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:
 - accuracy
 - f1
 model-index:
 - name: tiny_bert_rand_10_v2_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6936274509803921
+    - name: F1
+      type: f1
+      value: 0.8049921996879875
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_rand_10_v2_mrpc
 
-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 MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9016
-- Accuracy: 0.6569
-- F1: 0.7578
-- Combined Score: 0.7073
+- Loss: 0.5925
+- Accuracy: 0.6936
+- F1: 0.8050
+- Combined Score: 0.7493
 
 ## Model description
 

all_results.json

@@ -4,14 +4,14 @@
     "eval_combined_score": 0.7493098253341899,
     "eval_f1": 0.8049921996879875,
     "eval_loss": 0.5925148725509644,
-    "eval_runtime": 0.1712,
+    "eval_runtime": 0.1461,
     "eval_samples": 408,
-    "eval_samples_per_second": 2382.616,
-    "eval_steps_per_second": 11.679,
+    "eval_samples_per_second": 2792.58,
+    "eval_steps_per_second": 13.689,
     "total_flos": 673316591603712.0,
     "train_loss": 0.4811921028863816,
-    "train_runtime": 19.5808,
+    "train_runtime": 20.9726,
     "train_samples": 3668,
-    "train_samples_per_second": 9366.303,
-    "train_steps_per_second": 38.303
+    "train_samples_per_second": 8744.756,
+    "train_steps_per_second": 35.761
 }

eval_results.json

@@ -4,8 +4,8 @@
     "eval_combined_score": 0.7493098253341899,
     "eval_f1": 0.8049921996879875,
     "eval_loss": 0.5925148725509644,
-    "eval_runtime": 0.1712,
+    "eval_runtime": 0.1461,
     "eval_samples": 408,
-    "eval_samples_per_second": 2382.616,
-    "eval_steps_per_second": 11.679
+    "eval_samples_per_second": 2792.58,
+    "eval_steps_per_second": 13.689
 }

logs/events.out.tfevents.1745307409.s_005_m.2850172.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f8e1845e846303041d3c4ab5f2c2d9b411902b258ece206573e2422b895bac
+size 459

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 7.0,
     "total_flos": 673316591603712.0,
     "train_loss": 0.4811921028863816,
-    "train_runtime": 19.5808,
+    "train_runtime": 20.9726,
     "train_samples": 3668,
-    "train_samples_per_second": 9366.303,
-    "train_steps_per_second": 38.303
+    "train_samples_per_second": 8744.756,
+    "train_steps_per_second": 35.761
 }

trainer_state.json

@@ -22,9 +22,9 @@
       "eval_combined_score": 0.7493098253341899,
       "eval_f1": 0.8049921996879875,
       "eval_loss": 0.6069743037223816,
-      "eval_runtime": 0.1365,
-      "eval_samples_per_second": 2988.638,
-      "eval_steps_per_second": 14.65,
+      "eval_runtime": 0.2253,
+      "eval_samples_per_second": 1810.799,
+      "eval_steps_per_second": 8.876,
       "step": 15
     },
     {
@@ -40,9 +40,9 @@
       "eval_combined_score": 0.7493098253341899,
       "eval_f1": 0.8049921996879875,
       "eval_loss": 0.5925148725509644,
-      "eval_runtime": 0.1403,
-      "eval_samples_per_second": 2908.483,
-      "eval_steps_per_second": 14.257,
+      "eval_runtime": 0.1646,
+      "eval_samples_per_second": 2479.406,
+      "eval_steps_per_second": 12.154,
       "step": 30
     },
     {
@@ -58,9 +58,9 @@
       "eval_combined_score": 0.7553715761113606,
       "eval_f1": 0.8122137404580153,
       "eval_loss": 0.6044036746025085,
-      "eval_runtime": 0.1319,
-      "eval_samples_per_second": 3093.061,
-      "eval_steps_per_second": 15.162,
+      "eval_runtime": 0.1362,
+      "eval_samples_per_second": 2995.695,
+      "eval_steps_per_second": 14.685,
       "step": 45
     },
     {
@@ -76,9 +76,9 @@
       "eval_combined_score": 0.7210159380207779,
       "eval_f1": 0.7631103074141049,
       "eval_loss": 0.6260837316513062,
-      "eval_runtime": 0.1669,
-      "eval_samples_per_second": 2444.296,
-      "eval_steps_per_second": 11.982,
+      "eval_runtime": 0.1534,
+      "eval_samples_per_second": 2659.28,
+      "eval_steps_per_second": 13.036,
       "step": 60
     },
     {
@@ -94,9 +94,9 @@
       "eval_combined_score": 0.6964081086980247,
       "eval_f1": 0.738404452690167,
       "eval_loss": 0.6786839962005615,
-      "eval_runtime": 0.1589,
-      "eval_samples_per_second": 2567.194,
-      "eval_steps_per_second": 12.584,
+      "eval_runtime": 0.1384,
+      "eval_samples_per_second": 2947.056,
+      "eval_steps_per_second": 14.446,
       "step": 75
     },
     {
@@ -112,9 +112,9 @@
       "eval_combined_score": 0.7001788553259142,
       "eval_f1": 0.745945945945946,
       "eval_loss": 0.7894179224967957,
-      "eval_runtime": 0.1302,
-      "eval_samples_per_second": 3132.822,
-      "eval_steps_per_second": 15.357,
+      "eval_runtime": 0.1647,
+      "eval_samples_per_second": 2477.03,
+      "eval_steps_per_second": 12.142,
       "step": 90
     },
     {
@@ -130,9 +130,9 @@
       "eval_combined_score": 0.7073241061130334,
       "eval_f1": 0.7577854671280276,
       "eval_loss": 0.9015735387802124,
-      "eval_runtime": 0.1374,
-      "eval_samples_per_second": 2970.145,
-      "eval_steps_per_second": 14.56,
+      "eval_runtime": 0.1697,
+      "eval_samples_per_second": 2404.916,
+      "eval_steps_per_second": 11.789,
       "step": 105
     },
     {
@@ -140,9 +140,9 @@
       "step": 105,
       "total_flos": 673316591603712.0,
       "train_loss": 0.4811921028863816,
-      "train_runtime": 19.5808,
-      "train_samples_per_second": 9366.303,
-      "train_steps_per_second": 38.303
+      "train_runtime": 20.9726,
+      "train_samples_per_second": 8744.756,
+      "train_steps_per_second": 35.761
     }
   ],
   "logging_steps": 1,