Upload folder using huggingface_hub

wavlm/general/10_wavlm-large/all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.4009701013565063,
+    "eval_mse_0": 1.5458636283874512,
+    "eval_mse_1": 1.239806056022644,
+    "eval_mse_2": 1.2594882249832153,
+    "eval_mse_3": 1.5587239265441895,
+    "eval_pcc_0": 0.6125877099330943,
+    "eval_pcc_1": 0.6539146157205031,
+    "eval_pcc_2": 0.6440193878083593,
+    "eval_pcc_3": 0.620091192529623,
+    "eval_runtime": 135.5138,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 18.448,
+    "eval_steps_per_second": 2.31,
+    "train_loss": 4.090279127614567,
+    "train_runtime": 11155.1323,
+    "train_samples": 2500,
+    "train_samples_per_second": 6.723,
+    "train_steps_per_second": 0.842
+}

wavlm/general/10_wavlm-large/args.json

@@ -0,0 +1,11 @@
+{
+    "batch_size": 4,
+    "model_name": "microsoft/wavlm-large",
+    "learning_rate": 1e-05,
+    "num_train_epochs": 30,
+    "save_dir": "./model_saved",
+    "freeze_feature_extractor": false,
+    "exp_name": "microsoft/wavlm-large_lr1e-05_epochs30_batch4",
+    "save_dir_path": "./model_saved/microsoft/wavlm-large_lr1e-05_epochs30_batch4",
+    "save_log_path": "./model_saved/logs/microsoft/wavlm-large_lr1e-05_epochs30_batch4"
+}

wavlm/general/10_wavlm-large/eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.4009701013565063,
+    "eval_mse_0": 1.5458636283874512,
+    "eval_mse_1": 1.239806056022644,
+    "eval_mse_2": 1.2594882249832153,
+    "eval_mse_3": 1.5587239265441895,
+    "eval_pcc_0": 0.6125877099330943,
+    "eval_pcc_1": 0.6539146157205031,
+    "eval_pcc_2": 0.6440193878083593,
+    "eval_pcc_3": 0.620091192529623,
+    "eval_runtime": 135.5138,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 18.448,
+    "eval_steps_per_second": 2.31
+}

wavlm/general/10_wavlm-large/finetuned_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7ff3ce134f07f973ee021b8fb4469cccf866f817b590bb1d530ce7a0ba0d72
+size 1262024382

wavlm/general/10_wavlm-large/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53152eb26468c5ea27ab00f3bb005d0b4e636b8241c8843ddc6a9e4e85dad898
+size 1261888608

wavlm/general/10_wavlm-large/model_weights.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc51f3d7ac4815f3dff191f1ff469f912a4778f592b97b8b757c87e3ab9ae5c
+size 1262019378

wavlm/general/10_wavlm-large/preprocessor_config.json

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

wavlm/general/10_wavlm-large/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "train_loss": 4.090279127614567,
+    "train_runtime": 11155.1323,
+    "train_samples": 2500,
+    "train_samples_per_second": 6.723,
+    "train_steps_per_second": 0.842
+}

