HamdanXI/w2v2_fb_labeled

README.md

@@ -1,8 +1,10 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: facebook/wav2vec2-base-960h
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: results
   results: []
@@ -13,7 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5525
+- Accuracy: 0.5206
 
 ## Model description
 
@@ -32,21 +37,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
+- learning_rate: 0.0001
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 1.5813        | 1.8762 | 500  | 1.5525          | 0.5206   |
 
 
 ### Framework versions
 
-- Transformers 4.35.0
-- Pytorch 2.1.0+cu118
-- Datasets 2.14.6
-- Tokenizers 0.14.1
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -1,26 +1,132 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "facebook/wav2vec2-base-960h",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
   "architectures": [
-    "BertForMaskedLM"
+    "Wav2Vec2ForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
+  "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_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": "wav2vec2",
+  "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,
-  "position_embedding_type": "absolute",
+  "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": "4.35.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30524
+  "transformers_version": "4.40.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c518f01f65f773edfc4c8ba762b390df8c638ab2e9d0bd15dc369c0f727de2
-size 438087048
+oid sha256:b2fd207087b4eff6b40547b6e73ab95b205afe263ca4b61f330aea5ee4447d19
+size 378309564

runs/Apr30_20-10-13_7db393de5383/events.out.tfevents.1714507814.7db393de5383.729.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6adb3fac1d69f19ae885b3fc04d60907312d5426e2775c178786c69d3b5689
+size 6516

runs/Apr30_20-12-24_7db393de5383/events.out.tfevents.1714507944.7db393de5383.729.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c6e641bb924b0439ff34f8212162c3d3734dd98acf4d7ab9235a5f11d69502
+size 6478

runs/Apr30_20-17-23_7db393de5383/events.out.tfevents.1714508244.7db393de5383.3206.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb800c2cc62989f98f703a770158669c52de2077fea1bfd894f893788a0202cf
+size 4184

runs/Apr30_20-20-19_7db393de5383/events.out.tfevents.1714508420.7db393de5383.4036.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a926effef80e607b95394d96f3e0bdd2ae9d46a3ed1270cb3556d41f45445b8f
+size 4184

runs/Apr30_20-21-00_7db393de5383/events.out.tfevents.1714508461.7db393de5383.4551.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205b328be468fe8f157b41e0c6744aeec928c0514055205b61aae337676d90ae
+size 6478

runs/Apr30_20-21-19_7db393de5383/events.out.tfevents.1714508480.7db393de5383.4551.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999a4e667055d13c14a2de268db241350e77c08958e532286ce9b7989533f66b
+size 7366

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a178dc70b82a3ffecbe9f8f9b75e16f76c6d6b630f620ad1ddc3cd6edc0947
-size 4536
+oid sha256:0c7a7f87c86c164b7b3e3bae033e8936d39c7294f4f07d521d63edbe85f7d62e
+size 4984