End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_lda_5_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: 0.8188073394495413
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_lda_5_v1_sst2
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_5_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_5_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_5_v1) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6628
+- Loss: 0.4155
 - Accuracy: 0.8188
 
 ## Model description

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 9.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6957963109016418,
-    "eval_runtime": 0.5735,
+    "epoch": 6.0,
+    "eval_accuracy": 0.8188073394495413,
+    "eval_loss": 0.4155426025390625,
+    "eval_runtime": 0.5668,
     "eval_samples": 872,
-    "eval_samples_per_second": 1520.583,
-    "eval_steps_per_second": 6.975,
-    "total_flos": 7.974119910348288e+16,
-    "train_loss": 0.690731016473738,
-    "train_runtime": 1003.1459,
+    "eval_samples_per_second": 1538.417,
+    "eval_steps_per_second": 7.057,
+    "total_flos": 5.316079940232192e+16,
+    "train_loss": 0.1595491110676467,
+    "train_runtime": 673.4183,
     "train_samples": 67349,
-    "train_samples_per_second": 3356.89,
-    "train_steps_per_second": 13.159
+    "train_samples_per_second": 5000.533,
+    "train_steps_per_second": 19.601
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 9.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6957963109016418,
-    "eval_runtime": 0.5735,
+    "epoch": 6.0,
+    "eval_accuracy": 0.8188073394495413,
+    "eval_loss": 0.4155426025390625,
+    "eval_runtime": 0.5668,
     "eval_samples": 872,
-    "eval_samples_per_second": 1520.583,
-    "eval_steps_per_second": 6.975
+    "eval_samples_per_second": 1538.417,
+    "eval_steps_per_second": 7.057
 }

logs/events.out.tfevents.1733316567.ki-g0008.1206925.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f691ace0a10c567e6f7d8dc265169814552a2a835b50cfddf7ee2d8a2d16b2
+size 411

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 9.0,
-    "total_flos": 7.974119910348288e+16,
-    "train_loss": 0.690731016473738,
-    "train_runtime": 1003.1459,
+    "epoch": 6.0,
+    "total_flos": 5.316079940232192e+16,
+    "train_loss": 0.1595491110676467,
+    "train_runtime": 673.4183,
     "train_samples": 67349,
-    "train_samples_per_second": 3356.89,
-    "train_steps_per_second": 13.159
+    "train_samples_per_second": 5000.533,
+    "train_steps_per_second": 19.601
 }