wavlm/general/10_wavlm-large/trainer_args.json

@@ -0,0 +1 @@
+{"output_dir": "./model_saved/microsoft/wavlm-large_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": "./model_saved/logs/microsoft/wavlm-large_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": "./model_saved/microsoft/wavlm-large_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/general/10_wavlm-large/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": 25.78005599975586,
+      "eval_mse_0": 28.098997116088867,
+      "eval_mse_1": 26.715993881225586,
+      "eval_mse_2": 24.948816299438477,
+      "eval_mse_3": 23.35636329650879,
+      "eval_pcc_0": -0.18451053964452674,
+      "eval_pcc_1": 0.28817171600641167,
+      "eval_pcc_2": -0.25654328946200594,
+      "eval_pcc_3": 0.05085872444138174,
+      "eval_runtime": 135.7658,
+      "eval_samples_per_second": 18.414,
+      "eval_steps_per_second": 2.305,
+      "step": 313
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.467518636847711e-06,
+      "loss": 32.5216,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 18.6761474609375,
+      "eval_mse_0": 20.534852981567383,
+      "eval_mse_1": 19.295068740844727,
+      "eval_mse_2": 17.831636428833008,
+      "eval_mse_3": 17.043046951293945,
+      "eval_pcc_0": -0.1870721212076314,
+      "eval_pcc_1": 0.22301086445242135,
+      "eval_pcc_2": -0.15167800399430065,
+      "eval_pcc_3": 0.05720822664765886,
+      "eval_runtime": 136.111,
+      "eval_samples_per_second": 18.367,
+      "eval_steps_per_second": 2.3,
+      "step": 626
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 12.908292770385742,
+      "eval_mse_0": 14.195310592651367,
+      "eval_mse_1": 13.437732696533203,
+      "eval_mse_2": 12.234976768493652,
+      "eval_mse_3": 11.76514720916748,
+      "eval_pcc_0": -0.17289340951023557,
+      "eval_pcc_1": 0.18949590699229704,
+      "eval_pcc_2": 0.0045060773819017635,
+      "eval_pcc_3": -0.04047795297287696,
+      "eval_runtime": 128.9243,
+      "eval_samples_per_second": 19.391,
+      "eval_steps_per_second": 2.428,
+      "step": 939
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.935037273695422e-06,
+      "loss": 16.9639,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 8.241400718688965,
+      "eval_mse_0": 9.317843437194824,
+      "eval_mse_1": 8.415904998779297,
+      "eval_mse_2": 7.581799030303955,
+      "eval_mse_3": 7.6500444412231445,
+      "eval_pcc_0": -0.2734581657479225,
+      "eval_pcc_1": 0.1388333139105179,
+      "eval_pcc_2": 0.06190884903680619,
+      "eval_pcc_3": -0.03685733655912809,
+      "eval_runtime": 132.5886,
+      "eval_samples_per_second": 18.855,
+      "eval_steps_per_second": 2.361,
+      "step": 1252
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 8.402555910543132e-06,
+      "loss": 8.8132,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 4.874174118041992,
+      "eval_mse_0": 5.490235328674316,
+      "eval_mse_1": 4.89415979385376,
+      "eval_mse_2": 4.462656021118164,
+      "eval_mse_3": 4.649643421173096,
+      "eval_pcc_0": -0.27538453192335854,
+      "eval_pcc_1": 0.09398464090113141,
+      "eval_pcc_2": 0.11958461908456552,
+      "eval_pcc_3": 0.019343077368142423,
+      "eval_runtime": 134.5896,
+      "eval_samples_per_second": 18.575,
+      "eval_steps_per_second": 2.326,
+      "step": 1565
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.9445176124572754,
+      "eval_mse_0": 3.1629297733306885,
+      "eval_mse_1": 2.8798022270202637,
+      "eval_mse_2": 2.715522527694702,
+      "eval_mse_3": 3.019822835922241,
+      "eval_pcc_0": -0.1967573833934448,
+      "eval_pcc_1": 0.2547007368517576,
+      "eval_pcc_2": 0.22492191185528165,
+      "eval_pcc_3": 0.14722693337633838,
+      "eval_runtime": 136.0131,
