Upload folder using huggingface_hub

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

@@ -0,0 +1,21 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.2429771423339844,
+    "eval_mse_0": 1.4556059837341309,
+    "eval_mse_1": 1.0280197858810425,
+    "eval_mse_2": 1.067594289779663,
+    "eval_mse_3": 1.4206887483596802,
+    "eval_pcc_0": 0.6313722743433603,
+    "eval_pcc_1": 0.7037270165618034,
+    "eval_pcc_2": 0.6932208330461226,
+    "eval_pcc_3": 0.6458695352840674,
+    "eval_runtime": 203.1577,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 12.306,
+    "eval_steps_per_second": 1.541,
+    "train_loss": 2.5273987888908995,
+    "train_runtime": 20465.2379,
+    "train_samples": 2500,
+    "train_samples_per_second": 3.665,
+    "train_steps_per_second": 0.459
+}

hubert/general/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/general/model_saved",
+    "freeze_feature_extractor": false,
+    "exp_name": "facebook/hubert-xlarge-ll60k_lr1e-05_epochs30_batch4",
+    "save_dir_path": "/data2/haeyoung/0303/general/model_saved/facebook/hubert-xlarge-ll60k_lr1e-05_epochs30_batch4",
+    "save_log_path": "/data2/haeyoung/0303/general/model_saved/logs/facebook/hubert-xlarge-ll60k_lr1e-05_epochs30_batch4"
+}

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

@@ -0,0 +1,16 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.2429771423339844,
+    "eval_mse_0": 1.4556059837341309,
+    "eval_mse_1": 1.0280197858810425,
+    "eval_mse_2": 1.067594289779663,
+    "eval_mse_3": 1.4206887483596802,
+    "eval_pcc_0": 0.6313722743433603,
+    "eval_pcc_1": 0.7037270165618034,
+    "eval_pcc_2": 0.6932208330461226,
+    "eval_pcc_3": 0.6458695352840674,
+    "eval_runtime": 203.1577,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 12.306,
+    "eval_steps_per_second": 1.541
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bdf6078598ee60b7151e1e254389d1387e8525e8df9d1072388998140edf6c
+size 3850336162

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dabeda8cedf70664c98ca3b40415de4c24cbffdbcc82bdf60bfa1ca875d8b41
+size 3850109072

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94feaa82e49ace5cba602e85c71ada7bb6a4039a24f1f54d410f6bed8315adc
+size 3850327978

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

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "train_loss": 2.5273987888908995,
+    "train_runtime": 20465.2379,
+    "train_samples": 2500,
+    "train_samples_per_second": 3.665,
+    "train_steps_per_second": 0.459
+}

