Upload folder using huggingface_hub (#15)

- Upload folder using huggingface_hub (0cea313fb704d39a3415039c9a36924c5904a107)

hubert/general/06_hubert-large-ll60k/all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.2733672857284546,
+    "eval_mse_0": 1.4760698080062866,
+    "eval_mse_1": 1.0627834796905518,
+    "eval_mse_2": 1.1057844161987305,
+    "eval_mse_3": 1.4488344192504883,
+    "eval_pcc_0": 0.6199948029869515,
+    "eval_pcc_1": 0.6915483694344182,
+    "eval_pcc_2": 0.6834053326494252,
+    "eval_pcc_3": 0.6329598099212757,
+    "eval_runtime": 102.7724,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 24.326,
+    "eval_steps_per_second": 3.046,
+    "train_loss": 3.272454752734167,
+    "train_runtime": 9378.2152,
+    "train_samples": 2500,
+    "train_samples_per_second": 7.997,
+    "train_steps_per_second": 1.001
+}

hubert/general/06_hubert-large-ll60k/args.json

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

hubert/general/06_hubert-large-ll60k/eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.2733672857284546,
+    "eval_mse_0": 1.4760698080062866,
+    "eval_mse_1": 1.0627834796905518,
+    "eval_mse_2": 1.1057844161987305,
+    "eval_mse_3": 1.4488344192504883,
+    "eval_pcc_0": 0.6199948029869515,
+    "eval_pcc_1": 0.6915483694344182,
+    "eval_pcc_2": 0.6834053326494252,
+    "eval_pcc_3": 0.6329598099212757,
+    "eval_runtime": 102.7724,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 24.326,
+    "eval_steps_per_second": 3.046
+}

hubert/general/06_hubert-large-ll60k/finetuned_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab2e7c25d44e4ebbc3cca64b9a2eee0996a95909f3b5cb119bd71efd7197b78
+size 1261942498

hubert/general/06_hubert-large-ll60k/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46dd4736f7ea3448aae881a9bb163f387cdec38317e80a75994bcee5455df28
+size 1261822608

hubert/general/06_hubert-large-ll60k/model_weights.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b6afbc05475eb63e463c3a0e4c78374de5b9a543967f9521cf611cd76ddca8
+size 1261938154

hubert/general/06_hubert-large-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/06_hubert-large-ll60k/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "train_loss": 3.272454752734167,
+    "train_runtime": 9378.2152,
+    "train_samples": 2500,
+    "train_samples_per_second": 7.997,
+    "train_steps_per_second": 1.001
+}

