End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_lda_50_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: 0.49295774647887325
 ---
 
 <!-- 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. -->
 
 # distilbert_lda_50_v1_wnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_50_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_50_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_50_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_50_v1) on the GLUE WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7832
-- Accuracy: 0.1831
+- Loss: 0.7239
+- Accuracy: 0.4930
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 12.0,
-    "eval_accuracy": 0.5633802816901409,
-    "eval_loss": 0.6858494281768799,
-    "eval_runtime": 0.0378,
+    "epoch": 8.0,
+    "eval_accuracy": 0.49295774647887325,
+    "eval_loss": 0.7239218354225159,
+    "eval_runtime": 0.0392,
     "eval_samples": 71,
-    "eval_samples_per_second": 1879.999,
-    "eval_steps_per_second": 26.479,
-    "total_flos": 504700788879360.0,
-    "train_loss": 0.8197853101624383,
-    "train_runtime": 26.8315,
+    "eval_samples_per_second": 1809.867,
+    "eval_steps_per_second": 25.491,
+    "total_flos": 336467192586240.0,
+    "train_loss": 0.7035509645938873,
+    "train_runtime": 19.7006,
     "train_samples": 635,
-    "train_samples_per_second": 1183.309,
-    "train_steps_per_second": 5.59
+    "train_samples_per_second": 1611.629,
+    "train_steps_per_second": 7.614
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 12.0,
-    "eval_accuracy": 0.5633802816901409,
-    "eval_loss": 0.6858494281768799,
-    "eval_runtime": 0.0378,
+    "epoch": 8.0,
+    "eval_accuracy": 0.49295774647887325,
+    "eval_loss": 0.7239218354225159,
+    "eval_runtime": 0.0392,
     "eval_samples": 71,
-    "eval_samples_per_second": 1879.999,
-    "eval_steps_per_second": 26.479
+    "eval_samples_per_second": 1809.867,
+    "eval_steps_per_second": 25.491
 }

logs/events.out.tfevents.1733313765.ki-g0008.1206436.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb2377805459e2830ffba1ecd517b48b9ab2a65ad42fea25633e726ecebb444
+size 405

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 12.0,
-    "total_flos": 504700788879360.0,
-    "train_loss": 0.8197853101624383,
-    "train_runtime": 26.8315,
+    "epoch": 8.0,
+    "total_flos": 336467192586240.0,
+    "train_loss": 0.7035509645938873,
+    "train_runtime": 19.7006,
     "train_samples": 635,
-    "train_samples_per_second": 1183.309,
-    "train_steps_per_second": 5.59
+    "train_samples_per_second": 1611.629,
+    "train_steps_per_second": 7.614
 }

