End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_10_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: tiny_bert_rand_10_v2_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.0
+    - name: Accuracy
+      type: accuracy
+      value: 0.6912751793861389
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,11 +34,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_rand_10_v2_cola
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_10_v2](https://huggingface.co/Hartunka/tiny_bert_rand_10_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_10_v2](https://huggingface.co/Hartunka/tiny_bert_rand_10_v2) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7248
-- Matthews Correlation: 0.0595
-- Accuracy: 0.6366
+- Loss: 0.6162
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -3,14 +3,14 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6162062287330627,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.3433,
+    "eval_runtime": 0.3587,
     "eval_samples": 1043,
-    "eval_samples_per_second": 3038.19,
-    "eval_steps_per_second": 14.565,
+    "eval_samples_per_second": 2907.542,
+    "eval_steps_per_second": 13.938,
     "total_flos": 1345426898614272.0,
     "train_loss": 0.5475386077282476,
-    "train_runtime": 33.5155,
+    "train_runtime": 34.669,
     "train_samples": 8551,
-    "train_samples_per_second": 12756.768,
-    "train_steps_per_second": 50.723
+    "train_samples_per_second": 12332.349,
+    "train_steps_per_second": 49.035
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6162062287330627,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.3433,
+    "eval_runtime": 0.3587,
     "eval_samples": 1043,
-    "eval_samples_per_second": 3038.19,
-    "eval_steps_per_second": 14.565
+    "eval_samples_per_second": 2907.542,
+    "eval_steps_per_second": 13.938
 }

logs/events.out.tfevents.1745307357.s_005_m.2850172.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaab27a393e26ee1ec162a9b47dd69a5b2e3466e1815c2005c4021c6f192ce69
+size 427

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 6.0,
     "total_flos": 1345426898614272.0,
     "train_loss": 0.5475386077282476,
-    "train_runtime": 33.5155,
+    "train_runtime": 34.669,
     "train_samples": 8551,
-    "train_samples_per_second": 12756.768,
-    "train_steps_per_second": 50.723
+    "train_samples_per_second": 12332.349,
+    "train_steps_per_second": 49.035
 }

trainer_state.json

@@ -21,9 +21,9 @@
       "eval_accuracy": 0.6912751793861389,
       "eval_loss": 0.6162062287330627,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.3168,
-      "eval_samples_per_second": 3292.815,
-      "eval_steps_per_second": 15.785,
+      "eval_runtime": 0.3253,
+      "eval_samples_per_second": 3205.893,
+      "eval_steps_per_second": 15.369,
       "step": 34
     },
     {
@@ -38,9 +38,9 @@
       "eval_accuracy": 0.6912751793861389,
       "eval_loss": 0.6173672676086426,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.3527,
-      "eval_samples_per_second": 2957.353,
-      "eval_steps_per_second": 14.177,
+      "eval_runtime": 0.33,
+      "eval_samples_per_second": 3160.244,
+      "eval_steps_per_second": 15.15,
       "step": 68
     },
     {
@@ -55,9 +55,9 @@
       "eval_accuracy": 0.6922339200973511,
       "eval_loss": 0.61886066198349,
       "eval_matthews_correlation": 0.04161454566059593,
-      "eval_runtime": 0.3115,
-      "eval_samples_per_second": 3348.732,
-      "eval_steps_per_second": 16.053,
+      "eval_runtime": 0.3769,
+      "eval_samples_per_second": 2767.11,
+      "eval_steps_per_second": 13.265,
       "step": 102
     },
     {
@@ -72,9 +72,9 @@
       "eval_accuracy": 0.668264627456665,
       "eval_loss": 0.6651514172554016,
       "eval_matthews_correlation": 0.04797771844318346,
-      "eval_runtime": 0.3091,
-      "eval_samples_per_second": 3374.181,
-      "eval_steps_per_second": 16.175,
+      "eval_runtime": 0.3127,
+      "eval_samples_per_second": 3335.951,
+      "eval_steps_per_second": 15.992,
       "step": 136
     },
     {
@@ -89,9 +89,9 @@
       "eval_accuracy": 0.6625120043754578,
       "eval_loss": 0.6673993468284607,
       "eval_matthews_correlation": 0.08811408651094657,
-      "eval_runtime": 0.3487,
-      "eval_samples_per_second": 2991.212,
-      "eval_steps_per_second": 14.339,
+      "eval_runtime": 0.3261,
+      "eval_samples_per_second": 3198.762,
+      "eval_steps_per_second": 15.334,
       "step": 170
     },
     {
@@ -106,9 +106,9 @@
       "eval_accuracy": 0.6366251111030579,
       "eval_loss": 0.7247511148452759,
       "eval_matthews_correlation": 0.05950348658831357,
-      "eval_runtime": 0.3382,
-      "eval_samples_per_second": 3083.636,
-      "eval_steps_per_second": 14.783,
+      "eval_runtime": 0.3524,
+      "eval_samples_per_second": 2959.388,
+      "eval_steps_per_second": 14.187,
       "step": 204
     },
     {
@@ -116,9 +116,9 @@
       "step": 204,
       "total_flos": 1345426898614272.0,
       "train_loss": 0.5475386077282476,
-      "train_runtime": 33.5155,
-      "train_samples_per_second": 12756.768,
-      "train_steps_per_second": 50.723
+      "train_runtime": 34.669,
+      "train_samples_per_second": 12332.349,
+      "train_steps_per_second": 49.035
     }
   ],
   "logging_steps": 1,