hubert/general/06_hubert-large-ll60k/trainer_args.json

@@ -0,0 +1 @@
+{"output_dir": "./model_saved/facebook/hubert-large-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": "./model_saved/logs/facebook/hubert-large-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": "./model_saved/facebook/hubert-large-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/06_hubert-large-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": 21.016597747802734,
+      "eval_mse_0": 20.95767593383789,
+      "eval_mse_1": 22.38915252685547,
+      "eval_mse_2": 21.25518798828125,
+      "eval_mse_3": 19.464326858520508,
+      "eval_pcc_0": 0.4519826553496678,
+      "eval_pcc_1": 0.15608438667284,
+      "eval_pcc_2": -0.20855669002324612,
+      "eval_pcc_3": 0.010228279983547797,
+      "eval_runtime": 141.8283,
+      "eval_samples_per_second": 17.627,
+      "eval_steps_per_second": 2.207,
+      "step": 313
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.467518636847711e-06,
+      "loss": 29.0553,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 13.291801452636719,
+      "eval_mse_0": 13.294625282287598,
+      "eval_mse_1": 14.258051872253418,
+      "eval_mse_2": 13.27319049835205,
+      "eval_mse_3": 12.341375350952148,
+      "eval_pcc_0": 0.39875637956212395,
+      "eval_pcc_1": 0.41780231608862517,
+      "eval_pcc_2": -0.3849514339422125,
+      "eval_pcc_3": -0.022266931875406612,
+      "eval_runtime": 103.7063,
+      "eval_samples_per_second": 24.107,
+      "eval_steps_per_second": 3.018,
+      "step": 626
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 7.75575065612793,
+      "eval_mse_0": 7.584864616394043,
+      "eval_mse_1": 8.541671752929688,
+      "eval_mse_2": 7.75163459777832,
+      "eval_mse_3": 7.144848346710205,
+      "eval_pcc_0": 0.43030645192754613,
+      "eval_pcc_1": 0.41587640970896206,
+      "eval_pcc_2": -0.4837044970042333,
+      "eval_pcc_3": 0.029984099998568783,
+      "eval_runtime": 103.7069,
+      "eval_samples_per_second": 24.106,
+      "eval_steps_per_second": 3.018,
+      "step": 939
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.935037273695422e-06,
+      "loss": 11.5539,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 4.125542163848877,
+      "eval_mse_0": 4.266629219055176,
+      "eval_mse_1": 4.310248374938965,
+      "eval_mse_2": 3.875537395477295,
+      "eval_mse_3": 4.049736022949219,
+      "eval_pcc_0": 0.4566269352728974,
+      "eval_pcc_1": 0.05118764580742642,
+      "eval_pcc_2": -0.5701398418016826,
+      "eval_pcc_3": 0.37549506777775443,
+      "eval_runtime": 103.5867,
+      "eval_samples_per_second": 24.134,
+      "eval_steps_per_second": 3.022,
+      "step": 1252
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 8.402555910543132e-06,
+      "loss": 4.7388,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.5191287994384766,
+      "eval_mse_0": 2.66662335395813,
+      "eval_mse_1": 2.3949482440948486,
+      "eval_mse_2": 2.3714287281036377,
+      "eval_mse_3": 2.6435108184814453,
+      "eval_pcc_0": 0.29849261773097063,
+      "eval_pcc_1": -0.42243863710867685,
+      "eval_pcc_2": -0.4337840641375614,
+      "eval_pcc_3": 0.3226227406491439,
+      "eval_runtime": 103.6532,
+      "eval_samples_per_second": 24.119,
+      "eval_steps_per_second": 3.02,
+      "step": 1565
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.6782524585723877,
+      "eval_mse_0": 2.8961381912231445,
+      "eval_mse_1": 2.534928560256958,
+      "eval_mse_2": 2.424395799636841,
+      "eval_mse_3": 2.8575472831726074,
+      "eval_pcc_0": 0.3285565993948873,
+      "eval_pcc_1": 0.41879754622501647,
+      "eval_pcc_2": 0.3951385484095019,
+      "eval_pcc_3": 0.3435233810214959,
+      "eval_runtime": 103.7909,
