| { | |
| "best_metric": 0.17724749445915222, | |
| "best_model_checkpoint": "wav2vec2-xlsr-1b-mecita-portuguese-all-text-protecao_aos_pandas/checkpoint-225", | |
| "epoch": 50.0, | |
| "global_step": 375, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.9957142857142858e-05, | |
| "loss": 13.7229, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_cer": 0.9995906672124437, | |
| "eval_loss": 4.859188556671143, | |
| "eval_runtime": 1.8002, | |
| "eval_samples_per_second": 16.109, | |
| "eval_steps_per_second": 2.222, | |
| "eval_wer": 1.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_cer": 1.0, | |
| "eval_loss": 3.002265691757202, | |
| "eval_runtime": 1.7603, | |
| "eval_samples_per_second": 16.475, | |
| "eval_steps_per_second": 2.272, | |
| "eval_wer": 1.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_cer": 1.0, | |
| "eval_loss": 2.929029941558838, | |
| "eval_runtime": 1.7878, | |
| "eval_samples_per_second": 16.221, | |
| "eval_steps_per_second": 2.237, | |
| "eval_wer": 1.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_cer": 1.0, | |
| "eval_loss": 2.98417067527771, | |
| "eval_runtime": 1.7731, | |
| "eval_samples_per_second": 16.355, | |
| "eval_steps_per_second": 2.256, | |
| "eval_wer": 1.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "eval_cer": 1.0, | |
| "eval_loss": 2.845335006713867, | |
| "eval_runtime": 1.7685, | |
| "eval_samples_per_second": 16.398, | |
| "eval_steps_per_second": 2.262, | |
| "eval_wer": 1.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_cer": 1.0, | |
| "eval_loss": 2.8119678497314453, | |
| "eval_runtime": 1.8211, | |
| "eval_samples_per_second": 15.924, | |
| "eval_steps_per_second": 2.196, | |
| "eval_wer": 1.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "eval_cer": 1.0, | |
| "eval_loss": 2.816225528717041, | |
| "eval_runtime": 1.805, | |
| "eval_samples_per_second": 16.067, | |
| "eval_steps_per_second": 2.216, | |
| "eval_wer": 1.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_cer": 1.0, | |
| "eval_loss": 2.7843384742736816, | |
| "eval_runtime": 1.7945, | |
| "eval_samples_per_second": 16.161, | |
| "eval_steps_per_second": 2.229, | |
| "eval_wer": 1.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "eval_cer": 1.0, | |
| "eval_loss": 2.782341957092285, | |
| "eval_runtime": 1.7839, | |
| "eval_samples_per_second": 16.256, | |
| "eval_steps_per_second": 2.242, | |
| "eval_wer": 1.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_cer": 1.0, | |
| "eval_loss": 2.743428945541382, | |
| "eval_runtime": 1.77, | |
| "eval_samples_per_second": 16.384, | |
| "eval_steps_per_second": 2.26, | |
| "eval_wer": 1.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "eval_cer": 1.0, | |
| "eval_loss": 2.636403799057007, | |
| "eval_runtime": 1.7839, | |
| "eval_samples_per_second": 16.256, | |
| "eval_steps_per_second": 2.242, | |
| "eval_wer": 1.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_cer": 0.9860826852230864, | |
| "eval_loss": 2.3797059059143066, | |
| "eval_runtime": 1.7797, | |
| "eval_samples_per_second": 16.295, | |
| "eval_steps_per_second": 2.248, | |
| "eval_wer": 0.9876237623762376, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "eval_cer": 0.9770773638968482, | |
| "eval_loss": 1.9516112804412842, | |
| "eval_runtime": 1.7769, | |
| "eval_samples_per_second": 16.32, | |
| "eval_steps_per_second": 2.251, | |
| "eval_wer": 0.995049504950495, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 2.58e-05, | |
| "loss": 3.3197, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_cer": 0.7474416700777732, | |