trainer_state.json

@@ -1,213 +1,149 @@
 {
-  "best_metric": 0.6858494281768799,
-  "best_model_checkpoint": "distilbert_lda_50_v1_wnli/checkpoint-21",
-  "epoch": 12.0,
+  "best_metric": 0.7239218354225159,
+  "best_model_checkpoint": "distilbert_lda_50_v1_wnli/checkpoint-9",
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 36,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 23.70015525817871,
-      "learning_rate": 0.00098,
-      "loss": 1.0921,
+      "grad_norm": 2.593956708908081,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7829,
       "step": 3
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 2.6930952072143555,
-      "eval_runtime": 0.038,
-      "eval_samples_per_second": 1866.25,
-      "eval_steps_per_second": 26.285,
+      "eval_accuracy": 0.3380281690140845,
+      "eval_loss": 0.7284329533576965,
+      "eval_runtime": 0.0557,
+      "eval_samples_per_second": 1274.439,
+      "eval_steps_per_second": 17.95,
       "step": 3
     },
     {
       "epoch": 2.0,
-      "grad_norm": 1.4811052083969116,
-      "learning_rate": 0.00096,
-      "loss": 1.5486,
+      "grad_norm": 1.2626270055770874,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7048,
       "step": 6
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 1.2594494819641113,
-      "eval_runtime": 0.0378,
-      "eval_samples_per_second": 1878.943,
-      "eval_steps_per_second": 26.464,
+      "eval_accuracy": 0.3380281690140845,
+      "eval_loss": 0.7267274260520935,
+      "eval_runtime": 0.038,
+      "eval_samples_per_second": 1867.408,
+      "eval_steps_per_second": 26.302,
       "step": 6
     },
     {
       "epoch": 3.0,
-      "grad_norm": 3.323134660720825,
-      "learning_rate": 0.00094,
-      "loss": 0.8963,
+      "grad_norm": 1.094574213027954,
+      "learning_rate": 4.7e-05,
+      "loss": 0.689,
       "step": 9
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6907734870910645,
-      "eval_runtime": 0.0376,
-      "eval_samples_per_second": 1889.926,
-      "eval_steps_per_second": 26.619,
+      "eval_accuracy": 0.49295774647887325,
+      "eval_loss": 0.7239218354225159,
+      "eval_runtime": 0.0391,
+      "eval_samples_per_second": 1815.749,
+      "eval_steps_per_second": 25.574,
       "step": 9
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.34992969036102295,
-      "learning_rate": 0.00092,
-      "loss": 0.709,
+      "grad_norm": 1.0490866899490356,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6915,
       "step": 12
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.704280436038971,
-      "eval_runtime": 0.0375,
-      "eval_samples_per_second": 1893.988,
-      "eval_steps_per_second": 26.676,
+      "eval_accuracy": 0.39436619718309857,
+      "eval_loss": 0.7566296458244324,
+      "eval_runtime": 0.0395,
+      "eval_samples_per_second": 1797.143,
+      "eval_steps_per_second": 25.312,
       "step": 12
     },
     {
       "epoch": 5.0,
-      "grad_norm": 1.6908652782440186,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.719,
+      "grad_norm": 1.0118927955627441,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6916,
       "step": 15
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6901406645774841,
-      "eval_runtime": 0.0395,
-      "eval_samples_per_second": 1796.493,
-      "eval_steps_per_second": 25.303,
+      "eval_accuracy": 0.2535211267605634,
+      "eval_loss": 0.754951536655426,
+      "eval_runtime": 0.0404,
+      "eval_samples_per_second": 1756.274,
+      "eval_steps_per_second": 24.736,
       "step": 15
     },
     {
       "epoch": 6.0,
-      "grad_norm": 1.2121317386627197,
-      "learning_rate": 0.00088,
-      "loss": 0.6999,
+      "grad_norm": 1.1331769227981567,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6936,
       "step": 18
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.6995489597320557,
-      "eval_runtime": 0.0382,
-      "eval_samples_per_second": 1857.253,
-      "eval_steps_per_second": 26.158,
+      "eval_accuracy": 0.2535211267605634,
+      "eval_loss": 0.7512102127075195,
+      "eval_runtime": 0.0378,
+      "eval_samples_per_second": 1876.634,
+      "eval_steps_per_second": 26.431,
       "step": 18
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.45708081126213074,
-      "learning_rate": 0.00086,
-      "loss": 0.6954,
+      "grad_norm": 0.7647018432617188,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6908,
       "step": 21
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6858494281768799,
-      "eval_runtime": 0.0379,
-      "eval_samples_per_second": 1873.128,
-      "eval_steps_per_second": 26.382,
+      "eval_accuracy": 0.2535211267605634,
+      "eval_loss": 0.7626540064811707,
+      "eval_runtime": 0.0417,
+      "eval_samples_per_second": 1701.864,
+      "eval_steps_per_second": 23.97,
       "step": 21
     },
     {
       "epoch": 8.0,
-      "grad_norm": 1.3719453811645508,
-      "learning_rate": 0.00084,
-      "loss": 0.6945,
+      "grad_norm": 2.0840747356414795,
+      "learning_rate": 4.2e-05,
+      "loss": 0.6841,
       "step": 24
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.6976781487464905,
-      "eval_runtime": 0.0374,
-      "eval_samples_per_second": 1899.328,
-      "eval_steps_per_second": 26.751,
+      "eval_accuracy": 0.18309859154929578,
+      "eval_loss": 0.7832306623458862,
+      "eval_runtime": 0.0385,
+      "eval_samples_per_second": 1843.148,
+      "eval_steps_per_second": 25.96,
       "step": 24
     },
     {
-      "epoch": 9.0,
-      "grad_norm": 0.6170178651809692,
-      "learning_rate": 0.00082,
-      "loss": 0.6984,
-      "step": 27
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.7000439763069153,
-      "eval_runtime": 0.04,
-      "eval_samples_per_second": 1776.134,
-      "eval_steps_per_second": 25.016,
-      "step": 27
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 0.6333069801330566,
-      "learning_rate": 0.0008,
-      "loss": 0.6986,
-      "step": 30
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6868947148323059,
-      "eval_runtime": 0.0376,
-      "eval_samples_per_second": 1889.134,
-      "eval_steps_per_second": 26.608,
-      "step": 30
-    },
-    {
-      "epoch": 11.0,
-      "grad_norm": 0.5037391185760498,
-      "learning_rate": 0.0007800000000000001,
-      "loss": 0.6915,
-      "step": 33
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.688160240650177,
-      "eval_runtime": 0.0374,
-      "eval_samples_per_second": 1897.948,
-      "eval_steps_per_second": 26.732,
-      "step": 33
-    },
-    {
-      "epoch": 12.0,
-      "grad_norm": 0.8827735781669617,
-      "learning_rate": 0.00076,
-      "loss": 0.6943,
-      "step": 36
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.694597065448761,
-      "eval_runtime": 0.0374,
-      "eval_samples_per_second": 1896.884,
-      "eval_steps_per_second": 26.717,
-      "step": 36
-    },
-    {
-      "epoch": 12.0,
-      "step": 36,
-      "total_flos": 504700788879360.0,
-      "train_loss": 0.8197853101624383,
-      "train_runtime": 26.8315,
-      "train_samples_per_second": 1183.309,
-      "train_steps_per_second": 5.59
+      "epoch": 8.0,
+      "step": 24,
+      "total_flos": 336467192586240.0,
+      "train_loss": 0.7035509645938873,
+      "train_runtime": 19.7006,
+      "train_samples_per_second": 1611.629,
+      "train_steps_per_second": 7.614
     }
   ],
   "logging_steps": 1,
@@ -236,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 504700788879360.0,
+  "total_flos": 336467192586240.0,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null