Upload folder using huggingface_hub

hubert/ctc/08_hubert-xlarge-ll60k/all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.0636274814605713,
+    "eval_mse_0": 1.291344404220581,
+    "eval_mse_1": 0.8609154224395752,
+    "eval_mse_2": 0.8673214912414551,
+    "eval_mse_3": 1.2349287271499634,
+    "eval_pcc_0": 0.6857904234808526,
+    "eval_pcc_1": 0.7593770185673134,
+    "eval_pcc_2": 0.7611637554520289,
+    "eval_pcc_3": 0.7046817934160569,
+    "eval_runtime": 209.3256,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 11.943,
+    "eval_steps_per_second": 1.495,
+    "train_loss": 2.660792814504605,
+    "train_runtime": 20639.7022,
+    "train_samples": 2500,
+    "train_samples_per_second": 3.634,
+    "train_steps_per_second": 0.455
+}

hubert/ctc/08_hubert-xlarge-ll60k/args.json

@@ -0,0 +1,11 @@
+{
+    "batch_size": 4,
+    "model_name": "facebook/hubert-xlarge-ll60k",
+    "learning_rate": 1e-05,
+    "num_train_epochs": 30,
+    "save_dir": "/data2/haeyoung/0303/ctc/model_saved",
+    "freeze_feature_extractor": false,
+    "exp_name": "facebook/hubert-xlarge-ll60k_lr1e-05_epochs30_batch4",
+    "save_dir_path": "/data2/haeyoung/0303/ctc/model_saved/facebook/hubert-xlarge-ll60k_lr1e-05_epochs30_batch4",
+    "save_log_path": "/data2/haeyoung/0303/ctc/model_saved/logs/facebook/hubert-xlarge-ll60k_lr1e-05_epochs30_batch4"
+}

hubert/ctc/08_hubert-xlarge-ll60k/eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.0636274814605713,
+    "eval_mse_0": 1.291344404220581,
+    "eval_mse_1": 0.8609154224395752,
+    "eval_mse_2": 0.8673214912414551,
+    "eval_mse_3": 1.2349287271499634,
+    "eval_pcc_0": 0.6857904234808526,
+    "eval_pcc_1": 0.7593770185673134,
+    "eval_pcc_2": 0.7611637554520289,
+    "eval_pcc_3": 0.7046817934160569,
+    "eval_runtime": 209.3256,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 11.943,
+    "eval_steps_per_second": 1.495
+}

hubert/ctc/08_hubert-xlarge-ll60k/finetuned_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b2525c592450292cb6238897310cf93de6940041d6a58d50b36da65c067a62
+size 3850503230

hubert/ctc/08_hubert-xlarge-ll60k/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f1116f889c4864fc0e356f42a2017c51fe933ede9316e9bf607109c4aabb55
+size 3850258896

hubert/ctc/08_hubert-xlarge-ll60k/model_weights.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b7978dce9b91f67a172ff360138e72fd9ae9d8aeb48d389b48b48ffa8d7391f
+size 3850495026

hubert/ctc/08_hubert-xlarge-ll60k/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/08_hubert-xlarge-ll60k/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "train_loss": 2.660792814504605,
+    "train_runtime": 20639.7022,
+    "train_samples": 2500,
+    "train_samples_per_second": 3.634,
+    "train_steps_per_second": 0.455
+}

hubert/ctc/08_hubert-xlarge-ll60k/trainer_args.json

@@ -0,0 +1 @@
+{"output_dir": "/data2/haeyoung/0303/ctc/model_saved/facebook/hubert-xlarge-ll60k_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/facebook/hubert-xlarge-ll60k_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/facebook/hubert-xlarge-ll60k_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/08_hubert-xlarge-ll60k/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": 20.333858489990234,
+      "eval_mse_0": 16.554113388061523,
+      "eval_mse_1": 23.708436965942383,
+      "eval_mse_2": 26.395322799682617,
+      "eval_mse_3": 14.677531242370605,
+      "eval_pcc_0": 0.08887771336999509,
+      "eval_pcc_1": 0.30416897399834153,
+      "eval_pcc_2": -0.11869277397195638,
+      "eval_pcc_3": -0.05092855944760599,
+      "eval_runtime": 203.6146,
