End of training

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: test_wav2vec2_ESC50
+  results: []
+---
+
+<!-- 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. -->
+
+# test_wav2vec2_ESC50
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0326
+- Accuracy: 0.7104
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 2.1292        | 0.9863 | 54   | 2.1314          | 0.2576   |
+| 1.7714        | 1.9909 | 109  | 1.7812          | 0.4087   |
+| 1.5023        | 2.9954 | 164  | 1.6238          | 0.4951   |
+| 1.3402        | 4.0    | 219  | 1.3518          | 0.6022   |
+| 1.1629        | 4.9863 | 273  | 1.2371          | 0.6440   |
+| 1.0466        | 5.9909 | 328  | 1.1422          | 0.6789   |
+| 0.9478        | 6.9954 | 383  | 1.0848          | 0.6875   |
+| 0.879         | 8.0    | 438  | 1.1490          | 0.6577   |
+| 0.8719        | 8.9863 | 492  | 1.0175          | 0.7121   |
+| 0.8069        | 9.8630 | 540  | 1.0326          | 0.7104   |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,142 @@
+{
+  "_name_or_path": "facebook/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": "air_conditioner",
+    "1": "car_horn",
+    "2": "children_playing",
+    "3": "dog_bark",
+    "4": "drilling",
+    "5": "engine_idling",
+    "6": "gun_shot",
+    "7": "jackhammer",
+    "8": "siren",
+    "9": "street_music"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "air_conditioner": "0",
+    "car_horn": "1",
+    "children_playing": "2",
+    "dog_bark": "3",
+    "drilling": "4",
+    "engine_idling": "5",
+    "gun_shot": "6",
+    "jackhammer": "7",
+    "siren": "8",
+    "street_music": "9"
+  },
+  "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": "4.40.2",
+  "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:b551d3400142f497e271615447fa9229d39cb1402b45d3984b8631b63fc63117
+size 378310592

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/May13_22-10-12_4f7c61af4893/events.out.tfevents.1715638212.4f7c61af4893.11446.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c05d5afc84e9fc033fe95d009d631c2263b37332b6fe33d645b061328258b48
+size 21811

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b802a5dcc60722558616285c84fc8e1a5018fe8446df1d0b22c20c9f373d5582
+size 4984