End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_20
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_tiny_lda_20_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6838235294117647
+    - name: F1
+      type: f1
+      value: 0.8122270742358079
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,9 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_tiny_lda_20_mrpc
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6279
+- Loss: 0.6247
 - Accuracy: 0.6838
 - F1: 0.8122
 - Combined Score: 0.7480

all_results.json

@@ -3,15 +3,15 @@
     "eval_accuracy": 0.6838235294117647,
     "eval_combined_score": 0.7480253018237863,
     "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6239542961120605,
-    "eval_runtime": 0.3395,
+    "eval_loss": 0.6246840357780457,
+    "eval_runtime": 0.1368,
     "eval_samples": 408,
-    "eval_samples_per_second": 1201.848,
-    "eval_steps_per_second": 14.729,
+    "eval_samples_per_second": 2982.731,
+    "eval_steps_per_second": 14.621,
     "total_flos": 865692760633344.0,
-    "train_loss": 0.6400821718395265,
-    "train_runtime": 79.8923,
+    "train_loss": 0.35235131635964767,
+    "train_runtime": 15.55,
     "train_samples": 3668,
-    "train_samples_per_second": 1377.354,
-    "train_steps_per_second": 14.645
+    "train_samples_per_second": 7076.519,
+    "train_steps_per_second": 75.241
 }

eval_results.json

@@ -3,9 +3,9 @@
     "eval_accuracy": 0.6838235294117647,
     "eval_combined_score": 0.7480253018237863,
     "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6239542961120605,
-    "eval_runtime": 0.3395,
+    "eval_loss": 0.6246840357780457,
+    "eval_runtime": 0.1368,
     "eval_samples": 408,
-    "eval_samples_per_second": 1201.848,
-    "eval_steps_per_second": 14.729
+    "eval_samples_per_second": 2982.731,
+    "eval_steps_per_second": 14.621
 }

logs/events.out.tfevents.1732251623.ki-g0008.1610732.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b57bc5880eaa4747a794bbab1b4de0de131f24a7757572355f2c9ecd9846a171
+size 515

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 9.0,
     "total_flos": 865692760633344.0,
-    "train_loss": 0.6400821718395265,
-    "train_runtime": 79.8923,
+    "train_loss": 0.35235131635964767,
+    "train_runtime": 15.55,
     "train_samples": 3668,
-    "train_samples_per_second": 1377.354,
-    "train_steps_per_second": 14.645
+    "train_samples_per_second": 7076.519,
+    "train_steps_per_second": 75.241
 }

trainer_state.json

@@ -82,7 +82,7 @@
     },
     {
       "epoch": 5.0,
-      "grad_norm": 1.0611114501953125,
+      "grad_norm": 1.0560246706008911,
       "learning_rate": 0.0008333333333333334,
       "loss": 0.6361,
       "step": 195
@@ -92,15 +92,15 @@
       "eval_accuracy": 0.6838235294117647,
       "eval_combined_score": 0.7480253018237863,
       "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6252522468566895,
-      "eval_runtime": 0.3312,
-      "eval_samples_per_second": 1231.985,
-      "eval_steps_per_second": 15.098,
+      "eval_loss": 0.625359058380127,
+      "eval_runtime": 0.1374,
+      "eval_samples_per_second": 2968.497,
+      "eval_steps_per_second": 14.551,
       "step": 195
     },
     {
       "epoch": 6.0,
-      "grad_norm": 2.5196642875671387,
+      "grad_norm": 2.507007122039795,
       "learning_rate": 0.0008,
       "loss": 0.6372,
       "step": 234
@@ -110,17 +110,17 @@
       "eval_accuracy": 0.6838235294117647,
       "eval_combined_score": 0.7480253018237863,
       "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6242114901542664,
-      "eval_runtime": 0.3333,
-      "eval_samples_per_second": 1223.974,
-      "eval_steps_per_second": 15.0,
+      "eval_loss": 0.6243536472320557,
+      "eval_runtime": 0.1406,
+      "eval_samples_per_second": 2901.456,
+      "eval_steps_per_second": 14.223,
       "step": 234
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.6646435856819153,
+      "grad_norm": 0.6576654314994812,
       "learning_rate": 0.0007666666666666667,
-      "loss": 0.6325,
+      "loss": 0.6324,
       "step": 273
     },
     {
@@ -128,15 +128,15 @@
       "eval_accuracy": 0.6838235294117647,
       "eval_combined_score": 0.7480253018237863,
       "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6240382194519043,
-      "eval_runtime": 0.3326,
-      "eval_samples_per_second": 1226.748,
-      "eval_steps_per_second": 15.034,
+      "eval_loss": 0.6248611807823181,
+      "eval_runtime": 0.1376,
+      "eval_samples_per_second": 2965.446,
+      "eval_steps_per_second": 14.537,
       "step": 273
     },
     {
       "epoch": 8.0,
-      "grad_norm": 1.2900689840316772,
+      "grad_norm": 1.2987427711486816,
       "learning_rate": 0.0007333333333333333,
       "loss": 0.6344,
       "step": 312
@@ -146,17 +146,17 @@
       "eval_accuracy": 0.6838235294117647,
       "eval_combined_score": 0.7480253018237863,
       "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6250187158584595,
-      "eval_runtime": 0.3335,
-      "eval_samples_per_second": 1223.535,
-      "eval_steps_per_second": 14.994,
+      "eval_loss": 0.6241096258163452,
+      "eval_runtime": 0.1631,
+      "eval_samples_per_second": 2501.529,
+      "eval_steps_per_second": 12.262,
       "step": 312
     },
     {
       "epoch": 9.0,
-      "grad_norm": 0.6405686736106873,
+      "grad_norm": 0.6472728848457336,
       "learning_rate": 0.0007,
-      "loss": 0.6312,
+      "loss": 0.631,
       "step": 351
     },
     {
@@ -164,20 +164,20 @@
       "eval_accuracy": 0.6838235294117647,
       "eval_combined_score": 0.7480253018237863,
       "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.628382682800293,
-      "eval_runtime": 0.3309,
-      "eval_samples_per_second": 1232.846,
-      "eval_steps_per_second": 15.108,
+      "eval_loss": 0.6279440522193909,
+      "eval_runtime": 0.1342,
+      "eval_samples_per_second": 3041.182,
+      "eval_steps_per_second": 14.908,
       "step": 351
     },
     {
       "epoch": 9.0,
       "step": 351,
       "total_flos": 865692760633344.0,
-      "train_loss": 0.6400821718395265,
-      "train_runtime": 79.8923,
-      "train_samples_per_second": 1377.354,
-      "train_steps_per_second": 14.645
+      "train_loss": 0.35235131635964767,
+      "train_runtime": 15.55,
+      "train_samples_per_second": 7076.519,
+      "train_steps_per_second": 75.241
     }
   ],
   "logging_steps": 1,