End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_lda_100_v1_wnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE WNLI
+      type: glue
+      args: wnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5633802816901409
 ---
 
 <!-- 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_tiny_lda_100_v1_wnli
 
-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 WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7216
-- Accuracy: 0.2958
+- Loss: 0.7026
+- Accuracy: 0.5634
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 11.0,
+    "epoch": 7.0,
     "eval_accuracy": 0.5633802816901409,
-    "eval_loss": 0.6844189763069153,
-    "eval_runtime": 0.0309,
+    "eval_loss": 0.7025748491287231,
+    "eval_runtime": 0.0316,
     "eval_samples": 71,
-    "eval_samples_per_second": 2297.504,
-    "eval_steps_per_second": 32.359,
-    "total_flos": 183171693112320.0,
-    "train_loss": 0.7242465091474128,
-    "train_runtime": 11.5122,
+    "eval_samples_per_second": 2249.993,
+    "eval_steps_per_second": 31.69,
+    "total_flos": 116563804707840.0,
+    "train_loss": 0.6973756040845599,
+    "train_runtime": 8.699,
     "train_samples": 635,
-    "train_samples_per_second": 2757.938,
-    "train_steps_per_second": 13.03
+    "train_samples_per_second": 3649.84,
+    "train_steps_per_second": 17.243
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 11.0,
+    "epoch": 7.0,
     "eval_accuracy": 0.5633802816901409,
-    "eval_loss": 0.6844189763069153,
-    "eval_runtime": 0.0309,
+    "eval_loss": 0.7025748491287231,
+    "eval_runtime": 0.0316,
     "eval_samples": 71,
-    "eval_samples_per_second": 2297.504,
-    "eval_steps_per_second": 32.359
+    "eval_samples_per_second": 2249.993,
+    "eval_steps_per_second": 31.69
 }

logs/events.out.tfevents.1733327421.ki-g0008.1208741.33

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb7cb88eb3810f724eff99b07b2fa31cfafeaf16453190a802458829bacdf15
+size 405

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 11.0,
-    "total_flos": 183171693112320.0,
-    "train_loss": 0.7242465091474128,
-    "train_runtime": 11.5122,
+    "epoch": 7.0,
+    "total_flos": 116563804707840.0,
+    "train_loss": 0.6973756040845599,
+    "train_runtime": 8.699,
     "train_samples": 635,
-    "train_samples_per_second": 2757.938,
-    "train_steps_per_second": 13.03
+    "train_samples_per_second": 3649.84,
+    "train_steps_per_second": 17.243
 }

