End of training

README.md

@@ -1,7 +1,11 @@
 ---
+language:
+- tr
 license: apache-2.0
 base_model: facebook/wav2vec2-large-xlsr-53
 tags:
+- automatic-speech-recognition
+- mozilla-foundation/common_voice_16_0
 - generated_from_trainer
 datasets:
 - common_voice_16_0
@@ -14,15 +18,15 @@ model-index:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: common_voice_16_0
+      name: MOZILLA-FOUNDATION/COMMON_VOICE_16_0 - TR
       type: common_voice_16_0
       config: tr
       split: test[0:250]
-      args: tr
+      args: 'Config: tr, Training split: train[0:3000], Eval split: test[0:250]'
     metrics:
     - name: Wer
       type: wer
-      value: 0.9729938271604939
+      value: 0.9382716049382716
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +34,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-common_voice-tr-demo-mini
 
-This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_16_0 dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MOZILLA-FOUNDATION/COMMON_VOICE_16_0 - TR dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2465
-- Wer: 0.9730
+- Loss: 0.9823
+- Wer: 0.9383
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.992,
+    "eval_loss": 0.9822820425033569,
+    "eval_runtime": 8.381,
+    "eval_samples": 250,
+    "eval_samples_per_second": 29.829,
+    "eval_steps_per_second": 3.818,
+    "eval_wer": 0.9382716049382716,
+    "total_flos": 1.0050115218562714e+18,
+    "train_loss": 4.179523862406957,
+    "train_runtime": 1022.6563,
+    "train_samples": 3000,
+    "train_samples_per_second": 8.801,
+    "train_steps_per_second": 0.549
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.992,
+    "eval_loss": 0.9822820425033569,
+    "eval_runtime": 8.381,
+    "eval_samples": 250,
+    "eval_samples_per_second": 29.829,
+    "eval_steps_per_second": 3.818,
+    "eval_wer": 0.9382716049382716
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.992,
+    "total_flos": 1.0050115218562714e+18,
+    "train_loss": 4.179523862406957,
+    "train_runtime": 1022.6563,
+    "train_samples": 3000,
+    "train_samples_per_second": 8.801,
+    "train_steps_per_second": 0.549
+}

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.992,
+  "eval_steps": 100,
+  "global_step": 561,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 4.023805141448975,
+      "eval_runtime": 9.119,
+      "eval_samples_per_second": 27.415,
+      "eval_steps_per_second": 3.509,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "eval_loss": 3.2450873851776123,
+      "eval_runtime": 8.4082,
+      "eval_samples_per_second": 29.733,
+      "eval_steps_per_second": 3.806,
+      "eval_wer": 1.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 2.9997410774230957,
+      "eval_runtime": 8.4129,
+      "eval_samples_per_second": 29.716,
+      "eval_steps_per_second": 3.804,
+      "eval_wer": 1.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "eval_loss": 1.425586223602295,
+      "eval_runtime": 8.5669,
+      "eval_samples_per_second": 29.182,
+      "eval_steps_per_second": 3.735,
+      "eval_wer": 1.0054012345679013,
+      "step": 400
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.884314775466919,
+      "learning_rate": 0.0002982,
+      "loss": 4.5926,
+      "step": 500
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 1.2465466260910034,
+      "eval_runtime": 610.4372,
+      "eval_samples_per_second": 0.41,
+      "eval_steps_per_second": 0.052,
+      "eval_wer": 0.9729938271604939,
+      "step": 500
+    },
+    {
+      "epoch": 2.992,
+      "step": 561,
+      "total_flos": 1.0050115218562714e+18,
+      "train_loss": 4.179523862406957,
+      "train_runtime": 1022.6563,
+      "train_samples_per_second": 8.801,
+      "train_steps_per_second": 0.549
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 561,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0050115218562714e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}