+      "eval_samples_per_second": 24.087,
+      "eval_steps_per_second": 3.016,
+      "step": 1878
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 7.870074547390843e-06,
+      "loss": 2.416,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.603594422340393,
+      "eval_mse_0": 1.7275574207305908,
+      "eval_mse_1": 1.5131033658981323,
+      "eval_mse_2": 1.4804449081420898,
+      "eval_mse_3": 1.6932716369628906,
+      "eval_pcc_0": 0.5804141219653273,
+      "eval_pcc_1": 0.6143931882677098,
+      "eval_pcc_2": 0.5971921659802566,
+      "eval_pcc_3": 0.5896122308386182,
+      "eval_runtime": 103.7994,
+      "eval_samples_per_second": 24.085,
+      "eval_steps_per_second": 3.015,
+      "step": 2191
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 7.337593184238552e-06,
+      "loss": 1.5666,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.5601857900619507,
+      "eval_mse_0": 1.691264033317566,
+      "eval_mse_1": 1.4080955982208252,
+      "eval_mse_2": 1.4401195049285889,
+      "eval_mse_3": 1.7012628316879272,
+      "eval_pcc_0": 0.5370806880189257,
+      "eval_pcc_1": 0.564036418958649,
+      "eval_pcc_2": 0.5505712885553037,
+      "eval_pcc_3": 0.5408123479178698,
+      "eval_runtime": 103.9415,
+      "eval_samples_per_second": 24.052,
+      "eval_steps_per_second": 3.011,
+      "step": 2504
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.5477173328399658,
+      "eval_mse_0": 1.6471492052078247,
+      "eval_mse_1": 1.4317377805709839,
+      "eval_mse_2": 1.4445171356201172,
+      "eval_mse_3": 1.6674691438674927,
+      "eval_pcc_0": 0.568005981007569,
+      "eval_pcc_1": 0.5729933804843009,
+      "eval_pcc_2": 0.5616983509306596,
+      "eval_pcc_3": 0.5705892294383248,
+      "eval_runtime": 103.7622,
+      "eval_samples_per_second": 24.094,
+      "eval_steps_per_second": 3.017,
+      "step": 2817
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 6.805111821086262e-06,
+      "loss": 1.2844,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.5216816663742065,
+      "eval_mse_0": 1.6385308504104614,
+      "eval_mse_1": 1.383074402809143,
+      "eval_mse_2": 1.4118603467941284,
+      "eval_mse_3": 1.653259515762329,
+      "eval_pcc_0": 0.5788210473071668,
+      "eval_pcc_1": 0.5911625350747768,
+      "eval_pcc_2": 0.5777656765075281,
+      "eval_pcc_3": 0.580935732808973,
+      "eval_runtime": 104.3178,
+      "eval_samples_per_second": 23.965,
+      "eval_steps_per_second": 3.0,
+      "step": 3130
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.4696030616760254,
+      "eval_mse_0": 1.6351954936981201,
+      "eval_mse_1": 1.287829041481018,
+      "eval_mse_2": 1.31747305393219,
+      "eval_mse_3": 1.6379148960113525,
+      "eval_pcc_0": 0.6045656325194463,
+      "eval_pcc_1": 0.6463932075609694,
+      "eval_pcc_2": 0.6277553640880934,
+      "eval_pcc_3": 0.6119131861742635,
+      "eval_runtime": 104.4337,
+      "eval_samples_per_second": 23.939,
+      "eval_steps_per_second": 2.997,
+      "step": 3443
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 6.272630457933972e-06,
+      "loss": 1.0497,
+      "step": 3500
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.3319154977798462,
+      "eval_mse_0": 1.5184181928634644,
+      "eval_mse_1": 1.1186933517456055,
+      "eval_mse_2": 1.1844432353973389,
+      "eval_mse_3": 1.5061111450195312,
+      "eval_pcc_0": 0.6074663091481849,
+      "eval_pcc_1": 0.6713691464026713,
+      "eval_pcc_2": 0.6534366547387829,
+      "eval_pcc_3": 0.6174073865634576,
+      "eval_runtime": 104.5768,
+      "eval_samples_per_second": 23.906,
+      "eval_steps_per_second": 2.993,
+      "step": 3756
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 5.7401490947816826e-06,