+      "eval_samples_per_second": 12.278,
+      "eval_steps_per_second": 1.537,
+      "step": 313
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.467518636847711e-06,
+      "loss": 29.1628,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 8.371243476867676,
+      "eval_mse_0": 6.608287334442139,
+      "eval_mse_1": 10.010001182556152,
+      "eval_mse_2": 11.445313453674316,
+      "eval_mse_3": 5.421355724334717,
+      "eval_pcc_0": 0.15230714518503505,
+      "eval_pcc_1": 0.31651858655786524,
+      "eval_pcc_2": -0.3098743749181427,
+      "eval_pcc_3": -0.08943039168565037,
+      "eval_runtime": 202.8185,
+      "eval_samples_per_second": 12.326,
+      "eval_steps_per_second": 1.543,
+      "step": 626
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.84228253364563,
+      "eval_mse_0": 2.8173067569732666,
+      "eval_mse_1": 2.8192200660705566,
+      "eval_mse_2": 3.008348226547241,
+      "eval_mse_3": 2.7242579460144043,
+      "eval_pcc_0": 0.26284629405677384,
+      "eval_pcc_1": 0.3395178235678686,
+      "eval_pcc_2": -0.4887300856906985,
+      "eval_pcc_3": 0.2144796816379417,
+      "eval_runtime": 203.2406,
+      "eval_samples_per_second": 12.301,
+      "eval_steps_per_second": 1.54,
+      "step": 939
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.935037273695422e-06,
+      "loss": 6.4573,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.5990328788757324,
+      "eval_mse_0": 2.7770566940307617,
+      "eval_mse_1": 2.4433836936950684,
+      "eval_mse_2": 2.4372899532318115,
+      "eval_mse_3": 2.738408088684082,
+      "eval_pcc_0": 0.3161769003199966,
+      "eval_pcc_1": 0.3966704647645627,
+      "eval_pcc_2": 0.3754604857681634,
+      "eval_pcc_3": 0.3229699560349081,
+      "eval_runtime": 203.0933,
+      "eval_samples_per_second": 12.31,
+      "eval_steps_per_second": 1.541,
+      "step": 1252
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 8.402555910543132e-06,
+      "loss": 2.0303,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.5712674856185913,
+      "eval_mse_0": 1.7247648239135742,
+      "eval_mse_1": 1.3775886297225952,
+      "eval_mse_2": 1.4481903314590454,
+      "eval_mse_3": 1.734527587890625,
+      "eval_pcc_0": 0.5231576361013757,
+      "eval_pcc_1": 0.5697144912224956,
+      "eval_pcc_2": 0.5507807353215809,
+      "eval_pcc_3": 0.5317655927100577,
+      "eval_runtime": 202.7022,
+      "eval_samples_per_second": 12.333,
+      "eval_steps_per_second": 1.544,
+      "step": 1565
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.6596863269805908,
+      "eval_mse_0": 1.8965370655059814,
+      "eval_mse_1": 1.4242517948150635,
+      "eval_mse_2": 1.4227795600891113,
+      "eval_mse_3": 1.8951765298843384,
+      "eval_pcc_0": 0.5577199537295284,
+      "eval_pcc_1": 0.6456385345601334,
+      "eval_pcc_2": 0.6251746051142912,
+      "eval_pcc_3": 0.5699618394088968,
+      "eval_runtime": 203.7545,
+      "eval_samples_per_second": 12.27,
+      "eval_steps_per_second": 1.536,
+      "step": 1878
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 7.870074547390843e-06,
+      "loss": 1.3252,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.3559465408325195,
+      "eval_mse_0": 2.761385917663574,
+      "eval_mse_1": 1.9953265190124512,
+      "eval_mse_2": 1.9403605461120605,
+      "eval_mse_3": 2.7267091274261475,
+      "eval_pcc_0": 0.5567282316614617,
+      "eval_pcc_1": 0.6535631176210748,
+      "eval_pcc_2": 0.6353176903080382,
+      "eval_pcc_3": 0.5689403558879337,
+      "eval_runtime": 206.0447,
