Upload folder using huggingface_hub

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

@@ -0,0 +1,21 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.2990093231201172,
+    "eval_mse_0": 1.5060529708862305,
+    "eval_mse_1": 1.099517822265625,
+    "eval_mse_2": 1.133305311203003,
+    "eval_mse_3": 1.4571605920791626,
+    "eval_pcc_0": 0.6162701381731509,
+    "eval_pcc_1": 0.6867923339565917,
+    "eval_pcc_2": 0.6805020447302117,
+    "eval_pcc_3": 0.6327768215304354,
+    "eval_runtime": 104.4503,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 23.935,
+    "eval_steps_per_second": 2.997,
+    "train_loss": 3.191356456622529,
+    "train_runtime": 9611.9679,
+    "train_samples": 2500,
+    "train_samples_per_second": 7.803,
+    "train_steps_per_second": 0.977
+}

hubert/ctc/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": "./ctc/model_saved",
+    "freeze_feature_extractor": false,
+    "exp_name": "facebook/hubert-large-ll60k_lr1e-05_epochs30_batch4",
+    "save_dir_path": "./ctc/model_saved/facebook/hubert-large-ll60k_lr1e-05_epochs30_batch4",
+    "save_log_path": "./ctc/model_saved/logs/facebook/hubert-large-ll60k_lr1e-05_epochs30_batch4"
+}

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

@@ -0,0 +1,16 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.2990093231201172,
+    "eval_mse_0": 1.5060529708862305,
+    "eval_mse_1": 1.099517822265625,
+    "eval_mse_2": 1.133305311203003,
+    "eval_mse_3": 1.4571605920791626,
+    "eval_pcc_0": 0.6162701381731509,
+    "eval_pcc_1": 0.6867923339565917,
+    "eval_pcc_2": 0.6805020447302117,
+    "eval_pcc_3": 0.6327768215304354,
+    "eval_runtime": 104.4503,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 23.935,
+    "eval_steps_per_second": 2.997
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc574ac46b48e42b987720324c80c9bdc6cd6c7fbe26af6afe0c1b49c3ebb87
+size 1262064318

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17b8f386e72f7ce427ec4089f5cc1ae3d8cb519de2db89885bd907c62e4ddd2
+size 1261941072

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6ae3ef47f80dd9c84361ab7784984b1b5ff951c8d3d4260443d3fdfb6f9a17
+size 1262059954

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

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "train_loss": 3.191356456622529,
+    "train_runtime": 9611.9679,
+    "train_samples": 2500,
+    "train_samples_per_second": 7.803,
+    "train_steps_per_second": 0.977
+}

