End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_lda_50_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: 0.6936274509803921
+    - name: F1
+      type: f1
+      value: 0.8085758039816232
 ---
 
 <!-- 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_base_lda_50_v1_mrpc
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_50_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_50_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_50_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_50_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0029
-- Accuracy: 0.6961
-- F1: 0.7898
-- Combined Score: 0.7430
+- Loss: 0.6034
+- Accuracy: 0.6936
+- F1: 0.8086
+- Combined Score: 0.7511
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
-    "epoch": 15.0,
-    "eval_accuracy": 0.6838235294117647,
-    "eval_combined_score": 0.7480253018237863,
-    "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6226160526275635,
-    "eval_runtime": 0.2891,
+    "epoch": 7.0,
+    "eval_accuracy": 0.6936274509803921,
+    "eval_combined_score": 0.7511016274810076,
+    "eval_f1": 0.8085758039816232,
+    "eval_loss": 0.6033744215965271,
+    "eval_runtime": 0.2803,
     "eval_samples": 408,
-    "eval_samples_per_second": 1411.139,
-    "eval_steps_per_second": 6.917,
-    "total_flos": 7238185132953600.0,
-    "train_loss": 0.7287869644165039,
-    "train_runtime": 125.4342,
+    "eval_samples_per_second": 1455.604,
+    "eval_steps_per_second": 7.135,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.4559453896113804,
+    "train_runtime": 63.2715,
     "train_samples": 3668,
-    "train_samples_per_second": 1462.121,
-    "train_steps_per_second": 5.979
+    "train_samples_per_second": 2898.617,
+    "train_steps_per_second": 11.854
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 15.0,
-    "eval_accuracy": 0.6838235294117647,
-    "eval_combined_score": 0.7480253018237863,
-    "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6226160526275635,
-    "eval_runtime": 0.2891,
+    "epoch": 7.0,
+    "eval_accuracy": 0.6936274509803921,
+    "eval_combined_score": 0.7511016274810076,
+    "eval_f1": 0.8085758039816232,
+    "eval_loss": 0.6033744215965271,
+    "eval_runtime": 0.2803,
     "eval_samples": 408,
-    "eval_samples_per_second": 1411.139,
-    "eval_steps_per_second": 6.917
+    "eval_samples_per_second": 1455.604,
+    "eval_steps_per_second": 7.135
 }

logs/events.out.tfevents.1733309777.ki-g0008.1207984.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d826b00ea7a48732f2540c1b15943458c761499b8d05f106c4db5518f4cc1d
+size 507

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 15.0,
-    "total_flos": 7238185132953600.0,
-    "train_loss": 0.7287869644165039,
-    "train_runtime": 125.4342,
+    "epoch": 7.0,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.4559453896113804,
+    "train_runtime": 63.2715,
     "train_samples": 3668,
-    "train_samples_per_second": 1462.121,
-    "train_steps_per_second": 5.979
+    "train_samples_per_second": 2898.617,
+    "train_steps_per_second": 11.854
 }

