Upload 6 files

README.md

@@ -0,0 +1,78 @@
+---
+license: apache-2.0
+tags:
+- audio-classification
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- f1
+model-index:
+- name: wav2vec2-base
+  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. -->
+
+# wav2vec2-base
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the galsenai/waxal_dataset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7504
+- Accuracy: 0.8632
+- Precision: 0.9380
+- F1: 0.8954
+
+## 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: 30
+- eval_batch_size: 30
+- seed: 0
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 120
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 32.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|
+| 4.3647        | 2.53  | 500  | 4.8202          | 0.0117   | 0.0134    | 0.0032 |
+| 2.6202        | 5.05  | 1000 | 4.2238          | 0.0625   | 0.0781    | 0.0355 |
+| 1.38          | 7.58  | 1500 | 3.6392          | 0.2941   | 0.5211    | 0.3174 |
+| 0.8601        | 10.1  | 2000 | 2.7953          | 0.4907   | 0.7446    | 0.5657 |
+| 0.5645        | 12.63 | 2500 | 1.9829          | 0.6862   | 0.8363    | 0.7421 |
+| 0.4009        | 15.15 | 3000 | 1.4535          | 0.7635   | 0.9000    | 0.8174 |
+| 0.3054        | 17.68 | 3500 | 1.1426          | 0.7882   | 0.9058    | 0.8298 |
+| 0.2448        | 20.2  | 4000 | 0.9860          | 0.8189   | 0.9206    | 0.8593 |
+| 0.2116        | 22.73 | 4500 | 0.8820          | 0.8325   | 0.9261    | 0.8711 |
+| 0.1863        | 25.25 | 5000 | 0.8191          | 0.8465   | 0.9366    | 0.8848 |
+| 0.1701        | 27.78 | 5500 | 0.7504          | 0.8632   | 0.9380    | 0.8954 |
+| 0.1558        | 30.3  | 6000 | 0.7665          | 0.8609   | 0.9398    | 0.8956 |
+
+
+### Framework versions
+
+- Transformers 4.27.0.dev0
+- Pytorch 1.11.0+cu113
+- Datasets 2.9.1.dev0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 32.0,
+    "eval_accuracy": 0.8632057597574839,
+    "eval_f1": 0.8953598709937869,
+    "eval_loss": 0.7504324913024902,
+    "eval_precision": 0.9379743242290526,
+    "eval_runtime": 101.1391,
+    "eval_samples_per_second": 26.093,
+    "eval_steps_per_second": 0.87,
+    "train_loss": 0.9127645113251426,
+    "train_runtime": 39385.6266,
+    "train_samples_per_second": 19.295,
+    "train_steps_per_second": 0.161
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 32.0,
+    "eval_accuracy": 0.8632057597574839,
+    "eval_f1": 0.8953598709937869,
+    "eval_loss": 0.7504324913024902,
+    "eval_precision": 0.9379743242290526,
+    "eval_runtime": 101.1391,
+    "eval_samples_per_second": 26.093,
+    "eval_steps_per_second": 0.87
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 32.0,
+    "train_loss": 0.9127645113251426,
+    "train_runtime": 39385.6266,
+    "train_samples_per_second": 19.295,
+    "train_steps_per_second": 0.161
+}

