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
@@ -14,9 +17,9 @@ 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 - FUS dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3460
+- Loss: 0.3461
 - Cer: 0.0870
 
 ## Model description

adapter.fus.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34015f57daddab11ffba96f31a654e0f94a0f7e423366f2bc88018b180ba5379
+size 339945692

all_results.json

@@ -1,16 +1,15 @@
 {
-    "epoch": 9.845849802371541,
-    "eval_cer": 0.060331486756229395,
-    "eval_loss": 0.3616417646408081,
-    "eval_runtime": 44.1198,
+    "epoch": 3.150197628458498,
+    "eval_cer": 0.08695359633974029,
+    "eval_loss": 0.34606558084487915,
+    "eval_runtime": 49.9666,
     "eval_samples": 693,
-    "eval_samples_per_second": 15.707,
-    "eval_steps_per_second": 3.944,
-    "lambda_grl": 0.9952304067043316,
-    "total_flos": 1.2130383128358582e+19,
-    "train_loss": 0.7589177124023437,
-    "train_runtime": 1792.364,
+    "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,
     "train_samples": 2020,
-    "train_samples_per_second": 16.905,
-    "train_steps_per_second": 1.063
+    "train_samples_per_second": 64.023,
+    "train_steps_per_second": 4.025
 }

eval_results.json

@@ -1,10 +1,9 @@
 {
-    "epoch": 9.845849802371541,
-    "eval_cer": 0.060331486756229395,
-    "eval_loss": 0.3616417646408081,
-    "eval_runtime": 44.1198,
+    "epoch": 3.150197628458498,
+    "eval_cer": 0.08695359633974029,
+    "eval_loss": 0.34606558084487915,
+    "eval_runtime": 49.9666,
     "eval_samples": 693,
-    "eval_samples_per_second": 15.707,
-    "eval_steps_per_second": 3.944,
-    "lambda_grl": 0.9952304067043316
+    "eval_samples_per_second": 13.869,
+    "eval_steps_per_second": 3.482
 }

train_results.json

@@ -1,10 +1,9 @@
 {
-    "epoch": 9.845849802371541,
-    "lambda_grl": 0.9952304067043316,
-    "total_flos": 1.2130383128358582e+19,
-    "train_loss": 0.7589177124023437,
-    "train_runtime": 1792.364,
+    "epoch": 3.150197628458498,
+    "total_flos": 4.226925921384762e+18,
+    "train_loss": 0.6646933555603027,
+    "train_runtime": 946.532,
     "train_samples": 2020,
-    "train_samples_per_second": 16.905,
-    "train_steps_per_second": 1.063
+    "train_samples_per_second": 64.023,
+    "train_steps_per_second": 4.025
 }