End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_lda_5_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: 0.4507042253521127
 ---
 
 <!-- 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_5_v1_wnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_5_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_5_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_5_v1) on the GLUE WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8085
-- Accuracy: 0.2113
+- Loss: 0.7299
+- Accuracy: 0.4507
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 12.0,
-    "eval_accuracy": 0.5633802816901409,
-    "eval_loss": 0.685299277305603,
-    "eval_runtime": 0.0412,
+    "epoch": 7.0,
+    "eval_accuracy": 0.4507042253521127,
+    "eval_loss": 0.7299185991287231,
+    "eval_runtime": 0.0435,
     "eval_samples": 71,
-    "eval_samples_per_second": 1721.541,
-    "eval_steps_per_second": 24.247,
-    "total_flos": 504700788879360.0,
-    "train_loss": 0.8709115054872301,
-    "train_runtime": 28.0372,
+    "eval_samples_per_second": 1631.864,
+    "eval_steps_per_second": 22.984,
+    "total_flos": 294408793512960.0,
+    "train_loss": 0.7033271676018125,
+    "train_runtime": 17.0611,
     "train_samples": 635,
-    "train_samples_per_second": 1132.424,
-    "train_steps_per_second": 5.35
+    "train_samples_per_second": 1860.963,
+    "train_steps_per_second": 8.792
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 12.0,
-    "eval_accuracy": 0.5633802816901409,
-    "eval_loss": 0.685299277305603,
-    "eval_runtime": 0.0412,
+    "epoch": 7.0,
+    "eval_accuracy": 0.4507042253521127,
+    "eval_loss": 0.7299185991287231,
+    "eval_runtime": 0.0435,
     "eval_samples": 71,
-    "eval_samples_per_second": 1721.541,
-    "eval_steps_per_second": 24.247
+    "eval_samples_per_second": 1631.864,
+    "eval_steps_per_second": 22.984
 }

logs/events.out.tfevents.1733314020.ki-g0008.1206098.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4de3cedd3c23be21a33caf4441c4b74ec558fd8a7967aa9d66ab3b45961946b
+size 405

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 12.0,
-    "total_flos": 504700788879360.0,
-    "train_loss": 0.8709115054872301,
-    "train_runtime": 28.0372,
+    "epoch": 7.0,
+    "total_flos": 294408793512960.0,
+    "train_loss": 0.7033271676018125,
+    "train_runtime": 17.0611,
     "train_samples": 635,
-    "train_samples_per_second": 1132.424,
-    "train_steps_per_second": 5.35
+    "train_samples_per_second": 1860.963,
+    "train_steps_per_second": 8.792
 }

trainer_state.json

@@ -1,213 +1,133 @@
 {
-  "best_metric": 0.685299277305603,
-  "best_model_checkpoint": "distilbert_lda_5_v1_wnli/checkpoint-21",
-  "epoch": 12.0,
+  "best_metric": 0.7299185991287231,
+  "best_model_checkpoint": "distilbert_lda_5_v1_wnli/checkpoint-6",
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 36,
+  "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": 15.61489486694336,
-      "learning_rate": 0.00098,
-      "loss": 1.0804,
+      "grad_norm": 2.3966708183288574,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7316,
       "step": 3
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 1.5934889316558838,
-      "eval_runtime": 0.0388,
-      "eval_samples_per_second": 1828.459,
-      "eval_steps_per_second": 25.753,
+      "eval_accuracy": 0.30985915492957744,
+      "eval_loss": 0.744938313961029,
+      "eval_runtime": 0.0425,
+      "eval_samples_per_second": 1670.119,
+      "eval_steps_per_second": 23.523,
       "step": 3
     },
     {
       "epoch": 2.0,
-      "grad_norm": 12.052063941955566,
-      "learning_rate": 0.00096,
-      "loss": 1.4159,
+      "grad_norm": 1.5810788869857788,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7137,
       "step": 6
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 1.348474383354187,
-      "eval_runtime": 0.0376,
-      "eval_samples_per_second": 1887.673,
-      "eval_steps_per_second": 26.587,
+      "eval_accuracy": 0.4507042253521127,
+      "eval_loss": 0.7299185991287231,
+      "eval_runtime": 0.0402,
+      "eval_samples_per_second": 1767.018,
+      "eval_steps_per_second": 24.888,
       "step": 6
     },
     {
       "epoch": 3.0,
-      "grad_norm": 7.796391010284424,
-      "learning_rate": 0.00094,
-      "loss": 0.9801,
+      "grad_norm": 1.5314455032348633,
+      "learning_rate": 4.7e-05,
+      "loss": 0.7026,
       "step": 9
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.8126101493835449,
-      "eval_runtime": 0.0384,
-      "eval_samples_per_second": 1846.909,
-      "eval_steps_per_second": 26.013,
+      "eval_accuracy": 0.29577464788732394,
+      "eval_loss": 0.7607282996177673,
+      "eval_runtime": 0.0414,
+      "eval_samples_per_second": 1715.106,
+      "eval_steps_per_second": 24.156,
       "step": 9
     },
     {
       "epoch": 4.0,
-      "grad_norm": 5.139472961425781,
-      "learning_rate": 0.00092,
-      "loss": 0.8215,
+      "grad_norm": 2.062108278274536,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6937,
       "step": 12
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.7312939763069153,
-      "eval_runtime": 0.0408,
-      "eval_samples_per_second": 1738.343,
-      "eval_steps_per_second": 24.484,
+      "eval_accuracy": 0.49295774647887325,
+      "eval_loss": 0.7552266120910645,
+      "eval_runtime": 0.0406,
+      "eval_samples_per_second": 1747.237,
+      "eval_steps_per_second": 24.609,
       "step": 12
     },
     {
       "epoch": 5.0,
-      "grad_norm": 1.9815768003463745,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.7206,
+      "grad_norm": 1.7301479578018188,
+      "learning_rate": 4.5e-05,
+      "loss": 0.7014,
       "step": 15
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6868947148323059,
-      "eval_runtime": 0.0382,
-      "eval_samples_per_second": 1858.064,
-      "eval_steps_per_second": 26.17,
+      "eval_accuracy": 0.2112676056338028,
+      "eval_loss": 0.7826256155967712,
+      "eval_runtime": 0.0424,
+      "eval_samples_per_second": 1674.505,
+      "eval_steps_per_second": 23.585,
       "step": 15
     },
     {
       "epoch": 6.0,
-      "grad_norm": 2.4411139488220215,
-      "learning_rate": 0.00088,
-      "loss": 0.7118,
+      "grad_norm": 1.8389469385147095,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6909,
       "step": 18
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.6952577233314514,
-      "eval_runtime": 0.0381,
-      "eval_samples_per_second": 1862.643,
-      "eval_steps_per_second": 26.234,
+      "eval_accuracy": 0.23943661971830985,
+      "eval_loss": 0.8128851652145386,
+      "eval_runtime": 0.0401,
+      "eval_samples_per_second": 1771.918,
+      "eval_steps_per_second": 24.957,
       "step": 18
     },
     {
       "epoch": 7.0,
-      "grad_norm": 2.29660701751709,
-      "learning_rate": 0.00086,
-      "loss": 0.7245,
+      "grad_norm": 0.9974502325057983,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6894,
       "step": 21
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.685299277305603,
-      "eval_runtime": 0.0389,
-      "eval_samples_per_second": 1823.287,
-      "eval_steps_per_second": 25.68,
+      "eval_accuracy": 0.2112676056338028,
+      "eval_loss": 0.8085389733314514,
+      "eval_runtime": 0.0406,
+      "eval_samples_per_second": 1747.114,
+      "eval_steps_per_second": 24.607,
       "step": 21
     },
     {
-      "epoch": 8.0,
-      "grad_norm": 8.002218246459961,
-      "learning_rate": 0.00084,
-      "loss": 0.8215,
-      "step": 24
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.8461431264877319,
-      "eval_runtime": 0.0369,
-      "eval_samples_per_second": 1922.502,
-      "eval_steps_per_second": 27.077,
-      "step": 24
-    },
-    {
-      "epoch": 9.0,
-      "grad_norm": 7.1968560218811035,
-      "learning_rate": 0.00082,
-      "loss": 0.8608,
-      "step": 27
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.8202713131904602,
-      "eval_runtime": 0.038,
-      "eval_samples_per_second": 1868.451,
-      "eval_steps_per_second": 26.316,
-      "step": 27
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 4.442270755767822,
-      "learning_rate": 0.0008,
-      "loss": 0.8305,
-      "step": 30
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.9017935991287231,
-      "eval_runtime": 0.0383,
-      "eval_samples_per_second": 1852.481,
-      "eval_steps_per_second": 26.091,
-      "step": 30
-    },
-    {
-      "epoch": 11.0,
-      "grad_norm": 0.5188452005386353,
-      "learning_rate": 0.0007800000000000001,
-      "loss": 0.7692,
-      "step": 33
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6873898506164551,
-      "eval_runtime": 0.0407,
-      "eval_samples_per_second": 1743.758,
-      "eval_steps_per_second": 24.56,
-      "step": 33
-    },
-    {
-      "epoch": 12.0,
-      "grad_norm": 0.8371219038963318,
-      "learning_rate": 0.00076,
-      "loss": 0.7142,
-      "step": 36
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.685299277305603,
-      "eval_runtime": 0.0404,
-      "eval_samples_per_second": 1756.243,
-      "eval_steps_per_second": 24.736,
-      "step": 36
-    },
-    {
-      "epoch": 12.0,
-      "step": 36,
-      "total_flos": 504700788879360.0,
-      "train_loss": 0.8709115054872301,
-      "train_runtime": 28.0372,
-      "train_samples_per_second": 1132.424,
-      "train_steps_per_second": 5.35
+      "epoch": 7.0,
+      "step": 21,
+      "total_flos": 294408793512960.0,
+      "train_loss": 0.7033271676018125,
+      "train_runtime": 17.0611,
+      "train_samples_per_second": 1860.963,
+      "train_steps_per_second": 8.792
     }
   ],
   "logging_steps": 1,
@@ -236,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 504700788879360.0,
+  "total_flos": 294408793512960.0,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null