Upload folder using huggingface_hub (#47)

- Upload folder using huggingface_hub (0285b39ad619b789f4506379b23d89c5a3067e82)

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

@@ -0,0 +1,21 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.0948735475540161,
+    "eval_mse_0": 1.3283392190933228,
+    "eval_mse_1": 0.8795621991157532,
+    "eval_mse_2": 0.9013708829879761,
+    "eval_mse_3": 1.2702199220657349,
+    "eval_pcc_0": 0.7021826040010801,
+    "eval_pcc_1": 0.7854537370686618,
+    "eval_pcc_2": 0.7833671948442064,
+    "eval_pcc_3": 0.7276810306429349,
+    "eval_runtime": 208.9683,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 11.964,
+    "eval_steps_per_second": 1.498,
+    "train_loss": 2.4084234739390933,
+    "train_runtime": 21831.2419,
+    "train_samples": 2500,
+    "train_samples_per_second": 3.435,
+    "train_steps_per_second": 0.43
+}

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

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

@@ -0,0 +1,16 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.0948735475540161,
+    "eval_mse_0": 1.3283392190933228,
+    "eval_mse_1": 0.8795621991157532,
+    "eval_mse_2": 0.9013708829879761,
+    "eval_mse_3": 1.2702199220657349,
+    "eval_pcc_0": 0.7021826040010801,
+    "eval_pcc_1": 0.7854537370686618,
+    "eval_pcc_2": 0.7833671948442064,
+    "eval_pcc_3": 0.7276810306429349,
+    "eval_runtime": 208.9683,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 11.964,
+    "eval_steps_per_second": 1.498
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23acada074cc1d3431c6e70e69a00f943b6f838d3f39623302cba61f515cd3ef
+size 3850336162

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d64f93bd4a7b55cc605cc1ca8d2d29fe18bdd476c9225a28540479c16379567f
+size 3850109072

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98b3898ea596c2f206c788faa139566f044b91f4cca11d8911bc2cfb1db803f
+size 3850327978

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

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "train_loss": 2.4084234739390933,
+    "train_runtime": 21831.2419,
+    "train_samples": 2500,
+    "train_samples_per_second": 3.435,
+    "train_steps_per_second": 0.43
+}

