End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: cointegrated/rubert-tiny
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: finetuned-tiny-bert
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # finetuned-tiny-bert
 
 This model is a fine-tuned version of [cointegrated/rubert-tiny](https://huggingface.co/cointegrated/rubert-tiny) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5832
+- Accuracy: 0.5167
 
 ## Model description
 

all_results.json

@@ -2,14 +2,14 @@
     "epoch": 1.0,
     "eval_accuracy": 0.5167136043030395,
     "eval_loss": 2.5832159519195557,
-    "eval_runtime": 62.4515,
+    "eval_runtime": 62.4114,
     "eval_samples": 15263,
-    "eval_samples_per_second": 244.398,
-    "eval_steps_per_second": 7.638,
+    "eval_samples_per_second": 244.555,
+    "eval_steps_per_second": 7.643,
     "perplexity": 13.23964783936109,
     "train_loss": 3.04393067064311,
-    "train_runtime": 385.498,
+    "train_runtime": 388.0084,
     "train_samples": 35613,
-    "train_samples_per_second": 92.382,
-    "train_steps_per_second": 2.887
+    "train_samples_per_second": 91.784,
+    "train_steps_per_second": 2.868
 }

eval_results.json

@@ -2,9 +2,9 @@
     "epoch": 1.0,
     "eval_accuracy": 0.5167136043030395,
     "eval_loss": 2.5832159519195557,
-    "eval_runtime": 62.4515,
+    "eval_runtime": 62.4114,
     "eval_samples": 15263,
-    "eval_samples_per_second": 244.398,
-    "eval_steps_per_second": 7.638,
+    "eval_samples_per_second": 244.555,
+    "eval_steps_per_second": 7.643,
     "perplexity": 13.23964783936109
 }

runs/Feb25_10-54-45_e77a61bc3de0/events.out.tfevents.1708858943.e77a61bc3de0.13217.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd2482654241dd4697dcc72aaa9f2a7ef1b8ac0b48ec107fd59376a7ed0f6c5
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 3.04393067064311,
-    "train_runtime": 385.498,
+    "train_runtime": 388.0084,
     "train_samples": 35613,
-    "train_samples_per_second": 92.382,
-    "train_steps_per_second": 2.887
+    "train_samples_per_second": 91.784,
+    "train_steps_per_second": 2.868
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "step": 1113,
       "total_flos": 159583189651080.0,
       "train_loss": 3.04393067064311,
-      "train_runtime": 385.498,
-      "train_samples_per_second": 92.382,
-      "train_steps_per_second": 2.887
+      "train_runtime": 388.0084,
+      "train_samples_per_second": 91.784,
+      "train_steps_per_second": 2.868
     }
   ],
   "logging_steps": 500,