Upload folder using huggingface_hub (#38)

- Upload folder using huggingface_hub (84e02a067c04d441d2a61ecb73051442334d6174)

hubert/ctc/09_hubert-xlarge-ls960-ft/all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.0285080671310425,
+    "eval_mse_0": 1.2710857391357422,
+    "eval_mse_1": 0.8113386034965515,
+    "eval_mse_2": 0.8502917289733887,
+    "eval_mse_3": 1.1813127994537354,
+    "eval_pcc_0": 0.7187760622799816,
+    "eval_pcc_1": 0.7966815578451035,
+    "eval_pcc_2": 0.7880753758720686,
+    "eval_pcc_3": 0.7343475719122529,
+    "eval_runtime": 209.2133,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 11.95,
+    "eval_steps_per_second": 1.496,
+    "train_loss": 0.8967580890757081,
+    "train_runtime": 20656.0843,
+    "train_samples": 2500,
+    "train_samples_per_second": 3.631,
+    "train_steps_per_second": 0.455
+}

hubert/ctc/09_hubert-xlarge-ls960-ft/args.json

@@ -0,0 +1,11 @@
+{
+    "batch_size": 4,
+    "model_name": "facebook/hubert-xlarge-ls960-ft",
+    "learning_rate": 1e-05,
+    "num_train_epochs": 30,
+    "save_dir": "./ctc/model_saved",
+    "freeze_feature_extractor": false,
+    "exp_name": "facebook/hubert-xlarge-ls960-ft_lr1e-05_epochs30_batch4",
+    "save_dir_path": "./ctc/model_saved/facebook/hubert-xlarge-ls960-ft_lr1e-05_epochs30_batch4",
+    "save_log_path": "./ctc/model_saved/logs/facebook/hubert-xlarge-ls960-ft_lr1e-05_epochs30_batch4"
+}

hubert/ctc/09_hubert-xlarge-ls960-ft/eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.0285080671310425,
+    "eval_mse_0": 1.2710857391357422,
+    "eval_mse_1": 0.8113386034965515,
+    "eval_mse_2": 0.8502917289733887,
+    "eval_mse_3": 1.1813127994537354,
+    "eval_pcc_0": 0.7187760622799816,
+    "eval_pcc_1": 0.7966815578451035,
+    "eval_pcc_2": 0.7880753758720686,
+    "eval_pcc_3": 0.7343475719122529,
+    "eval_runtime": 209.2133,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 11.95,
+    "eval_steps_per_second": 1.496
+}

hubert/ctc/09_hubert-xlarge-ls960-ft/finetuned_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6091e736eac0f184b32bce7605df806bfc5953ab1fe46dab4bb3a48e6c52430
+size 3850503230

hubert/ctc/09_hubert-xlarge-ls960-ft/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ada9054cfc3e8206eae20cf991ebb516e20e0ee36405d24543772a9c65b5461
+size 3850258896

hubert/ctc/09_hubert-xlarge-ls960-ft/model_weights.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c25ecc1788060973e9542a3b79afccbd5673368775ea1d77950f4434d7ea53
+size 3850495026

hubert/ctc/09_hubert-xlarge-ls960-ft/preprocessor_config.json

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

hubert/ctc/09_hubert-xlarge-ls960-ft/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "train_loss": 0.8967580890757081,
+    "train_runtime": 20656.0843,
+    "train_samples": 2500,
+    "train_samples_per_second": 3.631,
+    "train_steps_per_second": 0.455
+}

hubert/ctc/09_hubert-xlarge-ls960-ft/trainer_args.json

@@ -0,0 +1 @@
+{"output_dir": "./ctc/model_saved/facebook/hubert-xlarge-ls960-ft_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": "./ctc/model_saved/logs/facebook/hubert-xlarge-ls960-ft_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": "./ctc/model_saved/facebook/hubert-xlarge-ls960-ft_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}

