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-42-0.04
 tags:
+- automatic-speech-recognition
+- swagen
+- mms
 - generated_from_trainer
 model-index:
 - name: mms-1b-all-swagen-combined-m50f50-dnn-42-0.04
@@ -14,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mms-1b-all-swagen-combined-m50f50-dnn-42-0.04
 
-This model is a fine-tuned version of [csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.04](https://huggingface.co/csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.04) on an unknown dataset.
+This model is a fine-tuned version of [csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.04](https://huggingface.co/csikasote/mms-1b-all-swagen-combined-m50f50-dnn-42-0.04) on the SWAGEN - FUS dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.3241
-- Cer: 0.0790
+- Cer: 0.0789
 
 ## Model description
 

adapter.fus.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:940d1a77d93e66e57627638a9452bf14866bcb86e4dd3ca2c51a6cb7d6c14812
+oid sha256:856d73c9a40af9db97ae49807c425fb81d1b78091c8c1c7263c2201d82779816
 size 339945692

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 15.0,
-    "eval_cer": 4.136048624038397,
-    "eval_loss": 15.094812393188477,
-    "eval_runtime": 28.8119,
+    "epoch": 4.7272727272727275,
+    "eval_cer": 0.07894677820889497,
+    "eval_loss": 0.32411274313926697,
+    "eval_runtime": 49.74,
     "eval_samples": 693,
-    "eval_samples_per_second": 24.053,
-    "eval_steps_per_second": 6.039,
-    "total_flos": 1.844747726932012e+19,
-    "train_loss": 0.3706513572552699,
-    "train_runtime": 1918.1869,
+    "eval_samples_per_second": 13.932,
+    "eval_steps_per_second": 3.498,
+    "total_flos": 6.310179615845671e+18,
+    "train_loss": 0.709945068359375,
+    "train_runtime": 1386.8476,
     "train_samples": 2020,
-    "train_samples_per_second": 15.796,
-    "train_steps_per_second": 0.993
+    "train_samples_per_second": 43.696,
+    "train_steps_per_second": 2.747
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 15.0,
-    "eval_cer": 4.136048624038397,
-    "eval_loss": 15.094812393188477,
-    "eval_runtime": 28.8119,
+    "epoch": 4.7272727272727275,
+    "eval_cer": 0.07894677820889497,
+    "eval_loss": 0.32411274313926697,
+    "eval_runtime": 49.74,
     "eval_samples": 693,
-    "eval_samples_per_second": 24.053,
-    "eval_steps_per_second": 6.039
+    "eval_samples_per_second": 13.932,
+    "eval_steps_per_second": 3.498
 }

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 15.0,
-    "total_flos": 1.844747726932012e+19,
-    "train_loss": 0.3706513572552699,
-    "train_runtime": 1918.1869,
+    "epoch": 4.7272727272727275,
+    "total_flos": 6.310179615845671e+18,
+    "train_loss": 0.709945068359375,
+    "train_runtime": 1386.8476,
     "train_samples": 2020,
-    "train_samples_per_second": 15.796,
-    "train_steps_per_second": 0.993
+    "train_samples_per_second": 43.696,
+    "train_steps_per_second": 2.747
 }