+      "loss": 1.0191,
+      "step": 4000
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.3655729293823242,
+      "eval_mse_0": 1.6080780029296875,
+      "eval_mse_1": 1.1169698238372803,
+      "eval_mse_2": 1.1537631750106812,
+      "eval_mse_3": 1.583478569984436,
+      "eval_pcc_0": 0.5952489411006241,
+      "eval_pcc_1": 0.6885571014024544,
+      "eval_pcc_2": 0.6685776971756485,
+      "eval_pcc_3": 0.6096848417236609,
+      "eval_runtime": 104.1415,
+      "eval_samples_per_second": 24.006,
+      "eval_steps_per_second": 3.006,
+      "step": 4069
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.260452151298523,
+      "eval_mse_0": 1.4540808200836182,
+      "eval_mse_1": 1.0452821254730225,
+      "eval_mse_2": 1.087522029876709,
+      "eval_mse_3": 1.4549213647842407,
+      "eval_pcc_0": 0.6286949228450185,
+      "eval_pcc_1": 0.7124926965466419,
+      "eval_pcc_2": 0.6940816741565711,
+      "eval_pcc_3": 0.6411306958097317,
+      "eval_runtime": 103.7032,
+      "eval_samples_per_second": 24.107,
+      "eval_steps_per_second": 3.018,
+      "step": 4382
+    },
+    {
+      "epoch": 14.38,
+      "learning_rate": 5.207667731629393e-06,
+      "loss": 0.9526,
+      "step": 4500
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.3316799402236938,
+      "eval_mse_0": 1.508797526359558,
+      "eval_mse_1": 1.1205905675888062,
+      "eval_mse_2": 1.1920998096466064,
+      "eval_mse_3": 1.505226731300354,
+      "eval_pcc_0": 0.6183428795961865,
+      "eval_pcc_1": 0.6735063092888841,
+      "eval_pcc_2": 0.65595079037976,
+      "eval_pcc_3": 0.6265726288914425,
+      "eval_runtime": 103.0463,
+      "eval_samples_per_second": 24.261,
+      "eval_steps_per_second": 3.037,
+      "step": 4695
+    },
+    {
+      "epoch": 15.97,
+      "learning_rate": 4.675186368477103e-06,
+      "loss": 0.9034,
+      "step": 5000
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.340736746788025,
+      "eval_mse_0": 1.5332651138305664,
+      "eval_mse_1": 1.1219561100006104,
+      "eval_mse_2": 1.1931809186935425,
+      "eval_mse_3": 1.514542818069458,
+      "eval_pcc_0": 0.602791060273745,
+      "eval_pcc_1": 0.6819348886047203,
+      "eval_pcc_2": 0.664361051306895,
+      "eval_pcc_3": 0.6144448247521468,
+      "eval_runtime": 102.3217,
+      "eval_samples_per_second": 24.433,
+      "eval_steps_per_second": 3.059,
+      "step": 5008
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.3361705541610718,
+      "eval_mse_0": 1.5136650800704956,
+      "eval_mse_1": 1.1383566856384277,
+      "eval_mse_2": 1.1637253761291504,
+      "eval_mse_3": 1.528939962387085,
+      "eval_pcc_0": 0.6211469696106267,
+      "eval_pcc_1": 0.6958871383355408,
+      "eval_pcc_2": 0.681749540737601,
+      "eval_pcc_3": 0.6331775276510975,
+      "eval_runtime": 102.4872,
+      "eval_samples_per_second": 24.393,
+      "eval_steps_per_second": 3.054,
+      "step": 5321
+    },
+    {
+      "epoch": 17.57,
+      "learning_rate": 4.142705005324814e-06,
+      "loss": 0.8645,
+      "step": 5500
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.2796813249588013,
+      "eval_mse_0": 1.4679397344589233,
+      "eval_mse_1": 1.0760267972946167,
+      "eval_mse_2": 1.121977686882019,
+      "eval_mse_3": 1.4527777433395386,
+      "eval_pcc_0": 0.6164567503347664,
+      "eval_pcc_1": 0.6924855888134458,
+      "eval_pcc_2": 0.6808692829780811,
+      "eval_pcc_3": 0.6285140350502874,
+      "eval_runtime": 102.7808,
+      "eval_samples_per_second": 24.324,
+      "eval_steps_per_second": 3.045,
+      "step": 5634
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.2729549407958984,
+      "eval_mse_0": 1.4689959287643433,
+      "eval_mse_1": 1.0598036050796509,