+      "eval_samples_per_second": 12.133,
+      "eval_steps_per_second": 1.519,
+      "step": 2191
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 7.337593184238552e-06,
+      "loss": 1.0838,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.774496078491211,
+      "eval_mse_0": 2.0387697219848633,
+      "eval_mse_1": 1.5231553316116333,
+      "eval_mse_2": 1.4725456237792969,
+      "eval_mse_3": 2.063514232635498,
+      "eval_pcc_0": 0.5942018206531998,
+      "eval_pcc_1": 0.6840947488000324,
+      "eval_pcc_2": 0.6707717908763593,
+      "eval_pcc_3": 0.6080548747004896,
+      "eval_runtime": 203.1109,
+      "eval_samples_per_second": 12.309,
+      "eval_steps_per_second": 1.541,
+      "step": 2504
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.266087293624878,
+      "eval_mse_0": 1.4825718402862549,
+      "eval_mse_1": 1.0457584857940674,
+      "eval_mse_2": 1.0797761678695679,
+      "eval_mse_3": 1.4562429189682007,
+      "eval_pcc_0": 0.6348035344851367,
+      "eval_pcc_1": 0.7058168118714253,
+      "eval_pcc_2": 0.6944099878573109,
+      "eval_pcc_3": 0.6492674743054553,
+      "eval_runtime": 202.9007,
+      "eval_samples_per_second": 12.321,
+      "eval_steps_per_second": 1.543,
+      "step": 2817
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 6.805111821086262e-06,
+      "loss": 0.9748,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.2405636310577393,
+      "eval_mse_0": 1.4680604934692383,
+      "eval_mse_1": 1.016302227973938,
+      "eval_mse_2": 1.0383095741271973,
+      "eval_mse_3": 1.4395811557769775,
+      "eval_pcc_0": 0.6480777858763171,
+      "eval_pcc_1": 0.7231846473962125,
+      "eval_pcc_2": 0.714282014843502,
+      "eval_pcc_3": 0.6630857126360169,
+      "eval_runtime": 210.6434,
+      "eval_samples_per_second": 11.868,
+      "eval_steps_per_second": 1.486,
+      "step": 3130
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.3747354745864868,
+      "eval_mse_0": 1.631429672241211,
+      "eval_mse_1": 1.133544683456421,
+      "eval_mse_2": 1.131657600402832,
+      "eval_mse_3": 1.602310299873352,
+      "eval_pcc_0": 0.6393380023455071,
+      "eval_pcc_1": 0.7172979276438516,
+      "eval_pcc_2": 0.7073642880248558,
+      "eval_pcc_3": 0.655665291158119,
+      "eval_runtime": 203.1919,
+      "eval_samples_per_second": 12.304,
+      "eval_steps_per_second": 1.54,
+      "step": 3443
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 6.272630457933972e-06,
+      "loss": 0.8641,
+      "step": 3500
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.179725170135498,
+      "eval_mse_0": 1.3889130353927612,
+      "eval_mse_1": 0.9846572279930115,
+      "eval_mse_2": 0.9835968613624573,
+      "eval_mse_3": 1.361733078956604,
+      "eval_pcc_0": 0.6626884650703191,
+      "eval_pcc_1": 0.7321900517085644,
+      "eval_pcc_2": 0.728170511532941,
+      "eval_pcc_3": 0.6781896265330651,
+      "eval_runtime": 210.3945,
+      "eval_samples_per_second": 11.882,
+      "eval_steps_per_second": 1.488,
+      "step": 3756
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 5.7401490947816826e-06,
+      "loss": 0.833,
+      "step": 4000
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.1307871341705322,
+      "eval_mse_0": 1.3401113748550415,
+      "eval_mse_1": 0.9279629588127136,
+      "eval_mse_2": 0.9595462083816528,
+      "eval_mse_3": 1.2955329418182373,
+      "eval_pcc_0": 0.6689292790071075,
+      "eval_pcc_1": 0.7383271729531051,
+      "eval_pcc_2": 0.7320943286242071,
+      "eval_pcc_3": 0.6855265374628569,
+      "eval_runtime": 202.9294,
