End of training

README.md

@@ -3,6 +3,7 @@ library_name: transformers
 license: apache-2.0
 base_model: facebook/wav2vec2-base
 tags:
+- audio-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-base-wakeword
 
-This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
 It achieves the following results on the evaluation set:
 - Loss: 6.0557
 - Accuracy: 0.6140

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.6140350877192983,
+    "eval_loss": 6.055716037750244,
+    "eval_runtime": 1.2768,
+    "eval_samples_per_second": 44.644,
+    "eval_steps_per_second": 1.566,
+    "total_flos": 2.286384817968e+16,
+    "train_loss": 1.5362668991088868,
+    "train_runtime": 34.37,
+    "train_samples_per_second": 73.174,
+    "train_steps_per_second": 0.145
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.6140350877192983,
+    "eval_loss": 6.055716037750244,
+    "eval_runtime": 1.2768,
+    "eval_samples_per_second": 44.644,
+    "eval_steps_per_second": 1.566
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.286384817968e+16,
+    "train_loss": 1.5362668991088868,
+    "train_runtime": 34.37,
+    "train_samples_per_second": 73.174,
+    "train_steps_per_second": 0.145
+}

trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.6140350877192983,
+  "best_model_checkpoint": "wav2vec2-base-wakeword/checkpoint-5",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.0,
+      "eval_loss": 6.203948020935059,
+      "eval_runtime": 1.1877,
+      "eval_samples_per_second": 47.993,
+      "eval_steps_per_second": 1.684,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.017543859649122806,
+      "eval_loss": 6.150973320007324,
+      "eval_runtime": 1.1793,
+      "eval_samples_per_second": 48.332,
+      "eval_steps_per_second": 1.696,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.43859649122807015,
+      "eval_loss": 6.095394611358643,
+      "eval_runtime": 1.2414,
+      "eval_samples_per_second": 45.915,
+      "eval_steps_per_second": 1.611,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5789473684210527,
+      "eval_loss": 6.068804740905762,
+      "eval_runtime": 1.2218,
+      "eval_samples_per_second": 46.654,
+      "eval_steps_per_second": 1.637,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6140350877192983,
+      "eval_loss": 6.055716037750244,
+      "eval_runtime": 1.3159,
+      "eval_samples_per_second": 43.317,
+      "eval_steps_per_second": 1.52,
+      "step": 5
+    },
+    {
+      "epoch": 5.0,
+      "step": 5,
+      "total_flos": 2.286384817968e+16,
+      "train_loss": 1.5362668991088868,
+      "train_runtime": 34.37,
+      "train_samples_per_second": 73.174,
+      "train_steps_per_second": 0.145
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.286384817968e+16,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}