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

@@ -0,0 +1 @@
+{"output_dir": "./ctc/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": "./ctc/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": "./ctc/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/ctc/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": 24.979978561401367,
+      "eval_mse_0": 28.16019630432129,
+      "eval_mse_1": 31.803714752197266,
+      "eval_mse_2": 18.175222396850586,
+      "eval_mse_3": 21.780847549438477,
+      "eval_pcc_0": 0.08447442520034334,
+      "eval_pcc_1": -0.434424108863052,
+      "eval_pcc_2": 0.44286241004363835,
+      "eval_pcc_3": -0.04614851692663958,
+      "eval_runtime": 104.4241,
+      "eval_samples_per_second": 23.941,
+      "eval_steps_per_second": 2.997,
+      "step": 313
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.467518636847711e-06,
+      "loss": 32.114,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 13.006314277648926,
+      "eval_mse_0": 16.635089874267578,
+      "eval_mse_1": 17.904869079589844,
+      "eval_mse_2": 6.9167866706848145,
+      "eval_mse_3": 10.5684814453125,
+      "eval_pcc_0": 0.1459064690559934,
+      "eval_pcc_1": -0.2951093517142375,
+      "eval_pcc_2": 0.6024194426686006,
+      "eval_pcc_3": -0.16492245226217225,
+      "eval_runtime": 104.0768,
+      "eval_samples_per_second": 24.021,
+      "eval_steps_per_second": 3.007,
+      "step": 626
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.625720500946045,
+      "eval_mse_0": 7.457537651062012,
+      "eval_mse_1": 7.611800670623779,
+      "eval_mse_2": 2.929844617843628,
+      "eval_mse_3": 4.503726005554199,
+      "eval_pcc_0": 0.24351828261383707,
+      "eval_pcc_1": -0.3417122879288906,
+      "eval_pcc_2": 0.6282428553385933,
+      "eval_pcc_3": 0.107819654142747,
+      "eval_runtime": 104.2212,
+      "eval_samples_per_second": 23.987,
+      "eval_steps_per_second": 3.003,
+      "step": 939
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.935037273695422e-06,
+      "loss": 10.5591,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.562793016433716,
+      "eval_mse_0": 2.9483797550201416,
+      "eval_mse_1": 2.5424118041992188,
+      "eval_mse_2": 2.1228203773498535,
+      "eval_mse_3": 2.6375598907470703,
+      "eval_pcc_0": 0.23478812321205403,
+      "eval_pcc_1": 0.3151159129828575,
+      "eval_pcc_2": 0.2889779759041432,
+      "eval_pcc_3": 0.2387598354918888,
+      "eval_runtime": 119.6429,
+      "eval_samples_per_second": 20.896,
+      "eval_steps_per_second": 2.616,
+      "step": 1252
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 8.402555910543132e-06,
+      "loss": 3.1448,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.790495753288269,
+      "eval_mse_0": 2.167940139770508,
+      "eval_mse_1": 1.720595121383667,
+      "eval_mse_2": 1.369637370109558,
+      "eval_mse_3": 1.9038156270980835,
+      "eval_pcc_0": 0.5420294328995108,
+      "eval_pcc_1": 0.6438103301855875,
+      "eval_pcc_2": 0.6237525402787583,
+      "eval_pcc_3": 0.5619630452770021,
+      "eval_runtime": 105.0116,
+      "eval_samples_per_second": 23.807,
+      "eval_steps_per_second": 2.981,
+      "step": 1565
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.5345312356948853,
+      "eval_mse_0": 1.6931366920471191,
+      "eval_mse_1": 1.374876618385315,
+      "eval_mse_2": 1.4084863662719727,
+      "eval_mse_3": 1.661619782447815,
+      "eval_pcc_0": 0.5434052341521307,
+      "eval_pcc_1": 0.5825963389942408,
+      "eval_pcc_2": 0.5778560094270981,
+      "eval_pcc_3": 0.5567450706138993,
+      "eval_runtime": 104.605,
+      "eval_samples_per_second": 23.899,
+      "eval_steps_per_second": 2.992,
+      "step": 1878
