End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_lda_20_v1_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8165137614678899
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_tiny_lda_20_v1_sst2
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7103
-- Accuracy: 0.7970
+- Loss: 0.4656
+- Accuracy: 0.8165
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 7.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6938790082931519,
-    "eval_runtime": 0.2767,
+    "eval_accuracy": 0.8165137614678899,
+    "eval_loss": 0.46561405062675476,
+    "eval_runtime": 0.2713,
     "eval_samples": 872,
-    "eval_samples_per_second": 3151.194,
-    "eval_steps_per_second": 14.455,
+    "eval_samples_per_second": 3214.537,
+    "eval_steps_per_second": 14.746,
     "total_flos": 1.2362922335855616e+16,
-    "train_loss": 0.6874211381524156,
-    "train_runtime": 259.3366,
+    "train_loss": 0.19844082836464885,
+    "train_runtime": 261.6164,
     "train_samples": 67349,
-    "train_samples_per_second": 12984.864,
-    "train_steps_per_second": 50.899
+    "train_samples_per_second": 12871.711,
+    "train_steps_per_second": 50.456
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 7.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6938790082931519,
-    "eval_runtime": 0.2767,
+    "eval_accuracy": 0.8165137614678899,
+    "eval_loss": 0.46561405062675476,
+    "eval_runtime": 0.2713,
     "eval_samples": 872,
-    "eval_samples_per_second": 3151.194,
-    "eval_steps_per_second": 14.455
+    "eval_samples_per_second": 3214.537,
+    "eval_steps_per_second": 14.746
 }

logs/events.out.tfevents.1733326024.ki-g0008.1207389.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c0f421c14dcc7a311266aa38754fb6dc18312885a57b899bdd70f1ad4c57cb
+size 411

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 7.0,
     "total_flos": 1.2362922335855616e+16,
-    "train_loss": 0.6874211381524156,
-    "train_runtime": 259.3366,
+    "train_loss": 0.19844082836464885,
+    "train_runtime": 261.6164,
     "train_samples": 67349,
-    "train_samples_per_second": 12984.864,
-    "train_steps_per_second": 50.899
+    "train_samples_per_second": 12871.711,
+    "train_steps_per_second": 50.456
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6938790082931519,
+  "best_metric": 0.46561405062675476,
   "best_model_checkpoint": "bert_tiny_lda_20_v1_sst2/checkpoint-528",
   "epoch": 7.0,
   "eval_steps": 500,
@@ -10,124 +10,124 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.7342337965965271,
-      "learning_rate": 0.00098,
-      "loss": 0.6918,
+      "grad_norm": 12.078267097473145,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4233,
       "step": 264
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.695652961730957,
-      "eval_runtime": 0.2707,
-      "eval_samples_per_second": 3221.409,
-      "eval_steps_per_second": 14.777,
+      "eval_accuracy": 0.7844036697247706,
+      "eval_loss": 0.4931957721710205,
+      "eval_runtime": 0.2795,
+      "eval_samples_per_second": 3119.529,
+      "eval_steps_per_second": 14.31,
       "step": 264
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.1505114883184433,
-      "learning_rate": 0.00096,
-      "loss": 0.6872,
+      "grad_norm": 5.435814380645752,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2592,
       "step": 528
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6938790082931519,
-      "eval_runtime": 0.2836,
-      "eval_samples_per_second": 3075.093,
-      "eval_steps_per_second": 14.106,
+      "eval_accuracy": 0.8165137614678899,
+      "eval_loss": 0.46561405062675476,
+      "eval_runtime": 0.2723,
+      "eval_samples_per_second": 3202.14,
+      "eval_steps_per_second": 14.689,
       "step": 528
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.24582037329673767,
-      "learning_rate": 0.00094,
-      "loss": 0.6867,
+      "grad_norm": 3.6048450469970703,
+      "learning_rate": 4.7e-05,
+      "loss": 0.1987,
       "step": 792
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6983273029327393,
-      "eval_runtime": 0.2681,
-      "eval_samples_per_second": 3252.295,
-      "eval_steps_per_second": 14.919,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 0.47246110439300537,
+      "eval_runtime": 0.2782,
+      "eval_samples_per_second": 3134.998,
+      "eval_steps_per_second": 14.381,
       "step": 792
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.3541450500488281,
-      "learning_rate": 0.00092,
-      "loss": 0.6867,
+      "grad_norm": 6.613548755645752,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.161,
       "step": 1056
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.695652961730957,
-      "eval_runtime": 0.268,
-      "eval_samples_per_second": 3253.504,
-      "eval_steps_per_second": 14.924,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 0.531734824180603,
+      "eval_runtime": 0.278,
+      "eval_samples_per_second": 3136.958,
+      "eval_steps_per_second": 14.39,
       "step": 1056
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.18224285542964935,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6867,
+      "grad_norm": 9.82017993927002,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1363,
       "step": 1320
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6973552107810974,
-      "eval_runtime": 0.272,
-      "eval_samples_per_second": 3206.126,
-      "eval_steps_per_second": 14.707,
+      "eval_accuracy": 0.8073394495412844,
+      "eval_loss": 0.5661426782608032,
+      "eval_runtime": 0.2752,
+      "eval_samples_per_second": 3168.806,
+      "eval_steps_per_second": 14.536,
       "step": 1320
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.08771929144859314,
-      "learning_rate": 0.00088,
-      "loss": 0.6864,
+      "grad_norm": 2.2137458324432373,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1147,
       "step": 1584
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6970685124397278,
-      "eval_runtime": 0.2805,
-      "eval_samples_per_second": 3109.229,
-      "eval_steps_per_second": 14.263,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 0.6461686491966248,
+      "eval_runtime": 0.2696,
+      "eval_samples_per_second": 3234.111,
+      "eval_steps_per_second": 14.835,
       "step": 1584
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.24813300371170044,
-      "learning_rate": 0.00086,
-      "loss": 0.6863,
+      "grad_norm": 4.09332799911499,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0959,
       "step": 1848
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6987707614898682,
-      "eval_runtime": 0.2765,
-      "eval_samples_per_second": 3153.642,
-      "eval_steps_per_second": 14.466,
+      "eval_accuracy": 0.7970183486238532,
+      "eval_loss": 0.7102797627449036,
+      "eval_runtime": 0.2804,
+      "eval_samples_per_second": 3109.959,
+      "eval_steps_per_second": 14.266,
       "step": 1848
     },
     {
       "epoch": 7.0,
       "step": 1848,
       "total_flos": 1.2362922335855616e+16,
-      "train_loss": 0.6874211381524156,
-      "train_runtime": 259.3366,
-      "train_samples_per_second": 12984.864,
-      "train_steps_per_second": 50.899
+      "train_loss": 0.19844082836464885,
+      "train_runtime": 261.6164,
+      "train_samples_per_second": 12871.711,
+      "train_steps_per_second": 50.456
     }
   ],
   "logging_steps": 1,