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

@@ -0,0 +1 @@
+{"output_dir": "/data2/haeyoung/0303/general/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/general/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/general/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/general/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": 14.21042537689209,
+      "eval_mse_0": 14.491374969482422,
+      "eval_mse_1": 15.235848426818848,
+      "eval_mse_2": 14.3114013671875,
+      "eval_mse_3": 12.803138732910156,
+      "eval_pcc_0": 0.31339751872992866,
+      "eval_pcc_1": -0.04449913037593279,
+      "eval_pcc_2": -0.04967818623406147,
+      "eval_pcc_3": 0.08094723832328224,
+      "eval_runtime": 203.4695,
+      "eval_samples_per_second": 12.287,
+      "eval_steps_per_second": 1.538,
+      "step": 313
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.467518636847711e-06,
+      "loss": 22.8829,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.845417022705078,
+      "eval_mse_0": 7.102958679199219,
+      "eval_mse_1": 7.256675720214844,
+      "eval_mse_2": 6.656838417053223,
+      "eval_mse_3": 6.365192413330078,
+      "eval_pcc_0": 0.29890354113360085,
+      "eval_pcc_1": -0.27095290678086076,
+      "eval_pcc_2": -0.2753067152316496,
+      "eval_pcc_3": 0.18439805543792603,
+      "eval_runtime": 202.3633,
+      "eval_samples_per_second": 12.354,
+      "eval_steps_per_second": 1.547,
+      "step": 626
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.069031000137329,
+      "eval_mse_0": 3.271282911300659,
+      "eval_mse_1": 2.9518942832946777,
+      "eval_mse_2": 2.876866102218628,
+      "eval_mse_3": 3.1760778427124023,
+      "eval_pcc_0": 0.024049449943351883,
+      "eval_pcc_1": -0.38753965092171117,
+      "eval_pcc_2": -0.23522291605713105,
+      "eval_pcc_3": 0.3209360366878388,
+      "eval_runtime": 202.2913,
+      "eval_samples_per_second": 12.358,
+      "eval_steps_per_second": 1.547,
+      "step": 939
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.935037273695422e-06,
+      "loss": 5.6851,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.8592846393585205,
+      "eval_mse_0": 3.0352439880371094,
+      "eval_mse_1": 2.683088541030884,
+      "eval_mse_2": 2.6833605766296387,
+      "eval_mse_3": 3.0354487895965576,
+      "eval_pcc_0": 0.10058683345062165,
+      "eval_pcc_1": 0.16762379635599575,
+      "eval_pcc_2": 0.15318104456855372,
+      "eval_pcc_3": 0.11198007088424215,
+      "eval_runtime": 202.1341,
+      "eval_samples_per_second": 12.368,
+      "eval_steps_per_second": 1.548,
+      "step": 1252
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 8.402555910543132e-06,
+      "loss": 2.3898,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.094325304031372,
+      "eval_mse_0": 2.28056001663208,
+      "eval_mse_1": 1.9052369594573975,
+      "eval_mse_2": 1.9120941162109375,
+      "eval_mse_3": 2.2794132232666016,
+      "eval_pcc_0": 0.23374732962768424,
+      "eval_pcc_1": 0.3047207246310872,
+      "eval_pcc_2": 0.2956174462954376,
+      "eval_pcc_3": 0.2466028680257805,
+      "eval_runtime": 202.0851,
+      "eval_samples_per_second": 12.371,
+      "eval_steps_per_second": 1.549,
+      "step": 1565
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.7370017766952515,
+      "eval_mse_0": 1.9125233888626099,
+      "eval_mse_1": 1.5698639154434204,
+      "eval_mse_2": 1.5325552225112915,
+      "eval_mse_3": 1.9330638647079468,
+      "eval_pcc_0": 0.5140619887798299,
+      "eval_pcc_1": 0.6165094335718002,
+      "eval_pcc_2": 0.5968038395482518,
+      "eval_pcc_3": 0.5365474624195974,
+      "eval_runtime": 202.1675,
+      "eval_samples_per_second": 12.366,
+      "eval_steps_per_second": 1.548,
