End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_lda_50_v1_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7367746659344683
 ---
 
 <!-- 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_base_lda_50_v1_qnli
 
-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 QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0230
-- Accuracy: 0.7276
+- Loss: 0.5458
+- Accuracy: 0.7368
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 6.0,
-    "eval_accuracy": 0.5053999633900788,
-    "eval_loss": 0.69140625,
-    "eval_runtime": 3.4852,
+    "epoch": 8.0,
+    "eval_accuracy": 0.7367746659344683,
+    "eval_loss": 0.5458308458328247,
+    "eval_runtime": 3.5103,
     "eval_samples": 5463,
-    "eval_samples_per_second": 1567.487,
-    "eval_steps_per_second": 6.312,
-    "total_flos": 8.267712381471744e+16,
-    "train_loss": 0.700571944073933,
-    "train_runtime": 1041.1142,
+    "eval_samples_per_second": 1556.293,
+    "eval_steps_per_second": 6.267,
+    "total_flos": 1.1023616508628992e+17,
+    "train_loss": 0.33002244205009645,
+    "train_runtime": 1412.0901,
     "train_samples": 104743,
-    "train_samples_per_second": 5030.332,
-    "train_steps_per_second": 19.69
+    "train_samples_per_second": 3708.793,
+    "train_steps_per_second": 14.517
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 6.0,
-    "eval_accuracy": 0.5053999633900788,
-    "eval_loss": 0.69140625,
-    "eval_runtime": 3.4852,
+    "epoch": 8.0,
+    "eval_accuracy": 0.7367746659344683,
+    "eval_loss": 0.5458308458328247,
+    "eval_runtime": 3.5103,
     "eval_samples": 5463,
-    "eval_samples_per_second": 1567.487,
-    "eval_steps_per_second": 6.312
+    "eval_samples_per_second": 1556.293,
+    "eval_steps_per_second": 6.267
 }

logs/events.out.tfevents.1733311267.ki-g0008.1207984.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a0e9e7ba719ab830cd9eec59146b596644a4a5b376b3069eb2da4ae5a45067
+size 411

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 6.0,
-    "total_flos": 8.267712381471744e+16,
-    "train_loss": 0.700571944073933,
-    "train_runtime": 1041.1142,
+    "epoch": 8.0,
+    "total_flos": 1.1023616508628992e+17,
+    "train_loss": 0.33002244205009645,
+    "train_runtime": 1412.0901,
     "train_samples": 104743,
-    "train_samples_per_second": 5030.332,
-    "train_steps_per_second": 19.69
+    "train_samples_per_second": 3708.793,
+    "train_steps_per_second": 14.517
 }