trainer_state.json

@@ -1,165 +1,117 @@
 {
-  "best_metric": 0.6957963109016418,
-  "best_model_checkpoint": "bert_base_lda_5_v1_sst2/checkpoint-1056",
-  "epoch": 9.0,
+  "best_metric": 0.4155426025390625,
+  "best_model_checkpoint": "bert_base_lda_5_v1_sst2/checkpoint-264",
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 2376,
+  "global_step": 1584,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.312673807144165,
-      "learning_rate": 0.00098,
-      "loss": 0.7225,
+      "grad_norm": 11.683303833007812,
+      "learning_rate": 4.9e-05,
+      "loss": 0.3663,
       "step": 264
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6971402168273926,
-      "eval_runtime": 0.5874,
-      "eval_samples_per_second": 1484.493,
-      "eval_steps_per_second": 6.81,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 0.4155426025390625,
+      "eval_runtime": 0.5748,
+      "eval_samples_per_second": 1516.971,
+      "eval_steps_per_second": 6.959,
       "step": 264
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.6830663084983826,
-      "learning_rate": 0.00096,
-      "loss": 0.6869,
+      "grad_norm": 7.497736930847168,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2043,
       "step": 528
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.697937548160553,
-      "eval_runtime": 0.5689,
-      "eval_samples_per_second": 1532.765,
-      "eval_steps_per_second": 7.031,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 0.49000003933906555,
+      "eval_runtime": 0.5765,
+      "eval_samples_per_second": 1512.651,
+      "eval_steps_per_second": 6.939,
       "step": 528
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.2608537971973419,
-      "learning_rate": 0.00094,
-      "loss": 0.687,
+      "grad_norm": 5.43668794631958,
+      "learning_rate": 4.7e-05,
+      "loss": 0.1431,
       "step": 792
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.698914110660553,
-      "eval_runtime": 0.578,
-      "eval_samples_per_second": 1508.521,
-      "eval_steps_per_second": 6.92,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 0.5357560515403748,
+      "eval_runtime": 0.5806,
+      "eval_samples_per_second": 1502.021,
+      "eval_steps_per_second": 6.89,
       "step": 792
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.5241749882698059,
-      "learning_rate": 0.00092,
-      "loss": 0.687,
+      "grad_norm": 5.869522571563721,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1031,
       "step": 1056
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6957963109016418,
-      "eval_runtime": 0.573,
-      "eval_samples_per_second": 1521.859,
-      "eval_steps_per_second": 6.981,
+      "eval_accuracy": 0.8268348623853211,
+      "eval_loss": 0.606959342956543,
+      "eval_runtime": 0.5764,
+      "eval_samples_per_second": 1512.715,
+      "eval_steps_per_second": 6.939,
       "step": 1056
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.230000838637352,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6869,
+      "grad_norm": 5.141781330108643,
+      "learning_rate": 4.5e-05,
+      "loss": 0.0786,
       "step": 1320
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6986991167068481,
-      "eval_runtime": 0.571,
-      "eval_samples_per_second": 1527.197,
-      "eval_steps_per_second": 7.005,
+      "eval_accuracy": 0.8096330275229358,
+      "eval_loss": 0.5407425761222839,
+      "eval_runtime": 0.5718,
+      "eval_samples_per_second": 1524.94,
+      "eval_steps_per_second": 6.995,
       "step": 1320
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.08836159110069275,
-      "learning_rate": 0.00088,
-      "loss": 0.6865,
+      "grad_norm": 6.738317012786865,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0619,
       "step": 1584
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6990574598312378,
-      "eval_runtime": 0.5746,
-      "eval_samples_per_second": 1517.549,
-      "eval_steps_per_second": 6.961,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 0.6628296375274658,
+      "eval_runtime": 0.576,
+      "eval_samples_per_second": 1513.844,
+      "eval_steps_per_second": 6.944,
       "step": 1584
     },
     {
-      "epoch": 7.0,
-      "grad_norm": 0.2432480752468109,
-      "learning_rate": 0.00086,
-      "loss": 0.6865,
-      "step": 1848
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.7004730701446533,
-      "eval_runtime": 0.5665,
-      "eval_samples_per_second": 1539.391,
-      "eval_steps_per_second": 7.061,
-      "step": 1848
-    },
-    {
-      "epoch": 8.0,
-      "grad_norm": 0.12161114066839218,
-      "learning_rate": 0.00084,
-      "loss": 0.6866,
-      "step": 2112
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6989858150482178,
-      "eval_runtime": 0.5784,
-      "eval_samples_per_second": 1507.619,
-      "eval_steps_per_second": 6.916,
-      "step": 2112
-    },
-    {
-      "epoch": 9.0,
-      "grad_norm": 0.32175755500793457,
-      "learning_rate": 0.00082,
-      "loss": 0.6866,
-      "step": 2376
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.698914110660553,
-      "eval_runtime": 0.5775,
-      "eval_samples_per_second": 1509.895,
-      "eval_steps_per_second": 6.926,
-      "step": 2376
-    },
-    {
-      "epoch": 9.0,
-      "step": 2376,
-      "total_flos": 7.974119910348288e+16,
-      "train_loss": 0.690731016473738,
-      "train_runtime": 1003.1459,
-      "train_samples_per_second": 3356.89,
-      "train_steps_per_second": 13.159
+      "epoch": 6.0,
+      "step": 1584,
+      "total_flos": 5.316079940232192e+16,
+      "train_loss": 0.1595491110676467,
+      "train_runtime": 673.4183,
+      "train_samples_per_second": 5000.533,
+      "train_steps_per_second": 19.601
     }
   ],
   "logging_steps": 1,
@@ -188,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.974119910348288e+16,
+  "total_flos": 5.316079940232192e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null