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

@@ -0,0 +1 @@
+{"output_dir": "/data2/haeyoung/0303/cnnfreeze/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/cnnfreeze/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/cnnfreeze/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/freeze/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": 16.218280792236328,
+      "eval_mse_0": 17.802480697631836,
+      "eval_mse_1": 18.155719757080078,
+      "eval_mse_2": 14.126106262207031,
+      "eval_mse_3": 14.788859367370605,
+      "eval_pcc_0": -0.22481502950988502,
+      "eval_pcc_1": 0.027133910849329135,
+      "eval_pcc_2": 0.20227880310142587,
+      "eval_pcc_3": 0.11151929966621901,
+      "eval_runtime": 214.1139,
+      "eval_samples_per_second": 11.676,
+      "eval_steps_per_second": 1.462,
+      "step": 313
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.467518636847711e-06,
+      "loss": 25.0507,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 8.59992790222168,
+      "eval_mse_0": 9.499269485473633,
+      "eval_mse_1": 9.545639038085938,
+      "eval_mse_2": 7.361404895782471,
+      "eval_mse_3": 7.9933977127075195,
+      "eval_pcc_0": -0.3838095571944921,
+      "eval_pcc_1": 0.21055681530011738,
+      "eval_pcc_2": 0.30771108537508796,
+      "eval_pcc_3": 0.3319953656955543,
+      "eval_runtime": 217.917,
+      "eval_samples_per_second": 11.472,
+      "eval_steps_per_second": 1.436,
+      "step": 626
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 4.078005313873291,
+      "eval_mse_0": 4.5147223472595215,
+      "eval_mse_1": 4.191625595092773,
+      "eval_mse_2": 3.5707597732543945,
+      "eval_mse_3": 4.034916400909424,
+      "eval_pcc_0": -0.5098991192174415,
+      "eval_pcc_1": 0.3747362745901819,
+      "eval_pcc_2": 0.32219473547290267,
+      "eval_pcc_3": 0.29375816196915006,
+      "eval_runtime": 209.0199,
+      "eval_samples_per_second": 11.961,
+      "eval_steps_per_second": 1.497,
+      "step": 939
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.935037273695422e-06,
+      "loss": 7.2298,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.380504608154297,
+      "eval_mse_0": 2.555655002593994,
+      "eval_mse_1": 2.2386953830718994,
+      "eval_mse_2": 2.1945056915283203,
+      "eval_mse_3": 2.53316330909729,
+      "eval_pcc_0": -0.4949800490310783,
+      "eval_pcc_1": 0.3493241030582537,
+      "eval_pcc_2": 0.35010250059337805,
+      "eval_pcc_3": 0.29891574279163136,
+      "eval_runtime": 208.6775,
+      "eval_samples_per_second": 11.98,
+      "eval_steps_per_second": 1.5,
+      "step": 1252
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 8.402555910543132e-06,
+      "loss": 2.8072,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.4422848224639893,
+      "eval_mse_0": 1.6522321701049805,
+      "eval_mse_1": 1.2618173360824585,
+      "eval_mse_2": 1.245812177658081,
+      "eval_mse_3": 1.6092774868011475,
+      "eval_pcc_0": 0.59788592589008,
+      "eval_pcc_1": 0.6923001588397848,
+      "eval_pcc_2": 0.6849604114622538,
+      "eval_pcc_3": 0.6192939062114817,
+      "eval_runtime": 247.4382,
+      "eval_samples_per_second": 10.104,
+      "eval_steps_per_second": 1.265,
+      "step": 1565
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.224753975868225,
+      "eval_mse_0": 1.4419572353363037,
+      "eval_mse_1": 1.0168206691741943,
+      "eval_mse_2": 1.04183030128479,
+      "eval_mse_3": 1.3984031677246094,
+      "eval_pcc_0": 0.6259470612750265,
+      "eval_pcc_1": 0.7094005712093703,
+      "eval_pcc_2": 0.703077583011027,
+      "eval_pcc_3": 0.6463406612652987,
+      "eval_runtime": 312.4808,
+      "eval_samples_per_second": 8.0,
+      "eval_steps_per_second": 1.002,
