End of training

README.md

@@ -3,6 +3,9 @@ library_name: transformers
 license: cc-by-nc-4.0
 base_model: csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.09
 tags:
+- automatic-speech-recognition
+- swagen
+- mms
 - generated_from_trainer
 model-index:
 - name: mms-1b-all-swagen-combined-m50f50-dnn-42-0.09
@@ -14,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mms-1b-all-swagen-combined-m50f50-dnn-42-0.09
 
-This model is a fine-tuned version of [csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.09](https://huggingface.co/csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.09) on an unknown dataset.
+This model is a fine-tuned version of [csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.09](https://huggingface.co/csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.09) on the SWAGEN - AFA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3098
-- Cer: 0.0759
+- Loss: 0.2911
+- Cer: 0.0731
 
 ## Model description
 

adapter.afa.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83f757935c25078de7e4e1cde0c037934d43dd1b9f0ae2ce0a93ea1a64a9483
+size 339945692

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 3.150197628458498,
-    "eval_cer": 0.08695359633974029,
-    "eval_loss": 0.34606558084487915,
-    "eval_runtime": 49.9666,
+    "epoch": 5.513833992094861,
+    "eval_cer": 0.07309305402920134,
+    "eval_loss": 0.291103333234787,
+    "eval_runtime": 57.7716,
     "eval_samples": 693,
-    "eval_samples_per_second": 13.869,
-    "eval_steps_per_second": 3.482,
-    "total_flos": 4.226925921384762e+18,
-    "train_loss": 0.6646933555603027,
-    "train_runtime": 946.532,
+    "eval_samples_per_second": 11.996,
+    "eval_steps_per_second": 3.012,
+    "total_flos": 7.370435389350818e+18,
+    "train_loss": 0.2938505799429757,
+    "train_runtime": 1825.9089,
     "train_samples": 2020,
-    "train_samples_per_second": 64.023,
-    "train_steps_per_second": 4.025
+    "train_samples_per_second": 33.189,
+    "train_steps_per_second": 2.087
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.150197628458498,
-    "eval_cer": 0.08695359633974029,
-    "eval_loss": 0.34606558084487915,
-    "eval_runtime": 49.9666,
+    "epoch": 5.513833992094861,
+    "eval_cer": 0.07309305402920134,
+    "eval_loss": 0.291103333234787,
+    "eval_runtime": 57.7716,
     "eval_samples": 693,
-    "eval_samples_per_second": 13.869,
-    "eval_steps_per_second": 3.482
+    "eval_samples_per_second": 11.996,
+    "eval_steps_per_second": 3.012
 }

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.150197628458498,
-    "total_flos": 4.226925921384762e+18,
-    "train_loss": 0.6646933555603027,
-    "train_runtime": 946.532,
+    "epoch": 5.513833992094861,
+    "total_flos": 7.370435389350818e+18,
+    "train_loss": 0.2938505799429757,
+    "train_runtime": 1825.9089,
     "train_samples": 2020,
-    "train_samples_per_second": 64.023,
-    "train_steps_per_second": 4.025
+    "train_samples_per_second": 33.189,
+    "train_steps_per_second": 2.087
 }