+      "step": 1878
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 7.870074547390843e-06,
+      "loss": 1.7343,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.4363682270050049,
+      "eval_mse_0": 1.6495369672775269,
+      "eval_mse_1": 1.2387735843658447,
+      "eval_mse_2": 1.2743381261825562,
+      "eval_mse_3": 1.582825779914856,
+      "eval_pcc_0": 0.559592662885545,
+      "eval_pcc_1": 0.6414001632215514,
+      "eval_pcc_2": 0.6253666235201432,
+      "eval_pcc_3": 0.5867745738256969,
+      "eval_runtime": 204.2137,
+      "eval_samples_per_second": 12.242,
+      "eval_steps_per_second": 1.533,
+      "step": 2191
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 7.337593184238552e-06,
+      "loss": 1.4834,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.513439416885376,
+      "eval_mse_0": 1.719864010810852,
+      "eval_mse_1": 1.301133155822754,
+      "eval_mse_2": 1.3386423587799072,
+      "eval_mse_3": 1.694117784500122,
+      "eval_pcc_0": 0.5361834800849117,
+      "eval_pcc_1": 0.619180419395474,
+      "eval_pcc_2": 0.6030785279507598,
+      "eval_pcc_3": 0.5596766506227445,
+      "eval_runtime": 204.7361,
+      "eval_samples_per_second": 12.211,
+      "eval_steps_per_second": 1.529,
+      "step": 2504
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.4969929456710815,
+      "eval_mse_0": 1.7085679769515991,
+      "eval_mse_1": 1.2726653814315796,
+      "eval_mse_2": 1.3180763721466064,
+      "eval_mse_3": 1.6886677742004395,
+      "eval_pcc_0": 0.5385912405981793,
+      "eval_pcc_1": 0.6183121131335464,
+      "eval_pcc_2": 0.601516113665211,
+      "eval_pcc_3": 0.5590966893978593,
+      "eval_runtime": 202.4366,
+      "eval_samples_per_second": 12.35,
+      "eval_steps_per_second": 1.546,
+      "step": 2817
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 6.805111821086262e-06,
+      "loss": 1.2797,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.5733281373977661,
+      "eval_mse_0": 1.810664415359497,
+      "eval_mse_1": 1.3257596492767334,
+      "eval_mse_2": 1.3689907789230347,
+      "eval_mse_3": 1.7878972291946411,
+      "eval_pcc_0": 0.5118173910600906,
+      "eval_pcc_1": 0.6012007060618889,
+      "eval_pcc_2": 0.5817518145155346,
+      "eval_pcc_3": 0.5291008306885933,
+      "eval_runtime": 202.365,
+      "eval_samples_per_second": 12.354,
+      "eval_steps_per_second": 1.547,
+      "step": 3130
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.4168530702590942,
+      "eval_mse_0": 1.624433994293213,
+      "eval_mse_1": 1.1858290433883667,
+      "eval_mse_2": 1.2418301105499268,
+      "eval_mse_3": 1.6153185367584229,
+      "eval_pcc_0": 0.5870925235239078,
+      "eval_pcc_1": 0.651762788628645,
+      "eval_pcc_2": 0.6360938286039809,
+      "eval_pcc_3": 0.6027094405619812,
+      "eval_runtime": 202.5365,
+      "eval_samples_per_second": 12.343,
+      "eval_steps_per_second": 1.545,
+      "step": 3443
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 6.272630457933972e-06,
+      "loss": 1.2067,
+      "step": 3500
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.5180150270462036,
+      "eval_mse_0": 1.7579376697540283,
+      "eval_mse_1": 1.2659412622451782,
+      "eval_mse_2": 1.2921298742294312,
+      "eval_mse_3": 1.7560502290725708,
+      "eval_pcc_0": 0.5587278843704406,
+      "eval_pcc_1": 0.6528470336671222,
+      "eval_pcc_2": 0.6323330684215877,
+      "eval_pcc_3": 0.572543705400061,
+      "eval_runtime": 203.1636,
+      "eval_samples_per_second": 12.305,
+      "eval_steps_per_second": 1.541,
+      "step": 3756
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 5.7401490947816826e-06,
+      "loss": 1.1442,
+      "step": 4000