trainer_state.json

@@ -1,197 +1,133 @@
 {
-  "best_metric": 0.6844189763069153,
-  "best_model_checkpoint": "bert_tiny_lda_100_v1_wnli/checkpoint-18",
-  "epoch": 11.0,
+  "best_metric": 0.7025748491287231,
+  "best_model_checkpoint": "bert_tiny_lda_100_v1_wnli/checkpoint-6",
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 33,
+  "global_step": 21,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 8.367554664611816,
-      "learning_rate": 0.00098,
-      "loss": 0.988,
+      "grad_norm": 1.800396203994751,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7082,
       "step": 3
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6867297291755676,
-      "eval_runtime": 0.0295,
-      "eval_samples_per_second": 2410.246,
-      "eval_steps_per_second": 33.947,
+      "eval_accuracy": 0.352112676056338,
+      "eval_loss": 0.7107725739479065,
+      "eval_runtime": 0.0282,
+      "eval_samples_per_second": 2516.037,
+      "eval_steps_per_second": 35.437,
       "step": 3
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.5282027125358582,
-      "learning_rate": 0.00096,
-      "loss": 0.694,
+      "grad_norm": 1.2788060903549194,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7024,
       "step": 6
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6856295466423035,
-      "eval_runtime": 0.0289,
-      "eval_samples_per_second": 2460.978,
-      "eval_steps_per_second": 34.662,
+      "eval_loss": 0.7025748491287231,
+      "eval_runtime": 0.0293,
+      "eval_samples_per_second": 2424.71,
+      "eval_steps_per_second": 34.151,
       "step": 6
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.9888330101966858,
-      "learning_rate": 0.00094,
-      "loss": 0.7144,
+      "grad_norm": 0.7909756302833557,
+      "learning_rate": 4.7e-05,
+      "loss": 0.7001,
       "step": 9
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6856295466423035,
-      "eval_runtime": 0.0284,
-      "eval_samples_per_second": 2497.971,
-      "eval_steps_per_second": 35.183,
+      "eval_accuracy": 0.352112676056338,
+      "eval_loss": 0.723371684551239,
+      "eval_runtime": 0.0314,
+      "eval_samples_per_second": 2260.411,
+      "eval_steps_per_second": 31.837,
       "step": 9
     },
     {
       "epoch": 4.0,
-      "grad_norm": 1.2957957983016968,
-      "learning_rate": 0.00092,
-      "loss": 0.7011,
+      "grad_norm": 0.8608013987541199,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6938,
       "step": 12
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.6941022872924805,
-      "eval_runtime": 0.0294,
-      "eval_samples_per_second": 2412.218,
-      "eval_steps_per_second": 33.975,
+      "eval_accuracy": 0.5070422535211268,
+      "eval_loss": 0.7065912485122681,
+      "eval_runtime": 0.0296,
+      "eval_samples_per_second": 2398.618,
+      "eval_steps_per_second": 33.783,
       "step": 12
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.28737398982048035,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6932,
+      "grad_norm": 1.210613489151001,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6922,
       "step": 15
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.7037302851676941,
-      "eval_runtime": 0.0277,
-      "eval_samples_per_second": 2565.434,
-      "eval_steps_per_second": 36.133,
+      "eval_accuracy": 0.4225352112676056,
+      "eval_loss": 0.7106072902679443,
+      "eval_runtime": 0.0321,
+      "eval_samples_per_second": 2208.56,
+      "eval_steps_per_second": 31.106,
       "step": 15
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.4876857399940491,
-      "learning_rate": 0.00088,
-      "loss": 0.6964,
+      "grad_norm": 1.0442590713500977,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6958,
       "step": 18
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6844189763069153,
-      "eval_runtime": 0.0275,
-      "eval_samples_per_second": 2579.769,
-      "eval_steps_per_second": 36.335,
+      "eval_accuracy": 0.36619718309859156,
+      "eval_loss": 0.7257372736930847,
+      "eval_runtime": 0.0321,
+      "eval_samples_per_second": 2214.884,
+      "eval_steps_per_second": 31.196,
       "step": 18
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.35543572902679443,
-      "learning_rate": 0.00086,
-      "loss": 0.6965,
+      "grad_norm": 0.6264722943305969,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6891,
       "step": 21
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6926164627075195,
-      "eval_runtime": 0.0276,
-      "eval_samples_per_second": 2574.861,
-      "eval_steps_per_second": 36.266,
+      "eval_accuracy": 0.29577464788732394,
+      "eval_loss": 0.721610963344574,
+      "eval_runtime": 0.0298,
+      "eval_samples_per_second": 2382.593,
+      "eval_steps_per_second": 33.558,
       "step": 21
     },
     {
-      "epoch": 8.0,
-      "grad_norm": 0.9181599617004395,
-      "learning_rate": 0.00084,
-      "loss": 0.6957,
-      "step": 24
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.7037302851676941,
-      "eval_runtime": 0.0276,
-      "eval_samples_per_second": 2572.304,
-      "eval_steps_per_second": 36.23,
-      "step": 24
-    },
-    {
-      "epoch": 9.0,
-      "grad_norm": 0.4169580638408661,
-      "learning_rate": 0.00082,
-      "loss": 0.699,
-      "step": 27
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.694597065448761,
-      "eval_runtime": 0.0273,
-      "eval_samples_per_second": 2599.813,
-      "eval_steps_per_second": 36.617,
-      "step": 27
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 0.704374372959137,
-      "learning_rate": 0.0008,
-      "loss": 0.6936,
-      "step": 30
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6876101493835449,
-      "eval_runtime": 0.0276,
-      "eval_samples_per_second": 2573.526,
-      "eval_steps_per_second": 36.247,
-      "step": 30
-    },
-    {
-      "epoch": 11.0,
-      "grad_norm": 0.26875758171081543,
-      "learning_rate": 0.0007800000000000001,
-      "loss": 0.6948,
-      "step": 33
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.6944872736930847,
-      "eval_runtime": 0.028,
-      "eval_samples_per_second": 2538.427,
-      "eval_steps_per_second": 35.752,
-      "step": 33
-    },
-    {
-      "epoch": 11.0,
-      "step": 33,
-      "total_flos": 183171693112320.0,
-      "train_loss": 0.7242465091474128,
-      "train_runtime": 11.5122,
-      "train_samples_per_second": 2757.938,
-      "train_steps_per_second": 13.03
+      "epoch": 7.0,
+      "step": 21,
+      "total_flos": 116563804707840.0,
+      "train_loss": 0.6973756040845599,
+      "train_runtime": 8.699,
+      "train_samples_per_second": 3649.84,
+      "train_steps_per_second": 17.243
     }
   ],
   "logging_steps": 1,
@@ -220,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 183171693112320.0,
+  "total_flos": 116563804707840.0,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null