+      "eval_mse_2": 1.1233123540878296,
+      "eval_mse_3": 1.439705491065979,
+      "eval_pcc_0": 0.6263942044858991,
+      "eval_pcc_1": 0.703291827924832,
+      "eval_pcc_2": 0.6923721581311856,
+      "eval_pcc_3": 0.6406621296130252,
+      "eval_runtime": 103.2917,
+      "eval_samples_per_second": 24.203,
+      "eval_steps_per_second": 3.03,
+      "step": 5947
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 3.6102236421725247e-06,
+      "loss": 0.8423,
+      "step": 6000
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.2558881044387817,
+      "eval_mse_0": 1.4468300342559814,
+      "eval_mse_1": 1.0544439554214478,
+      "eval_mse_2": 1.0984488725662231,
+      "eval_mse_3": 1.4238260984420776,
+      "eval_pcc_0": 0.6260368750538718,
+      "eval_pcc_1": 0.6941454609202982,
+      "eval_pcc_2": 0.6832386209111154,
+      "eval_pcc_3": 0.6390511322741602,
+      "eval_runtime": 102.336,
+      "eval_samples_per_second": 24.429,
+      "eval_steps_per_second": 3.059,
+      "step": 6260
+    },
+    {
+      "epoch": 20.77,
+      "learning_rate": 3.0777422790202343e-06,
+      "loss": 0.7982,
+      "step": 6500
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.293521523475647,
+      "eval_mse_0": 1.4905046224594116,
+      "eval_mse_1": 1.0818946361541748,
+      "eval_mse_2": 1.123294472694397,
+      "eval_mse_3": 1.4783953428268433,
+      "eval_pcc_0": 0.6104622574042475,
+      "eval_pcc_1": 0.6842898231587979,
+      "eval_pcc_2": 0.6738936382891787,
+      "eval_pcc_3": 0.6223893078833137,
+      "eval_runtime": 102.5326,
+      "eval_samples_per_second": 24.382,
+      "eval_steps_per_second": 3.053,
+      "step": 6573
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.2579796314239502,
+      "eval_mse_0": 1.4315956830978394,
+      "eval_mse_1": 1.0721993446350098,
+      "eval_mse_2": 1.1054877042770386,
+      "eval_mse_3": 1.4226363897323608,
+      "eval_pcc_0": 0.6295137320075705,
+      "eval_pcc_1": 0.6938368027528539,
+      "eval_pcc_2": 0.683613786463381,
+      "eval_pcc_3": 0.6409943665072807,
+      "eval_runtime": 102.6632,
+      "eval_samples_per_second": 24.351,
+      "eval_steps_per_second": 3.049,
+      "step": 6886
+    },
+    {
+      "epoch": 22.36,
+      "learning_rate": 2.5452609158679447e-06,
+      "loss": 0.8021,
+      "step": 7000
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.275226354598999,
+      "eval_mse_0": 1.469885230064392,
+      "eval_mse_1": 1.0683677196502686,
+      "eval_mse_2": 1.1231023073196411,
+      "eval_mse_3": 1.439548134803772,
+      "eval_pcc_0": 0.6249204760539863,
+      "eval_pcc_1": 0.6982666373837786,
+      "eval_pcc_2": 0.6875090710115079,
+      "eval_pcc_3": 0.6374097405449456,
+      "eval_runtime": 102.9313,
+      "eval_samples_per_second": 24.288,
+      "eval_steps_per_second": 3.041,
+      "step": 7199
+    },
+    {
+      "epoch": 23.96,
+      "learning_rate": 2.012779552715655e-06,
+      "loss": 0.7845,
+      "step": 7500
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.289107084274292,
+      "eval_mse_0": 1.493590235710144,
+      "eval_mse_1": 1.076009750366211,
+      "eval_mse_2": 1.1205601692199707,
+      "eval_mse_3": 1.4662672281265259,
+      "eval_pcc_0": 0.613460936189163,
+      "eval_pcc_1": 0.6892199962030554,
+      "eval_pcc_2": 0.6806154642892492,
+      "eval_pcc_3": 0.6266502268706277,
+      "eval_runtime": 102.3891,
+      "eval_samples_per_second": 24.417,
+      "eval_steps_per_second": 3.057,
+      "step": 7512
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.2871264219284058,
+      "eval_mse_0": 1.4900933504104614,
+      "eval_mse_1": 1.0732802152633667,
+      "eval_mse_2": 1.1162198781967163,
+      "eval_mse_3": 1.4689126014709473,
+      "eval_pcc_0": 0.618061881247116,
