End of training

README.md

@@ -1,80 +1,81 @@
----
-license: apache-2.0
-base_model: ntu-spml/distilhubert
-tags:
-- generated_from_trainer
-datasets:
-- audiofolder
-metrics:
-- accuracy
-model-index:
-- name: distilhubert-finetuned-cry-detector
-  results:
-  - task:
-      name: Audio Classification
-      type: audio-classification
-    dataset:
-      name: audiofolder
-      type: audiofolder
-      config: default
-      split: train
-      args: default
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.9786096256684492
----
-
-<!-- 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. -->
-
-# distilhubert-finetuned-cry-detector
-
-This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0732
-- Accuracy: 0.9786
-
-## 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: 0.0001
-- train_batch_size: 8
-- eval_batch_size: 8
-- seed: 123
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 64
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- num_epochs: 4
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| No log        | 0.9362 | 11   | 0.1831          | 0.9358   |
-| No log        | 1.9574 | 23   | 0.1361          | 0.9519   |
-| No log        | 2.9787 | 35   | 0.0748          | 0.9786   |
-| No log        | 3.7447 | 44   | 0.0732          | 0.9786   |
-
-
-### Framework versions
-
-- Transformers 4.42.4
-- Pytorch 2.3.1+cu121
-- Datasets 2.21.0
-- Tokenizers 0.19.1
+---
+library_name: transformers
+license: apache-2.0
+base_model: ntu-spml/distilhubert
+tags:
+- generated_from_trainer
+datasets:
+- audiofolder
+metrics:
+- accuracy
+model-index:
+- name: distilhubert-finetuned-cry-detector
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: audiofolder
+      type: audiofolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9786096256684492
+---
+
+<!-- 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. -->
+
+# distilhubert-finetuned-cry-detector
+
+This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0748
+- Accuracy: 0.9786
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 123
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| No log        | 0.9362 | 11   | 0.1841          | 0.9358   |
+| No log        | 1.9574 | 23   | 0.1308          | 0.9519   |
+| No log        | 2.9787 | 35   | 0.0763          | 0.9733   |
+| No log        | 3.7447 | 44   | 0.0748          | 0.9786   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu118
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -1,80 +1,80 @@
-{
-  "_name_or_path": "ntu-spml/distilhubert",
-  "activation_dropout": 0.1,
-  "apply_spec_augment": false,
-  "architectures": [
-    "HubertForSequenceClassification"
-  ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 1,
-  "classifier_proj_size": 256,
-  "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,
-  "do_stable_layer_norm": false,
-  "eos_token_id": 2,
-  "feat_extract_activation": "gelu",
-  "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.0,
-  "feat_proj_layer_norm": false,
-  "final_dropout": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "crying",
-    "1": "no_crying"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "crying": "0",
-    "no_crying": "1"
-  },
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
-  "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": "hubert",
-  "num_attention_heads": 12,
-  "num_conv_pos_embedding_groups": 16,
-  "num_conv_pos_embeddings": 128,
-  "num_feat_extract_layers": 7,
-  "num_hidden_layers": 2,
-  "pad_token_id": 0,
-  "torch_dtype": "float32",
-  "transformers_version": "4.42.4",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 32
-}
+{
+  "_name_or_path": "ntu-spml/distilhubert",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": false,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "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,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": false,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "crying",
+    "1": "no_crying"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "crying": "0",
+    "no_crying": "1"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37fd4a948a69ccbbd999b0b48a7af1b366b82c87b508d35767cdfbf1c2bba96c
+oid sha256:b41a275fde4c9fcebaf0bd9fc5ae54fde8d749a3b2aa19361673f8dc31100514
 size 94763496

preprocessor_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc895582845e04f7b896e904848b260ab962b034fa8d8a0a3cd0d29f8a8cdc1
+oid sha256:e0cac9757157cce11a947d5910d5b2825a89549ee75602204d2845a5a6764f90
 size 5176