+      "step": 1878
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 7.870074547390843e-06,
+      "loss": 1.1777,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.165972113609314,
+      "eval_mse_0": 1.3944885730743408,
+      "eval_mse_1": 0.953380286693573,
+      "eval_mse_2": 0.9779050946235657,
+      "eval_mse_3": 1.338115930557251,
+      "eval_pcc_0": 0.6491591245493366,
+      "eval_pcc_1": 0.7322764329054596,
+      "eval_pcc_2": 0.7251806534115378,
+      "eval_pcc_3": 0.6713901066947345,
+      "eval_runtime": 281.503,
+      "eval_samples_per_second": 8.881,
+      "eval_steps_per_second": 1.112,
+      "step": 2191
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 7.337593184238552e-06,
+      "loss": 0.8925,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.1364933252334595,
+      "eval_mse_0": 1.3813132047653198,
+      "eval_mse_1": 0.9246936440467834,
+      "eval_mse_2": 0.9472079277038574,
+      "eval_mse_3": 1.2927637100219727,
+      "eval_pcc_0": 0.6636172236793332,
+      "eval_pcc_1": 0.7442196709226827,
+      "eval_pcc_2": 0.7408310321778832,
+      "eval_pcc_3": 0.6886282304090647,
+      "eval_runtime": 335.3344,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 0.933,
+      "step": 2504
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.164945125579834,
+      "eval_mse_0": 1.3997234106063843,
+      "eval_mse_1": 0.953402042388916,
+      "eval_mse_2": 0.9617190361022949,
+      "eval_mse_3": 1.3449345827102661,
+      "eval_pcc_0": 0.6671656314385908,
+      "eval_pcc_1": 0.7473768712223382,
+      "eval_pcc_2": 0.7482860149868756,
+      "eval_pcc_3": 0.6932340357789037,
+      "eval_runtime": 209.0164,
+      "eval_samples_per_second": 11.961,
+      "eval_steps_per_second": 1.497,
+      "step": 2817
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 6.805111821086262e-06,
+      "loss": 0.7703,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.1717320680618286,
+      "eval_mse_0": 1.3993605375289917,
+      "eval_mse_1": 0.9421942234039307,
+      "eval_mse_2": 0.9832373857498169,
+      "eval_mse_3": 1.3621364831924438,
+      "eval_pcc_0": 0.6659645825368572,
+      "eval_pcc_1": 0.754070460942255,
+      "eval_pcc_2": 0.7531686782534792,
+      "eval_pcc_3": 0.6925327269309437,
+      "eval_runtime": 208.4382,
+      "eval_samples_per_second": 11.994,
+      "eval_steps_per_second": 1.502,
+      "step": 3130
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.1003177165985107,
+      "eval_mse_0": 1.3511290550231934,
+      "eval_mse_1": 0.8601426482200623,
+      "eval_mse_2": 0.9058741331100464,
+      "eval_mse_3": 1.284125566482544,
+      "eval_pcc_0": 0.6823004720905385,
+      "eval_pcc_1": 0.7679569991440994,
+      "eval_pcc_2": 0.7669256432413208,
+      "eval_pcc_3": 0.7095652856474484,
+      "eval_runtime": 208.3712,
+      "eval_samples_per_second": 11.998,
+      "eval_steps_per_second": 1.502,
+      "step": 3443
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 6.272630457933972e-06,
+      "loss": 0.7243,
+      "step": 3500
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.1556166410446167,
+      "eval_mse_0": 1.387494683265686,
+      "eval_mse_1": 0.9246439337730408,
+      "eval_mse_2": 0.9701840877532959,
+      "eval_mse_3": 1.3401434421539307,
+      "eval_pcc_0": 0.6792211345115233,
+      "eval_pcc_1": 0.7643262106960501,
+      "eval_pcc_2": 0.7648803827498597,
+      "eval_pcc_3": 0.7061351730951151,
+      "eval_runtime": 208.1568,
+      "eval_samples_per_second": 12.01,
+      "eval_steps_per_second": 1.504,
+      "step": 3756
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 5.7401490947816826e-06,
+      "loss": 0.6807,
+      "step": 4000
