End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google/bigbird-roberta-base
 tags:
 - generated_from_trainer
+datasets:
+- squad
 model-index:
 - name: bigBird-base-fine-tuning-squad-B16R3-nobias
   results: []
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bigBird-base-fine-tuning-squad-B16R3-nobias
 
-This model is a fine-tuned version of [google/bigbird-roberta-base](https://huggingface.co/google/bigbird-roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [google/bigbird-roberta-base](https://huggingface.co/google/bigbird-roberta-base) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 2.0,
-    "eval_exact_match": 89.84375,
-    "eval_f1": 91.5327380952381,
+    "eval_exact_match": 82.32734153263955,
+    "eval_f1": 89.22304303329197,
     "eval_model_preparation_time": 0.0018,
-    "eval_runtime": 9.9215,
-    "eval_samples": 128,
-    "eval_samples_per_second": 12.901,
-    "eval_steps_per_second": 0.101,
-    "total_flos": 3.864501390676132e+17,
-    "train_loss": 0.05644623499482734,
-    "train_runtime": 4615.1991,
+    "eval_runtime": 834.3564,
+    "eval_samples": 10570,
+    "eval_samples_per_second": 12.668,
+    "eval_steps_per_second": 1.584,
+    "total_flos": 3.8619551920019866e+17,
+    "train_loss": 0.9270246051109,
+    "train_runtime": 51747.0424,
     "train_samples": 87599,
-    "train_samples_per_second": 37.961,
-    "train_steps_per_second": 9.49
+    "train_samples_per_second": 3.386,
+    "train_steps_per_second": 0.423
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "eval_exact_match": 89.84375,
-    "eval_f1": 91.5327380952381,
-    "eval_model_preparation_time": 0.0018,
-    "eval_runtime": 9.9215,
-    "eval_samples": 128,
-    "eval_samples_per_second": 12.901,
-    "eval_steps_per_second": 0.101
+    "epoch": 2.0,
+    "eval_exact_match": 82.32734153263955,
+    "eval_f1": 89.22304303329197,
+    "eval_runtime": 834.3564,
+    "eval_samples": 10570,
+    "eval_samples_per_second": 12.668,
+    "eval_steps_per_second": 1.584
 }

log/events.out.tfevents.1723149965.isl-gpu4.878776.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f168d79fce90aba6e5b265cb4c52505c77107245cada8e9c987c5d1d9529e5
+size 418

log/events.out.tfevents.1723149965.isl-gpu4.878776.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b008e94da6b7c8aeb7de0468302961370fad647060c22a4453c5e5eddf6e9cf
+size 418

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 2.0,
-    "total_flos": 3.864501390676132e+17,
-    "train_loss": 0.05644623499482734,
-    "train_runtime": 4615.1991,
+    "total_flos": 3.8619551920019866e+17,
+    "train_loss": 0.9270246051109,
+    "train_runtime": 51747.0424,
     "train_samples": 87599,
-    "train_samples_per_second": 37.961,
-    "train_steps_per_second": 9.49
+    "train_samples_per_second": 3.386,
+    "train_steps_per_second": 0.423
 }