End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -12,7 +14,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE WNLI
       type: glue
       config: wnli
       split: validation
@@ -20,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.43661971830985913
+      value: 0.5633802816901409
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # add_BERT_no_pretrain_wnli
 
-This model is a fine-tuned version of [](https://huggingface.co/) on the glue dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7075
-- Accuracy: 0.4366
+- Loss: 0.6852
+- Accuracy: 0.5634
 
 ## Model description
 

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 14.0,
+    "epoch": 13.0,
     "eval_accuracy": 0.5633802816901409,
-    "eval_loss": 0.6850929856300354,
-    "eval_runtime": 0.1203,
+    "eval_loss": 0.6852201819419861,
+    "eval_runtime": 0.1637,
     "eval_samples": 71,
-    "eval_samples_per_second": 590.037,
-    "eval_steps_per_second": 8.31,
-    "train_loss": 0.8889250755310059,
-    "train_runtime": 81.2599,
+    "eval_samples_per_second": 433.656,
+    "eval_steps_per_second": 6.108,
+    "train_loss": 0.7377610133244441,
+    "train_runtime": 98.1104,
     "train_samples": 635,
-    "train_samples_per_second": 390.722,
-    "train_steps_per_second": 3.077
+    "train_samples_per_second": 323.615,
+    "train_steps_per_second": 2.548
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 14.0,
+    "epoch": 13.0,
     "eval_accuracy": 0.5633802816901409,
-    "eval_loss": 0.6850929856300354,
-    "eval_runtime": 0.1203,
+    "eval_loss": 0.6852201819419861,
+    "eval_runtime": 0.1637,
     "eval_samples": 71,
-    "eval_samples_per_second": 590.037,
-    "eval_steps_per_second": 8.31
+    "eval_samples_per_second": 433.656,
+    "eval_steps_per_second": 6.108
 }

logs/events.out.tfevents.1686777823.serv-9219.1715196.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9618cc7918032bf18cce46886e811eb05a29293b6ea366b3b290d057b2166ff2
+size 357

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 14.0,
-    "train_loss": 0.8889250755310059,
-    "train_runtime": 81.2599,
+    "epoch": 13.0,
+    "train_loss": 0.7377610133244441,
+    "train_runtime": 98.1104,
     "train_samples": 635,
-    "train_samples_per_second": 390.722,
-    "train_steps_per_second": 3.077
+    "train_samples_per_second": 323.615,
+    "train_steps_per_second": 2.548
 }