trainer_state.json

@@ -0,0 +1,229 @@
+{
+  "best_metric": 0.8632057597574839,
+  "best_model_checkpoint": "wav2vec2-base/checkpoint-5500",
+  "epoch": 32.0,
+  "global_step": 6336,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.53,
+      "learning_rate": 2.3659305993690853e-05,
+      "loss": 4.3647,
+      "step": 500
+    },
+    {
+      "epoch": 2.53,
+      "eval_accuracy": 0.011746873815839333,
+      "eval_f1": 0.0031732207431106035,
+      "eval_loss": 4.820202350616455,
+      "eval_precision": 0.013376466669245454,
+      "eval_runtime": 109.2278,
+      "eval_samples_per_second": 24.161,
+      "eval_steps_per_second": 0.806,
+      "step": 500
+    },
+    {
+      "epoch": 5.05,
+      "learning_rate": 2.8074359873728517e-05,
+      "loss": 2.6202,
+      "step": 1000
+    },
+    {
+      "epoch": 5.05,
+      "eval_accuracy": 0.06252368321333839,
+      "eval_f1": 0.035540285078168796,
+      "eval_loss": 4.223803520202637,
+      "eval_precision": 0.07806791077535753,
+      "eval_runtime": 106.4124,
+      "eval_samples_per_second": 24.8,
+      "eval_steps_per_second": 0.827,
+      "step": 1000
+    },
+    {
+      "epoch": 7.58,
+      "learning_rate": 2.5443703963521573e-05,
+      "loss": 1.38,
+      "step": 1500
+    },
+    {
+      "epoch": 7.58,
+      "eval_accuracy": 0.2940507768093975,
+      "eval_f1": 0.31740258677108446,
+      "eval_loss": 3.6391522884368896,
+      "eval_precision": 0.5210640247794917,
+      "eval_runtime": 107.4509,
+      "eval_samples_per_second": 24.56,
+      "eval_steps_per_second": 0.819,
+      "step": 1500
+    },
+    {
+      "epoch": 10.1,
+      "learning_rate": 2.2813048053314627e-05,
+      "loss": 0.8601,
+      "step": 2000
+    },
+    {
+      "epoch": 10.1,
+      "eval_accuracy": 0.4907161803713528,
+      "eval_f1": 0.5656528274556744,
+      "eval_loss": 2.7952940464019775,
+      "eval_precision": 0.7446099073666071,
+      "eval_runtime": 108.5624,
+      "eval_samples_per_second": 24.309,
+      "eval_steps_per_second": 0.811,
+      "step": 2000
+    },
+    {
+      "epoch": 12.63,
+      "learning_rate": 2.0182392143107683e-05,
+      "loss": 0.5645,
+      "step": 2500
+    },
+    {
+      "epoch": 12.63,
+      "eval_accuracy": 0.6862447896930656,
+      "eval_f1": 0.7421301241460049,
+      "eval_loss": 1.9828652143478394,
+      "eval_precision": 0.836316121433408,
+      "eval_runtime": 101.2702,
+      "eval_samples_per_second": 26.059,
+      "eval_steps_per_second": 0.869,
+      "step": 2500
+    },
+    {
+      "epoch": 15.15,
+      "learning_rate": 1.7551736232900737e-05,
+      "loss": 0.4009,
+      "step": 3000
+    },
+    {
+      "epoch": 15.15,
+      "eval_accuracy": 0.7635467980295566,
+      "eval_f1": 0.8174024577222706,
+      "eval_loss": 1.453549861907959,
+      "eval_precision": 0.9000157931943787,
+      "eval_runtime": 107.7592,
+      "eval_samples_per_second": 24.49,
+      "eval_steps_per_second": 0.817,
+      "step": 3000
+    },
+    {
+      "epoch": 17.68,
+      "learning_rate": 1.4921080322693792e-05,
+      "loss": 0.3054,
+      "step": 3500
+    },
+    {
+      "epoch": 17.68,
+      "eval_accuracy": 0.7881773399014779,
+      "eval_f1": 0.8297806830083403,
+      "eval_loss": 1.1425673961639404,
+      "eval_precision": 0.905752007054303,
+      "eval_runtime": 106.3252,
+      "eval_samples_per_second": 24.82,
+      "eval_steps_per_second": 0.828,
+      "step": 3500
+    },
+    {
+      "epoch": 20.2,
+      "learning_rate": 1.2290424412486847e-05,
+      "loss": 0.2448,
+      "step": 4000
+    },
+    {
+      "epoch": 20.2,
+      "eval_accuracy": 0.8188707843880257,
+      "eval_f1": 0.8593023386044745,
+      "eval_loss": 0.9859854578971863,
+      "eval_precision": 0.9206175798530246,
+      "eval_runtime": 107.5476,
+      "eval_samples_per_second": 24.538,
+      "eval_steps_per_second": 0.818,
+      "step": 4000
+    },
+    {
+      "epoch": 22.73,
+      "learning_rate": 9.659768502279902e-06,
+      "loss": 0.2116,
+      "step": 4500
+    },
+    {
+      "epoch": 22.73,
+      "eval_accuracy": 0.8325123152709359,
+      "eval_f1": 0.8711410752519451,
+      "eval_loss": 0.8820037841796875,
+      "eval_precision": 0.9261488248866633,
+      "eval_runtime": 107.1712,
+      "eval_samples_per_second": 24.624,
+      "eval_steps_per_second": 0.821,
+      "step": 4500
+    },
+    {
+      "epoch": 25.25,
+      "learning_rate": 7.029112592072957e-06,
+      "loss": 0.1863,
+      "step": 5000
+    },
+    {
+      "epoch": 25.25,
+      "eval_accuracy": 0.8465327775672603,
+      "eval_f1": 0.8848136570821419,
+      "eval_loss": 0.8190948367118835,
+      "eval_precision": 0.9366165612791744,
+      "eval_runtime": 101.4217,
+      "eval_samples_per_second": 26.02,
+      "eval_steps_per_second": 0.868,
+      "step": 5000
+    },
+    {
+      "epoch": 27.78,
+      "learning_rate": 4.398456681866012e-06,
+      "loss": 0.1701,
+      "step": 5500
+    },
+    {
+      "epoch": 27.78,
+      "eval_accuracy": 0.8632057597574839,
+      "eval_f1": 0.8953598709937869,
+      "eval_loss": 0.7504324913024902,
+      "eval_precision": 0.9379743242290526,
+      "eval_runtime": 106.5347,
+      "eval_samples_per_second": 24.771,
+      "eval_steps_per_second": 0.826,
+      "step": 5500
+    },
+    {
+      "epoch": 30.3,
+      "learning_rate": 1.767800771659067e-06,
+      "loss": 0.1558,
+      "step": 6000
+    },
+    {
+      "epoch": 30.3,
+      "eval_accuracy": 0.8609321712769988,
+      "eval_f1": 0.8955970854963186,
+      "eval_loss": 0.7665356993675232,
+      "eval_precision": 0.9398430168070748,
+      "eval_runtime": 106.7434,
+      "eval_samples_per_second": 24.723,
+      "eval_steps_per_second": 0.824,
+      "step": 6000
+    },
+    {
+      "epoch": 32.0,
+      "step": 6336,
+      "total_flos": 3.804433776973221e+19,
+      "train_loss": 0.9127645113251426,
+      "train_runtime": 39385.6266,
+      "train_samples_per_second": 19.295,
+      "train_steps_per_second": 0.161
+    }
+  ],
+  "max_steps": 6336,
+  "num_train_epochs": 32,
+  "total_flos": 3.804433776973221e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:749657517aeb2dad9dcddd9525416d7352d8c24d5d4f9b9c87e67bc96d23380c
+size 3503