End of training

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: my_awesome_model
+  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. -->
+
+# my_awesome_model
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3905
+- Accuracy: 0.9158
+
+## 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: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.7774        | 0.99  | 27   | 1.6708          | 0.4856   |
+| 1.3665        | 1.98  | 54   | 1.1744          | 0.7739   |
+| 0.9392        | 2.97  | 81   | 0.8476          | 0.8374   |
+| 0.7654        | 4.0   | 109  | 0.6763          | 0.8570   |
+| 0.5547        | 4.99  | 136  | 0.5508          | 0.8870   |
+| 0.4244        | 5.98  | 163  | 0.4724          | 0.8985   |
+| 0.371         | 6.97  | 190  | 0.4536          | 0.9054   |
+| 0.3302        | 8.0   | 218  | 0.4224          | 0.9031   |
+| 0.2883        | 8.99  | 245  | 0.3924          | 0.9146   |
+| 0.2642        | 9.91  | 270  | 0.3905          | 0.9158   |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,134 @@
+{
+  "_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": "neutral",
+    "1": "disgust",
+    "2": "fear",
+    "3": "sad",
+    "4": "happy",
+    "5": "angry"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "angry": "5",
+    "disgust": "1",
+    "fear": "2",
+    "happy": "4",
+    "neutral": "0",
+    "sad": "3"
+  },
+  "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": "4.37.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39dfd6a8567301615224e7e1c39937ffd8005a73a2a240a403080a06241c1ce2
+size 378306480

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
+}

runs/Feb05_14-10-09_28b95520cceb/events.out.tfevents.1707142211.28b95520cceb.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570d321157d743102b4e258ab25110ade35f4f55a1f2e8443ecc35fbb34714aa
+size 11514

runs/Feb05_14-22-30_28b95520cceb/events.out.tfevents.1707142951.28b95520cceb.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efec876fcc8a8356a284a00c05b9c3a34d726634afac2a22a50f99e80d0d3785
+size 14093

runs/Feb05_14-22-30_28b95520cceb/events.out.tfevents.1707146476.28b95520cceb.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36d7aaccc729bda21d51af0566247f5c0f21ded9cbe6562548d0d2a086b92b5
+size 411

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269155a8b23128568aa6a7e3037bce01d29f316353d614b0b331db96514b85c6
+size 4728