+      "eval_samples_per_second": 12.32,
+      "eval_steps_per_second": 1.542,
+      "step": 4069
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.1691124439239502,
+      "eval_mse_0": 1.3750510215759277,
+      "eval_mse_1": 0.9653419852256775,
+      "eval_mse_2": 0.9743927717208862,
+      "eval_mse_3": 1.361662745475769,
+      "eval_pcc_0": 0.6749380300367478,
+      "eval_pcc_1": 0.7455898706611583,
+      "eval_pcc_2": 0.7430198722570088,
+      "eval_pcc_3": 0.6915992434418081,
+      "eval_runtime": 202.9468,
+      "eval_samples_per_second": 12.318,
+      "eval_steps_per_second": 1.542,
+      "step": 4382
+    },
+    {
+      "epoch": 14.38,
+      "learning_rate": 5.207667731629393e-06,
+      "loss": 0.7832,
+      "step": 4500
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.0932546854019165,
+      "eval_mse_0": 1.289063811302185,
+      "eval_mse_1": 0.9073979258537292,
+      "eval_mse_2": 0.9229546189308167,
+      "eval_mse_3": 1.253597378730774,
+      "eval_pcc_0": 0.6789636378061773,
+      "eval_pcc_1": 0.7472264571643817,
+      "eval_pcc_2": 0.7446864975682971,
+      "eval_pcc_3": 0.6944261831634843,
+      "eval_runtime": 202.7702,
+      "eval_samples_per_second": 12.329,
+      "eval_steps_per_second": 1.544,
+      "step": 4695
+    },
+    {
+      "epoch": 15.97,
+      "learning_rate": 4.675186368477103e-06,
+      "loss": 0.742,
+      "step": 5000
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.1521117687225342,
+      "eval_mse_0": 1.3778270483016968,
+      "eval_mse_1": 0.9466921091079712,
+      "eval_mse_2": 0.9404878616333008,
+      "eval_mse_3": 1.3434394598007202,
+      "eval_pcc_0": 0.6741285039814312,
+      "eval_pcc_1": 0.7479661984813933,
+      "eval_pcc_2": 0.7469445401051306,
+      "eval_pcc_3": 0.6919052906905563,
+      "eval_runtime": 202.8971,
+      "eval_samples_per_second": 12.322,
+      "eval_steps_per_second": 1.543,
+      "step": 5008
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.0943790674209595,
+      "eval_mse_0": 1.302241563796997,
+      "eval_mse_1": 0.902751088142395,
+      "eval_mse_2": 0.9067798852920532,
+      "eval_mse_3": 1.2657426595687866,
+      "eval_pcc_0": 0.6810487708192998,
+      "eval_pcc_1": 0.7500176759790266,
+      "eval_pcc_2": 0.7486362515517387,
+      "eval_pcc_3": 0.6972524049133376,
+      "eval_runtime": 203.6311,
+      "eval_samples_per_second": 12.277,
+      "eval_steps_per_second": 1.537,
+      "step": 5321
+    },
+    {
+      "epoch": 17.57,
+      "learning_rate": 4.142705005324814e-06,
+      "loss": 0.7185,
+      "step": 5500
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.0697906017303467,
+      "eval_mse_0": 1.2646998167037964,
+      "eval_mse_1": 0.8821287155151367,
+      "eval_mse_2": 0.9013919830322266,
+      "eval_mse_3": 1.2309443950653076,
+      "eval_pcc_0": 0.6852081116865166,
+      "eval_pcc_1": 0.7525057715556226,
+      "eval_pcc_2": 0.7509136662257396,
+      "eval_pcc_3": 0.7006620286548182,
+      "eval_runtime": 203.6533,
+      "eval_samples_per_second": 12.276,
+      "eval_steps_per_second": 1.537,
+      "step": 5634
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.1057201623916626,
+      "eval_mse_0": 1.3079144954681396,
+      "eval_mse_1": 0.9223601818084717,
+      "eval_mse_2": 0.9093884825706482,
+      "eval_mse_3": 1.2832152843475342,
+      "eval_pcc_0": 0.6862657383285174,
+      "eval_pcc_1": 0.7556456129660256,
+      "eval_pcc_2": 0.7571190868111386,
+      "eval_pcc_3": 0.7034618532757856,
+      "eval_runtime": 203.2442,
+      "eval_samples_per_second": 12.3,
