Upload folder using huggingface_hub

wavlm/ctc/12_wavlm-base-plus-sv/all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.2273026704788208,
+    "eval_mse_0": 1.4368343353271484,
+    "eval_mse_1": 1.021977186203003,
+    "eval_mse_2": 1.0692485570907593,
+    "eval_mse_3": 1.3811492919921875,
+    "eval_pcc_0": 0.6414290810747847,
+    "eval_pcc_1": 0.7125320279978511,
+    "eval_pcc_2": 0.6976719950149313,
+    "eval_pcc_3": 0.6638092006589431,
+    "eval_runtime": 81.7011,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 30.599,
+    "eval_steps_per_second": 3.831,
+    "train_loss": 7.476009532209402,
+    "train_runtime": 6065.0314,
+    "train_samples": 2500,
+    "train_samples_per_second": 12.366,
+    "train_steps_per_second": 1.548
+}

wavlm/ctc/12_wavlm-base-plus-sv/args.json

@@ -0,0 +1,11 @@
+{
+    "batch_size": 4,
+    "model_name": "microsoft/wavlm-base-plus-sv",
+    "learning_rate": 1e-05,
+    "num_train_epochs": 30,
+    "save_dir": "/data2/haeyoung/0303/ctc/model_saved",
+    "freeze_feature_extractor": false,
+    "exp_name": "microsoft/wavlm-base-plus-sv_lr1e-05_epochs30_batch4",
+    "save_dir_path": "/data2/haeyoung/0303/ctc/model_saved/microsoft/wavlm-base-plus-sv_lr1e-05_epochs30_batch4",
+    "save_log_path": "/data2/haeyoung/0303/ctc/model_saved/logs/microsoft/wavlm-base-plus-sv_lr1e-05_epochs30_batch4"
+}

wavlm/ctc/12_wavlm-base-plus-sv/eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.2273026704788208,
+    "eval_mse_0": 1.4368343353271484,
+    "eval_mse_1": 1.021977186203003,
+    "eval_mse_2": 1.0692485570907593,
+    "eval_mse_3": 1.3811492919921875,
+    "eval_pcc_0": 0.6414290810747847,
+    "eval_pcc_1": 0.7125320279978511,
+    "eval_pcc_2": 0.6976719950149313,
+    "eval_pcc_3": 0.6638092006589431,
+    "eval_runtime": 81.7011,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 30.599,
+    "eval_steps_per_second": 3.831
+}

wavlm/ctc/12_wavlm-base-plus-sv/finetuned_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fd20f4a1e96cf88cbf072127863a5b34b0c36cef0c68bda7e9111fb92682d6
+size 377734330

wavlm/ctc/12_wavlm-base-plus-sv/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6d4c88a0d1cfc06a95e0ab5f9c1f7a9d4cc8b8c7b2afb783f6c597cdaf3d26
+size 377658192

wavlm/ctc/12_wavlm-base-plus-sv/model_weights.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43964dadf4dfd92108ead8a6a7874ce0f194b8286777d6941654a41ae82051e7
+size 377731002

wavlm/ctc/12_wavlm-base-plus-sv/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": false,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

wavlm/ctc/12_wavlm-base-plus-sv/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "train_loss": 7.476009532209402,
+    "train_runtime": 6065.0314,
+    "train_samples": 2500,
+    "train_samples_per_second": 12.366,
+    "train_steps_per_second": 1.548
+}

