End of training

README.md

@@ -4,11 +4,24 @@ license: apache-2.0
 base_model: openai/whisper-base
 tags:
 - generated_from_trainer
+datasets:
+- razhan/DOLMA-speech
 metrics:
 - wer
 model-index:
 - name: whisper-base-mzn
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: razhan/DOLMA-speech mazanderani
+      type: razhan/DOLMA-speech
+      args: mazanderani
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.8149625935162095
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,7 +29,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-base-mzn
 
-This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
+This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the razhan/DOLMA-speech mazanderani dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.3368
 - Wer: 0.8150

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_cer": 0.31731325998841925,
+    "eval_loss": 1.3368451595306396,
+    "eval_runtime": 16.8714,
+    "eval_samples": 249,
+    "eval_samples_per_second": 14.759,
+    "eval_steps_per_second": 0.059,
+    "eval_wer": 0.8149625935162095,
+    "total_flos": 3.735935662717665e+17,
+    "train_loss": 1.820040480295817,
+    "train_runtime": 437.1257,
+    "train_samples": 875,
+    "train_samples_per_second": 10.009,
+    "train_steps_per_second": 0.034
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_cer": 0.31731325998841925,
+    "eval_loss": 1.3368451595306396,
+    "eval_runtime": 16.8714,
+    "eval_samples": 249,
+    "eval_samples_per_second": 14.759,
+    "eval_steps_per_second": 0.059,
+    "eval_wer": 0.8149625935162095
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3.735935662717665e+17,
+    "train_loss": 1.820040480295817,
+    "train_runtime": 437.1257,
+    "train_samples": 875,
+    "train_samples_per_second": 10.009,
+    "train_steps_per_second": 0.034
+}

trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_cer": 0.7427909669947886,
+      "eval_loss": 2.1575405597686768,
+      "eval_runtime": 18.939,
+      "eval_samples_per_second": 13.147,
+      "eval_steps_per_second": 0.053,
+      "eval_wer": 1.3605985037406483,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "eval_cer": 0.7427909669947886,
+      "eval_loss": 2.1575405597686768,
+      "eval_runtime": 18.0996,
+      "eval_samples_per_second": 13.757,
+      "eval_steps_per_second": 0.055,
+      "eval_wer": 1.3605985037406483,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_cer": 0.6618413433700058,
+      "eval_loss": 1.6346477270126343,
+      "eval_runtime": 18.3638,
+      "eval_samples_per_second": 13.559,
+      "eval_steps_per_second": 0.054,
+      "eval_wer": 0.9451371571072319,
+      "step": 9
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 18.044103622436523,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 2.0051,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "eval_cer": 0.3593514765489288,
+      "eval_loss": 1.4320271015167236,
+      "eval_runtime": 18.9886,
+      "eval_samples_per_second": 13.113,
+      "eval_steps_per_second": 0.053,
+      "eval_wer": 0.8413965087281795,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "eval_cer": 0.31731325998841925,
+      "eval_loss": 1.3368451595306396,
+      "eval_runtime": 17.4736,
+      "eval_samples_per_second": 14.25,
+      "eval_steps_per_second": 0.057,
+      "eval_wer": 0.8149625935162095,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "step": 15,
+      "total_flos": 3.735935662717665e+17,
+      "train_loss": 1.820040480295817,
+      "train_runtime": 437.1257,
+      "train_samples_per_second": 10.009,
+      "train_steps_per_second": 0.034
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 15,
+  "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": 3.735935662717665e+17,
+  "train_batch_size": 192,
+  "trial_name": null,
+  "trial_params": null
+}