hubert/ctc/09_hubert-xlarge-ls960-ft/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": 1.7604542970657349,
+      "eval_mse_0": 2.2891268730163574,
+      "eval_mse_1": 1.3835554122924805,
+      "eval_mse_2": 1.4830454587936401,
+      "eval_mse_3": 1.8860870599746704,
+      "eval_pcc_0": 0.5949950107509543,
+      "eval_pcc_1": 0.6690888754674116,
+      "eval_pcc_2": 0.6761228310172515,
+      "eval_pcc_3": 0.6185151101800396,
+      "eval_runtime": 209.8988,
+      "eval_samples_per_second": 11.91,
+      "eval_steps_per_second": 1.491,
+      "step": 313
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.467518636847711e-06,
+      "loss": 8.2296,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8357867002487183,
+      "eval_mse_0": 2.211723566055298,
+      "eval_mse_1": 1.360002875328064,
+      "eval_mse_2": 1.4621888399124146,
+      "eval_mse_3": 2.3092284202575684,
+      "eval_pcc_0": 0.6682445908306366,
+      "eval_pcc_1": 0.7357637021511422,
+      "eval_pcc_2": 0.7398762227436718,
+      "eval_pcc_3": 0.6934009818934106,
+      "eval_runtime": 209.4245,
+      "eval_samples_per_second": 11.937,
+      "eval_steps_per_second": 1.495,
+      "step": 626
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.1838189363479614,
+      "eval_mse_0": 1.4407283067703247,
+      "eval_mse_1": 0.9233540892601013,
+      "eval_mse_2": 0.9905136823654175,
+      "eval_mse_3": 1.3806804418563843,
+      "eval_pcc_0": 0.7018946460129335,
+      "eval_pcc_1": 0.7605681115601083,
+      "eval_pcc_2": 0.7613766180820963,
+      "eval_pcc_3": 0.7176544341885177,
+      "eval_runtime": 209.3913,
+      "eval_samples_per_second": 11.939,
+      "eval_steps_per_second": 1.495,
+      "step": 939
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.935037273695422e-06,
+      "loss": 0.9009,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.2771263122558594,
+      "eval_mse_0": 1.6051421165466309,
+      "eval_mse_1": 1.0666706562042236,
+      "eval_mse_2": 0.9894477725028992,
+      "eval_mse_3": 1.4472445249557495,
+      "eval_pcc_0": 0.7059142647273454,
+      "eval_pcc_1": 0.7775537888797579,
+      "eval_pcc_2": 0.7758972783171784,
+      "eval_pcc_3": 0.7284269184529911,
+      "eval_runtime": 211.1016,
+      "eval_samples_per_second": 11.843,
+      "eval_steps_per_second": 1.483,
+      "step": 1252
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 8.402555910543132e-06,
+      "loss": 0.7335,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.013259768486023,
+      "eval_mse_0": 1.1845321655273438,
+      "eval_mse_1": 0.8382721543312073,
+      "eval_mse_2": 0.8471496105194092,
+      "eval_mse_3": 1.1830846071243286,
+      "eval_pcc_0": 0.7220314248320598,
+      "eval_pcc_1": 0.7810873843585969,
+      "eval_pcc_2": 0.7820128992327345,
+      "eval_pcc_3": 0.7360157064832683,
+      "eval_runtime": 208.3778,
+      "eval_samples_per_second": 11.997,
+      "eval_steps_per_second": 1.502,
+      "step": 1565
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.1153326034545898,
+      "eval_mse_0": 1.3304675817489624,
+      "eval_mse_1": 0.967021107673645,
+      "eval_mse_2": 0.8986290097236633,
+      "eval_mse_3": 1.2652109861373901,
+      "eval_pcc_0": 0.7191154392641586,
+      "eval_pcc_1": 0.7844691588297669,
+      "eval_pcc_2": 0.7834242944128317,
+      "eval_pcc_3": 0.734926089754088,
+      "eval_runtime": 208.9096,
+      "eval_samples_per_second": 11.967,
+      "eval_steps_per_second": 1.498,
+      "step": 1878
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 7.870074547390843e-06,
+      "loss": 0.6582,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.9920685291290283,
+      "eval_mse_0": 1.188461184501648,
