End of training

README.md

@@ -1,7 +1,12 @@
 ---
+language:
+- tw
 license: apache-2.0
 base_model: facebook/wav2vec2-xls-r-300m
 tags:
+- automatic-speech-recognition
+- mozilla-foundation/common_voice_17_0
+- mms
 - generated_from_trainer
 datasets:
 - common_voice_17_0
@@ -14,11 +19,11 @@ model-index:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: common_voice_17_0
+      name: MOZILLA-FOUNDATION/COMMON_VOICE_17_0 - TW
       type: common_voice_17_0
       config: tw
       split: None
-      args: tw
+      args: 'Config: tw, Training split: train, Eval split: validation+test'
     metrics:
     - name: Wer
       type: wer
@@ -30,9 +35,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-twi-adapter
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_17_0 dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_17_0 - TW dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4281
+- Loss: 2.4092
 - Wer: 1.0
 - Cer: 1.0
 

adapter.aka.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7664ed8cbab872e1072a86fa0bf31d93a62cb3824ce10e27599544797e4bc49a
-size 3590904
+oid sha256:dd8f507e47e198eacd2db4170d87b37cac423669c10ba32972457fca6b52835e
+size 3615512

all_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 4.0,
-    "eval_cer": 5.130434782608695,
-    "eval_loss": 35.69469451904297,
-    "eval_runtime": 0.7985,
-    "eval_samples": 3,
-    "eval_samples_per_second": 3.757,
-    "eval_steps_per_second": 1.252,
+    "epoch": 26.666666666666668,
+    "eval_cer": 1.0,
+    "eval_loss": 2.409198522567749,
+    "eval_runtime": 0.9391,
+    "eval_samples": 9,
+    "eval_samples_per_second": 9.584,
+    "eval_steps_per_second": 1.065,
     "eval_wer": 1.0,
-    "total_flos": 3.89806936817664e+16,
-    "train_loss": 14.43960952758789,
-    "train_runtime": 61.1436,
-    "train_samples": 53,
-    "train_samples_per_second": 3.467,
-    "train_steps_per_second": 0.131
+    "total_flos": 5.3095066035971686e+17,
+    "train_loss": 7.207664489746094,
+    "train_runtime": 305.0878,
+    "train_samples": 136,
+    "train_samples_per_second": 13.373,
+    "train_steps_per_second": 0.393
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 4.0,
-    "eval_cer": 5.130434782608695,
-    "eval_loss": 35.69469451904297,
-    "eval_runtime": 0.7985,
-    "eval_samples": 3,
-    "eval_samples_per_second": 3.757,
-    "eval_steps_per_second": 1.252,
+    "epoch": 26.666666666666668,
+    "eval_cer": 1.0,
+    "eval_loss": 2.409198522567749,
+    "eval_runtime": 0.9391,
+    "eval_samples": 9,
+    "eval_samples_per_second": 9.584,
+    "eval_steps_per_second": 1.065,
     "eval_wer": 1.0
 }

runs/May24_03-34-21_cc57b0143c57/events.out.tfevents.1716522040.cc57b0143c57.714.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2973e6c1914c5d9b1d7ae85bd25bd6e57bf7aa7bde90d445cea6acbcd244ab
+size 398

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 4.0,
-    "total_flos": 3.89806936817664e+16,
-    "train_loss": 14.43960952758789,
-    "train_runtime": 61.1436,
-    "train_samples": 53,
-    "train_samples_per_second": 3.467,
-    "train_steps_per_second": 0.131
+    "epoch": 26.666666666666668,
+    "total_flos": 5.3095066035971686e+17,
+    "train_loss": 7.207664489746094,
+    "train_runtime": 305.0878,
+    "train_samples": 136,
+    "train_samples_per_second": 13.373,
+    "train_steps_per_second": 0.393
 }

trainer_state.json

@@ -1,27 +1,47 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 26.666666666666668,
   "eval_steps": 50,
-  "global_step": 8,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 4.0,
-      "step": 8,
-      "total_flos": 3.89806936817664e+16,
-      "train_loss": 14.43960952758789,
-      "train_runtime": 61.1436,
-      "train_samples_per_second": 3.467,
-      "train_steps_per_second": 0.131
+      "epoch": 11.11111111111111,
+      "eval_cer": 1.0,
+      "eval_loss": 5.89304256439209,
+      "eval_runtime": 0.9784,
+      "eval_samples_per_second": 9.198,
+      "eval_steps_per_second": 1.022,
+      "eval_wer": 1.0,
+      "step": 50
+    },
+    {
+      "epoch": 22.22222222222222,
+      "eval_cer": 1.0,
+      "eval_loss": 2.4281415939331055,
+      "eval_runtime": 0.8402,
+      "eval_samples_per_second": 10.711,
+      "eval_steps_per_second": 1.19,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 26.666666666666668,
+      "step": 120,
+      "total_flos": 5.3095066035971686e+17,
+      "train_loss": 7.207664489746094,
+      "train_runtime": 305.0878,
+      "train_samples_per_second": 13.373,
+      "train_steps_per_second": 0.393
     }
   ],
   "logging_steps": 500,
-  "max_steps": 8,
+  "max_steps": 120,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 30,
   "save_steps": 200,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -35,7 +55,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.89806936817664e+16,
+  "total_flos": 5.3095066035971686e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null