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 7.870074547390843e-06,
+      "loss": 1.6744,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.56795334815979,
+      "eval_mse_0": 1.691694736480713,
+      "eval_mse_1": 1.4296774864196777,
+      "eval_mse_2": 1.471792459487915,
+      "eval_mse_3": 1.678649663925171,
+      "eval_pcc_0": 0.5732697245477388,
+      "eval_pcc_1": 0.5988806483930382,
+      "eval_pcc_2": 0.5915888955876768,
+      "eval_pcc_3": 0.5849529876446674,
+      "eval_runtime": 104.1648,
+      "eval_samples_per_second": 24.0,
+      "eval_steps_per_second": 3.005,
+      "step": 2191
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 7.337593184238552e-06,
+      "loss": 1.2611,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.4975725412368774,
+      "eval_mse_0": 1.6374189853668213,
+      "eval_mse_1": 1.3291974067687988,
+      "eval_mse_2": 1.384625792503357,
+      "eval_mse_3": 1.6390482187271118,
+      "eval_pcc_0": 0.5815509839844824,
+      "eval_pcc_1": 0.6146242286008073,
+      "eval_pcc_2": 0.6093294883590791,
+      "eval_pcc_3": 0.593986854996163,
+      "eval_runtime": 104.8569,
+      "eval_samples_per_second": 23.842,
+      "eval_steps_per_second": 2.985,
+      "step": 2504
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.385452389717102,
+      "eval_mse_0": 1.5612801313400269,
+      "eval_mse_1": 1.2092715501785278,
+      "eval_mse_2": 1.2360713481903076,
+      "eval_mse_3": 1.535186767578125,
+      "eval_pcc_0": 0.6069065300247408,
+      "eval_pcc_1": 0.654707626165453,
+      "eval_pcc_2": 0.6430038066099911,
+      "eval_pcc_3": 0.6220298148364818,
+      "eval_runtime": 104.4697,
+      "eval_samples_per_second": 23.93,
+      "eval_steps_per_second": 2.996,
+      "step": 2817
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 6.805111821086262e-06,
+      "loss": 1.1243,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.2460265159606934,
+      "eval_mse_0": 1.4477919340133667,
+      "eval_mse_1": 1.0468342304229736,
+      "eval_mse_2": 1.1006340980529785,
+      "eval_mse_3": 1.3888448476791382,
+      "eval_pcc_0": 0.6343965881784424,
+      "eval_pcc_1": 0.6989810806900577,
+      "eval_pcc_2": 0.6841086100069462,
+      "eval_pcc_3": 0.6550396514803124,
+      "eval_runtime": 104.4441,
+      "eval_samples_per_second": 23.936,
+      "eval_steps_per_second": 2.997,
+      "step": 3130
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.242544412612915,
+      "eval_mse_0": 1.4355757236480713,
+      "eval_mse_1": 1.0427162647247314,
+      "eval_mse_2": 1.099190592765808,
+      "eval_mse_3": 1.3926929235458374,
+      "eval_pcc_0": 0.6411723354233848,
+      "eval_pcc_1": 0.7050154845461115,
+      "eval_pcc_2": 0.6878333468069526,
+      "eval_pcc_3": 0.6587134719186719,
+      "eval_runtime": 104.2603,
+      "eval_samples_per_second": 23.978,
+      "eval_steps_per_second": 3.002,
+      "step": 3443
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 6.272630457933972e-06,
+      "loss": 0.9917,
+      "step": 3500
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.2342461347579956,
+      "eval_mse_0": 1.4104150533676147,
+      "eval_mse_1": 1.0510520935058594,
+      "eval_mse_2": 1.1056771278381348,
+      "eval_mse_3": 1.3698387145996094,
+      "eval_pcc_0": 0.6421912019080789,
+      "eval_pcc_1": 0.6987397424918942,
+      "eval_pcc_2": 0.6851340681521141,
+      "eval_pcc_3": 0.6583270843649168,
+      "eval_runtime": 104.5121,
+      "eval_samples_per_second": 23.921,
+      "eval_steps_per_second": 2.995,
+      "step": 3756
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 5.7401490947816826e-06,
+      "loss": 0.9629,
+      "step": 4000