+      "eval_samples_per_second": 18.381,
+      "eval_steps_per_second": 2.301,
+      "step": 1878
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 7.870074547390843e-06,
+      "loss": 3.9919,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.5537784099578857,
+      "eval_mse_0": 2.7752676010131836,
+      "eval_mse_1": 2.3745803833007812,
+      "eval_mse_2": 2.3484272956848145,
+      "eval_mse_3": 2.7168328762054443,
+      "eval_pcc_0": 0.16580511330365824,
+      "eval_pcc_1": 0.23877037283224226,
+      "eval_pcc_2": 0.22002647806469494,
+      "eval_pcc_3": 0.17740649615981322,
+      "eval_runtime": 134.4071,
+      "eval_samples_per_second": 18.6,
+      "eval_steps_per_second": 2.329,
+      "step": 2191
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 7.337593184238552e-06,
+      "loss": 2.0682,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.9987887144088745,
+      "eval_mse_0": 2.1391544342041016,
+      "eval_mse_1": 1.8746179342269897,
+      "eval_mse_2": 1.8764265775680542,
+      "eval_mse_3": 2.1049561500549316,
+      "eval_pcc_0": 0.4795375878136092,
+      "eval_pcc_1": 0.4979213113066353,
+      "eval_pcc_2": 0.4768635833492293,
+      "eval_pcc_3": 0.4858633140039566,
+      "eval_runtime": 135.0944,
+      "eval_samples_per_second": 18.506,
+      "eval_steps_per_second": 2.317,
+      "step": 2504
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.7573435306549072,
+      "eval_mse_0": 1.886688232421875,
+      "eval_mse_1": 1.6100713014602661,
+      "eval_mse_2": 1.6289024353027344,
+      "eval_mse_3": 1.9037095308303833,
+      "eval_pcc_0": 0.5166172381162671,
+      "eval_pcc_1": 0.5430215878153999,
+      "eval_pcc_2": 0.523587717873113,
+      "eval_pcc_3": 0.5260717464662105,
+      "eval_runtime": 134.1946,
+      "eval_samples_per_second": 18.63,
+      "eval_steps_per_second": 2.332,
+      "step": 2817
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 6.805111821086262e-06,
+      "loss": 1.3344,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.574723482131958,
+      "eval_mse_0": 1.6954877376556396,
+      "eval_mse_1": 1.423547625541687,
+      "eval_mse_2": 1.4693849086761475,
+      "eval_mse_3": 1.710472822189331,
+      "eval_pcc_0": 0.5371217365518883,
+      "eval_pcc_1": 0.5502498692350887,
+      "eval_pcc_2": 0.5369972839753233,
+      "eval_pcc_3": 0.5435321709268838,
+      "eval_runtime": 126.0281,
+      "eval_samples_per_second": 19.837,
+      "eval_steps_per_second": 2.484,
+      "step": 3130
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 2.0485382080078125,
+      "eval_mse_0": 2.2502353191375732,
+      "eval_mse_1": 1.8471835851669312,
+      "eval_mse_2": 1.8188210725784302,
+      "eval_mse_3": 2.27790904045105,
+      "eval_pcc_0": 0.5113085662353668,
+      "eval_pcc_1": 0.5609132138623332,
+      "eval_pcc_2": 0.5357821525057226,
+      "eval_pcc_3": 0.5202442051277879,
+      "eval_runtime": 129.5327,
+      "eval_samples_per_second": 19.3,
+      "eval_steps_per_second": 2.416,
+      "step": 3443
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 6.272630457933972e-06,
+      "loss": 1.1036,
+      "step": 3500
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.471645712852478,
+      "eval_mse_0": 1.613988995552063,
+      "eval_mse_1": 1.2970263957977295,
+      "eval_mse_2": 1.3566508293151855,
+      "eval_mse_3": 1.6189168691635132,
+      "eval_pcc_0": 0.572946856315743,
+      "eval_pcc_1": 0.6081674173741975,
+      "eval_pcc_2": 0.5894921356034519,
+      "eval_pcc_3": 0.5815459179188294,
+      "eval_runtime": 133.1812,
+      "eval_samples_per_second": 18.771,
+      "eval_steps_per_second": 2.35,
+      "step": 3756
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 5.7401490947816826e-06,