+      "eval_steps_per_second": 1.54,
+      "step": 5947
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 3.6102236421725247e-06,
+      "loss": 0.6893,
+      "step": 6000
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.10100257396698,
+      "eval_mse_0": 1.3233023881912231,
+      "eval_mse_1": 0.9011407494544983,
+      "eval_mse_2": 0.8982234597206116,
+      "eval_mse_3": 1.2813421487808228,
+      "eval_pcc_0": 0.6819159089249017,
+      "eval_pcc_1": 0.7517299372382112,
+      "eval_pcc_2": 0.7528194511731832,
+      "eval_pcc_3": 0.6989106198951501,
+      "eval_runtime": 203.565,
+      "eval_samples_per_second": 12.281,
+      "eval_steps_per_second": 1.538,
+      "step": 6260
+    },
+    {
+      "epoch": 20.77,
+      "learning_rate": 3.0777422790202343e-06,
+      "loss": 0.6658,
+      "step": 6500
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.0957356691360474,
+      "eval_mse_0": 1.3362116813659668,
+      "eval_mse_1": 0.8827068209648132,
+      "eval_mse_2": 0.885504961013794,
+      "eval_mse_3": 1.2785204648971558,
+      "eval_pcc_0": 0.680628697779889,
+      "eval_pcc_1": 0.7537818509480396,
+      "eval_pcc_2": 0.754908944347794,
+      "eval_pcc_3": 0.6988052791553623,
+      "eval_runtime": 218.0439,
+      "eval_samples_per_second": 11.466,
+      "eval_steps_per_second": 1.435,
+      "step": 6573
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.0966740846633911,
+      "eval_mse_0": 1.32157301902771,
+      "eval_mse_1": 0.8951436281204224,
+      "eval_mse_2": 0.8909459710121155,
+      "eval_mse_3": 1.2790309190750122,
+      "eval_pcc_0": 0.6810520664221775,
+      "eval_pcc_1": 0.7539423199883235,
+      "eval_pcc_2": 0.7542814490884132,
+      "eval_pcc_3": 0.6987981671631167,
+      "eval_runtime": 203.24,
+      "eval_samples_per_second": 12.301,
+      "eval_steps_per_second": 1.54,
+      "step": 6886
+    },
+    {
+      "epoch": 22.36,
+      "learning_rate": 2.5452609158679447e-06,
+      "loss": 0.6526,
+      "step": 7000
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.083720326423645,
+      "eval_mse_0": 1.3151943683624268,
+      "eval_mse_1": 0.8776894807815552,
+      "eval_mse_2": 0.8770623803138733,
+      "eval_mse_3": 1.2649331092834473,
+      "eval_pcc_0": 0.6842123557293225,
+      "eval_pcc_1": 0.756332720948954,
+      "eval_pcc_2": 0.7577995238455972,
+      "eval_pcc_3": 0.702366896719456,
+      "eval_runtime": 203.5325,
+      "eval_samples_per_second": 12.283,
+      "eval_steps_per_second": 1.538,
+      "step": 7199
+    },
+    {
+      "epoch": 23.96,
+      "learning_rate": 2.012779552715655e-06,
+      "loss": 0.6531,
+      "step": 7500
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.0782527923583984,
+      "eval_mse_0": 1.312295913696289,
+      "eval_mse_1": 0.8694647550582886,
+      "eval_mse_2": 0.8759238123893738,
+      "eval_mse_3": 1.2553253173828125,
+      "eval_pcc_0": 0.6857522164751878,
+      "eval_pcc_1": 0.759346756347098,
+      "eval_pcc_2": 0.7607800582151766,
+      "eval_pcc_3": 0.7048817341886087,
+      "eval_runtime": 203.6628,
+      "eval_samples_per_second": 12.275,
+      "eval_steps_per_second": 1.537,
+      "step": 7512
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.07210111618042,
+      "eval_mse_0": 1.3089362382888794,
+      "eval_mse_1": 0.8625428676605225,
+      "eval_mse_2": 0.8729068636894226,
+      "eval_mse_3": 1.2440167665481567,
+      "eval_pcc_0": 0.6852372358039052,
+      "eval_pcc_1": 0.7598475908517249,
+      "eval_pcc_2": 0.7609290750485831,
+      "eval_pcc_3": 0.7044899253802238,