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.1403584480285645,
+      "eval_mse_0": 1.378049373626709,
+      "eval_mse_1": 0.9393852353096008,
+      "eval_mse_2": 0.9474803805351257,
+      "eval_mse_3": 1.2965223789215088,
+      "eval_pcc_0": 0.685714030106479,
+      "eval_pcc_1": 0.7701273842984031,
+      "eval_pcc_2": 0.7719005152839391,
+      "eval_pcc_3": 0.7132850798755096,
+      "eval_runtime": 207.7825,
+      "eval_samples_per_second": 12.032,
+      "eval_steps_per_second": 1.506,
+      "step": 4069
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.0986577272415161,
+      "eval_mse_0": 1.3405073881149292,
+      "eval_mse_1": 0.9005590081214905,
+      "eval_mse_2": 0.8833965063095093,
+      "eval_mse_3": 1.270165205001831,
+      "eval_pcc_0": 0.6908638660162009,
+      "eval_pcc_1": 0.7757356770571214,
+      "eval_pcc_2": 0.776955459294741,
+      "eval_pcc_3": 0.7183248042789347,
+      "eval_runtime": 208.4925,
+      "eval_samples_per_second": 11.991,
+      "eval_steps_per_second": 1.501,
+      "step": 4382
+    },
+    {
+      "epoch": 14.38,
+      "learning_rate": 5.207667731629393e-06,
+      "loss": 0.6508,
+      "step": 4500
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.1057186126708984,
+      "eval_mse_0": 1.34336256980896,
+      "eval_mse_1": 0.8891988396644592,
+      "eval_mse_2": 0.9110406041145325,
+      "eval_mse_3": 1.2792694568634033,
+      "eval_pcc_0": 0.6913396627789129,
+      "eval_pcc_1": 0.7777092425949328,
+      "eval_pcc_2": 0.7779608746447034,
+      "eval_pcc_3": 0.7193755872411963,
+      "eval_runtime": 208.2997,
+      "eval_samples_per_second": 12.002,
+      "eval_steps_per_second": 1.503,
+      "step": 4695
+    },
+    {
+      "epoch": 15.97,
+      "learning_rate": 4.675186368477103e-06,
+      "loss": 0.6,
+      "step": 5000
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.1194236278533936,
+      "eval_mse_0": 1.358150839805603,
+      "eval_mse_1": 0.9049779176712036,
+      "eval_mse_2": 0.9220144748687744,
+      "eval_mse_3": 1.2925522327423096,
+      "eval_pcc_0": 0.6929465023615248,
+      "eval_pcc_1": 0.7780722906636613,
+      "eval_pcc_2": 0.7788806309502682,
+      "eval_pcc_3": 0.7219376061872848,
+      "eval_runtime": 208.2861,
+      "eval_samples_per_second": 12.003,
+      "eval_steps_per_second": 1.503,
+      "step": 5008
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.1674102544784546,
+      "eval_mse_0": 1.3676834106445312,
+      "eval_mse_1": 0.9515432715415955,
+      "eval_mse_2": 1.001997709274292,
+      "eval_mse_3": 1.3484163284301758,
+      "eval_pcc_0": 0.6921208151486974,
+      "eval_pcc_1": 0.774493306623929,
+      "eval_pcc_2": 0.7760156604229923,
+      "eval_pcc_3": 0.7189250546931115,
+      "eval_runtime": 208.5477,
+      "eval_samples_per_second": 11.988,
+      "eval_steps_per_second": 1.501,
+      "step": 5321
+    },
+    {
+      "epoch": 17.57,
+      "learning_rate": 4.142705005324814e-06,
+      "loss": 0.5835,
+      "step": 5500
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.0919314622879028,
+      "eval_mse_0": 1.3341715335845947,
+      "eval_mse_1": 0.8896929621696472,
+      "eval_mse_2": 0.8880434632301331,
+      "eval_mse_3": 1.2558188438415527,
+      "eval_pcc_0": 0.6987603679056807,
+      "eval_pcc_1": 0.7801065144503536,
+      "eval_pcc_2": 0.7808335149834718,
+      "eval_pcc_3": 0.7262217024343912,
+      "eval_runtime": 208.2957,
+      "eval_samples_per_second": 12.002,
+      "eval_steps_per_second": 1.503,
+      "step": 5634
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.0437231063842773,
+      "eval_mse_0": 1.2895662784576416,
+      "eval_mse_1": 0.8252150416374207,
+      "eval_mse_2": 0.8597472906112671,
+      "eval_mse_3": 1.2003629207611084,