+      "loss": 1.0226,
+      "step": 4000
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.523953914642334,
+      "eval_mse_0": 1.6985650062561035,
+      "eval_mse_1": 1.3248023986816406,
+      "eval_mse_2": 1.3798528909683228,
+      "eval_mse_3": 1.692597508430481,
+      "eval_pcc_0": 0.5617750796115597,
+      "eval_pcc_1": 0.603753619613184,
+      "eval_pcc_2": 0.5847780917978835,
+      "eval_pcc_3": 0.5710611107898864,
+      "eval_runtime": 133.9365,
+      "eval_samples_per_second": 18.666,
+      "eval_steps_per_second": 2.337,
+      "step": 4069
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.3943829536437988,
+      "eval_mse_0": 1.549199104309082,
+      "eval_mse_1": 1.2074002027511597,
+      "eval_mse_2": 1.2678221464157104,
+      "eval_mse_3": 1.553109884262085,
+      "eval_pcc_0": 0.5925742271049399,
+      "eval_pcc_1": 0.6472105350854597,
+      "eval_pcc_2": 0.625772450087358,
+      "eval_pcc_3": 0.6028799784063099,
+      "eval_runtime": 132.9989,
+      "eval_samples_per_second": 18.797,
+      "eval_steps_per_second": 2.353,
+      "step": 4382
+    },
+    {
+      "epoch": 14.38,
+      "learning_rate": 5.207667731629393e-06,
+      "loss": 0.9725,
+      "step": 4500
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.4137483835220337,
+      "eval_mse_0": 1.5822710990905762,
+      "eval_mse_1": 1.2220001220703125,
+      "eval_mse_2": 1.2747286558151245,
+      "eval_mse_3": 1.5759928226470947,
+      "eval_pcc_0": 0.5882265370237295,
+      "eval_pcc_1": 0.6481239097635736,
+      "eval_pcc_2": 0.6274160674927931,
+      "eval_pcc_3": 0.6005838709117854,
+      "eval_runtime": 134.356,
+      "eval_samples_per_second": 18.607,
+      "eval_steps_per_second": 2.33,
+      "step": 4695
+    },
+    {
+      "epoch": 15.97,
+      "learning_rate": 4.675186368477103e-06,
+      "loss": 0.9204,
+      "step": 5000
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.5062298774719238,
+      "eval_mse_0": 1.667518973350525,
+      "eval_mse_1": 1.3080573081970215,
+      "eval_mse_2": 1.3583706617355347,
+      "eval_mse_3": 1.6909708976745605,
+      "eval_pcc_0": 0.5966820200145334,
+      "eval_pcc_1": 0.6536770110706099,
+      "eval_pcc_2": 0.6314774005527053,
+      "eval_pcc_3": 0.6076121218697804,
+      "eval_runtime": 133.438,
+      "eval_samples_per_second": 18.735,
+      "eval_steps_per_second": 2.346,
+      "step": 5008
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.3842324018478394,
+      "eval_mse_0": 1.5057488679885864,
+      "eval_mse_1": 1.2262545824050903,
+      "eval_mse_2": 1.2751030921936035,
+      "eval_mse_3": 1.5298200845718384,
+      "eval_pcc_0": 0.6153937479509105,
+      "eval_pcc_1": 0.6583711903703251,
+      "eval_pcc_2": 0.6400410092284629,
+      "eval_pcc_3": 0.6229387263345442,
+      "eval_runtime": 125.9539,
+      "eval_samples_per_second": 19.849,
+      "eval_steps_per_second": 2.485,
+      "step": 5321
+    },
+    {
+      "epoch": 17.57,
+      "learning_rate": 4.142705005324814e-06,
+      "loss": 0.882,
+      "step": 5500
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.4283748865127563,
+      "eval_mse_0": 1.5403162240982056,
+      "eval_mse_1": 1.2739295959472656,
+      "eval_mse_2": 1.3217359781265259,
+      "eval_mse_3": 1.577515721321106,
+      "eval_pcc_0": 0.6132533841173031,
+      "eval_pcc_1": 0.6534886512958944,
+      "eval_pcc_2": 0.6374234769700808,
+      "eval_pcc_3": 0.6193865043511572,
+      "eval_runtime": 130.7005,
+      "eval_samples_per_second": 19.128,
+      "eval_steps_per_second": 2.395,
+      "step": 5634
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.341154932975769,
+      "eval_mse_0": 1.4884107112884521,
+      "eval_mse_1": 1.1724251508712769,
