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_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.48736462093862815
 ---
 
 <!-- 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_rte
 
-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 RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8165
-- Accuracy: 0.5018
+- Loss: 0.6925
+- Accuracy: 0.4874
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 10.0,
-    "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.6910818815231323,
-    "eval_runtime": 0.0902,
+    "epoch": 7.0,
+    "eval_accuracy": 0.48736462093862815,
+    "eval_loss": 0.6925343871116638,
+    "eval_runtime": 0.096,
     "eval_samples": 277,
-    "eval_samples_per_second": 3069.608,
-    "eval_steps_per_second": 22.163,
-    "total_flos": 652967094988800.0,
-    "train_loss": 0.7079746341705322,
-    "train_runtime": 20.9087,
+    "eval_samples_per_second": 2885.475,
+    "eval_steps_per_second": 20.834,
+    "total_flos": 457076966492160.0,
+    "train_loss": 0.6549058369227818,
+    "train_runtime": 15.9605,
     "train_samples": 2490,
-    "train_samples_per_second": 5954.454,
-    "train_steps_per_second": 23.913
+    "train_samples_per_second": 7800.521,
+    "train_steps_per_second": 31.327
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 10.0,
-    "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.6910818815231323,
-    "eval_runtime": 0.0902,
+    "epoch": 7.0,
+    "eval_accuracy": 0.48736462093862815,
+    "eval_loss": 0.6925343871116638,
+    "eval_runtime": 0.096,
     "eval_samples": 277,
-    "eval_samples_per_second": 3069.608,
-    "eval_steps_per_second": 22.163
+    "eval_samples_per_second": 2885.475,
+    "eval_steps_per_second": 20.834
 }

logs/events.out.tfevents.1733327036.ki-g0008.1208741.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19429d3bb3b57ae6296ad20463fa71af263aa76d695c47569f5eed365b2a0434
+size 405

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 10.0,
-    "total_flos": 652967094988800.0,
-    "train_loss": 0.7079746341705322,
-    "train_runtime": 20.9087,
+    "epoch": 7.0,
+    "total_flos": 457076966492160.0,
+    "train_loss": 0.6549058369227818,
+    "train_runtime": 15.9605,
     "train_samples": 2490,
-    "train_samples_per_second": 5954.454,
-    "train_steps_per_second": 23.913
+    "train_samples_per_second": 7800.521,
+    "train_steps_per_second": 31.327
 }