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.2273322343826294,
+      "eval_mse_0": 1.4287023544311523,
+      "eval_mse_1": 1.007864236831665,
+      "eval_mse_2": 1.0712348222732544,
+      "eval_mse_3": 1.4015300273895264,
+      "eval_pcc_0": 0.6335129267540619,
+      "eval_pcc_1": 0.7100531590299713,
+      "eval_pcc_2": 0.6918067028499294,
+      "eval_pcc_3": 0.6474716554727297,
+      "eval_runtime": 103.8806,
+      "eval_samples_per_second": 24.066,
+      "eval_steps_per_second": 3.013,
+      "step": 4069
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.2677063941955566,
+      "eval_mse_0": 1.4451885223388672,
+      "eval_mse_1": 1.072100281715393,
+      "eval_mse_2": 1.1277052164077759,
+      "eval_mse_3": 1.4258337020874023,
+      "eval_pcc_0": 0.6265764198728185,
+      "eval_pcc_1": 0.689372090794572,
+      "eval_pcc_2": 0.673986584428412,
+      "eval_pcc_3": 0.6372274413385196,
+      "eval_runtime": 104.1136,
+      "eval_samples_per_second": 24.012,
+      "eval_steps_per_second": 3.006,
+      "step": 4382
+    },
+    {
+      "epoch": 14.38,
+      "learning_rate": 5.207667731629393e-06,
+      "loss": 0.8928,
+      "step": 4500
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.393066167831421,
+      "eval_mse_0": 1.5934511423110962,
+      "eval_mse_1": 1.1841371059417725,
+      "eval_mse_2": 1.2197777032852173,
+      "eval_mse_3": 1.57489812374115,
+      "eval_pcc_0": 0.6174218615099186,
+      "eval_pcc_1": 0.6757646470884817,
+      "eval_pcc_2": 0.6674357999481634,
+      "eval_pcc_3": 0.6305210586093476,
+      "eval_runtime": 105.2137,
+      "eval_samples_per_second": 23.761,
+      "eval_steps_per_second": 2.975,
+      "step": 4695
+    },
+    {
+      "epoch": 15.97,
+      "learning_rate": 4.675186368477103e-06,
+      "loss": 0.8364,
+      "step": 5000
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.3265507221221924,
+      "eval_mse_0": 1.5106405019760132,
+      "eval_mse_1": 1.131346583366394,
+      "eval_mse_2": 1.1748758554458618,
+      "eval_mse_3": 1.4893407821655273,
+      "eval_pcc_0": 0.6048419467785894,
+      "eval_pcc_1": 0.672069640857398,
+      "eval_pcc_2": 0.6628502559639159,
+      "eval_pcc_3": 0.6170699651742021,
+      "eval_runtime": 105.0444,
+      "eval_samples_per_second": 23.799,
+      "eval_steps_per_second": 2.98,
+      "step": 5008
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.3360716104507446,
+      "eval_mse_0": 1.494323492050171,
+      "eval_mse_1": 1.156771183013916,
+      "eval_mse_2": 1.1984198093414307,
+      "eval_mse_3": 1.4947763681411743,
+      "eval_pcc_0": 0.6070107389407768,
+      "eval_pcc_1": 0.6633442286016179,
+      "eval_pcc_2": 0.6555605186369209,
+      "eval_pcc_3": 0.6172658621707156,
+      "eval_runtime": 103.9583,
+      "eval_samples_per_second": 24.048,
+      "eval_steps_per_second": 3.011,
+      "step": 5321
+    },
+    {
+      "epoch": 17.57,
+      "learning_rate": 4.142705005324814e-06,
+      "loss": 0.7902,
+      "step": 5500
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.289337158203125,
+      "eval_mse_0": 1.4631069898605347,
+      "eval_mse_1": 1.0992158651351929,
+      "eval_mse_2": 1.140978217124939,
+      "eval_mse_3": 1.4540483951568604,
+      "eval_pcc_0": 0.6178384398417589,
+      "eval_pcc_1": 0.6834468987529572,
+      "eval_pcc_2": 0.6753122637305081,
+      "eval_pcc_3": 0.6303698197169479,
+      "eval_runtime": 105.0492,
+      "eval_samples_per_second": 23.798,
+      "eval_steps_per_second": 2.98,
+      "step": 5634
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.3840723037719727,
+      "eval_mse_0": 1.603720784187317,
+      "eval_mse_1": 1.1754611730575562,
+      "eval_mse_2": 1.2065637111663818,
+      "eval_mse_3": 1.550544023513794,