trainer_state.json

@@ -1,291 +1,147 @@
 {
-  "best_metric": 0.6226160526275635,
-  "best_model_checkpoint": "bert_base_lda_50_v1_mrpc/checkpoint-150",
-  "epoch": 15.0,
+  "best_metric": 0.6033744215965271,
+  "best_model_checkpoint": "bert_base_lda_50_v1_mrpc/checkpoint-30",
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 225,
+  "global_step": 105,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 22.977022171020508,
-      "learning_rate": 0.00098,
-      "loss": 1.9018,
+      "grad_norm": 0.8829944133758545,
+      "learning_rate": 4.9e-05,
+      "loss": 0.669,
       "step": 15
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.3161764705882353,
-      "eval_combined_score": 0.15808823529411764,
-      "eval_f1": 0.0,
-      "eval_loss": 1.746949315071106,
-      "eval_runtime": 0.2773,
-      "eval_samples_per_second": 1471.484,
-      "eval_steps_per_second": 7.213,
+      "eval_accuracy": 0.6813725490196079,
+      "eval_combined_score": 0.744247105370338,
+      "eval_f1": 0.8071216617210681,
+      "eval_loss": 0.6216921210289001,
+      "eval_runtime": 0.273,
+      "eval_samples_per_second": 1494.435,
+      "eval_steps_per_second": 7.326,
       "step": 15
     },
     {
       "epoch": 2.0,
-      "grad_norm": 5.6883745193481445,
-      "learning_rate": 0.00096,
-      "loss": 0.7758,
+      "grad_norm": 1.7580305337905884,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6174,
       "step": 30
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.713627815246582,
-      "eval_runtime": 0.2735,
-      "eval_samples_per_second": 1491.747,
-      "eval_steps_per_second": 7.312,
+      "eval_accuracy": 0.6936274509803921,
+      "eval_combined_score": 0.7511016274810076,
+      "eval_f1": 0.8085758039816232,
+      "eval_loss": 0.6033744215965271,
+      "eval_runtime": 0.2839,
+      "eval_samples_per_second": 1437.191,
+      "eval_steps_per_second": 7.045,
       "step": 30
     },
     {
       "epoch": 3.0,
-      "grad_norm": 2.137789249420166,
-      "learning_rate": 0.00094,
-      "loss": 0.6464,
+      "grad_norm": 1.2845402956008911,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5792,
       "step": 45
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6401654481887817,
-      "eval_runtime": 0.3133,
-      "eval_samples_per_second": 1302.407,
-      "eval_steps_per_second": 6.384,
+      "eval_accuracy": 0.7009803921568627,
+      "eval_combined_score": 0.7594454199590284,
+      "eval_f1": 0.817910447761194,
+      "eval_loss": 0.6052736639976501,
+      "eval_runtime": 0.2747,
+      "eval_samples_per_second": 1485.166,
+      "eval_steps_per_second": 7.28,
       "step": 45
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.9102729558944702,
-      "learning_rate": 0.00092,
-      "loss": 0.6412,
+      "grad_norm": 2.5384278297424316,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5085,
       "step": 60
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6260914206504822,
-      "eval_runtime": 0.2816,
-      "eval_samples_per_second": 1449.033,
-      "eval_steps_per_second": 7.103,
+      "eval_accuracy": 0.6740196078431373,
+      "eval_combined_score": 0.7140892863614947,
+      "eval_f1": 0.7541589648798522,
+      "eval_loss": 0.6419196128845215,
+      "eval_runtime": 0.2836,
+      "eval_samples_per_second": 1438.409,
+      "eval_steps_per_second": 7.051,
       "step": 60
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.8048895001411438,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6318,
+      "grad_norm": 5.037930488586426,
+      "learning_rate": 4.5e-05,
+      "loss": 0.373,
       "step": 75
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6250861883163452,
-      "eval_runtime": 0.2775,
-      "eval_samples_per_second": 1470.21,
-      "eval_steps_per_second": 7.207,
+      "eval_accuracy": 0.7083333333333334,
+      "eval_combined_score": 0.7592703349282297,
+      "eval_f1": 0.810207336523126,
+      "eval_loss": 0.749921441078186,
+      "eval_runtime": 0.2767,
+      "eval_samples_per_second": 1474.352,
+      "eval_steps_per_second": 7.227,
       "step": 75
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.975186288356781,
-      "learning_rate": 0.00088,
-      "loss": 0.6352,
+      "grad_norm": 6.258988857269287,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2611,
       "step": 90
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6246122717857361,
-      "eval_runtime": 0.2709,
-      "eval_samples_per_second": 1506.067,
-      "eval_steps_per_second": 7.383,
+      "eval_accuracy": 0.6495098039215687,
+      "eval_combined_score": 0.6911100421477001,
