End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_base_rand_100_v1_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. -->
 
 # bert_base_rand_100_v1_cola
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_100_v1](https://huggingface.co/Hartunka/bert_base_rand_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_100_v1](https://huggingface.co/Hartunka/bert_base_rand_100_v1) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7870
-- Matthews Correlation: 0.1194
-- Accuracy: 0.6568
+- Loss: 0.6176
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -3,14 +3,14 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6176116466522217,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.693,
+    "eval_runtime": 0.6903,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1505.088,
-    "eval_steps_per_second": 7.215,
+    "eval_samples_per_second": 1510.991,
+    "eval_steps_per_second": 7.243,
     "total_flos": 6749587903150080.0,
     "train_loss": 0.5041563651140999,
-    "train_runtime": 99.6183,
+    "train_runtime": 102.8186,
     "train_samples": 8551,
-    "train_samples_per_second": 4291.884,
-    "train_steps_per_second": 17.065
+    "train_samples_per_second": 4158.296,
+    "train_steps_per_second": 16.534
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6176116466522217,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.693,
+    "eval_runtime": 0.6903,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1505.088,
-    "eval_steps_per_second": 7.215
+    "eval_samples_per_second": 1510.991,
+    "eval_steps_per_second": 7.243
 }

logs/events.out.tfevents.1745183095.s_005_m.2815556.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d78a6cfc70c952f6cd59360fe5d4845baa4e5bb43ccb2ade8fe05afb0618cc
+size 427

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 6.0,
     "total_flos": 6749587903150080.0,
     "train_loss": 0.5041563651140999,
-    "train_runtime": 99.6183,
+    "train_runtime": 102.8186,
     "train_samples": 8551,
-    "train_samples_per_second": 4291.884,
-    "train_steps_per_second": 17.065
+    "train_samples_per_second": 4158.296,
+    "train_steps_per_second": 16.534
 }

trainer_state.json

@@ -21,9 +21,9 @@
       "eval_accuracy": 0.6912751793861389,
       "eval_loss": 0.6176116466522217,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.668,
-      "eval_samples_per_second": 1561.42,
-      "eval_steps_per_second": 7.485,
+      "eval_runtime": 0.6775,
+      "eval_samples_per_second": 1539.593,
+      "eval_steps_per_second": 7.381,
       "step": 34
     },
     {
@@ -38,9 +38,9 @@
       "eval_accuracy": 0.6883988380432129,
       "eval_loss": 0.6251381039619446,
       "eval_matthews_correlation": -0.03589254563226399,
-      "eval_runtime": 0.704,
-      "eval_samples_per_second": 1481.505,
-      "eval_steps_per_second": 7.102,
+      "eval_runtime": 0.6763,
+      "eval_samples_per_second": 1542.319,
+      "eval_steps_per_second": 7.394,
       "step": 68
     },
     {
@@ -55,9 +55,9 @@
       "eval_accuracy": 0.6481304168701172,
       "eval_loss": 0.6604347825050354,
       "eval_matthews_correlation": 0.10041605806534921,
-      "eval_runtime": 0.6763,
-      "eval_samples_per_second": 1542.121,
-      "eval_steps_per_second": 7.393,
+      "eval_runtime": 0.684,
+      "eval_samples_per_second": 1524.797,
+      "eval_steps_per_second": 7.31,
       "step": 102
     },
     {
@@ -72,9 +72,9 @@
       "eval_accuracy": 0.6567593216896057,
       "eval_loss": 0.7520363330841064,
       "eval_matthews_correlation": 0.08852460407026867,
-      "eval_runtime": 0.6979,
-      "eval_samples_per_second": 1494.554,
-      "eval_steps_per_second": 7.165,
+      "eval_runtime": 0.7103,
+      "eval_samples_per_second": 1468.365,
+      "eval_steps_per_second": 7.039,
       "step": 136
     },
     {
@@ -89,9 +89,9 @@
       "eval_accuracy": 0.6490891575813293,
       "eval_loss": 0.7340983748435974,
       "eval_matthews_correlation": 0.13750626640004746,
-      "eval_runtime": 0.6831,
-      "eval_samples_per_second": 1526.905,
-      "eval_steps_per_second": 7.32,
+      "eval_runtime": 0.684,
+      "eval_samples_per_second": 1524.759,
+      "eval_steps_per_second": 7.309,
       "step": 170
     },
     {
@@ -106,9 +106,9 @@
       "eval_accuracy": 0.6567593216896057,
       "eval_loss": 0.7870461940765381,
       "eval_matthews_correlation": 0.11941328770402174,
-      "eval_runtime": 0.6943,
-      "eval_samples_per_second": 1502.219,
-      "eval_steps_per_second": 7.201,
+      "eval_runtime": 0.6662,
+      "eval_samples_per_second": 1565.555,
+      "eval_steps_per_second": 7.505,
       "step": 204
     },
     {
@@ -116,9 +116,9 @@
       "step": 204,
       "total_flos": 6749587903150080.0,
       "train_loss": 0.5041563651140999,
-      "train_runtime": 99.6183,
-      "train_samples_per_second": 4291.884,
-      "train_steps_per_second": 17.065
+      "train_runtime": 102.8186,
+      "train_samples_per_second": 4158.296,
+      "train_steps_per_second": 16.534
     }
   ],
   "logging_steps": 1,