End of training

README.md

@@ -0,0 +1,79 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: facebook/hubert-base-ls960
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: hubert-base-ls960-2clsfinetuned-bmd-V1-20250201_145011-LOSO-section-out5
+  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. -->
+
+# hubert-base-ls960-2clsfinetuned-bmd-V1-20250201_145011-LOSO-section-out5
+
+This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7381
+- Accuracy: 0.7273
+- F1: 0.7273
+- Precision: 0.7273
+- Recall: 0.7273
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 1968
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 5    | 0.6674          | 0.5909   | 0.5087 | 0.775     | 0.5909 |
+| 0.6794        | 2.0   | 10   | 0.6130          | 0.7727   | 0.7723 | 0.775     | 0.7727 |
+| 0.6794        | 3.0   | 15   | 0.6236          | 0.6818   | 0.6645 | 0.7292    | 0.6818 |
+| 0.5818        | 4.0   | 20   | 0.6672          | 0.6364   | 0.5810 | 0.7895    | 0.6364 |
+| 0.5818        | 5.0   | 25   | 0.5214          | 0.7727   | 0.7723 | 0.775     | 0.7727 |
+| 0.49          | 6.0   | 30   | 0.5402          | 0.7273   | 0.7273 | 0.7273    | 0.7273 |
+| 0.49          | 7.0   | 35   | 0.7001          | 0.5455   | 0.5089 | 0.5647    | 0.5455 |
+| 0.3862        | 8.0   | 40   | 0.5804          | 0.8182   | 0.8167 | 0.8291    | 0.8182 |
+| 0.3862        | 9.0   | 45   | 0.6310          | 0.8182   | 0.8167 | 0.8291    | 0.8182 |
+| 0.2812        | 10.0  | 50   | 0.7381          | 0.7273   | 0.7273 | 0.7273    | 0.7273 |
+
+
+### Framework versions
+
+- Transformers 4.48.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,85 @@
+{
+  "_name_or_path": "facebook/hubert-base-ls960",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "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_pos_batch_norm": false,
+  "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_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "dep",
+    "1": "mnc"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "dep": "0",
+    "mnc": "1"
+  },
+  "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": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2842aece1caa4c51c8f9cfe813111845daf1e7103f7c60913660d00bfa489d80
+size 378301944

preprocessor_config.json

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

runs/Feb01_14-50-11_24e1b9c0abb4/events.out.tfevents.1738421414.24e1b9c0abb4.3310.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf420989c808feb2a7e6105edef17d58f900b6fe107c57dcf910a6d3a5ee3b7
+size 12262

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734403097cbdc554e561993c6d77e27d798cd5889d73d05a8f67d4db14bebbc1
+size 5496