Upload folder using huggingface_hub

README.md

@@ -0,0 +1,90 @@
+---
+license: apache-2.0
+base_model: facebook/hubert-large-ll60k
+tags:
+- audio-classification
+- generated_from_trainer
+datasets:
+- superb
+metrics:
+- accuracy
+model-index:
+- name: superb_ks_42
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: superb
+      type: superb
+      config: ks
+      split: validation
+      args: ks
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6209179170344219
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# superb_ks_42
+
+This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on the superb dataset.
+It achieves the following results on the evaluation set:
+- Loss: -6.8759
+- Accuracy: 0.6209
+- Test Accuracy: 0.6209
+- Df Accuracy: 0.1352
+- Unlearn Overall Accuracy: 0.7429
+- Unlearn Time: 652.0674
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:----------------:|:------------------------:|:----:|
+| No log        | 1.0   | 32   | -0.1223         | 0.9598   | 0.5101           | 0.5101                   | -1   |
+| No log        | 2.0   | 64   | -6.8759         | 0.1352   | 0.7429           | 0.7429                   | -1   |
+| No log        | 3.0   | 96   | -9.1867         | 0.1352   | 0.7429           | 0.7429                   | -1   |
+| No log        | 4.0   | 128  | -11.1371        | 0.1352   | 0.7429           | 0.7429                   | -1   |
+| No log        | 5.0   | 160  | -12.8684        | 0.1352   | 0.7429           | 0.7429                   | -1   |
+| No log        | 6.0   | 192  | -14.3520        | 0.1352   | 0.7429           | 0.7429                   | -1   |
+| No log        | 7.0   | 224  | -15.5595        | 0.1352   | 0.7429           | 0.7429                   | -1   |
+| No log        | 8.0   | 256  | -16.4513        | 0.1352   | 0.7429           | 0.7429                   | -1   |
+| No log        | 9.0   | 288  | -16.9985        | 0.1352   | 0.7429           | 0.7429                   | -1   |
+| No log        | 10.0  | 320  | -17.1870        | 0.1352   | 0.7429           | 0.7429                   | -1   |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,28 @@
+{
+    "df_accuracy": 0.13516160626836435,
+    "dr_accuracy": 0.6472949493739141,
+    "dr_loss": -6.39683198928833,
+    "dr_runtime": 180.7424,
+    "dr_samples_per_second": 277.041,
+    "dr_steps_per_second": 34.635,
+    "dr_unlearn_overall_accuracy": 0.7560666715527748,
+    "epoch": 10.0,
+    "eval_accuracy": 0.6209179170344219,
+    "eval_loss": -6.875938892364502,
+    "eval_runtime": 28.819,
+    "eval_samples_per_second": 235.886,
+    "eval_steps_per_second": 29.494,
+    "eval_unlearn_overall_accuracy": 0.7428781553830288,
+    "test_accuracy": 0.6472949493739141,
+    "test_loss": -17.2489013671875,
+    "test_runtime": 16.1315,
+    "test_samples_per_second": 190.993,
+    "test_steps_per_second": 23.928,
+    "test_unlearn_overall_accuracy": 0.47412643477558736,
+    "train_loss": -25.27679901123047,
+    "train_runtime": 651.3076,
+    "train_samples_per_second": 15.676,
+    "train_steps_per_second": 0.491,
+    "unlearn_overall_accuracy": 0.7560666715527748,
+    "unlearn_time": 652.0674347877502
+}

config.json

@@ -0,0 +1,112 @@
+{
+  "_name_or_path": "facebook/hubert-large-ll60k",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.0,
+  "finetuning_task": "audio-classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "yes",
+    "1": "no",
+    "10": "_silence_",
+    "11": "_unknown_",
+    "2": "up",
+    "3": "down",
+    "4": "left",
+    "5": "right",
+    "6": "on",
+    "7": "off",
+    "8": "stop",
+    "9": "go"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "_silence_": "10",
+    "_unknown_": "11",
+    "down": "3",
+    "go": "9",
+    "left": "4",
+    "no": "1",
+    "off": "7",
+    "on": "6",
+    "right": "5",
+    "stop": "8",
+    "up": "2",
+    "yes": "0"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
+  "model_type": "hubert",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