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.3503384590148926,
+      "eval_mse_0": 1.5781158208847046,
+      "eval_mse_1": 1.1069287061691284,
+      "eval_mse_2": 1.1657685041427612,
+      "eval_mse_3": 1.5505397319793701,
+      "eval_pcc_0": 0.5929588489857289,
+      "eval_pcc_1": 0.6787395882326697,
+      "eval_pcc_2": 0.6598568295122386,
+      "eval_pcc_3": 0.6093152772310467,
+      "eval_runtime": 203.1478,
+      "eval_samples_per_second": 12.306,
+      "eval_steps_per_second": 1.541,
+      "step": 4069
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.3296834230422974,
+      "eval_mse_0": 1.548305630683899,
+      "eval_mse_1": 1.0942931175231934,
+      "eval_mse_2": 1.1508172750473022,
+      "eval_mse_3": 1.5253173112869263,
+      "eval_pcc_0": 0.6056730290105409,
+      "eval_pcc_1": 0.6861127023814588,
+      "eval_pcc_2": 0.6676980213730956,
+      "eval_pcc_3": 0.6196654537023328,
+      "eval_runtime": 203.7374,
+      "eval_samples_per_second": 12.271,
+      "eval_steps_per_second": 1.536,
+      "step": 4382
+    },
+    {
+      "epoch": 14.38,
+      "learning_rate": 5.207667731629393e-06,
+      "loss": 1.0605,
+      "step": 4500
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.350088119506836,
+      "eval_mse_0": 1.5686118602752686,
+      "eval_mse_1": 1.112762212753296,
+      "eval_mse_2": 1.179888129234314,
+      "eval_mse_3": 1.539091944694519,
+      "eval_pcc_0": 0.5967808971749358,
+      "eval_pcc_1": 0.6783622814790322,
+      "eval_pcc_2": 0.6612157960786967,
+      "eval_pcc_3": 0.6129449994519047,
+      "eval_runtime": 202.4428,
+      "eval_samples_per_second": 12.349,
+      "eval_steps_per_second": 1.546,
+      "step": 4695
+    },
+    {
+      "epoch": 15.97,
+      "learning_rate": 4.675186368477103e-06,
+      "loss": 1.0184,
+      "step": 5000
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.3081681728363037,
+      "eval_mse_0": 1.5213674306869507,
+      "eval_mse_1": 1.07903254032135,
+      "eval_mse_2": 1.1227329969406128,
+      "eval_mse_3": 1.5095371007919312,
+      "eval_pcc_0": 0.6120559008261509,
+      "eval_pcc_1": 0.6976804387185814,
+      "eval_pcc_2": 0.6785508258538308,
+      "eval_pcc_3": 0.6247401079926268,
+      "eval_runtime": 202.8261,
+      "eval_samples_per_second": 12.326,
+      "eval_steps_per_second": 1.543,
+      "step": 5008
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.3428281545639038,
+      "eval_mse_0": 1.559637427330017,
+      "eval_mse_1": 1.1062233448028564,
+      "eval_mse_2": 1.1588975191116333,
+      "eval_mse_3": 1.546555995941162,
+      "eval_pcc_0": 0.6003672573947482,
+      "eval_pcc_1": 0.6803658782863133,
+      "eval_pcc_2": 0.6631328309010489,
+      "eval_pcc_3": 0.6120663309009345,
+      "eval_runtime": 204.1059,
+      "eval_samples_per_second": 12.249,
+      "eval_steps_per_second": 1.534,
+      "step": 5321
+    },
+    {
+      "epoch": 17.57,
+      "learning_rate": 4.142705005324814e-06,
+      "loss": 0.966,
+      "step": 5500
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.2832494974136353,
+      "eval_mse_0": 1.490411639213562,
+      "eval_mse_1": 1.063768744468689,
+      "eval_mse_2": 1.1144260168075562,
+      "eval_mse_3": 1.4643957614898682,
+      "eval_pcc_0": 0.6172838673610451,
+      "eval_pcc_1": 0.6911766637735346,
+      "eval_pcc_2": 0.6765814424667771,
+      "eval_pcc_3": 0.6294751791386366,
+      "eval_runtime": 203.9111,
+      "eval_samples_per_second": 12.26,
+      "eval_steps_per_second": 1.535,
+      "step": 5634
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.3138974905014038,
+      "eval_mse_0": 1.5475640296936035,
+      "eval_mse_1": 1.0769293308258057,
+      "eval_mse_2": 1.1150360107421875,