wavlm/ctc/12_wavlm-base-plus-sv/trainer_args.json

@@ -0,0 +1 @@
+{"output_dir": "/data2/haeyoung/0303/ctc/model_saved/microsoft/wavlm-base-plus-sv_lr1e-05_epochs30_batch4", "overwrite_output_dir": false, "do_train": false, "do_eval": true, "do_predict": false, "evaluation_strategy": "epoch", "prediction_loss_only": false, "per_device_train_batch_size": 4, "per_device_eval_batch_size": 4, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 1, "eval_accumulation_steps": null, "eval_delay": 0, "learning_rate": 1e-05, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 30, "max_steps": -1, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 0, "log_level": "info", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "/data2/haeyoung/0303/ctc/model_saved/logs/microsoft/wavlm-base-plus-sv_lr1e-05_epochs30_batch4", "logging_strategy": "steps", "logging_first_step": false, "logging_steps": 500, "logging_nan_inf_filter": true, "save_strategy": "epoch", "save_steps": 500, "save_total_limit": 3, "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": null, "jit_mode_eval": false, "use_ipex": false, "bf16": false, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": null, "local_rank": 0, "ddp_backend": null, "tpu_num_cores": null, "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": null, "dataloader_num_workers": 0, "past_index": -1, "run_name": "/data2/haeyoung/0303/ctc/model_saved/microsoft/wavlm-base-plus-sv_lr1e-05_epochs30_batch4", "disable_tqdm": false, "remove_unused_columns": true, "label_names": null, "load_best_model_at_end": false, "metric_for_best_model": null, "greater_is_better": null, "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": null, "deepspeed": null, "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["tensorboard"], "ddp_find_unused_parameters": null, "ddp_bucket_cap_mb": null, "ddp_broadcast_buffers": null, "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": null, "hub_model_id": null, "hub_strategy": "every_save", "hub_token": "<HUB_TOKEN>", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": false, "gradient_checkpointing_kwargs": null, "include_inputs_for_metrics": false, "fp16_backend": "auto", "push_to_hub_model_id": null, "push_to_hub_organization": null, "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": null, "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": null, "torch_compile_mode": null, "dispatch_batches": null, "split_batches": false, "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": null}

