End of training

README.md

@@ -1,21 +1,24 @@
 ---
+language:
+- bn
 license: mit
 base_model: bangla-speech-processing/BanglaASR
 tags:
+- whisper-event
 - generated_from_trainer
 datasets:
-- common_voice_16_0
+- mozilla-foundation/common_voice_16_0
 metrics:
 - wer
 model-index:
-- name: arun100/whisper-small-derived-bn-1
+- name: Whisper Base Hindi
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: common_voice_16_0
-      type: common_voice_16_0
+      name: mozilla-foundation/common_voice_16_0 bn
+      type: mozilla-foundation/common_voice_16_0
       config: bn
       split: test
       args: bn
@@ -28,9 +31,9 @@ model-index:
 <!-- 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. -->
 
-# bangla-speech-processing/BanglaASR
+# Whisper Base Hindi
 
-This model is a fine-tuned version of [bangla-speech-processing/BanglaASR](https://huggingface.co/bangla-speech-processing/BanglaASR) on the common_voice_16_0 dataset.
+This model is a fine-tuned version of [bangla-speech-processing/BanglaASR](https://huggingface.co/bangla-speech-processing/BanglaASR) on the mozilla-foundation/common_voice_16_0 bn dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.1281
 - Wer: 3.7265

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.12812651693820953,
+    "eval_runtime": 5982.3035,
+    "eval_samples_per_second": 1.557,
+    "eval_steps_per_second": 0.097,
+    "eval_wer": 3.7265218830814386,
+    "train_loss": 0.144483003616333,
+    "train_runtime": 13002.902,
+    "train_samples_per_second": 0.492,
+    "train_steps_per_second": 0.008
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.12812651693820953,
+    "eval_runtime": 5982.3035,
+    "eval_samples_per_second": 1.557,
+    "eval_steps_per_second": 0.097,
+    "eval_wer": 3.7265218830814386
+}

runs/Jan21_22-04-28_ip-172-31-23-125/events.out.tfevents.1705893691.ip-172-31-23-125.29447.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4070c463c0dfc4c8706c616deeac87bd7526a09cda9cc074f8e56917cd78d173
+size 400

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.144483003616333,
+    "train_runtime": 13002.902,
+    "train_samples_per_second": 0.492,
+    "train_steps_per_second": 0.008
+}

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 3.7265218830814386,
+  "best_model_checkpoint": "./checkpoint-100",
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 5e-08,
+      "loss": 0.1602,
+      "step": 25
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1e-07,
+      "loss": 0.1588,
+      "step": 50
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.14945247769355774,
+      "eval_runtime": 6007.4304,
+      "eval_samples_per_second": 1.55,
+      "eval_steps_per_second": 0.097,
+      "eval_wer": 3.7649995973262462,
+      "step": 50
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5e-08,
+      "loss": 0.1321,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.1267,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.12812651693820953,
+      "eval_runtime": 5985.3223,
+      "eval_samples_per_second": 1.556,
+      "eval_steps_per_second": 0.097,
+      "eval_wer": 3.7265218830814386,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 1.846946562048e+18,
+      "train_loss": 0.144483003616333,
+      "train_runtime": 13002.902,
+      "train_samples_per_second": 0.492,
+      "train_steps_per_second": 0.008
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 50,
+  "total_flos": 1.846946562048e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}