dr_results.json

@@ -0,0 +1,13 @@
+{
+    "df_accuracy": 0.13516160626836435,
+    "dr_accuracy": 0.6472949493739141,
+    "dr_loss": -6.39683198928833,
+    "dr_runtime": 180.7424,
+    "dr_samples_per_second": 277.041,
+    "dr_steps_per_second": 34.635,
+    "dr_unlearn_overall_accuracy": 0.7560666715527748,
+    "epoch": 10.0,
+    "test_accuracy": 0.6472949493739141,
+    "unlearn_overall_accuracy": 0.7560666715527748,
+    "unlearn_time": 652.0674347877502
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "df_accuracy": 0.13516160626836435,
+    "epoch": 10.0,
+    "eval_accuracy": 0.6209179170344219,
+    "eval_loss": -6.875938892364502,
+    "eval_runtime": 28.819,
+    "eval_samples_per_second": 235.886,
+    "eval_steps_per_second": 29.494,
+    "eval_unlearn_overall_accuracy": 0.7428781553830288,
+    "test_accuracy": 0.6209179170344219,
+    "unlearn_overall_accuracy": 0.7428781553830288,
+    "unlearn_time": 652.0674347877502
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4583c7c599bc39e0124a09f8f150b9ccd161bca4210ca87b88dc924b346b1f66
+size 1262868744

pred_logit_df.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211bf92f62b04c7872272be1cef5210b20f5ac4e2445252d2e1881ce3ce9ee27
+size 49136

pred_logit_dr.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52b2ba3d38b09b424abafede4435316be5fb8db7e5ff844ae5566d31eb798c2
+size 2403632

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b57f54f2f005d766d42e33c27d45a3c172e30100d2b276fc786d493c9f21b1c
+size 326432

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133f46dc49174e73b5e76c2c1ac14c1aa3a2965c1e66840e5c0e67c7cdfb5713
+size 148016

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
+}

test_results.json

@@ -0,0 +1,12 @@
+{
+    "df_accuracy": 0.13516160626836435,
+    "epoch": 10.0,
+    "test_accuracy": 0.0834144758195391,
+    "test_loss": -17.2489013671875,
+    "test_runtime": 16.1315,
+    "test_samples_per_second": 190.993,
+    "test_steps_per_second": 23.928,
+    "test_unlearn_overall_accuracy": 0.47412643477558736,
+    "unlearn_overall_accuracy": 0.47412643477558736,
+    "unlearn_time": 652.0674347877502
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "train_loss": -25.27679901123047,
+    "train_runtime": 651.3076,
+    "train_samples_per_second": 15.676,
+    "train_steps_per_second": 0.491
+}

trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": 0.7428781553830288,
+  "best_model_checkpoint": "audio/unlearn/checkpoint/hubert-large/neggrad/2.0/superb_ks_42/checkpoint-64",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 320,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "df_accuracy": 0.9598432908912831,
+      "epoch": 1.0,
+      "eval_accuracy": 0.9801412180052956,
+      "eval_loss": -0.12229806184768677,
+      "eval_runtime": 28.8279,
+      "eval_samples_per_second": 235.813,
+      "eval_steps_per_second": 29.485,
+      "eval_unlearn_overall_accuracy": 0.5101489635570062,
+      "step": 32,
+      "test_accuracy": 0.9801412180052956,
+      "unlearn_overall_accuracy": 0.5101489635570062,
+      "unlearn_time": -1
+    },
+    {
+      "df_accuracy": 0.13516160626836435,
+      "epoch": 2.0,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": -6.875938892364502,
+      "eval_runtime": 29.0591,
+      "eval_samples_per_second": 233.937,
+      "eval_steps_per_second": 29.251,
+      "eval_unlearn_overall_accuracy": 0.7428781553830288,
+      "step": 64,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7428781553830288,
+      "unlearn_time": -1
+    },
+    {
+      "df_accuracy": 0.13516160626836435,
+      "epoch": 3.0,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": -9.186688423156738,
+      "eval_runtime": 28.9567,
+      "eval_samples_per_second": 234.764,
+      "eval_steps_per_second": 29.354,
+      "eval_unlearn_overall_accuracy": 0.7428781553830288,
+      "step": 96,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7428781553830288,
+      "unlearn_time": -1
+    },
+    {
+      "df_accuracy": 0.13516160626836435,
+      "epoch": 4.0,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": -11.137105941772461,
+      "eval_runtime": 28.8853,
+      "eval_samples_per_second": 235.345,
+      "eval_steps_per_second": 29.427,
+      "eval_unlearn_overall_accuracy": 0.7428781553830288,
+      "step": 128,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7428781553830288,
+      "unlearn_time": -1
+    },
+    {
+      "df_accuracy": 0.13516160626836435,
+      "epoch": 5.0,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": -12.868447303771973,
+      "eval_runtime": 28.8975,
+      "eval_samples_per_second": 235.245,
+      "eval_steps_per_second": 29.414,
+      "eval_unlearn_overall_accuracy": 0.7428781553830288,
+      "step": 160,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7428781553830288,
+      "unlearn_time": -1
+    },
+    {
+      "df_accuracy": 0.13516160626836435,
+      "epoch": 6.0,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": -14.352008819580078,
+      "eval_runtime": 29.1333,
+      "eval_samples_per_second": 233.341,
+      "eval_steps_per_second": 29.176,
+      "eval_unlearn_overall_accuracy": 0.7428781553830288,
+      "step": 192,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7428781553830288,
+      "unlearn_time": -1
+    },
+    {
+      "df_accuracy": 0.13516160626836435,
+      "epoch": 7.0,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": -15.559453010559082,
+      "eval_runtime": 28.8044,
+      "eval_samples_per_second": 236.006,
+      "eval_steps_per_second": 29.509,
+      "eval_unlearn_overall_accuracy": 0.7428781553830288,
+      "step": 224,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7428781553830288,
+      "unlearn_time": -1
+    },
+    {
+      "df_accuracy": 0.13516160626836435,
+      "epoch": 8.0,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": -16.451257705688477,
+      "eval_runtime": 28.9153,
+      "eval_samples_per_second": 235.101,
+      "eval_steps_per_second": 29.396,
+      "eval_unlearn_overall_accuracy": 0.7428781553830288,
+      "step": 256,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7428781553830288,
+      "unlearn_time": -1
+    },
+    {
+      "df_accuracy": 0.13516160626836435,
+      "epoch": 9.0,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": -16.99852752685547,
+      "eval_runtime": 28.6371,
+      "eval_samples_per_second": 237.385,
+      "eval_steps_per_second": 29.682,
+      "eval_unlearn_overall_accuracy": 0.7428781553830288,
+      "step": 288,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7428781553830288,
+      "unlearn_time": -1
+    },
+    {
+      "df_accuracy": 0.13516160626836435,
+      "epoch": 10.0,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": -17.18701934814453,
+      "eval_runtime": 28.717,
+      "eval_samples_per_second": 236.724,
+      "eval_steps_per_second": 29.599,
+      "eval_unlearn_overall_accuracy": 0.7428781553830288,
+      "step": 320,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7428781553830288,
+      "unlearn_time": -1
+    },
+    {
+      "epoch": 10.0,
+      "step": 320,
+      "total_flos": 3.0944063259264e+17,
+      "train_loss": -25.27679901123047,
+      "train_runtime": 651.3076,
+      "train_samples_per_second": 15.676,
+      "train_steps_per_second": 0.491
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 320,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 3.0944063259264e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77449f4d1c2ef50563bf9a96389a55313e9d82adcac26519116d43834c543a6f
+size 5048