wavlm/ctc/12_wavlm-base-plus-sv/trainer_state.json

@@ -0,0 +1,618 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.0,
+  "eval_steps": 500,
+  "global_step": 9390,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 44.90961456298828,
+      "eval_mse_0": 56.778900146484375,
+      "eval_mse_1": 47.26267623901367,
+      "eval_mse_2": 39.249900817871094,
+      "eval_mse_3": 36.347145080566406,
+      "eval_pcc_0": -0.03394536588737346,
+      "eval_pcc_1": 0.10342177247621369,
+      "eval_pcc_2": 0.11715852502951991,
+      "eval_pcc_3": -0.1555199987140184,
+      "eval_runtime": 81.878,
+      "eval_samples_per_second": 30.533,
+      "eval_steps_per_second": 3.823,
+      "step": 313
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.467518636847711e-06,
+      "loss": 46.1302,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 38.042510986328125,
+      "eval_mse_0": 51.915382385253906,
+      "eval_mse_1": 40.12179946899414,
+      "eval_mse_2": 30.594240188598633,
+      "eval_mse_3": 29.53835678100586,
+      "eval_pcc_0": -0.006834091334911564,
+      "eval_pcc_1": 0.08292492762531721,
+      "eval_pcc_2": 0.13148746530417524,
+      "eval_pcc_3": -0.11594849062644394,
+      "eval_runtime": 79.8128,
+      "eval_samples_per_second": 31.323,
+      "eval_steps_per_second": 3.922,
+      "step": 626
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 30.9356632232666,
+      "eval_mse_0": 45.968318939208984,
+      "eval_mse_1": 32.628440856933594,
+      "eval_mse_2": 22.345170974731445,
+      "eval_mse_3": 22.80092430114746,
+      "eval_pcc_0": -0.04825686673843558,
+      "eval_pcc_1": -0.0010554256600267035,
+      "eval_pcc_2": 0.0996140707146581,
+      "eval_pcc_3": -0.042135283540825436,
+      "eval_runtime": 81.2957,
+      "eval_samples_per_second": 30.752,
+      "eval_steps_per_second": 3.85,
+      "step": 939
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.935037273695422e-06,
+      "loss": 34.5994,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 24.097660064697266,
+      "eval_mse_0": 39.03736114501953,
+      "eval_mse_1": 25.282779693603516,
+      "eval_mse_2": 15.37244987487793,
+      "eval_mse_3": 16.69801902770996,
+      "eval_pcc_0": -0.07336724875786774,
+      "eval_pcc_1": 0.05843888820972233,
+      "eval_pcc_2": 0.1521057139829659,
+      "eval_pcc_3": -0.006208394682816094,
+      "eval_runtime": 81.9783,
+      "eval_samples_per_second": 30.496,
+      "eval_steps_per_second": 3.818,
+      "step": 1252
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 8.402555910543132e-06,
+      "loss": 23.6701,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 17.873172760009766,
+      "eval_mse_0": 31.49028968811035,
+      "eval_mse_1": 18.4976806640625,
+      "eval_mse_2": 9.942625999450684,
+      "eval_mse_3": 11.562135696411133,
+      "eval_pcc_0": -0.08706589458399991,
+      "eval_pcc_1": 0.1011828078528546,
+      "eval_pcc_2": 0.13184216483016203,
+      "eval_pcc_3": 0.059095832337068444,
+      "eval_runtime": 80.7962,
+      "eval_samples_per_second": 30.942,
+      "eval_steps_per_second": 3.874,
+      "step": 1565
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 12.547210693359375,
+      "eval_mse_0": 24.04130744934082,
+      "eval_mse_1": 12.668954849243164,
+      "eval_mse_2": 5.982004165649414,
+      "eval_mse_3": 7.496542930603027,
+      "eval_pcc_0": -0.08801223239466616,
+      "eval_pcc_1": 0.14291410669192747,
+      "eval_pcc_2": 0.1240828699772365,
+      "eval_pcc_3": 0.07309285544000904,
+      "eval_runtime": 79.1358,
+      "eval_samples_per_second": 31.591,
+      "eval_steps_per_second": 3.955,
+      "step": 1878
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 7.870074547390843e-06,
