End of training

README.md

@@ -1,61 +1,61 @@
----
-library_name: transformers
-license: apache-2.0
-base_model: ntu-spml/distilhubert
-tags:
-- generated_from_trainer
-datasets:
-- audiofolder
-model-index:
-- name: distilhubert-finetuned-donateacry
-  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. -->
-
-# distilhubert-finetuned-donateacry
-
-This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
-
-## 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: 0.001
-- train_batch_size: 8
-- eval_batch_size: 8
-- seed: 42
-- 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
-- lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 1
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| No log        | 0.9032 | 7    | 1.0005          | 0.7317   | 0.6183 | 0.5354    | 0.7317 |
-
-
-### Framework versions
-
-- Transformers 4.44.2
-- Pytorch 2.4.0+cu118
-- 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
+model-index:
+- name: distilhubert-finetuned-donateacry
+  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. -->
+
+# distilhubert-finetuned-donateacry
+
+This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
+
+## 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: 0.001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- 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
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 0.8696 | 5    | 0.6828          | 0.8370   | 0.7627 | 0.7005    | 0.8370 |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -1,88 +1,86 @@
-{
-  "_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": "asphyxia",
-    "1": "burping",
-    "2": "discomfort",
-    "3": "hungry",
-    "4": "pain",
-    "5": "tired"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "asphyxia": "0",
-    "burping": "1",
-    "discomfort": "2",
-    "hungry": "3",
-    "pain": "4",
-    "tired": "5"
-  },
-  "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
-}
+{
+  "_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": "belly_pain",
+    "1": "burping",
+    "2": "discomfort",
+    "3": "hungry",
+    "4": "tired"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "belly_pain": "0",
+    "burping": "1",
+    "discomfort": "2",
+    "hungry": "3",
+    "tired": "4"
+  },
+  "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:ee89457dfabcb5266a0d9ddd072149adddb23b662b81849ffec13e9805e3969d
-size 94767616
+oid sha256:623cd3fd0f4d19a959195cf915d94c0da77d79663678fd23df83132a60f01518
+size 94766588

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
+}

runs/Aug31_20-07-18_ubumarcos/events.out.tfevents.1725127642.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6fd78425b5cd9473839c917dc3e68647117380a54f7f632ed7d49842a47354
+size 6736

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c67a6ea9c17797189d6d754d71b39da02a5c49105a41d05c69d958dbcf14759
+oid sha256:8383020fe31202c2ba3497839d530fb584df34bdc86c1c08bb753bbb11ed8244
 size 5240