+      "eval_mse_1": 0.797171413898468,
+      "eval_mse_2": 0.8041291236877441,
+      "eval_mse_3": 1.178512454032898,
+      "eval_pcc_0": 0.7178300854644514,
+      "eval_pcc_1": 0.7843874006734662,
+      "eval_pcc_2": 0.7816055307992213,
+      "eval_pcc_3": 0.7321382541990243,
+      "eval_runtime": 208.3569,
+      "eval_samples_per_second": 11.999,
+      "eval_steps_per_second": 1.502,
+      "step": 2191
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 7.337593184238552e-06,
+      "loss": 0.61,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.1334257125854492,
+      "eval_mse_0": 1.3587603569030762,
+      "eval_mse_1": 0.9839173555374146,
+      "eval_mse_2": 0.8571197390556335,
+      "eval_mse_3": 1.3339046239852905,
+      "eval_pcc_0": 0.7222960062328075,
+      "eval_pcc_1": 0.7918217852018566,
+      "eval_pcc_2": 0.7890134850847228,
+      "eval_pcc_3": 0.7406291667967669,
+      "eval_runtime": 208.9586,
+      "eval_samples_per_second": 11.964,
+      "eval_steps_per_second": 1.498,
+      "step": 2504
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.0356388092041016,
+      "eval_mse_0": 1.2761818170547485,
+      "eval_mse_1": 0.8244701027870178,
+      "eval_mse_2": 0.8450726270675659,
+      "eval_mse_3": 1.1968308687210083,
+      "eval_pcc_0": 0.7158327269721199,
+      "eval_pcc_1": 0.7887012663328065,
+      "eval_pcc_2": 0.7828718656643849,
+      "eval_pcc_3": 0.7324949959695232,
+      "eval_runtime": 208.4544,
+      "eval_samples_per_second": 11.993,
+      "eval_steps_per_second": 1.502,
+      "step": 2817
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 6.805111821086262e-06,
+      "loss": 0.558,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.0064268112182617,
+      "eval_mse_0": 1.2265743017196655,
+      "eval_mse_1": 0.7974323630332947,
+      "eval_mse_2": 0.8605502247810364,
+      "eval_mse_3": 1.1411466598510742,
+      "eval_pcc_0": 0.7194697476611159,
+      "eval_pcc_1": 0.7879356525339981,
+      "eval_pcc_2": 0.7825310225961822,
+      "eval_pcc_3": 0.7338939460552648,
+      "eval_runtime": 208.7012,
+      "eval_samples_per_second": 11.979,
+      "eval_steps_per_second": 1.5,
+      "step": 3130
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.0203851461410522,
+      "eval_mse_0": 1.2474987506866455,
+      "eval_mse_1": 0.7733442187309265,
+      "eval_mse_2": 0.8386961221694946,
+      "eval_mse_3": 1.2220022678375244,
+      "eval_pcc_0": 0.7227682523187445,
+      "eval_pcc_1": 0.7982387874431719,
+      "eval_pcc_2": 0.7927393301459043,
+      "eval_pcc_3": 0.7395565264308681,
+      "eval_runtime": 208.389,
+      "eval_samples_per_second": 11.997,
+      "eval_steps_per_second": 1.502,
+      "step": 3443
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 6.272630457933972e-06,
+      "loss": 0.521,
+      "step": 3500
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.047383427619934,
+      "eval_mse_0": 1.2933303117752075,
+      "eval_mse_1": 0.8162205815315247,
+      "eval_mse_2": 0.8277409076690674,
+      "eval_mse_3": 1.2522428035736084,
+      "eval_pcc_0": 0.7217570447433742,
+      "eval_pcc_1": 0.7925934732628623,
+      "eval_pcc_2": 0.7879495997288596,
+      "eval_pcc_3": 0.7361480726438472,
+      "eval_runtime": 208.4447,
+      "eval_samples_per_second": 11.994,
+      "eval_steps_per_second": 1.502,
+      "step": 3756
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 5.7401490947816826e-06,
+      "loss": 0.4827,
+      "step": 4000
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.133775234222412,
+      "eval_mse_0": 1.3003195524215698,
+      "eval_mse_1": 1.026171088218689,
+      "eval_mse_2": 0.9799304008483887,