+      "eval_pcc_0": 0.6035678734065899,
+      "eval_pcc_1": 0.6813206955844806,
+      "eval_pcc_2": 0.677510078904368,
+      "eval_pcc_3": 0.6197277991414735,
+      "eval_runtime": 105.1107,
+      "eval_samples_per_second": 23.784,
+      "eval_steps_per_second": 2.978,
+      "step": 5947
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 3.6102236421725247e-06,
+      "loss": 0.7731,
+      "step": 6000
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.2481200695037842,
+      "eval_mse_0": 1.4342713356018066,
+      "eval_mse_1": 1.0593796968460083,
+      "eval_mse_2": 1.0942435264587402,
+      "eval_mse_3": 1.404585599899292,
+      "eval_pcc_0": 0.6303758956496333,
+      "eval_pcc_1": 0.6924356908829079,
+      "eval_pcc_2": 0.6854885142079898,
+      "eval_pcc_3": 0.6446989900217669,
+      "eval_runtime": 105.9135,
+      "eval_samples_per_second": 23.604,
+      "eval_steps_per_second": 2.955,
+      "step": 6260
+    },
+    {
+      "epoch": 20.77,
+      "learning_rate": 3.0777422790202343e-06,
+      "loss": 0.7321,
+      "step": 6500
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.419948935508728,
+      "eval_mse_0": 1.6509391069412231,
+      "eval_mse_1": 1.2085292339324951,
+      "eval_mse_2": 1.228689193725586,
+      "eval_mse_3": 1.591638207435608,
+      "eval_pcc_0": 0.600744542386121,
+      "eval_pcc_1": 0.6754018310660278,
+      "eval_pcc_2": 0.6713927838849457,
+      "eval_pcc_3": 0.616840868096359,
+      "eval_runtime": 105.8667,
+      "eval_samples_per_second": 23.615,
+      "eval_steps_per_second": 2.957,
+      "step": 6573
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.288152813911438,
+      "eval_mse_0": 1.4787753820419312,
+      "eval_mse_1": 1.0978302955627441,
+      "eval_mse_2": 1.1353261470794678,
+      "eval_mse_3": 1.4406806230545044,
+      "eval_pcc_0": 0.6227544950777801,
+      "eval_pcc_1": 0.6867627568228214,
+      "eval_pcc_2": 0.6793328251200954,
+      "eval_pcc_3": 0.6360388258243701,
+      "eval_runtime": 103.9697,
+      "eval_samples_per_second": 24.045,
+      "eval_steps_per_second": 3.01,
+      "step": 6886
+    },
+    {
+      "epoch": 22.36,
+      "learning_rate": 2.5452609158679447e-06,
+      "loss": 0.7306,
+      "step": 7000
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.3645573854446411,
+      "eval_mse_0": 1.584963321685791,
+      "eval_mse_1": 1.158388614654541,
+      "eval_mse_2": 1.1865752935409546,
+      "eval_mse_3": 1.5283006429672241,
+      "eval_pcc_0": 0.6155547920218205,
+      "eval_pcc_1": 0.6864819709328003,
+      "eval_pcc_2": 0.680583123812986,
+      "eval_pcc_3": 0.6306266900025584,
+      "eval_runtime": 104.5098,
+      "eval_samples_per_second": 23.921,
+      "eval_steps_per_second": 2.995,
+      "step": 7199
+    },
+    {
+      "epoch": 23.96,
+      "learning_rate": 2.012779552715655e-06,
+      "loss": 0.7146,
+      "step": 7500
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.3409558534622192,
+      "eval_mse_0": 1.5570074319839478,
+      "eval_mse_1": 1.1370699405670166,
+      "eval_mse_2": 1.1649022102355957,
+      "eval_mse_3": 1.504842758178711,
+      "eval_pcc_0": 0.6102322449932297,
+      "eval_pcc_1": 0.6815928268666807,
+      "eval_pcc_2": 0.6757935295218792,
+      "eval_pcc_3": 0.6256673313743037,
+      "eval_runtime": 104.2708,
+      "eval_samples_per_second": 23.976,
+      "eval_steps_per_second": 3.002,
+      "step": 7512
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.3083544969558716,
+      "eval_mse_0": 1.5141199827194214,
+      "eval_mse_1": 1.1072171926498413,
+      "eval_mse_2": 1.1411473751068115,
+      "eval_mse_3": 1.470934271812439,
+      "eval_pcc_0": 0.6111966740089494,