+      "eval_f1": 0.7327102803738317,
+      "eval_loss": 0.907718300819397,
+      "eval_runtime": 0.2843,
+      "eval_samples_per_second": 1434.985,
+      "eval_steps_per_second": 7.034,
       "step": 90
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.4961640536785126,
-      "learning_rate": 0.00086,
-      "loss": 0.635,
+      "grad_norm": 10.116829872131348,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1835,
       "step": 105
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6256270408630371,
-      "eval_runtime": 0.2693,
-      "eval_samples_per_second": 1515.101,
-      "eval_steps_per_second": 7.427,
+      "eval_accuracy": 0.696078431372549,
+      "eval_combined_score": 0.7429544699235626,
+      "eval_f1": 0.7898305084745764,
+      "eval_loss": 1.00290048122406,
+      "eval_runtime": 0.281,
+      "eval_samples_per_second": 1451.74,
+      "eval_steps_per_second": 7.116,
       "step": 105
     },
     {
-      "epoch": 8.0,
-      "grad_norm": 0.3314763903617859,
-      "learning_rate": 0.00084,
-      "loss": 0.634,
-      "step": 120
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6243536472320557,
-      "eval_runtime": 0.2744,
-      "eval_samples_per_second": 1487.06,
-      "eval_steps_per_second": 7.29,
-      "step": 120
-    },
-    {
-      "epoch": 9.0,
-      "grad_norm": 0.5980406403541565,
-      "learning_rate": 0.00082,
-      "loss": 0.6297,
-      "step": 135
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.634880542755127,
-      "eval_runtime": 0.2751,
-      "eval_samples_per_second": 1482.984,
-      "eval_steps_per_second": 7.27,
-      "step": 135
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 0.4592650532722473,
-      "learning_rate": 0.0008,
-      "loss": 0.6357,
-      "step": 150
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6226160526275635,
-      "eval_runtime": 0.2684,
-      "eval_samples_per_second": 1520.307,
-      "eval_steps_per_second": 7.452,
-      "step": 150
-    },
-    {
-      "epoch": 11.0,
-      "grad_norm": 0.7528880834579468,
-      "learning_rate": 0.0007800000000000001,
-      "loss": 0.6341,
-      "step": 165
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6255601048469543,
-      "eval_runtime": 0.2722,
-      "eval_samples_per_second": 1499.113,
-      "eval_steps_per_second": 7.349,
-      "step": 165
-    },
-    {
-      "epoch": 12.0,
-      "grad_norm": 0.380775511264801,
-      "learning_rate": 0.00076,
-      "loss": 0.6333,
-      "step": 180
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6249569058418274,
-      "eval_runtime": 0.2722,
-      "eval_samples_per_second": 1498.681,
-      "eval_steps_per_second": 7.346,
-      "step": 180
-    },
-    {
-      "epoch": 13.0,
-      "grad_norm": 0.6090389490127563,
-      "learning_rate": 0.00074,
-      "loss": 0.6309,
-      "step": 195
-    },
-    {
-      "epoch": 13.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6240330338478088,
-      "eval_runtime": 0.2747,
-      "eval_samples_per_second": 1485.187,
-      "eval_steps_per_second": 7.28,
-      "step": 195
-    },
-    {
-      "epoch": 14.0,
-      "grad_norm": 1.031883716583252,
-      "learning_rate": 0.0007199999999999999,
-      "loss": 0.6343,
-      "step": 210
-    },
-    {
-      "epoch": 14.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6258903741836548,
-      "eval_runtime": 0.2733,
-      "eval_samples_per_second": 1492.679,
-      "eval_steps_per_second": 7.317,
-      "step": 210
-    },
-    {
-      "epoch": 15.0,
-      "grad_norm": 0.6238628029823303,
-      "learning_rate": 0.0007,
-      "loss": 0.6328,
-      "step": 225
-    },
-    {
-      "epoch": 15.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6254164576530457,
-      "eval_runtime": 0.2698,
-      "eval_samples_per_second": 1512.061,
-      "eval_steps_per_second": 7.412,
-      "step": 225
-    },
-    {
-      "epoch": 15.0,
-      "step": 225,
-      "total_flos": 7238185132953600.0,
-      "train_loss": 0.7287869644165039,
-      "train_runtime": 125.4342,
-      "train_samples_per_second": 1462.121,
-      "train_steps_per_second": 5.979
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 3377819728711680.0,
+      "train_loss": 0.4559453896113804,
+      "train_runtime": 63.2715,
+      "train_samples_per_second": 2898.617,
+      "train_steps_per_second": 11.854
     }
   ],
   "logging_steps": 1,
@@ -314,7 +170,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7238185132953600.0,
+  "total_flos": 3377819728711680.0,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null