End of training

README.md

@@ -3,6 +3,9 @@ library_name: transformers
 license: cc-by-nc-4.0
 base_model: facebook/mms-1b-all
 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 [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
+This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the SWAGEN - DEB dataset.
 It achieves the following results on the evaluation set:
 - Loss: 15.0948
-- Cer: 4.1370
+- Cer: 4.1360
 
 ## Model description
 

adapter.deb.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07844302f364860b2df427812c159b50f6829cede618ad2207d36efca1055a95
+oid sha256:c0ff04347e376c4045f3d18518e2a44cf219a1441a254ed869fe7a6ef6d7d34f
 size 8819028

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 5.513833992094861,
-    "eval_cer": 0.07309305402920134,
-    "eval_loss": 0.291103333234787,
-    "eval_runtime": 57.7716,
+    "epoch": 15.0,
+    "eval_cer": 4.136048624038397,
+    "eval_loss": 15.094812393188477,
+    "eval_runtime": 28.6697,
     "eval_samples": 693,
-    "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,
+    "eval_samples_per_second": 24.172,
+    "eval_steps_per_second": 6.069,
+    "total_flos": 1.844747726932012e+19,
+    "train_loss": 0.3706513572552699,
+    "train_runtime": 1905.6804,
     "train_samples": 2020,
-    "train_samples_per_second": 33.189,
-    "train_steps_per_second": 2.087
+    "train_samples_per_second": 15.9,
+    "train_steps_per_second": 1.0
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 5.513833992094861,
-    "eval_cer": 0.07309305402920134,
-    "eval_loss": 0.291103333234787,
-    "eval_runtime": 57.7716,
+    "epoch": 15.0,
+    "eval_cer": 4.136048624038397,
+    "eval_loss": 15.094812393188477,
+    "eval_runtime": 28.6697,
     "eval_samples": 693,
-    "eval_samples_per_second": 11.996,
-    "eval_steps_per_second": 3.012
+    "eval_samples_per_second": 24.172,
+    "eval_steps_per_second": 6.069
 }

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 5.513833992094861,
-    "total_flos": 7.370435389350818e+18,
-    "train_loss": 0.2938505799429757,
-    "train_runtime": 1825.9089,
+    "epoch": 15.0,
+    "total_flos": 1.844747726932012e+19,
+    "train_loss": 0.3706513572552699,
+    "train_runtime": 1905.6804,
     "train_samples": 2020,
-    "train_samples_per_second": 33.189,
-    "train_steps_per_second": 2.087
+    "train_samples_per_second": 15.9,
+    "train_steps_per_second": 1.0
 }