End of training

README.md

@@ -1,13 +1,33 @@
 ---
+language:
+- hi
 license: apache-2.0
 base_model: facebook/wav2vec2-large-xlsr-53
 tags:
+- automatic-speech-recognition
+- mozilla-foundation/common_voice_15_0
+- mms
 - generated_from_trainer
 datasets:
 - common_voice_15_0
+metrics:
+- wer
 model-index:
 - name: wav2vec2-common_voice-en-demo
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: MOZILLA-FOUNDATION/COMMON_VOICE_15_0 - HI
+      type: common_voice_15_0
+      config: hi
+      split: validation
+      args: 'Config: hi, Training split: train, Eval split: validation'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 1.0018709995076318
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +35,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-common_voice-en-demo
 
-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_15_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_15_0 - HI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 20.2335
+- Wer: 1.0019
 
 ## Model description
 

adapter.eng.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8f7630ac9b159754bf09a63f4c2101535a1287172d38e194eb4ea08c5e32bf
+oid sha256:f16202c0de9c8feeaa1cf336a6630fc754a6ed13dca6fb50a2468e0c7c3f94d2
 size 3918936

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 5.0,
-    "eval_loss": 3.4593591690063477,
-    "eval_runtime": 163.4642,
+    "epoch": 1.0,
+    "eval_loss": 20.233524322509766,
+    "eval_runtime": 167.9773,
     "eval_samples": 2416,
-    "eval_samples_per_second": 14.78,
-    "eval_steps_per_second": 1.847,
-    "eval_wer": 1.0,
-    "total_flos": 3.0520251232525025e+18,
-    "train_loss": 7.648091746363146,
-    "train_runtime": 3314.4653,
+    "eval_samples_per_second": 14.383,
+    "eval_steps_per_second": 1.798,
+    "eval_wer": 1.0018709995076318,
+    "total_flos": 6.105598680744346e+17,
+    "train_loss": 18.518729795258622,
+    "train_runtime": 625.4328,
     "train_samples": 4630,
-    "train_samples_per_second": 6.985,
-    "train_steps_per_second": 0.219
+    "train_samples_per_second": 7.403,
+    "train_steps_per_second": 0.232
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 5.0,
-    "eval_loss": 3.4593591690063477,
-    "eval_runtime": 163.4642,
+    "epoch": 1.0,
+    "eval_loss": 20.233524322509766,
+    "eval_runtime": 167.9773,
     "eval_samples": 2416,
-    "eval_samples_per_second": 14.78,
-    "eval_steps_per_second": 1.847,
-    "eval_wer": 1.0
+    "eval_samples_per_second": 14.383,
+    "eval_steps_per_second": 1.798,
+    "eval_wer": 1.0018709995076318
 }

runs/May24_13-44-28_05119ae56480/events.out.tfevents.1716559249.05119ae56480.2817.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1182a66fbf3e89b77dd386abe585ba9c3521b30e40c773a7181b58f5acefd2
+size 406

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 5.0,
-    "total_flos": 3.0520251232525025e+18,
-    "train_loss": 7.648091746363146,
-    "train_runtime": 3314.4653,
+    "epoch": 1.0,
+    "total_flos": 6.105598680744346e+17,
+    "train_loss": 18.518729795258622,
+    "train_runtime": 625.4328,
     "train_samples": 4630,
-    "train_samples_per_second": 6.985,
-    "train_steps_per_second": 0.219
+    "train_samples_per_second": 7.403,
+    "train_steps_per_second": 0.232
 }

trainer_state.json

@@ -1,97 +1,36 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 1.0,
   "eval_steps": 100,
-  "global_step": 725,
+  "global_step": 145,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.6896551724137931,
-      "eval_loss": 21.946964263916016,
-      "eval_runtime": 163.3947,
-      "eval_samples_per_second": 14.786,
-      "eval_steps_per_second": 1.848,
+      "eval_loss": 21.947891235351562,
+      "eval_runtime": 168.4847,
+      "eval_samples_per_second": 14.34,
+      "eval_steps_per_second": 1.792,
       "eval_wer": 1.0003446578040374,
       "step": 100
     },
     {
-      "epoch": 1.3793103448275863,
-      "eval_loss": 17.29347801208496,
-      "eval_runtime": 162.2438,
-      "eval_samples_per_second": 14.891,
-      "eval_steps_per_second": 1.861,
-      "eval_wer": 1.0,
-      "step": 200
-    },
-    {
-      "epoch": 2.0689655172413794,
-      "eval_loss": 3.521054267883301,
-      "eval_runtime": 161.4701,
-      "eval_samples_per_second": 14.963,
-      "eval_steps_per_second": 1.87,
-      "eval_wer": 1.0,
-      "step": 300
-    },
-    {
-      "epoch": 2.7586206896551726,
-      "eval_loss": 3.507359027862549,
-      "eval_runtime": 160.5709,
-      "eval_samples_per_second": 15.046,
-      "eval_steps_per_second": 1.881,
-      "eval_wer": 1.0,
-      "step": 400
-    },
-    {
-      "epoch": 3.4482758620689653,
-      "grad_norm": 0.5087113976478577,
-      "learning_rate": 0.00029759999999999997,
-      "loss": 9.5434,
-      "step": 500
-    },
-    {
-      "epoch": 3.4482758620689653,
-      "eval_loss": 3.4881255626678467,
-      "eval_runtime": 161.0375,
-      "eval_samples_per_second": 15.003,
-      "eval_steps_per_second": 1.875,
-      "eval_wer": 1.0,
-      "step": 500
-    },
-    {
-      "epoch": 4.137931034482759,
-      "eval_loss": 3.487558603286743,
-      "eval_runtime": 159.8397,
-      "eval_samples_per_second": 15.115,
-      "eval_steps_per_second": 1.889,
-      "eval_wer": 1.0,
-      "step": 600
-    },
-    {
-      "epoch": 4.827586206896552,
-      "eval_loss": 3.489640951156616,
-      "eval_runtime": 160.42,
-      "eval_samples_per_second": 15.06,
-      "eval_steps_per_second": 1.883,
-      "eval_wer": 1.0,
-      "step": 700
-    },
-    {
-      "epoch": 5.0,
-      "step": 725,
-      "total_flos": 3.0520251232525025e+18,
-      "train_loss": 7.648091746363146,
-      "train_runtime": 3314.4653,
-      "train_samples_per_second": 6.985,
-      "train_steps_per_second": 0.219
+      "epoch": 1.0,
+      "step": 145,
+      "total_flos": 6.105598680744346e+17,
+      "train_loss": 18.518729795258622,
+      "train_runtime": 625.4328,
+      "train_samples_per_second": 7.403,
+      "train_steps_per_second": 0.232
     }
   ],
   "logging_steps": 500,
-  "max_steps": 725,
+  "max_steps": 145,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 1,
   "save_steps": 400,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -105,7 +44,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.0520251232525025e+18,
+  "total_flos": 6.105598680744346e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null