End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_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: 0.6911764705882353
+    - name: F1
+      type: f1
+      value: 0.8061538461538462
 ---
 
 <!-- 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_100_v1_mrpc
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0601
-- Accuracy: 0.6691
-- F1: 0.7700
-- Combined Score: 0.7196
+- Loss: 0.5799
+- Accuracy: 0.6912
+- F1: 0.8062
+- Combined Score: 0.7487
 
 ## 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": 0.6229463219642639,
-    "eval_runtime": 0.2736,
+    "epoch": 8.0,
+    "eval_accuracy": 0.6911764705882353,
+    "eval_combined_score": 0.7486651583710408,
+    "eval_f1": 0.8061538461538462,
+    "eval_loss": 0.5798782706260681,
+    "eval_runtime": 0.2768,
     "eval_samples": 408,
-    "eval_samples_per_second": 1491.428,
-    "eval_steps_per_second": 7.311,
-    "total_flos": 3377819728711680.0,
-    "train_loss": 0.7818594705490839,
-    "train_runtime": 61.1043,
+    "eval_samples_per_second": 1474.165,
+    "eval_steps_per_second": 7.226,
+    "total_flos": 3860365404241920.0,
+    "train_loss": 0.4376857062180837,
+    "train_runtime": 71.3419,
     "train_samples": 3668,
-    "train_samples_per_second": 3001.426,
-    "train_steps_per_second": 12.274
+    "train_samples_per_second": 2570.719,
+    "train_steps_per_second": 10.513
 }

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": 0.6229463219642639,
-    "eval_runtime": 0.2736,
+    "epoch": 8.0,
+    "eval_accuracy": 0.6911764705882353,
+    "eval_combined_score": 0.7486651583710408,
+    "eval_f1": 0.8061538461538462,
+    "eval_loss": 0.5798782706260681,
+    "eval_runtime": 0.2768,
     "eval_samples": 408,
-    "eval_samples_per_second": 1491.428,
-    "eval_steps_per_second": 7.311
+    "eval_samples_per_second": 1474.165,
+    "eval_steps_per_second": 7.226
 }

logs/events.out.tfevents.1733309762.ki-g0008.1208741.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bbd6fa75d4ad1d1eb92df9bd9a1a334406d516a75f0492372bb4b71bf428392
+size 507

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 7.0,
-    "total_flos": 3377819728711680.0,
-    "train_loss": 0.7818594705490839,
-    "train_runtime": 61.1043,
+    "epoch": 8.0,
+    "total_flos": 3860365404241920.0,
+    "train_loss": 0.4376857062180837,
+    "train_runtime": 71.3419,
     "train_samples": 3668,
-    "train_samples_per_second": 3001.426,
-    "train_steps_per_second": 12.274
+    "train_samples_per_second": 2570.719,
+    "train_steps_per_second": 10.513
 }