| "eval_loss": 1.5396052598953247, | |
| "eval_runtime": 1.8171, | |
| "eval_samples_per_second": 15.96, | |
| "eval_steps_per_second": 2.201, | |
| "eval_wer": 1.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "eval_cer": 0.4273434302087597, | |
| "eval_loss": 1.103837251663208, | |
| "eval_runtime": 1.7792, | |
| "eval_samples_per_second": 16.3, | |
| "eval_steps_per_second": 2.248, | |
| "eval_wer": 0.995049504950495, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_cer": 0.16905444126074498, | |
| "eval_loss": 0.6535802483558655, | |
| "eval_runtime": 1.7778, | |
| "eval_samples_per_second": 16.313, | |
| "eval_steps_per_second": 2.25, | |
| "eval_wer": 0.6732673267326733, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 16.93, | |
| "eval_cer": 0.07286123618501841, | |
| "eval_loss": 0.40873047709465027, | |
| "eval_runtime": 1.7934, | |
| "eval_samples_per_second": 16.171, | |
| "eval_steps_per_second": 2.23, | |
| "eval_wer": 0.3217821782178218, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_cer": 0.056078591895210805, | |
| "eval_loss": 0.31188902258872986, | |
| "eval_runtime": 1.7728, | |
| "eval_samples_per_second": 16.358, | |
| "eval_steps_per_second": 2.256, | |
| "eval_wer": 0.22524752475247525, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "eval_cer": 0.04789193614408514, | |
| "eval_loss": 0.2720329761505127, | |
| "eval_runtime": 1.785, | |
| "eval_samples_per_second": 16.247, | |
| "eval_steps_per_second": 2.241, | |
| "eval_wer": 0.17574257425742573, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_cer": 0.04134261154318461, | |
| "eval_loss": 0.24048186838626862, | |
| "eval_runtime": 1.7775, | |
| "eval_samples_per_second": 16.315, | |
| "eval_steps_per_second": 2.25, | |
| "eval_wer": 0.15841584158415842, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 20.93, | |
| "eval_cer": 0.04093327875562833, | |
| "eval_loss": 0.23653259873390198, | |
| "eval_runtime": 1.8549, | |
| "eval_samples_per_second": 15.634, | |
| "eval_steps_per_second": 2.156, | |
| "eval_wer": 0.15841584158415842, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_cer": 0.03970528039295947, | |
| "eval_loss": 0.22812487185001373, | |
| "eval_runtime": 1.7767, | |
| "eval_samples_per_second": 16.323, | |
| "eval_steps_per_second": 2.251, | |
| "eval_wer": 0.15099009900990099, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 22.93, | |
| "eval_cer": 0.036021285304952924, | |
| "eval_loss": 0.19893357157707214, | |
| "eval_runtime": 1.7827, | |
| "eval_samples_per_second": 16.267, | |
| "eval_steps_per_second": 2.244, | |
| "eval_wer": 0.13613861386138615, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_cer": 0.036021285304952924, | |
| "eval_loss": 0.2050793319940567, | |
| "eval_runtime": 1.7818, | |
| "eval_samples_per_second": 16.275, | |
| "eval_steps_per_second": 2.245, | |
| "eval_wer": 0.12871287128712872, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 24.93, | |
| "eval_cer": 0.03561195251739664, | |
| "eval_loss": 0.22654221951961517, | |
| "eval_runtime": 1.7854, | |
| "eval_samples_per_second": 16.243, | |
| "eval_steps_per_second": 2.24, | |
| "eval_wer": 0.12871287128712872, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_cer": 0.03765861645517806, | |
| "eval_loss": 0.22025753557682037, | |
| "eval_runtime": 1.7733, | |
| "eval_samples_per_second": 16.354, | |
| "eval_steps_per_second": 2.256, | |
| "eval_wer": 0.12871287128712872, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 2.1514285714285717e-05, | |
