End of training

README.md

@@ -1,7 +1,12 @@
 ---
+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
@@ -14,11 +19,11 @@ model-index:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: common_voice_15_0
+      name: MOZILLA-FOUNDATION/COMMON_VOICE_15_0 - HI
       type: common_voice_15_0
       config: hi
       split: validation
-      args: hi
+      args: 'Config: hi, Training split: train, Eval split: validation'
     metrics:
     - name: Wer
       type: wer
@@ -30,9 +35,9 @@ 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: 3.4896
+- Loss: 3.4594
 - Wer: 1.0
 
 ## Model description

adapter.eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8f7630ac9b159754bf09a63f4c2101535a1287172d38e194eb4ea08c5e32bf
+size 3918936

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 3.4593591690063477,
+    "eval_runtime": 163.4642,
+    "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,
+    "train_samples": 4630,
+    "train_samples_per_second": 6.985,
+    "train_steps_per_second": 0.219
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 3.4593591690063477,
+    "eval_runtime": 163.4642,
+    "eval_samples": 2416,
+    "eval_samples_per_second": 14.78,
+    "eval_steps_per_second": 1.847,
+    "eval_wer": 1.0
+}

runs/May24_12-09-42_6469d6b4aa01/events.out.tfevents.1716556225.6469d6b4aa01.9812.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44beaf84c3d89169aa95e4c9b57cb2bade49ec40305ce487c2bf91ed136720f5
+size 406

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3.0520251232525025e+18,
+    "train_loss": 7.648091746363146,
+    "train_runtime": 3314.4653,
+    "train_samples": 4630,
+    "train_samples_per_second": 6.985,
+    "train_steps_per_second": 0.219
+}

trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 100,
+  "global_step": 725,
+  "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_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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 725,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 3.0520251232525025e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}