trainer_state.json

@@ -1,181 +1,133 @@
 {
-  "best_metric": 0.6910818815231323,
-  "best_model_checkpoint": "bert_tiny_lda_100_v1_rte/checkpoint-50",
-  "epoch": 10.0,
+  "best_metric": 0.6925343871116638,
+  "best_model_checkpoint": "bert_tiny_lda_100_v1_rte/checkpoint-20",
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.8250333070755005,
-      "learning_rate": 0.00098,
-      "loss": 0.8226,
+      "grad_norm": 1.2701410055160522,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7159,
       "step": 10
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.7099644541740417,
-      "eval_runtime": 0.0907,
-      "eval_samples_per_second": 3054.549,
-      "eval_steps_per_second": 22.055,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7091183662414551,
+      "eval_runtime": 0.0972,
+      "eval_samples_per_second": 2849.909,
+      "eval_steps_per_second": 20.577,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.27419352531433105,
-      "learning_rate": 0.00096,
-      "loss": 0.7009,
+      "grad_norm": 0.6685553789138794,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6926,
       "step": 20
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7083004713058472,
-      "eval_runtime": 0.0923,
-      "eval_samples_per_second": 3001.194,
-      "eval_steps_per_second": 21.669,
+      "eval_accuracy": 0.48736462093862815,
+      "eval_loss": 0.6925343871116638,
+      "eval_runtime": 0.1007,
+      "eval_samples_per_second": 2750.35,
+      "eval_steps_per_second": 19.858,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.2973408102989197,
-      "learning_rate": 0.00094,
-      "loss": 0.696,
+      "grad_norm": 0.5383151769638062,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6814,
       "step": 30
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6955804228782654,
-      "eval_runtime": 0.0912,
-      "eval_samples_per_second": 3038.309,
-      "eval_steps_per_second": 21.937,
+      "eval_accuracy": 0.51985559566787,
+      "eval_loss": 0.6944310665130615,
+      "eval_runtime": 0.0969,
+      "eval_samples_per_second": 2858.407,
+      "eval_steps_per_second": 20.638,
       "step": 30
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.25628429651260376,
-      "learning_rate": 0.00092,
-      "loss": 0.695,
+      "grad_norm": 0.6841632723808289,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6663,
       "step": 40
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6930421590805054,
-      "eval_runtime": 0.0958,
-      "eval_samples_per_second": 2892.623,
-      "eval_steps_per_second": 20.885,
+      "eval_loss": 0.697773277759552,
+      "eval_runtime": 0.0972,
+      "eval_samples_per_second": 2850.811,
+      "eval_steps_per_second": 20.583,
       "step": 40
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.6449291706085205,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6933,
+      "grad_norm": 1.6859617233276367,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6472,
       "step": 50
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6910818815231323,
-      "eval_runtime": 0.0889,
-      "eval_samples_per_second": 3114.696,
-      "eval_steps_per_second": 22.489,
+      "eval_accuracy": 0.5415162454873647,
+      "eval_loss": 0.7425259351730347,
+      "eval_runtime": 0.0971,
+      "eval_samples_per_second": 2851.944,
+      "eval_steps_per_second": 20.592,
       "step": 50
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.27499687671661377,
-      "learning_rate": 0.00088,
-      "loss": 0.6964,
+      "grad_norm": 1.9587653875350952,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6276,
       "step": 60
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.698697030544281,
-      "eval_runtime": 0.0888,
-      "eval_samples_per_second": 3117.998,
-      "eval_steps_per_second": 22.513,
+      "eval_accuracy": 0.5451263537906137,
+      "eval_loss": 0.7315176129341125,
+      "eval_runtime": 0.098,
+      "eval_samples_per_second": 2825.759,
+      "eval_steps_per_second": 20.403,
       "step": 60
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.1044619083404541,
-      "learning_rate": 0.00086,
-      "loss": 0.694,
+      "grad_norm": 1.4208569526672363,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5534,
       "step": 70
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6921958923339844,
-      "eval_runtime": 0.0893,
-      "eval_samples_per_second": 3100.888,
-      "eval_steps_per_second": 22.389,
+      "eval_accuracy": 0.5018050541516246,
+      "eval_loss": 0.816455602645874,
+      "eval_runtime": 0.1092,
+      "eval_samples_per_second": 2537.616,
+      "eval_steps_per_second": 18.322,
       "step": 70
     },
     {
-      "epoch": 8.0,
-      "grad_norm": 0.16408830881118774,
-      "learning_rate": 0.00084,
-      "loss": 0.6941,
-      "step": 80
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6951573491096497,
-      "eval_runtime": 0.0897,
-      "eval_samples_per_second": 3088.335,
-      "eval_steps_per_second": 22.298,
-      "step": 80
-    },
-    {
-      "epoch": 9.0,
-      "grad_norm": 0.14835208654403687,
-      "learning_rate": 0.00082,
-      "loss": 0.6942,
-      "step": 90
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6926190257072449,
-      "eval_runtime": 0.092,
-      "eval_samples_per_second": 3011.868,
-      "eval_steps_per_second": 21.746,
-      "step": 90
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 0.11492882668972015,
-      "learning_rate": 0.0008,
-      "loss": 0.6932,
-      "step": 100
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6936765909194946,
-      "eval_runtime": 0.0892,
-      "eval_samples_per_second": 3106.792,
-      "eval_steps_per_second": 22.432,
-      "step": 100
-    },
-    {
-      "epoch": 10.0,
-      "step": 100,
-      "total_flos": 652967094988800.0,
-      "train_loss": 0.7079746341705322,
-      "train_runtime": 20.9087,
-      "train_samples_per_second": 5954.454,
-      "train_steps_per_second": 23.913
+      "epoch": 7.0,
+      "step": 70,
+      "total_flos": 457076966492160.0,
+      "train_loss": 0.6549058369227818,
+      "train_runtime": 15.9605,
+      "train_samples_per_second": 7800.521,
+      "train_steps_per_second": 31.327
     }
   ],
   "logging_steps": 1,
@@ -204,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 652967094988800.0,
+  "total_flos": 457076966492160.0,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null