+      "eval_mse_3": 1.5160616636276245,
+      "eval_pcc_0": 0.6261539743469848,
+      "eval_pcc_1": 0.7055848948360127,
+      "eval_pcc_2": 0.6904049132282934,
+      "eval_pcc_3": 0.6399687362937224,
+      "eval_runtime": 204.3335,
+      "eval_samples_per_second": 12.235,
+      "eval_steps_per_second": 1.532,
+      "step": 5947
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 3.6102236421725247e-06,
+      "loss": 0.915,
+      "step": 6000
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.3266900777816772,
+      "eval_mse_0": 1.5566238164901733,
+      "eval_mse_1": 1.0915522575378418,
+      "eval_mse_2": 1.132910132408142,
+      "eval_mse_3": 1.5256727933883667,
+      "eval_pcc_0": 0.6162314031724366,
+      "eval_pcc_1": 0.6975514763626268,
+      "eval_pcc_2": 0.6825840045936838,
+      "eval_pcc_3": 0.630617684198053,
+      "eval_runtime": 203.7563,
+      "eval_samples_per_second": 12.27,
+      "eval_steps_per_second": 1.536,
+      "step": 6260
+    },
+    {
+      "epoch": 20.77,
+      "learning_rate": 3.0777422790202343e-06,
+      "loss": 0.9028,
+      "step": 6500
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.2940527200698853,
+      "eval_mse_0": 1.519923210144043,
+      "eval_mse_1": 1.0612545013427734,
+      "eval_mse_2": 1.1128571033477783,
+      "eval_mse_3": 1.4821780920028687,
+      "eval_pcc_0": 0.6198974812777845,
+      "eval_pcc_1": 0.6942544812603074,
+      "eval_pcc_2": 0.6827949615101815,
+      "eval_pcc_3": 0.6352332606845253,
+      "eval_runtime": 204.3408,
+      "eval_samples_per_second": 12.234,
+      "eval_steps_per_second": 1.532,
+      "step": 6573
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.2701632976531982,
+      "eval_mse_0": 1.4819650650024414,
+      "eval_mse_1": 1.0538557767868042,
+      "eval_mse_2": 1.0932190418243408,
+      "eval_mse_3": 1.4516133069992065,
+      "eval_pcc_0": 0.6209975387537724,
+      "eval_pcc_1": 0.6956350125679469,
+      "eval_pcc_2": 0.6839401228051497,
+      "eval_pcc_3": 0.6348397932416047,
+      "eval_runtime": 203.3908,
+      "eval_samples_per_second": 12.292,
+      "eval_steps_per_second": 1.539,
+      "step": 6886
+    },
+    {
+      "epoch": 22.36,
+      "learning_rate": 2.5452609158679447e-06,
+      "loss": 0.8716,
+      "step": 7000
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.2568182945251465,
+      "eval_mse_0": 1.469943642616272,
+      "eval_mse_1": 1.0371981859207153,
+      "eval_mse_2": 1.08242928981781,
+      "eval_mse_3": 1.4377042055130005,
+      "eval_pcc_0": 0.6284333258398216,
+      "eval_pcc_1": 0.7000358461547029,
+      "eval_pcc_2": 0.6888147960832176,
+      "eval_pcc_3": 0.6424986295768361,
+      "eval_runtime": 204.5187,
+      "eval_samples_per_second": 12.224,
+      "eval_steps_per_second": 1.53,
+      "step": 7199
+    },
+    {
+      "epoch": 23.96,
+      "learning_rate": 2.012779552715655e-06,
+      "loss": 0.8556,
+      "step": 7500
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.3086744546890259,
+      "eval_mse_0": 1.52476167678833,
+      "eval_mse_1": 1.085228681564331,
+      "eval_mse_2": 1.1310092210769653,
+      "eval_mse_3": 1.493698000907898,
+      "eval_pcc_0": 0.6128152525115359,
+      "eval_pcc_1": 0.6871395487353599,
+      "eval_pcc_2": 0.6769039183023791,
+      "eval_pcc_3": 0.6269240489285123,
+      "eval_runtime": 203.1608,
+      "eval_samples_per_second": 12.306,
+      "eval_steps_per_second": 1.541,
+      "step": 7512
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.2571042776107788,
+      "eval_mse_0": 1.47658109664917,
+      "eval_mse_1": 1.0334194898605347,
+      "eval_mse_2": 1.0786664485931396,
+      "eval_mse_3": 1.439751148223877,
+      "eval_pcc_0": 0.6270819562950619,
