End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.8061
-- Accuracy: 0.3846
+- Loss: 0.6711
+- Accuracy: 0.5385
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 1e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -50,21 +50,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7134        | 1.0   | 7    | 0.7379          | 0.3846   |
-| 0.5867        | 2.0   | 14   | 0.9301          | 0.3846   |
-| 0.6482        | 3.0   | 21   | 0.7815          | 0.3846   |
-| 0.6567        | 4.0   | 28   | 0.6915          | 0.6923   |
-| 0.73          | 5.0   | 35   | 0.7552          | 0.3846   |
-| 0.6602        | 6.0   | 42   | 0.7306          | 0.3846   |
-| 0.7           | 7.0   | 49   | 0.7854          | 0.3846   |
-| 0.7287        | 8.0   | 56   | 0.8455          | 0.3846   |
-| 0.6334        | 9.0   | 63   | 0.8219          | 0.3846   |
-| 0.7131        | 10.0  | 70   | 0.8342          | 0.3846   |
-| 0.709         | 11.0  | 77   | 0.8143          | 0.3846   |
-| 0.6305        | 12.0  | 84   | 0.8078          | 0.3846   |
-| 0.7037        | 13.0  | 91   | 0.8104          | 0.3846   |
-| 0.6274        | 14.0  | 98   | 0.8035          | 0.3846   |
-| 0.6255        | 15.0  | 105  | 0.8061          | 0.3846   |
+| 0.697         | 1.0   | 7    | 0.6964          | 0.3846   |
+| 0.667         | 2.0   | 14   | 0.6996          | 0.3846   |
+| 0.6334        | 3.0   | 21   | 0.7151          | 0.3846   |
+| 0.6045        | 4.0   | 28   | 0.7357          | 0.3846   |
+| 0.6263        | 5.0   | 35   | 0.7421          | 0.3846   |
+| 0.549         | 6.0   | 42   | 0.7133          | 0.3846   |
+| 0.5676        | 7.0   | 49   | 0.7031          | 0.3846   |
+| 0.5625        | 8.0   | 56   | 0.7056          | 0.3846   |
+| 0.5074        | 9.0   | 63   | 0.6912          | 0.4615   |
+| 0.5372        | 10.0  | 70   | 0.6904          | 0.4615   |
+| 0.5103        | 11.0  | 77   | 0.6856          | 0.4615   |
+| 0.47          | 12.0  | 84   | 0.6895          | 0.4615   |
+| 0.4951        | 13.0  | 91   | 0.6855          | 0.4615   |
+| 0.4505        | 14.0  | 98   | 0.6744          | 0.5385   |
+| 0.4395        | 15.0  | 105  | 0.6711          | 0.5385   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd65a2e903993d91e744982f4c3b2b71ad659860958bbb6107af39e6bde13c7c
+oid sha256:f2e5d04370bf47884801b387e141413b6ec69f3f49cabf851d01b32421c4508c
 size 378302360

tmp-checkpoint-4/config.json

@@ -0,0 +1,126 @@
+{
+  "_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": "healthy",
+    "1": "pathological"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "healthy": 0,
+    "pathological": 1
+  },
+  "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": "4.37.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

tmp-checkpoint-4/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8608ccc0500f63bb2980f66748d2c48ce0ffcd0c271b3c30919117462141607
+size 378302360

tmp-checkpoint-4/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d331120325828fc2740b11a392dc4978511d0791f99a4962f0d7bf1e3ae7b43
+size 600637568

tmp-checkpoint-4/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
+}

tmp-checkpoint-4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f474d3e9461269dada32c3424349fc1db96c76db7611856040383f2622bdf3
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db4ee2604ce6ddd1a6c211924c96d49ac5544822292d18f0c99e2841a33069ca
+oid sha256:b9f3c1cdb3575623103f822ff473340f0c47568885e2b6c18c719959e13d681b
 size 4664