+      "eval_mse_3": 1.2286752462387085,
+      "eval_pcc_0": 0.7179022866715287,
+      "eval_pcc_1": 0.7876187047135141,
+      "eval_pcc_2": 0.7823654487873046,
+      "eval_pcc_3": 0.7320379928488189,
+      "eval_runtime": 208.3722,
+      "eval_samples_per_second": 11.998,
+      "eval_steps_per_second": 1.502,
+      "step": 4069
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.0516111850738525,
+      "eval_mse_0": 1.2931753396987915,
+      "eval_mse_1": 0.8838064670562744,
+      "eval_mse_2": 0.8298025131225586,
+      "eval_mse_3": 1.1996608972549438,
+      "eval_pcc_0": 0.7221738534470319,
+      "eval_pcc_1": 0.792441337992792,
+      "eval_pcc_2": 0.7871210686536287,
+      "eval_pcc_3": 0.7372780501327556,
+      "eval_runtime": 208.9007,
+      "eval_samples_per_second": 11.967,
+      "eval_steps_per_second": 1.498,
+      "step": 4382
+    },
+    {
+      "epoch": 14.38,
+      "learning_rate": 5.207667731629393e-06,
+      "loss": 0.4729,
+      "step": 4500
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.0624889135360718,
+      "eval_mse_0": 1.2347221374511719,
+      "eval_mse_1": 0.9299283027648926,
+      "eval_mse_2": 0.9029843807220459,
+      "eval_mse_3": 1.1823203563690186,
+      "eval_pcc_0": 0.7235235571215815,
+      "eval_pcc_1": 0.7925054644282444,
+      "eval_pcc_2": 0.7877609910773938,
+      "eval_pcc_3": 0.7376391961595067,
+      "eval_runtime": 208.3877,
+      "eval_samples_per_second": 11.997,
+      "eval_steps_per_second": 1.502,
+      "step": 4695
+    },
+    {
+      "epoch": 15.97,
+      "learning_rate": 4.675186368477103e-06,
+      "loss": 0.4256,
+      "step": 5000
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.0295990705490112,
+      "eval_mse_0": 1.2828537225723267,
+      "eval_mse_1": 0.8042919039726257,
+      "eval_mse_2": 0.8219324946403503,
+      "eval_mse_3": 1.2093201875686646,
+      "eval_pcc_0": 0.7198396446229315,
+      "eval_pcc_1": 0.792083832658487,
+      "eval_pcc_2": 0.7868061270983931,
+      "eval_pcc_3": 0.7337071079854925,
+      "eval_runtime": 208.6005,
+      "eval_samples_per_second": 11.985,
+      "eval_steps_per_second": 1.5,
+      "step": 5008
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.0699937343597412,
+      "eval_mse_0": 1.3057812452316284,
+      "eval_mse_1": 0.8312128782272339,
+      "eval_mse_2": 0.9018996953964233,
+      "eval_mse_3": 1.2410811185836792,
+      "eval_pcc_0": 0.7231245665785527,
+      "eval_pcc_1": 0.7930446914091678,
+      "eval_pcc_2": 0.7859261139462301,
+      "eval_pcc_3": 0.7363907316508812,
+      "eval_runtime": 208.3877,
+      "eval_samples_per_second": 11.997,
+      "eval_steps_per_second": 1.502,
+      "step": 5321
+    },
+    {
+      "epoch": 17.57,
+      "learning_rate": 4.142705005324814e-06,
+      "loss": 0.4125,
+      "step": 5500
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.0604360103607178,
+      "eval_mse_0": 1.417197823524475,
+      "eval_mse_1": 0.7857402563095093,
+      "eval_mse_2": 0.8151865005493164,
+      "eval_mse_3": 1.223620891571045,
+      "eval_pcc_0": 0.719599052787515,
+      "eval_pcc_1": 0.7948456747947626,
+      "eval_pcc_2": 0.7873693601018915,
+      "eval_pcc_3": 0.735322395766516,
+      "eval_runtime": 208.719,
+      "eval_samples_per_second": 11.978,
+      "eval_steps_per_second": 1.5,
+      "step": 5634
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 0.9978102445602417,
+      "eval_mse_0": 1.2328013181686401,
+      "eval_mse_1": 0.7908715009689331,
+      "eval_mse_2": 0.8256710171699524,
+      "eval_mse_3": 1.141896367073059,
+      "eval_pcc_0": 0.7233352263233708,
+      "eval_pcc_1": 0.7955153410239142,
