Upload folder using huggingface_hub

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-large
+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/wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large) on the superb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 414.7518
+- Accuracy: 0.6209
+- Test Accuracy: 0.6209
+- Df Accuracy: 0.1343
+- Unlearn Overall Accuracy: 0.7433
+- Unlearn Time: 1648.8392
+
+## 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: 2.5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:----------------:|:------------------------:|:----:|
+| 0.0           | 1.0   | 1503 | 414.7518        | 0.1343   | 0.7433           | 0.7433                   | -1   |
+| 0.0           | 2.0   | 3006 | 1072.2520       | 0.1343   | 0.7433           | 0.7433                   | -1   |
+| 0.0           | 2.5   | 3758 | 1184.3600       | 0.1343   | 0.7433           | 0.7433                   | -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": 0.13425925925925927,
+    "dr_accuracy": 0.6686914915747868,
+    "dr_loss": 362.539794921875,
+    "dr_runtime": 168.0217,
+    "dr_samples_per_second": 286.094,
+    "dr_steps_per_second": 35.763,
+    "dr_unlearn_overall_accuracy": 0.7672161161577638,
+    "epoch": 2.5,
+    "eval_accuracy": 0.6209179170344219,
+    "eval_loss": 414.7518310546875,
+    "eval_runtime": 27.1613,
+    "eval_samples_per_second": 250.283,
+    "eval_steps_per_second": 31.295,
+    "eval_unlearn_overall_accuracy": 0.7433293288875813,
+    "test_accuracy": 0.6686914915747868,
+    "test_loss": 1029.048583984375,
+    "test_runtime": 14.5813,
+    "test_samples_per_second": 211.298,
+    "test_steps_per_second": 26.472,
+    "test_unlearn_overall_accuracy": 0.4745776082801399,
+    "train_loss": 0.0,
+    "train_runtime": 1382.7366,
+    "train_samples_per_second": 86.911,
+    "train_steps_per_second": 2.718,
+    "unlearn_overall_accuracy": 0.7672161161577638,
+    "unlearn_time": 1648.8391699790955
+}

config.json

@@ -0,0 +1,139 @@
+{
+  "_name_or_path": "./audio/train/checkpoint/wav2vec2-large/superb_ks_42",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "finetuning_task": "audio-classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 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_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

dr_results.json

@@ -0,0 +1,13 @@
+{
+    "df_accuracy": 0.13425925925925927,
+    "dr_accuracy": 0.6686914915747868,
+    "dr_loss": 362.539794921875,
+    "dr_runtime": 168.0217,
+    "dr_samples_per_second": 286.094,
+    "dr_steps_per_second": 35.763,
+    "dr_unlearn_overall_accuracy": 0.7672161161577638,
+    "epoch": 2.5,
+    "test_accuracy": 0.6686914915747868,
+    "unlearn_overall_accuracy": 0.7672161161577638,
+    "unlearn_time": 1648.8391699790955
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "df_accuracy": 0.13425925925925927,
+    "epoch": 2.5,
+    "eval_accuracy": 0.6209179170344219,
+    "eval_loss": 414.7518310546875,
+    "eval_runtime": 27.1613,
+    "eval_samples_per_second": 250.283,
+    "eval_steps_per_second": 31.295,
+    "eval_unlearn_overall_accuracy": 0.7433293288875813,
+    "test_accuracy": 0.6209179170344219,
+    "unlearn_overall_accuracy": 0.7433293288875813,
+    "unlearn_time": 1648.8391699790955
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6baa43a7c2758593f795abe271b1a1caa75421b447f6d19377ca2ff2f5c85f6
+size 1262828272

pred_logit_df.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0d10e3e5d83f9057c5cf322f90157ff37fd4532d571898c828aca932de1f34
+size 145280

pred_logit_dr.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3ebde1ba0c463b1469fa57fb863e13d9dc570228a3a1fea2a41794a52867b9a
+size 2307488

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9dfa356f9908b8458c384b4b94968e5ac0ee9eeb1830e57bbb11ae106d30daa
+size 326432

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aef23840ea7c8a584b6a2563ee22cf3a0fd3593069dece3525829dc8cf223b3
+size 148016

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

test_results.json

@@ -0,0 +1,12 @@
+{
+    "df_accuracy": 0.13425925925925927,
+    "epoch": 2.5,
+    "test_accuracy": 0.0834144758195391,
+    "test_loss": 1029.048583984375,
+    "test_runtime": 14.5813,
+    "test_samples_per_second": 211.298,
+    "test_steps_per_second": 26.472,
+    "test_unlearn_overall_accuracy": 0.4745776082801399,
+    "unlearn_overall_accuracy": 0.4745776082801399,
+    "unlearn_time": 1648.8391699790955
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.5,
+    "train_loss": 0.0,
+    "train_runtime": 1382.7366,
+    "train_samples_per_second": 86.911,
+    "train_steps_per_second": 2.718
+}

trainer_state.json

@@ -0,0 +1,93 @@
+{
+  "best_metric": 0.7433293288875813,
+  "best_model_checkpoint": "audio/unlearn/checkpoint/wav2vec2-large/scrub/6.0/superb_ks_42/checkpoint-1503",
+  "epoch": 2.5003326679973386,
+  "eval_steps": 500,
+  "global_step": 3758,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.67,
+      "grad_norm": 2860.644775390625,
+      "learning_rate": 4.077468953282082e-05,
+      "loss": 0.0,
+      "step": 1000
+    },
+    {
+      "df_accuracy": 0.13425925925925927,
+      "epoch": 1.0,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": 414.7518310546875,
+      "eval_runtime": 27.2,
+      "eval_samples_per_second": 249.927,
+      "eval_steps_per_second": 31.25,
+      "eval_unlearn_overall_accuracy": 0.7433293288875813,
+      "step": 1503,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7433293288875813,
+      "unlearn_time": -1
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 5017.3203125,
+      "learning_rate": 2.599053814311059e-05,
+      "loss": 0.0,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6478.43701171875,
+      "learning_rate": 1.1206386753400355e-05,
+      "loss": 0.0,
+      "step": 3000
+    },
+    {
+      "df_accuracy": 0.13425925925925927,
+      "epoch": 2.0,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": 1072.251953125,
+      "eval_runtime": 27.1274,
+      "eval_samples_per_second": 250.595,
+      "eval_steps_per_second": 31.334,
+      "eval_unlearn_overall_accuracy": 0.7433293288875813,
+      "step": 3006,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7433293288875813,
+      "unlearn_time": -1
+    },
+    {
+      "df_accuracy": 0.13425925925925927,
+      "epoch": 2.5,
+      "eval_accuracy": 0.6209179170344219,
+      "eval_loss": 1184.3599853515625,
+      "eval_runtime": 27.0968,
+      "eval_samples_per_second": 250.879,
+      "eval_steps_per_second": 31.369,
+      "eval_unlearn_overall_accuracy": 0.7433293288875813,
+      "step": 3758,
+      "test_accuracy": 0.6209179170344219,
+      "unlearn_overall_accuracy": 0.7433293288875813,
+      "unlearn_time": -1
+    },
+    {
+      "epoch": 2.5,
+      "step": 3758,
+      "total_flos": 3.642982924137984e+18,
+      "train_loss": 0.0,
+      "train_runtime": 1382.7366,
+      "train_samples_per_second": 86.911,
+      "train_steps_per_second": 2.718
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 3758,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.642982924137984e+18,
+  "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 sha256:4bc72d173aade6c14a335cad94b8ea747d3c698aabc671729a5c29be3363c284
+size 5048