+      "eval_pcc_1": 0.6789100259573769,
+      "eval_pcc_2": 0.6716300582517825,
+      "eval_pcc_3": 0.626430761035975,
+      "eval_runtime": 104.1873,
+      "eval_samples_per_second": 23.995,
+      "eval_steps_per_second": 3.004,
+      "step": 7825
+    },
+    {
+      "epoch": 25.56,
+      "learning_rate": 1.4802981895633654e-06,
+      "loss": 0.7176,
+      "step": 8000
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 1.3140721321105957,
+      "eval_mse_0": 1.5177463293075562,
+      "eval_mse_1": 1.1146221160888672,
+      "eval_mse_2": 1.1509774923324585,
+      "eval_mse_3": 1.4729410409927368,
+      "eval_pcc_0": 0.6097411853663964,
+      "eval_pcc_1": 0.6796226802996224,
+      "eval_pcc_2": 0.671900931690759,
+      "eval_pcc_3": 0.6252112879875048,
+      "eval_runtime": 103.8694,
+      "eval_samples_per_second": 24.069,
+      "eval_steps_per_second": 3.013,
+      "step": 8138
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 1.3034908771514893,
+      "eval_mse_0": 1.5157262086868286,
+      "eval_mse_1": 1.100796103477478,
+      "eval_mse_2": 1.1328198909759521,
+      "eval_mse_3": 1.4646155834197998,
+      "eval_pcc_0": 0.6165178975329266,
+      "eval_pcc_1": 0.6836285382161873,
+      "eval_pcc_2": 0.6772868623217754,
+      "eval_pcc_3": 0.6322221722707936,
+      "eval_runtime": 156.5262,
+      "eval_samples_per_second": 15.972,
+      "eval_steps_per_second": 2.0,
+      "step": 8451
+    },
+    {
+      "epoch": 27.16,
+      "learning_rate": 9.478168264110757e-07,
+      "loss": 0.6977,
+      "step": 8500
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 1.296176791191101,
+      "eval_mse_0": 1.495354175567627,
+      "eval_mse_1": 1.101500391960144,
+      "eval_mse_2": 1.1357016563415527,
+      "eval_mse_3": 1.4521503448486328,
+      "eval_pcc_0": 0.6150392316570756,
+      "eval_pcc_1": 0.6858794405503924,
+      "eval_pcc_2": 0.6796961971847624,
+      "eval_pcc_3": 0.631583735343265,
+      "eval_runtime": 104.1079,
+      "eval_samples_per_second": 24.014,
+      "eval_steps_per_second": 3.006,
+      "step": 8764
+    },
+    {
+      "epoch": 28.75,
+      "learning_rate": 4.1533546325878595e-07,
+      "loss": 0.6762,
+      "step": 9000
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 1.30547034740448,
+      "eval_mse_0": 1.5151373147964478,
+      "eval_mse_1": 1.1045734882354736,
+      "eval_mse_2": 1.1377769708633423,
+      "eval_mse_3": 1.464392900466919,
+      "eval_pcc_0": 0.6149115674811092,
+      "eval_pcc_1": 0.6857980322422439,
+      "eval_pcc_2": 0.6796899962887978,
+      "eval_pcc_3": 0.6315434200890307,
+      "eval_runtime": 123.7524,
+      "eval_samples_per_second": 20.202,
+      "eval_steps_per_second": 2.529,
+      "step": 9077
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 1.2990093231201172,
+      "eval_mse_0": 1.5060529708862305,
+      "eval_mse_1": 1.099517822265625,
+      "eval_mse_2": 1.133305311203003,
+      "eval_mse_3": 1.4571605920791626,
+      "eval_pcc_0": 0.6162701381731509,
+      "eval_pcc_1": 0.6867923339565917,
+      "eval_pcc_2": 0.6805020447302117,
+      "eval_pcc_3": 0.6327768215304354,
+      "eval_runtime": 104.2117,
+      "eval_samples_per_second": 23.99,
+      "eval_steps_per_second": 3.004,
+      "step": 9390
+    },
+    {
+      "epoch": 30.0,
+      "step": 9390,
+      "total_flos": 0.0,
+      "train_loss": 3.191356456622529,
+      "train_runtime": 9611.9679,
+      "train_samples_per_second": 7.803,
+      "train_steps_per_second": 0.977
+    }
+  ],
+  "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/06_hubert-large-ll60k/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d00e8333fb23780377082fe967cfcff58c8514131beb12aef76ee5bdff616be
+size 4792