+      "eval_pcc_0": 0.7026890019454506,
+      "eval_pcc_1": 0.7858380303522067,
+      "eval_pcc_2": 0.7849542059443247,
+      "eval_pcc_3": 0.7294818540628083,
+      "eval_runtime": 208.5445,
+      "eval_samples_per_second": 11.988,
+      "eval_steps_per_second": 1.501,
+      "step": 5947
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 3.6102236421725247e-06,
+      "loss": 0.5678,
+      "step": 6000
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.151486873626709,
+      "eval_mse_0": 1.3805490732192993,
+      "eval_mse_1": 0.942895233631134,
+      "eval_mse_2": 0.9465405344963074,
+      "eval_mse_3": 1.335962176322937,
+      "eval_pcc_0": 0.6949788901370473,
+      "eval_pcc_1": 0.7787714451137748,
+      "eval_pcc_2": 0.779151443590144,
+      "eval_pcc_3": 0.7215692214830622,
+      "eval_runtime": 208.439,
+      "eval_samples_per_second": 11.994,
+      "eval_steps_per_second": 1.502,
+      "step": 6260
+    },
+    {
+      "epoch": 20.77,
+      "learning_rate": 3.0777422790202343e-06,
+      "loss": 0.551,
+      "step": 6500
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.1019189357757568,
+      "eval_mse_0": 1.346902847290039,
+      "eval_mse_1": 0.8688396215438843,
+      "eval_mse_2": 0.9042496085166931,
+      "eval_mse_3": 1.287683129310608,
+      "eval_pcc_0": 0.7002976367992624,
+      "eval_pcc_1": 0.783528380766365,
+      "eval_pcc_2": 0.782716721891549,
+      "eval_pcc_3": 0.7265399783436903,
+      "eval_runtime": 208.5079,
+      "eval_samples_per_second": 11.99,
+      "eval_steps_per_second": 1.501,
+      "step": 6573
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.0888938903808594,
+      "eval_mse_0": 1.3434523344039917,
+      "eval_mse_1": 0.8522993922233582,
+      "eval_mse_2": 0.8866416811943054,
+      "eval_mse_3": 1.2731798887252808,
+      "eval_pcc_0": 0.7000358310205116,
+      "eval_pcc_1": 0.7840908362437411,
+      "eval_pcc_2": 0.7834154168240878,
+      "eval_pcc_3": 0.7263780561838219,
+      "eval_runtime": 208.6613,
+      "eval_samples_per_second": 11.981,
+      "eval_steps_per_second": 1.5,
+      "step": 6886
+    },
+    {
+      "epoch": 22.36,
+      "learning_rate": 2.5452609158679447e-06,
+      "loss": 0.5244,
+      "step": 7000
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.1030689477920532,
+      "eval_mse_0": 1.3297648429870605,
+      "eval_mse_1": 0.8905456066131592,
+      "eval_mse_2": 0.9094634652137756,
+      "eval_mse_3": 1.2824994325637817,
+      "eval_pcc_0": 0.6998152391302843,
+      "eval_pcc_1": 0.7819756526305894,
+      "eval_pcc_2": 0.7809308141655372,
+      "eval_pcc_3": 0.724755824960029,
+      "eval_runtime": 208.5735,
+      "eval_samples_per_second": 11.986,
+      "eval_steps_per_second": 1.501,
+      "step": 7199
+    },
+    {
+      "epoch": 23.96,
+      "learning_rate": 2.012779552715655e-06,
+      "loss": 0.5321,
+      "step": 7500
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.1527204513549805,
+      "eval_mse_0": 1.3845329284667969,
+      "eval_mse_1": 0.934273362159729,
+      "eval_mse_2": 0.9591948390007019,
+      "eval_mse_3": 1.3328787088394165,
+      "eval_pcc_0": 0.6979501633023902,
+      "eval_pcc_1": 0.7834698162108159,
+      "eval_pcc_2": 0.7822578881059007,
+      "eval_pcc_3": 0.7238119257524374,
+      "eval_runtime": 208.5469,
+      "eval_samples_per_second": 11.988,
+      "eval_steps_per_second": 1.501,
+      "step": 7512
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.1493885517120361,
+      "eval_mse_0": 1.3841156959533691,
+      "eval_mse_1": 0.934059202671051,
+      "eval_mse_2": 0.9498694539070129,
+      "eval_mse_3": 1.3295068740844727,
+      "eval_pcc_0": 0.6983873223409067,