+      "eval_pcc_1": 0.6871997020513806,
+      "eval_pcc_2": 0.6762607676227085,
+      "eval_pcc_3": 0.6302099063474356,
+      "eval_runtime": 103.0877,
+      "eval_samples_per_second": 24.251,
+      "eval_steps_per_second": 3.036,
+      "step": 7825
+    },
+    {
+      "epoch": 25.56,
+      "learning_rate": 1.4802981895633654e-06,
+      "loss": 0.7706,
+      "step": 8000
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 1.2603259086608887,
+      "eval_mse_0": 1.4595274925231934,
+      "eval_mse_1": 1.0522445440292358,
+      "eval_mse_2": 1.0920735597610474,
+      "eval_mse_3": 1.437459111213684,
+      "eval_pcc_0": 0.6219460875597032,
+      "eval_pcc_1": 0.6951302733827012,
+      "eval_pcc_2": 0.6861533215189392,
+      "eval_pcc_3": 0.6350624144867718,
+      "eval_runtime": 102.5804,
+      "eval_samples_per_second": 24.371,
+      "eval_steps_per_second": 3.051,
+      "step": 8138
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 1.2673265933990479,
+      "eval_mse_0": 1.4700430631637573,
+      "eval_mse_1": 1.0576117038726807,
+      "eval_mse_2": 1.0929465293884277,
+      "eval_mse_3": 1.4487053155899048,
+      "eval_pcc_0": 0.6220730155566848,
+      "eval_pcc_1": 0.6927627478516807,
+      "eval_pcc_2": 0.6841127452930019,
+      "eval_pcc_3": 0.6350509882760662,
+      "eval_runtime": 102.816,
+      "eval_samples_per_second": 24.315,
+      "eval_steps_per_second": 3.044,
+      "step": 8451
+    },
+    {
+      "epoch": 27.16,
+      "learning_rate": 9.478168264110757e-07,
+      "loss": 0.7402,
+      "step": 8500
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 1.2866432666778564,
+      "eval_mse_0": 1.4958163499832153,
+      "eval_mse_1": 1.069581151008606,
+      "eval_mse_2": 1.1153037548065186,
+      "eval_mse_3": 1.465869665145874,
+      "eval_pcc_0": 0.6168214026508431,
+      "eval_pcc_1": 0.6899367002199654,
+      "eval_pcc_2": 0.6817141856767752,
+      "eval_pcc_3": 0.6300330091231447,
+      "eval_runtime": 102.5731,
+      "eval_samples_per_second": 24.373,
+      "eval_steps_per_second": 3.051,
+      "step": 8764
+    },
+    {
+      "epoch": 28.75,
+      "learning_rate": 4.1533546325878595e-07,
+      "loss": 0.7432,
+      "step": 9000
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 1.2702583074569702,
+      "eval_mse_0": 1.471681833267212,
+      "eval_mse_1": 1.0614519119262695,
+      "eval_mse_2": 1.1038634777069092,
+      "eval_mse_3": 1.4440354108810425,
+      "eval_pcc_0": 0.6206342389252424,
+      "eval_pcc_1": 0.6924304579631482,
+      "eval_pcc_2": 0.6844938360771988,
+      "eval_pcc_3": 0.6336591899142138,
+      "eval_runtime": 102.3309,
+      "eval_samples_per_second": 24.431,
+      "eval_steps_per_second": 3.059,
+      "step": 9077
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 1.2733672857284546,
+      "eval_mse_0": 1.4760698080062866,
+      "eval_mse_1": 1.0627834796905518,
+      "eval_mse_2": 1.1057844161987305,
+      "eval_mse_3": 1.4488344192504883,
+      "eval_pcc_0": 0.6199948029869515,
+      "eval_pcc_1": 0.6915483694344182,
+      "eval_pcc_2": 0.6834053326494252,
+      "eval_pcc_3": 0.6329598099212757,
+      "eval_runtime": 103.1151,
+      "eval_samples_per_second": 24.245,
+      "eval_steps_per_second": 3.035,
+      "step": 9390
+    },
+    {
+      "epoch": 30.0,
+      "step": 9390,
+      "total_flos": 0.0,
+      "train_loss": 3.272454752734167,
+      "train_runtime": 9378.2152,
+      "train_samples_per_second": 7.997,
+      "train_steps_per_second": 1.001
+    }
+  ],
+  "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/06_hubert-large-ll60k/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8304c596aac1283ba6e3c8e516d401fbc1dfff91a394449519319f51062b79d
+size 4792