+      "loss": 14.5121,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 8.38403606414795,
+      "eval_mse_0": 16.73961639404297,
+      "eval_mse_1": 8.171566009521484,
+      "eval_mse_2": 3.710944890975952,
+      "eval_mse_3": 4.914018630981445,
+      "eval_pcc_0": -0.12185094233490208,
+      "eval_pcc_1": 0.20675659599504043,
+      "eval_pcc_2": 0.1732815661429634,
+      "eval_pcc_3": 0.13919069737786458,
+      "eval_runtime": 81.2982,
+      "eval_samples_per_second": 30.751,
+      "eval_steps_per_second": 3.85,
+      "step": 2191
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 7.337593184238552e-06,
+      "loss": 8.0138,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 5.372182846069336,
+      "eval_mse_0": 10.79847526550293,
+      "eval_mse_1": 4.977550983428955,
+      "eval_mse_2": 2.4349262714385986,
+      "eval_mse_3": 3.2777786254882812,
+      "eval_pcc_0": 0.21607133721043123,
+      "eval_pcc_1": 0.2541163503561237,
+      "eval_pcc_2": 0.23167304807270875,
+      "eval_pcc_3": 0.1967150391486112,
+      "eval_runtime": 79.0422,
+      "eval_samples_per_second": 31.629,
+      "eval_steps_per_second": 3.96,
+      "step": 2504
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.3494527339935303,
+      "eval_mse_0": 6.6392974853515625,
+      "eval_mse_1": 2.9384567737579346,
+      "eval_mse_2": 1.6669411659240723,
+      "eval_mse_3": 2.153123140335083,
+      "eval_pcc_0": 0.4722063660259092,
+      "eval_pcc_1": 0.47972126437261636,
+      "eval_pcc_2": 0.47567722013907554,
+      "eval_pcc_3": 0.48166391406272874,
+      "eval_runtime": 80.9362,
+      "eval_samples_per_second": 30.889,
+      "eval_steps_per_second": 3.867,
+      "step": 2817
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 6.805111821086262e-06,
+      "loss": 3.8134,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.2433218955993652,
+      "eval_mse_0": 3.646667957305908,
+      "eval_mse_1": 1.881966233253479,
+      "eval_mse_2": 1.596482753753662,
+      "eval_mse_3": 1.8481756448745728,
+      "eval_pcc_0": 0.4958560628595657,
+      "eval_pcc_1": 0.5171404163257346,
+      "eval_pcc_2": 0.503417919337264,
+      "eval_pcc_3": 0.5052516445809265,
+      "eval_runtime": 81.3388,
+      "eval_samples_per_second": 30.736,
+      "eval_steps_per_second": 3.848,
+      "step": 3130
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.8703898191452026,
+      "eval_mse_0": 2.2350335121154785,
+      "eval_mse_1": 1.6343435049057007,
+      "eval_mse_2": 1.689864993095398,
+      "eval_mse_3": 1.922315239906311,
+      "eval_pcc_0": 0.5184840563488403,
+      "eval_pcc_1": 0.541913290355545,
+      "eval_pcc_2": 0.5263888398821298,
+      "eval_pcc_3": 0.5280239486456239,
+      "eval_runtime": 80.696,
+      "eval_samples_per_second": 30.98,
+      "eval_steps_per_second": 3.879,
+      "step": 3443
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 6.272630457933972e-06,
+      "loss": 1.6851,
+      "step": 3500
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.510632872581482,
+      "eval_mse_0": 1.6816580295562744,
+      "eval_mse_1": 1.3168894052505493,
+      "eval_mse_2": 1.3761801719665527,
+      "eval_mse_3": 1.6678062677383423,
+      "eval_pcc_0": 0.5481115435995357,
+      "eval_pcc_1": 0.5935842191018236,
+      "eval_pcc_2": 0.5810698093463899,
+      "eval_pcc_3": 0.5636499513637937,
+      "eval_runtime": 82.1141,
+      "eval_samples_per_second": 30.445,
+      "eval_steps_per_second": 3.812,
+      "step": 3756
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 5.7401490947816826e-06,
+      "loss": 1.0716,
+      "step": 4000
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.4154906272888184,