trainer_state.json

@@ -1,235 +1,220 @@
 {
-  "best_metric": 0.6850929856300354,
-  "best_model_checkpoint": "add_BERT_no_pretrain_wnli/checkpoint-45",
-  "epoch": 14.0,
-  "global_step": 70,
+  "best_metric": 0.6852201819419861,
+  "best_model_checkpoint": "add_BERT_no_pretrain_wnli/checkpoint-40",
+  "epoch": 13.0,
+  "global_step": 65,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 0.000492,
-      "loss": 1.0868,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.9529,
       "step": 5
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 4.841630935668945,
-      "eval_runtime": 0.1197,
-      "eval_samples_per_second": 593.003,
-      "eval_steps_per_second": 8.352,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6859562397003174,
+      "eval_runtime": 0.1385,
+      "eval_samples_per_second": 512.641,
+      "eval_steps_per_second": 7.22,
       "step": 5
     },
     {
       "epoch": 2.0,
-      "learning_rate": 0.000484,
-      "loss": 2.3889,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.762,
       "step": 10
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 1.4091039896011353,
-      "eval_runtime": 0.1201,
-      "eval_samples_per_second": 591.068,
-      "eval_steps_per_second": 8.325,
+      "eval_loss": 0.8068376183509827,
+      "eval_runtime": 0.1395,
+      "eval_samples_per_second": 509.037,
+      "eval_steps_per_second": 7.17,
       "step": 10
     },
     {
       "epoch": 3.0,
-      "learning_rate": 0.000474,
-      "loss": 0.9615,
+      "learning_rate": 3.76e-05,
+      "loss": 0.7199,
       "step": 15
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.940690815448761,
-      "eval_runtime": 0.1192,
-      "eval_samples_per_second": 595.86,
-      "eval_steps_per_second": 8.392,
+      "eval_loss": 0.6986883878707886,
+      "eval_runtime": 0.14,
+      "eval_samples_per_second": 507.156,
+      "eval_steps_per_second": 7.143,
       "step": 15
     },
     {
       "epoch": 4.0,
-      "learning_rate": 0.00046400000000000006,
-      "loss": 0.7628,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.7092,
       "step": 20
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.698733925819397,
-      "eval_runtime": 0.1189,
-      "eval_samples_per_second": 597.267,
-      "eval_steps_per_second": 8.412,
+      "eval_loss": 0.6958004236221313,
+      "eval_runtime": 0.1388,
+      "eval_samples_per_second": 511.607,
+      "eval_steps_per_second": 7.206,
       "step": 20
     },
     {
       "epoch": 5.0,
-      "learning_rate": 0.00045400000000000003,
-      "loss": 0.7262,
+      "learning_rate": 3.6e-05,
+      "loss": 0.7149,
       "step": 25
     },
     {
       "epoch": 5.0,
       "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6886070966720581,
-      "eval_runtime": 0.119,
-      "eval_samples_per_second": 596.615,
-      "eval_steps_per_second": 8.403,
+      "eval_loss": 0.6853562593460083,
+      "eval_runtime": 0.1392,
+      "eval_samples_per_second": 509.961,
+      "eval_steps_per_second": 7.183,
       "step": 25
     },
     {
       "epoch": 6.0,
-      "learning_rate": 0.000444,
-      "loss": 0.7212,
+      "learning_rate": 3.52e-05,
+      "loss": 0.7069,
       "step": 30
     },
     {
       "epoch": 6.0,
       "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.733625590801239,
-      "eval_runtime": 0.119,
-      "eval_samples_per_second": 596.774,
-      "eval_steps_per_second": 8.405,
+      "eval_loss": 0.6955687403678894,
+      "eval_runtime": 0.1393,
+      "eval_samples_per_second": 509.691,
+      "eval_steps_per_second": 7.179,
       "step": 30
     },
     {
       "epoch": 7.0,
-      "learning_rate": 0.00043400000000000003,
-      "loss": 0.7087,
+      "learning_rate": 3.44e-05,
+      "loss": 0.7008,
       "step": 35
     },
     {
       "epoch": 7.0,
       "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.7464136481285095,
-      "eval_runtime": 0.1203,
-      "eval_samples_per_second": 590.349,
-      "eval_steps_per_second": 8.315,
+      "eval_loss": 0.6985586881637573,
+      "eval_runtime": 0.1391,
+      "eval_samples_per_second": 510.536,
+      "eval_steps_per_second": 7.191,
       "step": 35
     },
     {
       "epoch": 8.0,
-      "learning_rate": 0.000424,
-      "loss": 0.7215,
+      "learning_rate": 3.3600000000000004e-05,
+      "loss": 0.7079,
       "step": 40
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.7594732046127319,
-      "eval_runtime": 0.1194,
-      "eval_samples_per_second": 594.534,
-      "eval_steps_per_second": 8.374,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6852201819419861,
+      "eval_runtime": 0.139,
+      "eval_samples_per_second": 510.861,
+      "eval_steps_per_second": 7.195,
       "step": 40
     },
     {
       "epoch": 9.0,
-      "learning_rate": 0.000414,
-      "loss": 0.7534,
+      "learning_rate": 3.28e-05,
+      "loss": 0.7444,
       "step": 45
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6850929856300354,
-      "eval_runtime": 0.1181,
-      "eval_samples_per_second": 601.232,
-      "eval_steps_per_second": 8.468,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.7381781935691833,
+      "eval_runtime": 0.1382,
+      "eval_samples_per_second": 513.836,
+      "eval_steps_per_second": 7.237,
       "step": 45
     },
     {
       "epoch": 10.0,
-      "learning_rate": 0.000404,
-      "loss": 0.7058,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.7147,
       "step": 50
     },
     {
       "epoch": 10.0,
       "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6891197562217712,
-      "eval_runtime": 0.1198,
-      "eval_samples_per_second": 592.797,
-      "eval_steps_per_second": 8.349,
+      "eval_loss": 0.7008692026138306,
+      "eval_runtime": 0.1384,
+      "eval_samples_per_second": 512.872,
+      "eval_steps_per_second": 7.224,
       "step": 50
     },
     {
       "epoch": 11.0,
-      "learning_rate": 0.00039400000000000004,
-      "loss": 0.7342,
+      "learning_rate": 3.1200000000000006e-05,
+      "loss": 0.7318,
       "step": 55
     },
     {
       "epoch": 11.0,
       "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.727848470211029,
-      "eval_runtime": 0.119,
-      "eval_samples_per_second": 596.479,
-      "eval_steps_per_second": 8.401,
+      "eval_loss": 0.7316415309906006,
+      "eval_runtime": 0.1391,
+      "eval_samples_per_second": 510.379,
+      "eval_steps_per_second": 7.188,
       "step": 55
     },
     {
       "epoch": 12.0,
-      "learning_rate": 0.000384,
-      "loss": 0.7116,
+      "learning_rate": 3.0400000000000004e-05,
+      "loss": 0.7212,
       "step": 60
     },
     {
       "epoch": 12.0,
-      "eval_accuracy": 0.43661971830985913,
-      "eval_loss": 0.736307680606842,
-      "eval_runtime": 0.1186,
-      "eval_samples_per_second": 598.471,
-      "eval_steps_per_second": 8.429,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6857689023017883,
+      "eval_runtime": 0.1384,
+      "eval_samples_per_second": 512.863,
+      "eval_steps_per_second": 7.223,
       "step": 60
     },
     {
       "epoch": 13.0,
-      "learning_rate": 0.000374,
-      "loss": 0.7407,
+      "learning_rate": 2.96e-05,
+      "loss": 0.7043,
       "step": 65
     },
     {
       "epoch": 13.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.7217862606048584,
-      "eval_runtime": 0.1188,
-      "eval_samples_per_second": 597.422,
-      "eval_steps_per_second": 8.414,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.7075231075286865,
+      "eval_runtime": 0.1394,
+      "eval_samples_per_second": 509.331,
+      "eval_steps_per_second": 7.174,
       "step": 65
     },
     {
-      "epoch": 14.0,
-      "learning_rate": 0.000364,
-      "loss": 0.7215,
-      "step": 70
-    },
-    {
-      "epoch": 14.0,
-      "eval_accuracy": 0.5633802816901409,
-      "eval_loss": 0.6927335262298584,
-      "eval_runtime": 0.1189,
-      "eval_samples_per_second": 597.293,
-      "eval_steps_per_second": 8.413,
-      "step": 70
-    },
-    {
-      "epoch": 14.0,
-      "step": 70,
-      "total_flos": 1269705042034688.0,
-      "train_loss": 0.8889250755310059,
-      "train_runtime": 81.2599,
-      "train_samples_per_second": 390.722,
-      "train_steps_per_second": 3.077
+      "epoch": 13.0,
+      "step": 65,
+      "total_flos": 1179011824746496.0,
+      "train_loss": 0.7377610133244441,
+      "train_runtime": 98.1104,
+      "train_samples_per_second": 323.615,
+      "train_steps_per_second": 2.548
     }
   ],
   "max_steps": 250,
   "num_train_epochs": 50,
-  "total_flos": 1269705042034688.0,
+  "total_flos": 1179011824746496.0,
   "trial_name": null,
   "trial_params": null
 }