+      "eval_pcc_1": 0.7833872899779326,
+      "eval_pcc_2": 0.7823576683287323,
+      "eval_pcc_3": 0.7248192689633275,
+      "eval_runtime": 208.1072,
+      "eval_samples_per_second": 12.013,
+      "eval_steps_per_second": 1.504,
+      "step": 7825
+    },
+    {
+      "epoch": 25.56,
+      "learning_rate": 1.4802981895633654e-06,
+      "loss": 0.519,
+      "step": 8000
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 1.067149043083191,
+      "eval_mse_0": 1.315177321434021,
+      "eval_mse_1": 0.8451446294784546,
+      "eval_mse_2": 0.8623626828193665,
+      "eval_mse_3": 1.2459105253219604,
+      "eval_pcc_0": 0.7035180075293521,
+      "eval_pcc_1": 0.7866524412630329,
+      "eval_pcc_2": 0.7847478629923984,
+      "eval_pcc_3": 0.7294163208957346,
+      "eval_runtime": 209.3532,
+      "eval_samples_per_second": 11.942,
+      "eval_steps_per_second": 1.495,
+      "step": 8138
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 1.0915998220443726,
+      "eval_mse_0": 1.3283545970916748,
+      "eval_mse_1": 0.8693767786026001,
+      "eval_mse_2": 0.9016813635826111,
+      "eval_mse_3": 1.2669856548309326,
+      "eval_pcc_0": 0.7022674537199173,
+      "eval_pcc_1": 0.7867839427113587,
+      "eval_pcc_2": 0.7844608088168187,
+      "eval_pcc_3": 0.7281022613065216,
+      "eval_runtime": 208.5429,
+      "eval_samples_per_second": 11.988,
+      "eval_steps_per_second": 1.501,
+      "step": 8451
+    },
+    {
+      "epoch": 27.16,
+      "learning_rate": 9.478168264110757e-07,
+      "loss": 0.4895,
+      "step": 8500
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 1.0791786909103394,
+      "eval_mse_0": 1.3170232772827148,
+      "eval_mse_1": 0.8616071343421936,
+      "eval_mse_2": 0.8834137916564941,
+      "eval_mse_3": 1.2546700239181519,
+      "eval_pcc_0": 0.7030177964730663,
+      "eval_pcc_1": 0.7864131651978098,
+      "eval_pcc_2": 0.7841052712648172,
+      "eval_pcc_3": 0.7286159637386279,
+      "eval_runtime": 208.1678,
+      "eval_samples_per_second": 12.01,
+      "eval_steps_per_second": 1.504,
+      "step": 8764
+    },
+    {
+      "epoch": 28.75,
+      "learning_rate": 4.1533546325878595e-07,
+      "loss": 0.4848,
+      "step": 9000
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 1.1225056648254395,
+      "eval_mse_0": 1.3506780862808228,
+      "eval_mse_1": 0.9083937406539917,
+      "eval_mse_2": 0.9317901134490967,
+      "eval_mse_3": 1.2991586923599243,
+      "eval_pcc_0": 0.7005837490734602,
+      "eval_pcc_1": 0.7848103246399212,
+      "eval_pcc_2": 0.7829128909102594,
+      "eval_pcc_3": 0.7262707267405379,
+      "eval_runtime": 208.0129,
+      "eval_samples_per_second": 12.018,
+      "eval_steps_per_second": 1.505,
+      "step": 9077
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 1.0948735475540161,
+      "eval_mse_0": 1.3283392190933228,
+      "eval_mse_1": 0.8795621991157532,
+      "eval_mse_2": 0.9013708829879761,
+      "eval_mse_3": 1.2702199220657349,
+      "eval_pcc_0": 0.7021826040010801,
+      "eval_pcc_1": 0.7854537370686618,
+      "eval_pcc_2": 0.7833671948442064,
+      "eval_pcc_3": 0.7276810306429349,
+      "eval_runtime": 208.2849,
+      "eval_samples_per_second": 12.003,
+      "eval_steps_per_second": 1.503,
+      "step": 9390
+    },
+    {
+      "epoch": 30.0,
+      "step": 9390,
+      "total_flos": 0.0,
+      "train_loss": 2.4084234739390933,
+      "train_runtime": 21831.2419,
+      "train_samples_per_second": 3.435,
+      "train_steps_per_second": 0.43
+    }
+  ],
+  "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/freeze/08_hubert-xlarge-ll60k/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42067bac11d5df40b14edce863fd47290973f481e73a4e94a54cbd923c21c5a
+size 4856