+      "eval_mse_0": 1.5810251235961914,
+      "eval_mse_1": 1.207949161529541,
+      "eval_mse_2": 1.2833834886550903,
+      "eval_mse_3": 1.5896073579788208,
+      "eval_pcc_0": 0.5789602582866248,
+      "eval_pcc_1": 0.642950238371259,
+      "eval_pcc_2": 0.6175375381054339,
+      "eval_pcc_3": 0.589879079841077,
+      "eval_runtime": 82.0047,
+      "eval_samples_per_second": 30.486,
+      "eval_steps_per_second": 3.817,
+      "step": 4069
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.3758577108383179,
+      "eval_mse_0": 1.5708643198013306,
+      "eval_mse_1": 1.1744545698165894,
+      "eval_mse_2": 1.2256196737289429,
+      "eval_mse_3": 1.5324952602386475,
+      "eval_pcc_0": 0.5854124949972862,
+      "eval_pcc_1": 0.6554443130489785,
+      "eval_pcc_2": 0.645046148453159,
+      "eval_pcc_3": 0.6132672652524904,
+      "eval_runtime": 81.2829,
+      "eval_samples_per_second": 30.757,
+      "eval_steps_per_second": 3.851,
+      "step": 4382
+    },
+    {
+      "epoch": 14.38,
+      "learning_rate": 5.207667731629393e-06,
+      "loss": 0.888,
+      "step": 4500
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.4408560991287231,
+      "eval_mse_0": 1.638799786567688,
+      "eval_mse_1": 1.241701364517212,
+      "eval_mse_2": 1.2641960382461548,
+      "eval_mse_3": 1.6187268495559692,
+      "eval_pcc_0": 0.6142903591269896,
+      "eval_pcc_1": 0.6802917862272585,
+      "eval_pcc_2": 0.6696118440437349,
+      "eval_pcc_3": 0.6393569294574015,
+      "eval_runtime": 80.2405,
+      "eval_samples_per_second": 31.156,
+      "eval_steps_per_second": 3.901,
+      "step": 4695
+    },
+    {
+      "epoch": 15.97,
+      "learning_rate": 4.675186368477103e-06,
+      "loss": 0.7828,
+      "step": 5000
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.2738914489746094,
+      "eval_mse_0": 1.5100775957107544,
+      "eval_mse_1": 1.0691988468170166,
+      "eval_mse_2": 1.0985459089279175,
+      "eval_mse_3": 1.4177402257919312,
+      "eval_pcc_0": 0.6174324189391969,
+      "eval_pcc_1": 0.6904214447856399,
+      "eval_pcc_2": 0.6846738527340409,
+      "eval_pcc_3": 0.6508753200986239,
+      "eval_runtime": 82.1292,
+      "eval_samples_per_second": 30.44,
+      "eval_steps_per_second": 3.811,
+      "step": 5008
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.2328681945800781,
+      "eval_mse_0": 1.4462746381759644,
+      "eval_mse_1": 1.0265105962753296,
+      "eval_mse_2": 1.0654101371765137,
+      "eval_mse_3": 1.393277883529663,
+      "eval_pcc_0": 0.640427891758691,
+      "eval_pcc_1": 0.7117140296206613,
+      "eval_pcc_2": 0.7013584369586464,
+      "eval_pcc_3": 0.666124183259039,
+      "eval_runtime": 79.4597,
+      "eval_samples_per_second": 31.462,
+      "eval_steps_per_second": 3.939,
+      "step": 5321
+    },
+    {
+      "epoch": 17.57,
+      "learning_rate": 4.142705005324814e-06,
+      "loss": 0.7102,
+      "step": 5500
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.382307767868042,
+      "eval_mse_0": 1.5885093212127686,
+      "eval_mse_1": 1.1862882375717163,
+      "eval_mse_2": 1.2124754190444946,
+      "eval_mse_3": 1.54196035861969,
+      "eval_pcc_0": 0.6197797889635865,
+      "eval_pcc_1": 0.6924124939998728,
+      "eval_pcc_2": 0.6785692653879178,
+      "eval_pcc_3": 0.6439533166499901,
+      "eval_runtime": 81.1803,
+      "eval_samples_per_second": 30.796,
+      "eval_steps_per_second": 3.856,
+      "step": 5634
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.2693986892700195,
+      "eval_mse_0": 1.500505805015564,
+      "eval_mse_1": 1.043813943862915,
+      "eval_mse_2": 1.0940051078796387,
+      "eval_mse_3": 1.439268708229065,
+      "eval_pcc_0": 0.6224202385170968,