+      "eval_pcc_1": 0.7029997942703922,
+      "eval_pcc_2": 0.6915211988722211,
+      "eval_pcc_3": 0.6424069485490148,
+      "eval_runtime": 202.5206,
+      "eval_samples_per_second": 12.344,
+      "eval_steps_per_second": 1.546,
+      "step": 7825
+    },
+    {
+      "epoch": 25.56,
+      "learning_rate": 1.4802981895633654e-06,
+      "loss": 0.8405,
+      "step": 8000
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 1.2658495903015137,
+      "eval_mse_0": 1.4873664379119873,
+      "eval_mse_1": 1.0414340496063232,
+      "eval_mse_2": 1.0855013132095337,
+      "eval_mse_3": 1.449096441268921,
+      "eval_pcc_0": 0.6251476135887488,
+      "eval_pcc_1": 0.6994384867535656,
+      "eval_pcc_2": 0.6891347367802129,
+      "eval_pcc_3": 0.640242246403783,
+      "eval_runtime": 202.6983,
+      "eval_samples_per_second": 12.334,
+      "eval_steps_per_second": 1.544,
+      "step": 8138
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 1.2638978958129883,
+      "eval_mse_0": 1.4785104990005493,
+      "eval_mse_1": 1.0455129146575928,
+      "eval_mse_2": 1.0909162759780884,
+      "eval_mse_3": 1.4406505823135376,
+      "eval_pcc_0": 0.622519640454944,
+      "eval_pcc_1": 0.6972074033423277,
+      "eval_pcc_2": 0.6866778755585013,
+      "eval_pcc_3": 0.6374730956754262,
+      "eval_runtime": 203.1307,
+      "eval_samples_per_second": 12.307,
+      "eval_steps_per_second": 1.541,
+      "step": 8451
+    },
+    {
+      "epoch": 27.16,
+      "learning_rate": 9.478168264110757e-07,
+      "loss": 0.8045,
+      "step": 8500
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 1.245224952697754,
+      "eval_mse_0": 1.4587944746017456,
+      "eval_mse_1": 1.0294071435928345,
+      "eval_mse_2": 1.0689460039138794,
+      "eval_mse_3": 1.4237576723098755,
+      "eval_pcc_0": 0.6295444439771427,
+      "eval_pcc_1": 0.7033799239560641,
+      "eval_pcc_2": 0.6926526140214548,
+      "eval_pcc_3": 0.6445067513216154,
+      "eval_runtime": 202.1758,
+      "eval_samples_per_second": 12.365,
+      "eval_steps_per_second": 1.548,
+      "step": 8764
+    },
+    {
+      "epoch": 28.75,
+      "learning_rate": 4.1533546325878595e-07,
+      "loss": 0.7918,
+      "step": 9000
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 1.25887131690979,
+      "eval_mse_0": 1.47682523727417,
+      "eval_mse_1": 1.0370581150054932,
+      "eval_mse_2": 1.0806893110275269,
+      "eval_mse_3": 1.4409104585647583,
+      "eval_pcc_0": 0.6277033160732701,
+      "eval_pcc_1": 0.7008331975225768,
+      "eval_pcc_2": 0.6906056201099237,
+      "eval_pcc_3": 0.6425996774426014,
+      "eval_runtime": 203.0462,
+      "eval_samples_per_second": 12.312,
+      "eval_steps_per_second": 1.542,
+      "step": 9077
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 1.2429771423339844,
+      "eval_mse_0": 1.4556059837341309,
+      "eval_mse_1": 1.0280197858810425,
+      "eval_mse_2": 1.067594289779663,
+      "eval_mse_3": 1.4206887483596802,
+      "eval_pcc_0": 0.6313722743433603,
+      "eval_pcc_1": 0.7037270165618034,
+      "eval_pcc_2": 0.6932208330461226,
+      "eval_pcc_3": 0.6458695352840674,
+      "eval_runtime": 202.3865,
+      "eval_samples_per_second": 12.353,
+      "eval_steps_per_second": 1.547,
+      "step": 9390
+    },
+    {
+      "epoch": 30.0,
+      "step": 9390,
+      "total_flos": 0.0,
+      "train_loss": 2.5273987888908995,
+      "train_runtime": 20465.2379,
+      "train_samples_per_second": 3.665,
+      "train_steps_per_second": 0.459
+    }
+  ],
+  "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/general/08_hubert-xlarge-ll60k/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f598caaa3e414157895eeaea5570d3e986101a39317a01f51c72795d3789c31
+size 4792