End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_base_lda_20_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_lda_20_v1_cola
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7049
-- Matthews Correlation: 0.0539
-- Accuracy: 0.6395
+- Loss: 0.6199
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 7.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6188952922821045,
+    "eval_loss": 0.6198700070381165,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.6561,
+    "eval_runtime": 0.7095,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1589.606,
-    "eval_steps_per_second": 7.62,
+    "eval_samples_per_second": 1470.092,
+    "eval_steps_per_second": 7.047,
     "total_flos": 7874519220341760.0,
-    "train_loss": 0.6316283650758887,
-    "train_runtime": 116.2402,
+    "train_loss": 0.5315281884009097,
+    "train_runtime": 120.102,
     "train_samples": 8551,
-    "train_samples_per_second": 3678.16,
-    "train_steps_per_second": 14.625
+    "train_samples_per_second": 3559.89,
+    "train_steps_per_second": 14.155
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 7.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6188952922821045,
+    "eval_loss": 0.6198700070381165,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.6561,
+    "eval_runtime": 0.7095,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1589.606,
-    "eval_steps_per_second": 7.62
+    "eval_samples_per_second": 1470.092,
+    "eval_steps_per_second": 7.047
 }

logs/events.out.tfevents.1733309487.ki-g0008.1207389.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04216dbb9db67818fa47c9bcb8e21fa60a16c7ed89128f88350398bf35143c5c
+size 475

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 7.0,
     "total_flos": 7874519220341760.0,
-    "train_loss": 0.6316283650758887,
-    "train_runtime": 116.2402,
+    "train_loss": 0.5315281884009097,
+    "train_runtime": 120.102,
     "train_samples": 8551,
-    "train_samples_per_second": 3678.16,
-    "train_steps_per_second": 14.625
+    "train_samples_per_second": 3559.89,
+    "train_steps_per_second": 14.155
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6188952922821045,
+  "best_metric": 0.6198700070381165,
   "best_model_checkpoint": "bert_base_lda_20_v1_cola/checkpoint-68",
   "epoch": 7.0,
   "eval_steps": 500,
@@ -10,131 +10,131 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.4452758729457855,
-      "learning_rate": 0.00098,
-      "loss": 0.7571,
+      "grad_norm": 0.7223057150840759,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6136,
       "step": 34
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6196237802505493,
+      "eval_loss": 0.6265467405319214,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6803,
-      "eval_samples_per_second": 1533.141,
-      "eval_steps_per_second": 7.35,
+      "eval_runtime": 0.7187,
+      "eval_samples_per_second": 1451.19,
+      "eval_steps_per_second": 6.957,
       "step": 34
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.9407540559768677,
-      "learning_rate": 0.00096,
-      "loss": 0.613,
+      "grad_norm": 1.90400230884552,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6112,
       "step": 68
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6188952922821045,
+      "eval_loss": 0.6198700070381165,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6631,
-      "eval_samples_per_second": 1572.981,
-      "eval_steps_per_second": 7.541,
+      "eval_runtime": 0.684,
+      "eval_samples_per_second": 1524.743,
+      "eval_steps_per_second": 7.309,
       "step": 68
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.0614078044891357,
-      "learning_rate": 0.00094,
-      "loss": 0.6097,
+      "grad_norm": 1.334337592124939,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5873,
       "step": 102
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6194814443588257,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6519,
-      "eval_samples_per_second": 1599.847,
-      "eval_steps_per_second": 7.669,
+      "eval_accuracy": 0.641418993473053,
+      "eval_loss": 0.6348920464515686,
+      "eval_matthews_correlation": 0.06986894691574659,
+      "eval_runtime": 0.6727,
+      "eval_samples_per_second": 1550.524,
+      "eval_steps_per_second": 7.433,
       "step": 102
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.6363035440444946,
-      "learning_rate": 0.00092,
-      "loss": 0.6106,
+      "grad_norm": 1.9891555309295654,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5381,
       "step": 136
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6196293830871582,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6778,
-      "eval_samples_per_second": 1538.719,
-      "eval_steps_per_second": 7.376,
+      "eval_accuracy": 0.5963566899299622,
+      "eval_loss": 0.6501876711845398,
+      "eval_matthews_correlation": 0.10535705260984664,
+      "eval_runtime": 0.682,
+      "eval_samples_per_second": 1529.263,
+      "eval_steps_per_second": 7.331,
       "step": 136
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.9160279035568237,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6114,
+      "grad_norm": 2.578742027282715,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4951,
       "step": 170
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6194814443588257,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6776,
-      "eval_samples_per_second": 1539.156,
-      "eval_steps_per_second": 7.379,
+      "eval_accuracy": 0.6442952752113342,
+      "eval_loss": 0.6613349318504333,
+      "eval_matthews_correlation": 0.07683234381179825,
+      "eval_runtime": 0.6814,
+      "eval_samples_per_second": 1530.617,
+      "eval_steps_per_second": 7.338,
       "step": 170
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.48956847190856934,
-      "learning_rate": 0.00088,
-      "loss": 0.6094,
+      "grad_norm": 3.737532615661621,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4506,
       "step": 204
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6189964413642883,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6726,
-      "eval_samples_per_second": 1550.586,
-      "eval_steps_per_second": 7.433,
+      "eval_accuracy": 0.5810163021087646,
+      "eval_loss": 0.7528904676437378,
+      "eval_matthews_correlation": 0.12820404799222795,
+      "eval_runtime": 0.6701,
+      "eval_samples_per_second": 1556.391,
+      "eval_steps_per_second": 7.461,
       "step": 204
     },
     {
       "epoch": 7.0,
-      "grad_norm": 1.5084835290908813,
-      "learning_rate": 0.00086,
-      "loss": 0.6102,
+      "grad_norm": 4.000977516174316,
+      "learning_rate": 4.3e-05,
+      "loss": 0.4248,
       "step": 238
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.619966447353363,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6632,
-      "eval_samples_per_second": 1572.699,
-      "eval_steps_per_second": 7.539,
+      "eval_accuracy": 0.6395014524459839,
+      "eval_loss": 0.7049092650413513,
+      "eval_matthews_correlation": 0.053910422269610486,
+      "eval_runtime": 0.6819,
+      "eval_samples_per_second": 1529.505,
+      "eval_steps_per_second": 7.332,
       "step": 238
     },
     {
       "epoch": 7.0,
       "step": 238,
       "total_flos": 7874519220341760.0,
-      "train_loss": 0.6316283650758887,
-      "train_runtime": 116.2402,
-      "train_samples_per_second": 3678.16,
-      "train_steps_per_second": 14.625
+      "train_loss": 0.5315281884009097,
+      "train_runtime": 120.102,
+      "train_samples_per_second": 3559.89,
+      "train_steps_per_second": 14.155
     }
   ],
   "logging_steps": 1,