+      "eval_mse_2": 1.212692141532898,
+      "eval_mse_3": 1.4910962581634521,
+      "eval_pcc_0": 0.6155193242064069,
+      "eval_pcc_1": 0.6634995851874871,
+      "eval_pcc_2": 0.645645853377025,
+      "eval_pcc_3": 0.6234169879094179,
+      "eval_runtime": 133.8855,
+      "eval_samples_per_second": 18.673,
+      "eval_steps_per_second": 2.338,
+      "step": 5947
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 3.6102236421725247e-06,
+      "loss": 0.8599,
+      "step": 6000
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.5969125032424927,
+      "eval_mse_0": 1.775260329246521,
+      "eval_mse_1": 1.3972289562225342,
+      "eval_mse_2": 1.4095877408981323,
+      "eval_mse_3": 1.8055765628814697,
+      "eval_pcc_0": 0.6085865030449327,
+      "eval_pcc_1": 0.6581882204119307,
+      "eval_pcc_2": 0.6418717517970683,
+      "eval_pcc_3": 0.6165944632649418,
+      "eval_runtime": 131.9824,
+      "eval_samples_per_second": 18.942,
+      "eval_steps_per_second": 2.372,
+      "step": 6260
+    },
+    {
+      "epoch": 20.77,
+      "learning_rate": 3.0777422790202343e-06,
+      "loss": 0.8265,
+      "step": 6500
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.620095133781433,
+      "eval_mse_0": 1.7542890310287476,
+      "eval_mse_1": 1.4505913257598877,
+      "eval_mse_2": 1.454500436782837,
+      "eval_mse_3": 1.820999026298523,
+      "eval_pcc_0": 0.6087096889568085,
+      "eval_pcc_1": 0.6533957084119679,
+      "eval_pcc_2": 0.6385091217487125,
+      "eval_pcc_3": 0.6141772427546307,
+      "eval_runtime": 133.2939,
+      "eval_samples_per_second": 18.756,
+      "eval_steps_per_second": 2.348,
+      "step": 6573
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.4004989862442017,
+      "eval_mse_0": 1.534153938293457,
+      "eval_mse_1": 1.2430734634399414,
+      "eval_mse_2": 1.2678866386413574,
+      "eval_mse_3": 1.5568820238113403,
+      "eval_pcc_0": 0.6172693669023709,
+      "eval_pcc_1": 0.6641215618623881,
+      "eval_pcc_2": 0.6507671360020759,
+      "eval_pcc_3": 0.6251657199832752,
+      "eval_runtime": 133.4947,
+      "eval_samples_per_second": 18.727,
+      "eval_steps_per_second": 2.345,
+      "step": 6886
+    },
+    {
+      "epoch": 22.36,
+      "learning_rate": 2.5452609158679447e-06,
+      "loss": 0.8321,
+      "step": 7000
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.3635456562042236,
+      "eval_mse_0": 1.4831970930099487,
+      "eval_mse_1": 1.216675877571106,
+      "eval_mse_2": 1.2508056163787842,
+      "eval_mse_3": 1.5035041570663452,
+      "eval_pcc_0": 0.6219241000097753,
+      "eval_pcc_1": 0.6677692984879574,
+      "eval_pcc_2": 0.6542591206877052,
+      "eval_pcc_3": 0.6295498184658282,
+      "eval_runtime": 120.2351,
+      "eval_samples_per_second": 20.793,
+      "eval_steps_per_second": 2.603,
+      "step": 7199
+    },
+    {
+      "epoch": 23.96,
+      "learning_rate": 2.012779552715655e-06,
+      "loss": 0.7899,
+      "step": 7500
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.6058969497680664,
+      "eval_mse_0": 1.7093384265899658,
+      "eval_mse_1": 1.470818042755127,
+      "eval_mse_2": 1.4680759906768799,
+      "eval_mse_3": 1.7753560543060303,
+      "eval_pcc_0": 0.6181900305423599,
+      "eval_pcc_1": 0.664211395086592,
+      "eval_pcc_2": 0.6526812937467503,
+      "eval_pcc_3": 0.625673188856609,
+      "eval_runtime": 120.5071,
+      "eval_samples_per_second": 20.746,
+      "eval_steps_per_second": 2.597,
+      "step": 7512
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.504971981048584,
+      "eval_mse_0": 1.6674143075942993,
+      "eval_mse_1": 1.3263922929763794,
+      "eval_mse_2": 1.3394672870635986,
+      "eval_mse_3": 1.68661367893219,
+      "eval_pcc_0": 0.6137081085016365,