trainer_state.json

@@ -1,117 +1,149 @@
 {
-  "best_metric": 0.69140625,
-  "best_model_checkpoint": "bert_base_lda_50_v1_qnli/checkpoint-410",
-  "epoch": 6.0,
+  "best_metric": 0.5458308458328247,
+  "best_model_checkpoint": "bert_base_lda_50_v1_qnli/checkpoint-1230",
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 2460,
+  "global_step": 3280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.1446128487586975,
-      "learning_rate": 0.00098,
-      "loss": 0.7377,
+      "grad_norm": 2.3502628803253174,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6503,
       "step": 410
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.69140625,
-      "eval_runtime": 3.4916,
-      "eval_samples_per_second": 1564.617,
-      "eval_steps_per_second": 6.301,
+      "eval_accuracy": 0.6505583012996522,
+      "eval_loss": 0.6147003173828125,
+      "eval_runtime": 3.5547,
+      "eval_samples_per_second": 1536.826,
+      "eval_steps_per_second": 6.189,
       "step": 410
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.09045995026826859,
-      "learning_rate": 0.00096,
-      "loss": 0.6931,
+      "grad_norm": 3.2205982208251953,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5535,
       "step": 820
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 3.4757,
-      "eval_samples_per_second": 1571.764,
-      "eval_steps_per_second": 6.33,
+      "eval_accuracy": 0.7155409115870401,
+      "eval_loss": 0.5496997237205505,
+      "eval_runtime": 3.5498,
+      "eval_samples_per_second": 1538.962,
+      "eval_steps_per_second": 6.198,
       "step": 820
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.1270582526922226,
-      "learning_rate": 0.00094,
-      "loss": 0.6931,
+      "grad_norm": 3.7460732460021973,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4425,
       "step": 1230
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 3.4762,
-      "eval_samples_per_second": 1571.546,
-      "eval_steps_per_second": 6.329,
+      "eval_accuracy": 0.7367746659344683,
+      "eval_loss": 0.5458308458328247,
+      "eval_runtime": 3.5648,
+      "eval_samples_per_second": 1532.48,
+      "eval_steps_per_second": 6.171,
       "step": 1230
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.01812651753425598,
-      "learning_rate": 0.00092,
-      "loss": 0.6931,
+      "grad_norm": 6.930105209350586,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3413,
       "step": 1640
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 3.4854,
-      "eval_samples_per_second": 1567.408,
-      "eval_steps_per_second": 6.312,
+      "eval_accuracy": 0.733479773018488,
+      "eval_loss": 0.6162947416305542,
+      "eval_runtime": 3.5841,
+      "eval_samples_per_second": 1524.219,
+      "eval_steps_per_second": 6.138,
       "step": 1640
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.047646842896938324,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6931,
+      "grad_norm": 7.669921398162842,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2508,
       "step": 2050
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6934648156166077,
-      "eval_runtime": 3.4742,
-      "eval_samples_per_second": 1572.454,
-      "eval_steps_per_second": 6.332,
+      "eval_accuracy": 0.7384221123924584,
+      "eval_loss": 0.6988028883934021,
+      "eval_runtime": 3.562,
+      "eval_samples_per_second": 1533.698,
+      "eval_steps_per_second": 6.176,
       "step": 2050
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.05455218255519867,
-      "learning_rate": 0.00088,
-      "loss": 0.6932,
+      "grad_norm": 8.73188304901123,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1792,
       "step": 2460
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 3.4771,
-      "eval_samples_per_second": 1571.138,
-      "eval_steps_per_second": 6.327,
+      "eval_accuracy": 0.7338458722313747,
+      "eval_loss": 0.8530865907669067,
+      "eval_runtime": 3.5879,
+      "eval_samples_per_second": 1522.601,
+      "eval_steps_per_second": 6.132,
       "step": 2460
     },
     {
-      "epoch": 6.0,
-      "step": 2460,
-      "total_flos": 8.267712381471744e+16,
-      "train_loss": 0.700571944073933,
-      "train_runtime": 1041.1142,
-      "train_samples_per_second": 5030.332,
-      "train_steps_per_second": 19.69
+      "epoch": 7.0,
+      "grad_norm": 6.224167346954346,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1282,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7285374336445176,
+      "eval_loss": 0.9750887155532837,
+      "eval_runtime": 3.585,
+      "eval_samples_per_second": 1523.83,
+      "eval_steps_per_second": 6.137,
+      "step": 2870
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 6.511787414550781,
+      "learning_rate": 4.2e-05,
+      "loss": 0.0942,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.727622185612301,
+      "eval_loss": 1.022977352142334,
+      "eval_runtime": 3.522,
+      "eval_samples_per_second": 1551.101,
+      "eval_steps_per_second": 6.246,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "step": 3280,
+      "total_flos": 1.1023616508628992e+17,
+      "train_loss": 0.33002244205009645,
+      "train_runtime": 1412.0901,
+      "train_samples_per_second": 3708.793,
+      "train_steps_per_second": 14.517
     }
   ],
   "logging_steps": 1,
@@ -140,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.267712381471744e+16,
+  "total_flos": 1.1023616508628992e+17,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null