End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_tiny_lda_100_v1_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6813725490196079
+    - name: F1
+      type: f1
+      value: 0.7916666666666669
 ---
 
 <!-- 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. -->
 
 # bert_tiny_lda_100_v1_mrpc
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8055
-- Accuracy: 0.6299
-- F1: 0.7318
-- Combined Score: 0.6808
+- Loss: 0.5925
+- Accuracy: 0.6814
+- F1: 0.7917
+- Combined Score: 0.7365
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 7.0,
-    "eval_accuracy": 0.6838235294117647,
-    "eval_combined_score": 0.7480253018237863,
-    "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6236787438392639,
-    "eval_runtime": 0.143,
+    "eval_accuracy": 0.6813725490196079,
+    "eval_combined_score": 0.7365196078431373,
+    "eval_f1": 0.7916666666666669,
+    "eval_loss": 0.5924765467643738,
+    "eval_runtime": 0.1459,
     "eval_samples": 408,
-    "eval_samples_per_second": 2852.645,
-    "eval_steps_per_second": 13.984,
+    "eval_samples_per_second": 2797.039,
+    "eval_steps_per_second": 13.711,
     "total_flos": 673316591603712.0,
-    "train_loss": 0.6492394038609096,
-    "train_runtime": 20.0708,
+    "train_loss": 0.515889158703032,
+    "train_runtime": 20.6256,
     "train_samples": 3668,
-    "train_samples_per_second": 9137.635,
-    "train_steps_per_second": 37.368
+    "train_samples_per_second": 8891.875,
+    "train_steps_per_second": 36.363
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 7.0,
-    "eval_accuracy": 0.6838235294117647,
-    "eval_combined_score": 0.7480253018237863,
-    "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6236787438392639,
-    "eval_runtime": 0.143,
+    "eval_accuracy": 0.6813725490196079,
+    "eval_combined_score": 0.7365196078431373,
+    "eval_f1": 0.7916666666666669,
+    "eval_loss": 0.5924765467643738,
+    "eval_runtime": 0.1459,
     "eval_samples": 408,
-    "eval_samples_per_second": 2852.645,
-    "eval_steps_per_second": 13.984
+    "eval_samples_per_second": 2797.039,
+    "eval_steps_per_second": 13.711
 }

logs/events.out.tfevents.1733324075.ki-g0008.1208741.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5d6e7125f30b504aab9d9086e687c078f4ce64510357626b03154edfd31865
+size 507