+      "eval_pcc_1": 0.7012140856743723,
+      "eval_pcc_2": 0.6873748654950322,
+      "eval_pcc_3": 0.6488973472021053,
+      "eval_runtime": 79.5691,
+      "eval_samples_per_second": 31.419,
+      "eval_steps_per_second": 3.934,
+      "step": 5947
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 3.6102236421725247e-06,
+      "loss": 0.6595,
+      "step": 6000
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.3323901891708374,
+      "eval_mse_0": 1.512206792831421,
+      "eval_mse_1": 1.1507172584533691,
+      "eval_mse_2": 1.1775575876235962,
+      "eval_mse_3": 1.4890750646591187,
+      "eval_pcc_0": 0.6375545216687866,
+      "eval_pcc_1": 0.7103489142169261,
+      "eval_pcc_2": 0.6953027309652658,
+      "eval_pcc_3": 0.6591930123610972,
+      "eval_runtime": 82.1081,
+      "eval_samples_per_second": 30.448,
+      "eval_steps_per_second": 3.812,
+      "step": 6260
+    },
+    {
+      "epoch": 20.77,
+      "learning_rate": 3.0777422790202343e-06,
+      "loss": 0.6458,
+      "step": 6500
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.247666597366333,
+      "eval_mse_0": 1.4846857786178589,
+      "eval_mse_1": 1.0222755670547485,
+      "eval_mse_2": 1.0740835666656494,
+      "eval_mse_3": 1.4096157550811768,
+      "eval_pcc_0": 0.6312556910270483,
+      "eval_pcc_1": 0.7103781641738941,
+      "eval_pcc_2": 0.6999857430654227,
+      "eval_pcc_3": 0.6585274817242767,
+      "eval_runtime": 82.3724,
+      "eval_samples_per_second": 30.35,
+      "eval_steps_per_second": 3.8,
+      "step": 6573
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.3105732202529907,
+      "eval_mse_0": 1.52339506149292,
+      "eval_mse_1": 1.1076819896697998,
+      "eval_mse_2": 1.1394124031066895,
+      "eval_mse_3": 1.4718044996261597,
+      "eval_pcc_0": 0.6304459530085151,
+      "eval_pcc_1": 0.7009608173908444,
+      "eval_pcc_2": 0.6862704435334075,
+      "eval_pcc_3": 0.652390816296986,
+      "eval_runtime": 80.6499,
+      "eval_samples_per_second": 30.998,
+      "eval_steps_per_second": 3.881,
+      "step": 6886
+    },
+    {
+      "epoch": 22.36,
+      "learning_rate": 2.5452609158679447e-06,
+      "loss": 0.6056,
+      "step": 7000
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.336429238319397,
+      "eval_mse_0": 1.521738052368164,
+      "eval_mse_1": 1.1518150568008423,
+      "eval_mse_2": 1.1807482242584229,
+      "eval_mse_3": 1.4914147853851318,
+      "eval_pcc_0": 0.6375790045348386,
+      "eval_pcc_1": 0.7049335007280161,
+      "eval_pcc_2": 0.6888050877738252,
+      "eval_pcc_3": 0.6574742125675255,
+      "eval_runtime": 80.3701,
+      "eval_samples_per_second": 31.106,
+      "eval_steps_per_second": 3.894,
+      "step": 7199
+    },
+    {
+      "epoch": 23.96,
+      "learning_rate": 2.012779552715655e-06,
+      "loss": 0.5761,
+      "step": 7500
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.255359172821045,
+      "eval_mse_0": 1.4568367004394531,
+      "eval_mse_1": 1.0550090074539185,
+      "eval_mse_2": 1.0943888425827026,
+      "eval_mse_3": 1.4151999950408936,
+      "eval_pcc_0": 0.6449985625105988,
+      "eval_pcc_1": 0.7154405636142962,
+      "eval_pcc_2": 0.6994833565232761,
+      "eval_pcc_3": 0.6661063661323354,
+      "eval_runtime": 77.1016,
+      "eval_samples_per_second": 32.425,
+      "eval_steps_per_second": 4.06,
+      "step": 7512
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.231810212135315,
+      "eval_mse_0": 1.4440966844558716,
+      "eval_mse_1": 1.0186392068862915,
+      "eval_mse_2": 1.070443868637085,
+      "eval_mse_3": 1.39406156539917,
+      "eval_pcc_0": 0.6373700640667618,
+      "eval_pcc_1": 0.710193982908496,
+      "eval_pcc_2": 0.6954186624945753,
