wer": 0.980698902885006, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_cer": 0.8979435850773431, | |
| "eval_loss": 9.83806324005127, | |
| "eval_runtime": 52.7321, | |
| "eval_samples_per_second": 10.278, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.9794798862251117, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_cer": 0.8951774340309372, | |
| "eval_loss": 10.03061580657959, | |
| "eval_runtime": 52.6816, | |
| "eval_samples_per_second": 10.288, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.9788703778951645, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_cer": 0.8947042766151047, | |
| "eval_loss": 9.994989395141602, | |
| "eval_runtime": 53.3774, | |
| "eval_samples_per_second": 10.154, | |
| "eval_steps_per_second": 1.274, | |
| "eval_wer": 0.9792767167817961, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 2.432857142857143e-05, | |
| "loss": 3.316, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_cer": 0.8978707916287534, | |
| "eval_loss": 10.14880084991455, | |
| "eval_runtime": 52.6791, | |
| "eval_samples_per_second": 10.289, | |
| "eval_steps_per_second": 1.291, | |
| "eval_wer": 0.9780577001219016, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_cer": 0.9092265696087353, | |
| "eval_loss": 10.193445205688477, | |
| "eval_runtime": 52.6484, | |
| "eval_samples_per_second": 10.295, | |
| "eval_steps_per_second": 1.292, | |
| "eval_wer": 0.9809020723283218, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_cer": 0.9298999090081893, | |
| "eval_loss": 10.21463680267334, | |
| "eval_runtime": 52.7062, | |
| "eval_samples_per_second": 10.283, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.9880130028443722, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_cer": 0.9593084622383985, | |
| "eval_loss": 10.298548698425293, | |
| "eval_runtime": 52.7136, | |
| "eval_samples_per_second": 10.282, | |
| "eval_steps_per_second": 1.29, | |
| "eval_wer": 0.9997968305566842, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "step": 448, | |
| "total_flos": 3.9986309695731635e+18, | |
| "train_loss": 7.336955785751343, | |
| "train_runtime": 6516.6943, | |
| "train_samples_per_second": 10.312, | |
| "train_steps_per_second": 0.322 | |
| } | |
| ], | |
| "max_steps": 2100, | |
| "num_train_epochs": 150, | |
| "total_flos": 3.9986309695731635e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |