End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: mit
 base_model: facebook/w2v-bert-2.0
 tags:
+- automatic-speech-recognition
+- CLEAR-Global/luo_19_77h
 - generated_from_trainer
 metrics:
 - wer
@@ -16,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # w2v-bert-2.0-luo_19_77h
 
-This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
+This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the CLEAR-GLOBAL/LUO_19_77H - NA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2966
-- Wer: 0.2751
-- Cer: 0.0920
+- Loss: 0.2419
+- Wer: 0.2906
+- Cer: 0.0898
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 17.736486486486488,
+    "eval_cer": 0.08979198457955184,
+    "eval_loss": 0.24188752472400665,
+    "eval_runtime": 9.1201,
+    "eval_samples": 101,
+    "eval_samples_per_second": 11.074,
+    "eval_steps_per_second": 0.439,
+    "eval_wer": 0.29056437389770723,
+    "total_flos": 1.85831881720076e+20,
+    "train_loss": 0.19500272537244573,
+    "train_runtime": 26407.434,
+    "train_samples": 75771,
+    "train_samples_per_second": 242.356,
+    "train_steps_per_second": 3.787
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 17.736486486486488,
+    "eval_cer": 0.08979198457955184,
+    "eval_loss": 0.24188752472400665,
+    "eval_runtime": 9.1201,
+    "eval_samples": 101,
+    "eval_samples_per_second": 11.074,
+    "eval_steps_per_second": 0.439,
+    "eval_wer": 0.29056437389770723
+}

runs/Apr13_17-55-37_synvoices-single-a100/events.out.tfevents.1744596504.synvoices-single-a100.159308.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d6ca98b7986aaa361b7832f692042fa27bd04aaa2153f0ae1f23f6e5086f15a
+size 460

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 17.736486486486488,
+    "total_flos": 1.85831881720076e+20,
+    "train_loss": 0.19500272537244573,
+    "train_runtime": 26407.434,
+    "train_samples": 75771,
+    "train_samples_per_second": 242.356,
+    "train_steps_per_second": 3.787
+}