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 7.0,
     "total_flos": 673316591603712.0,
-    "train_loss": 0.6492394038609096,
-    "train_runtime": 20.0708,
+    "train_loss": 0.515889158703032,
+    "train_runtime": 20.6256,
     "train_samples": 3668,
-    "train_samples_per_second": 9137.635,
-    "train_steps_per_second": 37.368
+    "train_samples_per_second": 8891.875,
+    "train_steps_per_second": 36.363
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6236787438392639,
+  "best_metric": 0.5924765467643738,
   "best_model_checkpoint": "bert_tiny_lda_100_v1_mrpc/checkpoint-30",
   "epoch": 7.0,
   "eval_steps": 500,
@@ -10,138 +10,138 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.2620401084423065,
-      "learning_rate": 0.00098,
-      "loss": 0.7449,
+      "grad_norm": 0.7286933064460754,
+      "learning_rate": 4.9e-05,
+      "loss": 0.631,
       "step": 15
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6298397183418274,
-      "eval_runtime": 0.14,
-      "eval_samples_per_second": 2913.559,
-      "eval_steps_per_second": 14.282,
+      "eval_accuracy": 0.696078431372549,
+      "eval_combined_score": 0.756593787957661,
+      "eval_f1": 0.8171091445427728,
+      "eval_loss": 0.5995902419090271,
+      "eval_runtime": 0.1333,
+      "eval_samples_per_second": 3060.851,
+      "eval_steps_per_second": 15.004,
       "step": 15
     },
     {
       "epoch": 2.0,
-      "grad_norm": 1.1782532930374146,
-      "learning_rate": 0.00096,
-      "loss": 0.6364,
+      "grad_norm": 1.1771771907806396,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5947,
       "step": 30
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6236787438392639,
-      "eval_runtime": 0.1384,
-      "eval_samples_per_second": 2948.519,
-      "eval_steps_per_second": 14.454,
+      "eval_accuracy": 0.6813725490196079,
+      "eval_combined_score": 0.7365196078431373,
+      "eval_f1": 0.7916666666666669,
+      "eval_loss": 0.5924765467643738,
+      "eval_runtime": 0.1558,
+      "eval_samples_per_second": 2619.349,
+      "eval_steps_per_second": 12.84,
       "step": 30
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.6571235656738281,
-      "learning_rate": 0.00094,
-      "loss": 0.6276,
+      "grad_norm": 1.1937808990478516,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5708,
       "step": 45
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6311466097831726,
-      "eval_runtime": 0.1335,
-      "eval_samples_per_second": 3055.228,
-      "eval_steps_per_second": 14.977,
+      "eval_accuracy": 0.7009803921568627,
+      "eval_combined_score": 0.7572180248246088,
+      "eval_f1": 0.8134556574923548,
+      "eval_loss": 0.5934233069419861,
+      "eval_runtime": 0.1333,
+      "eval_samples_per_second": 3060.983,
+      "eval_steps_per_second": 15.005,
       "step": 45
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.7049502730369568,
-      "learning_rate": 0.00092,
-      "loss": 0.6363,
+      "grad_norm": 1.4581093788146973,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5419,
       "step": 60
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6257467865943909,
-      "eval_runtime": 0.138,
-      "eval_samples_per_second": 2956.659,
-      "eval_steps_per_second": 14.493,
+      "eval_accuracy": 0.6911764705882353,
+      "eval_combined_score": 0.7436464877213022,
+      "eval_f1": 0.796116504854369,
+      "eval_loss": 0.5989792943000793,
+      "eval_runtime": 0.1415,
+      "eval_samples_per_second": 2883.208,
+      "eval_steps_per_second": 14.133,
       "step": 60
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.30875012278556824,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6345,
+      "grad_norm": 1.7154335975646973,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4984,
       "step": 75
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6274126768112183,
-      "eval_runtime": 0.1399,
-      "eval_samples_per_second": 2917.384,
-      "eval_steps_per_second": 14.301,
+      "eval_accuracy": 0.678921568627451,
+      "eval_combined_score": 0.7369568719506583,
+      "eval_f1": 0.7949921752738655,
+      "eval_loss": 0.6379741430282593,
+      "eval_runtime": 0.1385,
+      "eval_samples_per_second": 2945.286,
+      "eval_steps_per_second": 14.438,
       "step": 75
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.5072498321533203,
-      "learning_rate": 0.00088,
-      "loss": 0.6332,
+      "grad_norm": 3.438758134841919,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4277,
       "step": 90
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6252154111862183,
-      "eval_runtime": 0.1373,
-      "eval_samples_per_second": 2971.961,
-      "eval_steps_per_second": 14.568,
+      "eval_accuracy": 0.6495098039215687,
+      "eval_combined_score": 0.6940419220704734,
+      "eval_f1": 0.7385740402193783,
+      "eval_loss": 0.7019862532615662,
+      "eval_runtime": 0.1332,
+      "eval_samples_per_second": 3061.947,
+      "eval_steps_per_second": 15.01,
       "step": 90
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.4643026888370514,
-      "learning_rate": 0.00086,
-      "loss": 0.6318,
+      "grad_norm": 2.9900314807891846,
+      "learning_rate": 4.3e-05,
+      "loss": 0.3467,
       "step": 105
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6241670250892639,
-      "eval_runtime": 0.135,
-      "eval_samples_per_second": 3022.719,
-      "eval_steps_per_second": 14.817,
+      "eval_accuracy": 0.6299019607843137,
+      "eval_combined_score": 0.6808479608539686,
+      "eval_f1": 0.7317939609236234,
+      "eval_loss": 0.8055003881454468,
+      "eval_runtime": 0.1441,
+      "eval_samples_per_second": 2832.183,
+      "eval_steps_per_second": 13.883,
       "step": 105
     },
     {
       "epoch": 7.0,
       "step": 105,
       "total_flos": 673316591603712.0,
-      "train_loss": 0.6492394038609096,
-      "train_runtime": 20.0708,
-      "train_samples_per_second": 9137.635,
-      "train_steps_per_second": 37.368
+      "train_loss": 0.515889158703032,
+      "train_runtime": 20.6256,
+      "train_samples_per_second": 8891.875,
+      "train_steps_per_second": 36.363
     }
   ],
   "logging_steps": 1,