+      "eval_pcc_1": 0.6609410896781117,
+      "eval_pcc_2": 0.6479914131566253,
+      "eval_pcc_3": 0.6226682330016088,
+      "eval_runtime": 124.2716,
+      "eval_samples_per_second": 20.117,
+      "eval_steps_per_second": 2.519,
+      "step": 7825
+    },
+    {
+      "epoch": 25.56,
+      "learning_rate": 1.4802981895633654e-06,
+      "loss": 0.7924,
+      "step": 8000
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 1.396066665649414,
+      "eval_mse_0": 1.5273590087890625,
+      "eval_mse_1": 1.2427642345428467,
+      "eval_mse_2": 1.266948938369751,
+      "eval_mse_3": 1.5471936464309692,
+      "eval_pcc_0": 0.6160967000045343,
+      "eval_pcc_1": 0.6578827586429048,
+      "eval_pcc_2": 0.6466460056883097,
+      "eval_pcc_3": 0.6234559331466528,
+      "eval_runtime": 117.03,
+      "eval_samples_per_second": 21.362,
+      "eval_steps_per_second": 2.675,
+      "step": 8138
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 1.4699628353118896,
+      "eval_mse_0": 1.6256612539291382,
+      "eval_mse_1": 1.301504373550415,
+      "eval_mse_2": 1.3069500923156738,
+      "eval_mse_3": 1.6457338333129883,
+      "eval_pcc_0": 0.6112617547833968,
+      "eval_pcc_1": 0.6566712400657333,
+      "eval_pcc_2": 0.6458557177070916,
+      "eval_pcc_3": 0.6194981917255858,
+      "eval_runtime": 117.674,
+      "eval_samples_per_second": 21.245,
+      "eval_steps_per_second": 2.66,
+      "step": 8451
+    },
+    {
+      "epoch": 27.16,
+      "learning_rate": 9.478168264110757e-07,
+      "loss": 0.7775,
+      "step": 8500
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 1.3778095245361328,
+      "eval_mse_0": 1.5245665311813354,
+      "eval_mse_1": 1.2149397134780884,
+      "eval_mse_2": 1.2385963201522827,
+      "eval_mse_3": 1.5331368446350098,
+      "eval_pcc_0": 0.6128273274510158,
+      "eval_pcc_1": 0.6552073854651396,
+      "eval_pcc_2": 0.6447955005509804,
+      "eval_pcc_3": 0.6203658026134583,
+      "eval_runtime": 128.6417,
+      "eval_samples_per_second": 19.434,
+      "eval_steps_per_second": 2.433,
+      "step": 8764
+    },
+    {
+      "epoch": 28.75,
+      "learning_rate": 4.1533546325878595e-07,
+      "loss": 0.7542,
+      "step": 9000
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 1.4188872575759888,
+      "eval_mse_0": 1.5585076808929443,
+      "eval_mse_1": 1.262168049812317,
+      "eval_mse_2": 1.2772693634033203,
+      "eval_mse_3": 1.577603816986084,
+      "eval_pcc_0": 0.612767509984247,
+      "eval_pcc_1": 0.6537875883987164,
+      "eval_pcc_2": 0.644070760099995,
+      "eval_pcc_3": 0.6200687645633882,
+      "eval_runtime": 128.617,
+      "eval_samples_per_second": 19.438,
+      "eval_steps_per_second": 2.434,
+      "step": 9077
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 1.4009701013565063,
+      "eval_mse_0": 1.5458636283874512,
+      "eval_mse_1": 1.239806056022644,
+      "eval_mse_2": 1.2594882249832153,
+      "eval_mse_3": 1.5587239265441895,
+      "eval_pcc_0": 0.6125877099330943,
+      "eval_pcc_1": 0.6539146157205031,
+      "eval_pcc_2": 0.6440193878083593,
+      "eval_pcc_3": 0.620091192529623,
+      "eval_runtime": 136.8398,
+      "eval_samples_per_second": 18.27,
+      "eval_steps_per_second": 2.287,
+      "step": 9390
+    },
+    {
+      "epoch": 30.0,
+      "step": 9390,
+      "total_flos": 0.0,
+      "train_loss": 4.090279127614567,
+      "train_runtime": 11155.1323,
+      "train_samples_per_second": 6.723,
+      "train_steps_per_second": 0.842
+    }
+  ],
+  "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/general/10_wavlm-large/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45fe4900f9385bd521573a2a688ac4d141cd0a301441ca0a5a5a34bda1848e9a
+size 4728