| "loss": 0.5589, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 26.93, | |
| "eval_cer": 0.03397462136717151, | |
| "eval_loss": 0.2180820107460022, | |
| "eval_runtime": 1.787, | |
| "eval_samples_per_second": 16.228, | |
| "eval_steps_per_second": 2.238, | |
| "eval_wer": 0.12128712871287128, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_cer": 0.03356528857961523, | |
| "eval_loss": 0.20063219964504242, | |
| "eval_runtime": 1.7961, | |
| "eval_samples_per_second": 16.146, | |
| "eval_steps_per_second": 2.227, | |
| "eval_wer": 0.12376237623762376, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 28.93, | |
| "eval_cer": 0.03315595579205895, | |
| "eval_loss": 0.18598036468029022, | |
| "eval_runtime": 1.7925, | |
| "eval_samples_per_second": 16.178, | |
| "eval_steps_per_second": 2.231, | |
| "eval_wer": 0.12128712871287128, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_cer": 0.03029062627916496, | |
| "eval_loss": 0.17724749445915222, | |
| "eval_runtime": 1.7802, | |
| "eval_samples_per_second": 16.29, | |
| "eval_steps_per_second": 2.247, | |
| "eval_wer": 0.11138613861386139, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 30.93, | |
| "eval_cer": 0.032337290216946375, | |
| "eval_loss": 0.19143883883953094, | |
| "eval_runtime": 1.7768, | |
| "eval_samples_per_second": 16.322, | |
| "eval_steps_per_second": 2.251, | |
| "eval_wer": 0.12376237623762376, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_cer": 0.032337290216946375, | |
| "eval_loss": 0.19965380430221558, | |
| "eval_runtime": 1.8097, | |
| "eval_samples_per_second": 16.025, | |
| "eval_steps_per_second": 2.21, | |
| "eval_wer": 0.12376237623762376, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 32.93, | |
| "eval_cer": 0.03397462136717151, | |
| "eval_loss": 0.19473285973072052, | |
| "eval_runtime": 1.8384, | |
| "eval_samples_per_second": 15.775, | |
| "eval_steps_per_second": 2.176, | |
| "eval_wer": 0.12623762376237624, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_cer": 0.03274662300450266, | |
| "eval_loss": 0.20558013021945953, | |
| "eval_runtime": 1.7938, | |
| "eval_samples_per_second": 16.167, | |
| "eval_steps_per_second": 2.23, | |
| "eval_wer": 0.12128712871287128, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 34.93, | |
| "eval_cer": 0.03315595579205895, | |
| "eval_loss": 0.1984556019306183, | |
| "eval_runtime": 1.7744, | |
| "eval_samples_per_second": 16.343, | |
| "eval_steps_per_second": 2.254, | |
| "eval_wer": 0.12128712871287128, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_cer": 0.03274662300450266, | |
| "eval_loss": 0.20163008570671082, | |
| "eval_runtime": 1.8047, | |
| "eval_samples_per_second": 16.069, | |
| "eval_steps_per_second": 2.216, | |
| "eval_wer": 0.12128712871287128, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 36.93, | |
| "eval_cer": 0.031109291854277528, | |
| "eval_loss": 0.19409456849098206, | |
| "eval_runtime": 1.7987, | |
| "eval_samples_per_second": 16.123, | |
| "eval_steps_per_second": 2.224, | |
| "eval_wer": 0.11386138613861387, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_cer": 0.03192795742939009, | |
| "eval_loss": 0.18242661654949188, | |
| "eval_runtime": 1.806, | |
| "eval_samples_per_second": 16.058, | |
| "eval_steps_per_second": 2.215, | |
| "eval_wer": 0.12376237623762376, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 38.93, | |
| "eval_cer": 0.029471960704052395, | |
| "eval_loss": 0.18223299086093903, | |
| "eval_runtime": 1.8045, | |
| "eval_samples_per_second": 16.071, | |
| "eval_steps_per_second": 2.217, | |