+      "eval_runtime": 203.4179,
+      "eval_samples_per_second": 12.29,
+      "eval_steps_per_second": 1.539,
+      "step": 7825
+    },
+    {
+      "epoch": 25.56,
+      "learning_rate": 1.4802981895633654e-06,
+      "loss": 0.634,
+      "step": 8000
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 1.0625019073486328,
+      "eval_mse_0": 1.288314700126648,
+      "eval_mse_1": 0.861156165599823,
+      "eval_mse_2": 0.8685433864593506,
+      "eval_mse_3": 1.2319947481155396,
+      "eval_pcc_0": 0.686111757779938,
+      "eval_pcc_1": 0.7589608454379306,
+      "eval_pcc_2": 0.7603087630609361,
+      "eval_pcc_3": 0.7045669997269809,
+      "eval_runtime": 203.454,
+      "eval_samples_per_second": 12.288,
+      "eval_steps_per_second": 1.538,
+      "step": 8138
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 1.0610527992248535,
+      "eval_mse_0": 1.282828450202942,
+      "eval_mse_1": 0.8629063367843628,
+      "eval_mse_2": 0.8696379661560059,
+      "eval_mse_3": 1.2288366556167603,
+      "eval_pcc_0": 0.6852411835942828,
+      "eval_pcc_1": 0.7583895761389947,
+      "eval_pcc_2": 0.7597067873285279,
+      "eval_pcc_3": 0.70371582773465,
+      "eval_runtime": 203.591,
+      "eval_samples_per_second": 12.28,
+      "eval_steps_per_second": 1.537,
+      "step": 8451
+    },
+    {
+      "epoch": 27.16,
+      "learning_rate": 9.478168264110757e-07,
+      "loss": 0.61,
+      "step": 8500
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 1.062330722808838,
+      "eval_mse_0": 1.2870919704437256,
+      "eval_mse_1": 0.8616698384284973,
+      "eval_mse_2": 0.8681812286376953,
+      "eval_mse_3": 1.2323803901672363,
+      "eval_pcc_0": 0.6854279959984694,
+      "eval_pcc_1": 0.7588494733710003,
+      "eval_pcc_2": 0.7604017612939257,
+      "eval_pcc_3": 0.7041986226570947,
+      "eval_runtime": 203.5945,
+      "eval_samples_per_second": 12.279,
+      "eval_steps_per_second": 1.537,
+      "step": 8764
+    },
+    {
+      "epoch": 28.75,
+      "learning_rate": 4.1533546325878595e-07,
+      "loss": 0.6029,
+      "step": 9000
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 1.067120909690857,
+      "eval_mse_0": 1.2960582971572876,
+      "eval_mse_1": 0.8634568452835083,
+      "eval_mse_2": 0.868851363658905,
+      "eval_mse_3": 1.240116000175476,
+      "eval_pcc_0": 0.6853392267802676,
+      "eval_pcc_1": 0.7589099331256576,
+      "eval_pcc_2": 0.7606892686277734,
+      "eval_pcc_3": 0.704235141249362,
+      "eval_runtime": 203.5285,
+      "eval_samples_per_second": 12.283,
+      "eval_steps_per_second": 1.538,
+      "step": 9077
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 1.0636274814605713,
+      "eval_mse_0": 1.291344404220581,
+      "eval_mse_1": 0.8609154224395752,
+      "eval_mse_2": 0.8673214912414551,
+      "eval_mse_3": 1.2349287271499634,
+      "eval_pcc_0": 0.6857904234808526,
+      "eval_pcc_1": 0.7593770185673134,
+      "eval_pcc_2": 0.7611637554520289,
+      "eval_pcc_3": 0.7046817934160569,
+      "eval_runtime": 203.4868,
+      "eval_samples_per_second": 12.286,
+      "eval_steps_per_second": 1.538,
+      "step": 9390
+    },
+    {
+      "epoch": 30.0,
+      "step": 9390,
+      "total_flos": 0.0,
+      "train_loss": 2.660792814504605,
+      "train_runtime": 20639.7022,
+      "train_samples_per_second": 3.634,
+      "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/08_hubert-xlarge-ll60k/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55527e397f853b810616ba12cb1c257bc568411c56d14cbc3c10884740f9f1b7
+size 4792