trainer_state.json

@@ -1,147 +1,165 @@
 {
-  "best_metric": 0.6229463219642639,
-  "best_model_checkpoint": "bert_base_lda_100_v1_mrpc/checkpoint-30",
-  "epoch": 7.0,
+  "best_metric": 0.5798782706260681,
+  "best_model_checkpoint": "bert_base_lda_100_v1_mrpc/checkpoint-45",
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 105,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.3839820325374603,
-      "learning_rate": 0.00098,
-      "loss": 1.6608,
+      "grad_norm": 1.1343425512313843,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6665,
       "step": 15
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6274126768112183,
-      "eval_runtime": 0.3333,
-      "eval_samples_per_second": 1224.147,
-      "eval_steps_per_second": 6.001,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_combined_score": 0.7136150234741783,
+      "eval_f1": 0.76056338028169,
+      "eval_loss": 0.6143702864646912,
+      "eval_runtime": 0.2749,
+      "eval_samples_per_second": 1484.233,
+      "eval_steps_per_second": 7.276,
       "step": 15
     },
     {
       "epoch": 2.0,
-      "grad_norm": 1.8113455772399902,
-      "learning_rate": 0.00096,
-      "loss": 0.6437,
+      "grad_norm": 1.3366286754608154,
+      "learning_rate": 4.8e-05,
+      "loss": 0.594,
       "step": 30
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6229463219642639,
-      "eval_runtime": 0.2779,
-      "eval_samples_per_second": 1467.932,
-      "eval_steps_per_second": 7.196,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_combined_score": 0.7505520979722948,
+      "eval_f1": 0.795221843003413,
+      "eval_loss": 0.5914976596832275,
+      "eval_runtime": 0.2751,
+      "eval_samples_per_second": 1482.998,
+      "eval_steps_per_second": 7.27,
       "step": 30
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.1818019151687622,
-      "learning_rate": 0.00094,
-      "loss": 0.6306,
+      "grad_norm": 1.057149052619934,
+      "learning_rate": 4.7e-05,
+      "loss": 0.575,
       "step": 45
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6274126768112183,
-      "eval_runtime": 0.2695,
-      "eval_samples_per_second": 1513.829,
-      "eval_steps_per_second": 7.421,
+      "eval_accuracy": 0.6911764705882353,
+      "eval_combined_score": 0.7486651583710408,
+      "eval_f1": 0.8061538461538462,
+      "eval_loss": 0.5798782706260681,
+      "eval_runtime": 0.2754,
+      "eval_samples_per_second": 1481.593,
+      "eval_steps_per_second": 7.263,
       "step": 45
     },
     {
       "epoch": 4.0,
-      "grad_norm": 1.0649493932724,
-      "learning_rate": 0.00092,
-      "loss": 0.637,
+      "grad_norm": 3.827286958694458,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5285,
       "step": 60
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6244111061096191,
-      "eval_runtime": 0.2681,
-      "eval_samples_per_second": 1521.562,
-      "eval_steps_per_second": 7.459,
+      "eval_accuracy": 0.7034313725490197,
+      "eval_combined_score": 0.7510501288701837,
+      "eval_f1": 0.7986688851913478,
+      "eval_loss": 0.5992879867553711,
+      "eval_runtime": 0.2877,
+      "eval_samples_per_second": 1417.975,
+      "eval_steps_per_second": 6.951,
       "step": 60
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.477798730134964,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6341,
+      "grad_norm": 2.9875845909118652,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4277,
       "step": 75
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6260770559310913,
-      "eval_runtime": 0.2813,
-      "eval_samples_per_second": 1450.245,
-      "eval_steps_per_second": 7.109,
+      "eval_accuracy": 0.6764705882352942,
+      "eval_combined_score": 0.715100965759438,
+      "eval_f1": 0.753731343283582,
+      "eval_loss": 0.655691385269165,
+      "eval_runtime": 0.2814,
+      "eval_samples_per_second": 1450.083,
+      "eval_steps_per_second": 7.108,
       "step": 75
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.7583205699920654,
-      "learning_rate": 0.00088,
-      "loss": 0.6342,
+      "grad_norm": 2.7185416221618652,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3244,
       "step": 90
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6254164576530457,
-      "eval_runtime": 0.27,
-      "eval_samples_per_second": 1511.199,
-      "eval_steps_per_second": 7.408,
+      "eval_accuracy": 0.696078431372549,
+      "eval_combined_score": 0.749313101036593,
+      "eval_f1": 0.8025477707006369,
+      "eval_loss": 0.8220387101173401,
+      "eval_runtime": 0.2781,
+      "eval_samples_per_second": 1467.238,
+      "eval_steps_per_second": 7.192,
       "step": 90
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.5159490704536438,
-      "learning_rate": 0.00086,
-      "loss": 0.6328,
+      "grad_norm": 4.188333988189697,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2387,
       "step": 105
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6252872347831726,
-      "eval_runtime": 0.2806,
-      "eval_samples_per_second": 1454.165,
-      "eval_steps_per_second": 7.128,
+      "eval_accuracy": 0.6421568627450981,
+      "eval_combined_score": 0.6838603862597672,
+      "eval_f1": 0.7255639097744362,
+      "eval_loss": 0.8551956415176392,
+      "eval_runtime": 0.2771,
+      "eval_samples_per_second": 1472.601,
+      "eval_steps_per_second": 7.219,
       "step": 105
     },
     {
-      "epoch": 7.0,
-      "step": 105,
-      "total_flos": 3377819728711680.0,
-      "train_loss": 0.7818594705490839,
-      "train_runtime": 61.1043,
-      "train_samples_per_second": 3001.426,
-      "train_steps_per_second": 12.274
+      "epoch": 8.0,
+      "grad_norm": 3.75746488571167,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1466,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6691176470588235,
+      "eval_combined_score": 0.7195673414169756,
+      "eval_f1": 0.7700170357751278,
+      "eval_loss": 1.0601282119750977,
+      "eval_runtime": 0.2766,
+      "eval_samples_per_second": 1475.248,
+      "eval_steps_per_second": 7.232,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "step": 120,
+      "total_flos": 3860365404241920.0,
+      "train_loss": 0.4376857062180837,
+      "train_runtime": 71.3419,
+      "train_samples_per_second": 2570.719,
+      "train_steps_per_second": 10.513
     }
   ],
   "logging_steps": 1,
@@ -170,7 +188,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3377819728711680.0,
+  "total_flos": 3860365404241920.0,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null