| "eval_wer": 0.10891089108910891, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.7271428571428574e-05, | |
| "loss": 0.1503, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_cer": 0.031109291854277528, | |
| "eval_loss": 0.19688135385513306, | |
| "eval_runtime": 1.8319, | |
| "eval_samples_per_second": 15.83, | |
| "eval_steps_per_second": 2.184, | |
| "eval_wer": 0.11633663366336634, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 40.93, | |
| "eval_cer": 0.029471960704052395, | |
| "eval_loss": 0.19957467913627625, | |
| "eval_runtime": 1.8232, | |
| "eval_samples_per_second": 15.906, | |
| "eval_steps_per_second": 2.194, | |
| "eval_wer": 0.11633663366336634, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_cer": 0.029471960704052395, | |
| "eval_loss": 0.18802578747272491, | |
| "eval_runtime": 1.7999, | |
| "eval_samples_per_second": 16.112, | |
| "eval_steps_per_second": 2.222, | |
| "eval_wer": 0.10891089108910891, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 42.93, | |
| "eval_cer": 0.034383954154727794, | |
| "eval_loss": 0.20173507928848267, | |
| "eval_runtime": 1.7941, | |
| "eval_samples_per_second": 16.164, | |
| "eval_steps_per_second": 2.23, | |
| "eval_wer": 0.1311881188118812, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_cer": 0.03274662300450266, | |
| "eval_loss": 0.19139862060546875, | |
| "eval_runtime": 1.8064, | |
| "eval_samples_per_second": 16.054, | |
| "eval_steps_per_second": 2.214, | |
| "eval_wer": 0.11633663366336634, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 44.93, | |
| "eval_cer": 0.03315595579205895, | |
| "eval_loss": 0.19346125423908234, | |
| "eval_runtime": 1.8407, | |
| "eval_samples_per_second": 15.755, | |
| "eval_steps_per_second": 2.173, | |
| "eval_wer": 0.11633663366336634, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_cer": 0.03192795742939009, | |
| "eval_loss": 0.19668900966644287, | |
| "eval_runtime": 1.8343, | |
| "eval_samples_per_second": 15.81, | |
| "eval_steps_per_second": 2.181, | |
| "eval_wer": 0.11386138613861387, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 46.93, | |
| "eval_cer": 0.029881293491608677, | |
| "eval_loss": 0.19127391278743744, | |
| "eval_runtime": 1.7943, | |
| "eval_samples_per_second": 16.162, | |
| "eval_steps_per_second": 2.229, | |
| "eval_wer": 0.10643564356435643, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_cer": 0.03029062627916496, | |
| "eval_loss": 0.1993999034166336, | |
| "eval_runtime": 1.8021, | |
| "eval_samples_per_second": 16.092, | |
| "eval_steps_per_second": 2.22, | |
| "eval_wer": 0.11138613861386139, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 48.93, | |
| "eval_cer": 0.029062627916496112, | |
| "eval_loss": 0.18826055526733398, | |
| "eval_runtime": 1.81, | |
| "eval_samples_per_second": 16.022, | |
| "eval_steps_per_second": 2.21, | |
| "eval_wer": 0.10891089108910891, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_cer": 0.03029062627916496, | |
| "eval_loss": 0.18807141482830048, | |
| "eval_runtime": 1.8146, | |
| "eval_samples_per_second": 15.982, | |
| "eval_steps_per_second": 2.204, | |
| "eval_wer": 0.11386138613861387, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 375, | |
| "total_flos": 9.822732861444276e+18, | |
| "train_loss": 1.1235487569173177, | |
| "train_runtime": 3285.5807, | |
| "train_samples_per_second": 6.879, | |
| "train_steps_per_second": 0.213 | |
| } | |
| ], | |
| "max_steps": 700, | |
| "num_train_epochs": 100, | |
| "total_flos": 9.822732861444276e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |