End of training

README.md

@@ -0,0 +1,83 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- minds14
+metrics:
+- accuracy
+model-index:
+- name: audio-classification-minds14
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: minds14
+      type: minds14
+      config: en-US
+      split: train
+      args: en-US
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.061946902654867256
+---
+
+<!-- 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. -->
+
+# audio-classification-minds14
+
+This model was trained from scratch on the minds14 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.6501
+- Accuracy: 0.0619
+
+## 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: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- 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
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 0.8   | 3    | 2.6374          | 0.1062   |
+| No log        | 1.87  | 7    | 2.6353          | 0.0973   |
+| 2.6354        | 2.93  | 11   | 2.6417          | 0.0885   |
+| 2.6354        | 4.0   | 15   | 2.6444          | 0.0796   |
+| 2.6354        | 4.8   | 18   | 2.6440          | 0.0708   |
+| 2.6209        | 5.87  | 22   | 2.6470          | 0.0708   |
+| 2.6209        | 6.93  | 26   | 2.6484          | 0.0619   |
+| 2.6178        | 8.0   | 30   | 2.6501          | 0.0619   |
+
+
+### Framework versions
+
+- Transformers 4.36.1
+- Pytorch 2.1.1
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,150 @@
+{
+  "_name_or_path": "D:/AudioClassification/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "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": 256,
+  "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_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "abroad",
+    "1": "address",
+    "10": "high_value_payment",
+    "11": "joint_account",
+    "12": "latest_transactions",
+    "13": "pay_bill",
+    "2": "app_error",
+    "3": "atm_limit",
+    "4": "balance",
+    "5": "business_loan",
+    "6": "card_issues",
+    "7": "cash_deposit",
+    "8": "direct_debit",
+    "9": "freeze"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "abroad": "0",
+    "address": "1",
+    "app_error": "2",
+    "atm_limit": "3",
+    "balance": "4",
+    "business_loan": "5",
+    "card_issues": "6",
+    "cash_deposit": "7",
+    "direct_debit": "8",
+    "freeze": "9",
+    "high_value_payment": "10",
+    "joint_account": "11",
+    "latest_transactions": "12",
+    "pay_bill": "13"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "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": "4.36.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51196af60f504c171ea9f1555a46f3d9bbb20ee53f2b6604e9d555dcb12a20c9
+size 378314704

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": false,
+  "sampling_rate": 16000
+}

runs/Dec16_12-31-45_DESKTOP-RI439S7/events.out.tfevents.1702701107.DESKTOP-RI439S7.14216.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:640b982787550dfa391164a5302c98170ea369b465371f7454eac0886e2f7888
+size 10241

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71cae922eb2f191b24b0e999589212abf0943a8360aeda7fb36cee87a3014dc
+size 4792