+      "eval_pcc_3": 0.6599617243667115,
+      "eval_runtime": 81.2589,
+      "eval_samples_per_second": 30.766,
+      "eval_steps_per_second": 3.852,
+      "step": 7825
+    },
+    {
+      "epoch": 25.56,
+      "learning_rate": 1.4802981895633654e-06,
+      "loss": 0.5674,
+      "step": 8000
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 1.2170995473861694,
+      "eval_mse_0": 1.4013334512710571,
+      "eval_mse_1": 1.0318217277526855,
+      "eval_mse_2": 1.0800848007202148,
+      "eval_mse_3": 1.3551557064056396,
+      "eval_pcc_0": 0.6429355623751383,
+      "eval_pcc_1": 0.7091594109025471,
+      "eval_pcc_2": 0.6936732520383968,
+      "eval_pcc_3": 0.6634486618273856,
+      "eval_runtime": 79.4233,
+      "eval_samples_per_second": 31.477,
+      "eval_steps_per_second": 3.941,
+      "step": 8138
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 1.2207973003387451,
+      "eval_mse_0": 1.4302600622177124,
+      "eval_mse_1": 1.0141854286193848,
+      "eval_mse_2": 1.0655509233474731,
+      "eval_mse_3": 1.3731926679611206,
+      "eval_pcc_0": 0.6420414006841837,
+      "eval_pcc_1": 0.7112473415710203,
+      "eval_pcc_2": 0.6960559157712126,
+      "eval_pcc_3": 0.6639178801171381,
+      "eval_runtime": 80.9752,
+      "eval_samples_per_second": 30.874,
+      "eval_steps_per_second": 3.865,
+      "step": 8451
+    },
+    {
+      "epoch": 27.16,
+      "learning_rate": 9.478168264110757e-07,
+      "loss": 0.5357,
+      "step": 8500
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 1.230727195739746,
+      "eval_mse_0": 1.4374960660934448,
+      "eval_mse_1": 1.0289753675460815,
+      "eval_mse_2": 1.0744554996490479,
+      "eval_mse_3": 1.3819823265075684,
+      "eval_pcc_0": 0.64220648083207,
+      "eval_pcc_1": 0.7126541102829277,
+      "eval_pcc_2": 0.6977914999012619,
+      "eval_pcc_3": 0.6640096341995462,
+      "eval_runtime": 82.1699,
+      "eval_samples_per_second": 30.425,
+      "eval_steps_per_second": 3.809,
+      "step": 8764
+    },
+    {
+      "epoch": 28.75,
+      "learning_rate": 4.1533546325878595e-07,
+      "loss": 0.5192,
+      "step": 9000
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 1.2241783142089844,
+      "eval_mse_0": 1.4269994497299194,
+      "eval_mse_1": 1.0242198705673218,
+      "eval_mse_2": 1.0715134143829346,
+      "eval_mse_3": 1.3739817142486572,
+      "eval_pcc_0": 0.642379593381856,
+      "eval_pcc_1": 0.7120333359867065,
+      "eval_pcc_2": 0.697045817763541,
+      "eval_pcc_3": 0.6641748304017993,
+      "eval_runtime": 82.139,
+      "eval_samples_per_second": 30.436,
+      "eval_steps_per_second": 3.811,
+      "step": 9077
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 1.2273026704788208,
+      "eval_mse_0": 1.4368343353271484,
+      "eval_mse_1": 1.021977186203003,
+      "eval_mse_2": 1.0692485570907593,
+      "eval_mse_3": 1.3811492919921875,
+      "eval_pcc_0": 0.6414290810747847,
+      "eval_pcc_1": 0.7125320279978511,
+      "eval_pcc_2": 0.6976719950149313,
+      "eval_pcc_3": 0.6638092006589431,
+      "eval_runtime": 79.7517,
+      "eval_samples_per_second": 31.347,
+      "eval_steps_per_second": 3.925,
+      "step": 9390
+    },
+    {
+      "epoch": 30.0,
+      "step": 9390,
+      "total_flos": 0.0,
+      "train_loss": 7.476009532209402,
+      "train_runtime": 6065.0314,
+      "train_samples_per_second": 12.366,
+      "train_steps_per_second": 1.548
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9390,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

wavlm/ctc/12_wavlm-base-plus-sv/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebaa1adfb1cd46dbb85ee1d59bdcdae170b0689dc5d3cbeb85b8c7767ca20671
+size 4792