+      "eval_pcc_2": 0.7886118783652329,
+      "eval_pcc_3": 0.7387880075588535,
+      "eval_runtime": 208.625,
+      "eval_samples_per_second": 11.983,
+      "eval_steps_per_second": 1.5,
+      "step": 5947
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 3.6102236421725247e-06,
+      "loss": 0.408,
+      "step": 6000
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.0034513473510742,
+      "eval_mse_0": 1.271166205406189,
+      "eval_mse_1": 0.7616897225379944,
+      "eval_mse_2": 0.798088788986206,
+      "eval_mse_3": 1.1828594207763672,
+      "eval_pcc_0": 0.7158333707506873,
+      "eval_pcc_1": 0.7980149681944232,
+      "eval_pcc_2": 0.7903887242443307,
+      "eval_pcc_3": 0.733952342512612,
+      "eval_runtime": 209.1487,
+      "eval_samples_per_second": 11.953,
+      "eval_steps_per_second": 1.497,
+      "step": 6260
+    },
+    {
+      "epoch": 20.77,
+      "learning_rate": 3.0777422790202343e-06,
+      "loss": 0.3933,
+      "step": 6500
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.0128971338272095,
+      "eval_mse_0": 1.2781158685684204,
+      "eval_mse_1": 0.7844489812850952,
+      "eval_mse_2": 0.8275609612464905,
+      "eval_mse_3": 1.1614614725112915,
+      "eval_pcc_0": 0.7171888316949959,
+      "eval_pcc_1": 0.7979542917618553,
+      "eval_pcc_2": 0.7908615541342248,
+      "eval_pcc_3": 0.7340458194168231,
+      "eval_runtime": 208.5853,
+      "eval_samples_per_second": 11.986,
+      "eval_steps_per_second": 1.501,
+      "step": 6573
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.0257415771484375,
+      "eval_mse_0": 1.2726078033447266,
+      "eval_mse_1": 0.798060953617096,
+      "eval_mse_2": 0.87810879945755,
+      "eval_mse_3": 1.1541907787322998,
+      "eval_pcc_0": 0.7157861802878516,
+      "eval_pcc_1": 0.7956912115918899,
+      "eval_pcc_2": 0.788469660815682,
+      "eval_pcc_3": 0.7329414127759406,
+      "eval_runtime": 208.8719,
+      "eval_samples_per_second": 11.969,
+      "eval_steps_per_second": 1.499,
+      "step": 6886
+    },
+    {
+      "epoch": 22.36,
+      "learning_rate": 2.5452609158679447e-06,
+      "loss": 0.3771,
+      "step": 7000
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.0453354120254517,
+      "eval_mse_0": 1.2379229068756104,
+      "eval_mse_1": 0.8579115271568298,
+      "eval_mse_2": 0.9011425971984863,
+      "eval_mse_3": 1.1843643188476562,
+      "eval_pcc_0": 0.7206315686829957,
+      "eval_pcc_1": 0.7958260398687528,
+      "eval_pcc_2": 0.7881329938884019,
+      "eval_pcc_3": 0.7346575150007393,
+      "eval_runtime": 208.5854,
+      "eval_samples_per_second": 11.986,
+      "eval_steps_per_second": 1.501,
+      "step": 7199
+    },
+    {
+      "epoch": 23.96,
+      "learning_rate": 2.012779552715655e-06,
+      "loss": 0.3658,
+      "step": 7500
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.0164525508880615,
+      "eval_mse_0": 1.2356749773025513,
+      "eval_mse_1": 0.8079164028167725,
+      "eval_mse_2": 0.8315185308456421,
+      "eval_mse_3": 1.1907004117965698,
+      "eval_pcc_0": 0.7230764531548024,
+      "eval_pcc_1": 0.7967303359103496,
+      "eval_pcc_2": 0.7882004474676807,
+      "eval_pcc_3": 0.7364224170170541,
+      "eval_runtime": 208.7929,
+      "eval_samples_per_second": 11.974,
+      "eval_steps_per_second": 1.499,
+      "step": 7512
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.0428879261016846,
+      "eval_mse_0": 1.316085696220398,
+      "eval_mse_1": 0.8296839594841003,
+      "eval_mse_2": 0.8361263871192932,
+      "eval_mse_3": 1.1896562576293945,
+      "eval_pcc_0": 0.7194161454664743,
+      "eval_pcc_1": 0.7958110988096722,
+      "eval_pcc_2": 0.7871496601733409,
+      "eval_pcc_3": 0.734582701567013,
+      "eval_runtime": 208.3025,
+      "eval_samples_per_second": 12.002,
+      "eval_steps_per_second": 1.503,
+      "step": 7825
+    },
+    {
+      "epoch": 25.56,
+      "learning_rate": 1.4802981895633654e-06,
+      "loss": 0.3543,
+      "step": 8000
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 1.0259170532226562,
+      "eval_mse_0": 1.2972633838653564,
+      "eval_mse_1": 0.7949677109718323,
+      "eval_mse_2": 0.8365034461021423,
+      "eval_mse_3": 1.1749347448349,
+      "eval_pcc_0": 0.7194368574298652,
+      "eval_pcc_1": 0.7955950565920835,
+      "eval_pcc_2": 0.7873632613095414,
+      "eval_pcc_3": 0.7349721995703357,
+      "eval_runtime": 208.8052,
+      "eval_samples_per_second": 11.973,
+      "eval_steps_per_second": 1.499,
+      "step": 8138
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 1.0281763076782227,
+      "eval_mse_0": 1.1985270977020264,
+      "eval_mse_1": 0.8656768798828125,
+      "eval_mse_2": 0.8898044228553772,
+      "eval_mse_3": 1.1586942672729492,
+      "eval_pcc_0": 0.7197179608986528,
+      "eval_pcc_1": 0.7964511206909821,
+      "eval_pcc_2": 0.7879550281969636,
+      "eval_pcc_3": 0.7354344501757079,
+      "eval_runtime": 208.4407,
+      "eval_samples_per_second": 11.994,
+      "eval_steps_per_second": 1.502,
+      "step": 8451
+    },
+    {
+      "epoch": 27.16,
+      "learning_rate": 9.478168264110757e-07,
+      "loss": 0.3335,
+      "step": 8500
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 1.0045982599258423,
+      "eval_mse_0": 1.2505394220352173,
+      "eval_mse_1": 0.7828913331031799,
+      "eval_mse_2": 0.8181142807006836,
+      "eval_mse_3": 1.166848063468933,
+      "eval_pcc_0": 0.7200083665099367,
+      "eval_pcc_1": 0.7965623791617499,
+      "eval_pcc_2": 0.7880405390944626,
+      "eval_pcc_3": 0.7352189154878063,
+      "eval_runtime": 208.5843,
+      "eval_samples_per_second": 11.986,
+      "eval_steps_per_second": 1.501,
+      "step": 8764
+    },
+    {
+      "epoch": 28.75,
+      "learning_rate": 4.1533546325878595e-07,
+      "loss": 0.3339,
+      "step": 9000
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 1.0302956104278564,
+      "eval_mse_0": 1.2489368915557861,
+      "eval_mse_1": 0.8331665992736816,
+      "eval_mse_2": 0.8591735363006592,
+      "eval_mse_3": 1.1799054145812988,
+      "eval_pcc_0": 0.7194748370263948,
+      "eval_pcc_1": 0.796604271734207,
+      "eval_pcc_2": 0.7879863900669919,
+      "eval_pcc_3": 0.7348973012646607,
+      "eval_runtime": 208.4581,
+      "eval_samples_per_second": 11.993,
+      "eval_steps_per_second": 1.502,
+      "step": 9077
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 1.0285080671310425,
+      "eval_mse_0": 1.2710857391357422,
+      "eval_mse_1": 0.8113386034965515,
+      "eval_mse_2": 0.8502917289733887,
+      "eval_mse_3": 1.1813127994537354,
+      "eval_pcc_0": 0.7187760622799816,
+      "eval_pcc_1": 0.7966815578451035,
+      "eval_pcc_2": 0.7880753758720686,
+      "eval_pcc_3": 0.7343475719122529,
+      "eval_runtime": 208.7552,
+      "eval_samples_per_second": 11.976,
+      "eval_steps_per_second": 1.499,
+      "step": 9390
+    },
+    {
+      "epoch": 30.0,
+      "step": 9390,
+      "total_flos": 0.0,
+      "train_loss": 0.8967580890757081,
+      "train_runtime": 20656.0843,
+      "train_samples_per_second": 3.631,
+      "train_steps_per_second": 0.455
+    }
+  ],
+  "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
+}

hubert/ctc/09_hubert-xlarge-ls960-ft/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a10ddf01b270a5cb50779d6f6ba5be82c0172f7f723692dc1849205404948f2
+size 4792