End of training

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: bert-base-uncased
 tags:
+- question-answering
 - generated_from_trainer
+datasets:
+- squad
 model-index:
 - name: out
   results: []
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # out
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 39.93333333333333,
-    "f1": 50.14867522598639,
-    "train_loss": 3.0218854268391926,
-    "train_runtime": 82.3883,
+    "exact_match": 53.9,
+    "f1": 64.17883819925899,
+    "train_loss": 1.81767946879069,
+    "train_runtime": 159.7771,
     "train_samples": 3000,
-    "train_samples_per_second": 182.065,
-    "train_steps_per_second": 0.728
+    "train_samples_per_second": 187.762,
+    "train_steps_per_second": 0.751
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a6490ff3c81318b7f5b3a67aa100970d4d22bf556943dab8155685109a3878
+oid sha256:0fbceb73b80eb3aeb316dc20dbd970bfdc2d006c8a24661d3e4a990ae73cf2d8
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b8d7bc61038af9b4d045c1ba5ca7a251c5836c1f1ac63c3e5269190dc0747e
-size 13993522
+oid sha256:0842e8293193052a1b5a3e67b1a54a65a8a995e44e339e887706a9fe21f47009
+size 14016823

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 39.93333333333333,
-    "f1": 50.14867522598639
+    "exact_match": 53.9,
+    "f1": 64.17883819925899
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 3.0218854268391926,
-    "train_runtime": 82.3883,
+    "epoch": 10.0,
+    "train_loss": 1.81767946879069,
+    "train_runtime": 159.7771,
     "train_samples": 3000,
-    "train_samples_per_second": 182.065,
-    "train_steps_per_second": 0.728
+    "train_samples_per_second": 187.762,
+    "train_steps_per_second": 0.751
 }

trainer_state.json

@@ -1,28 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 60,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 5.0,
-      "step": 60,
-      "total_flos": 2939588513280000.0,
-      "train_loss": 3.0218854268391926,
-      "train_runtime": 82.3883,
-      "train_samples_per_second": 182.065,
-      "train_steps_per_second": 0.728
+      "epoch": 10.0,
+      "step": 120,
+      "total_flos": 5879177026560000.0,
+      "train_loss": 1.81767946879069,
+      "train_runtime": 159.7771,
+      "train_samples_per_second": 187.762,
+      "train_steps_per_second": 0.751
     }
   ],
   "logging_steps": 500,
-  "max_steps": 60,
-  "num_train_epochs": 5,
+  "max_steps": 120,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2939588513280000.0,
+  "total_flos": 5879177026560000.0,
   "trial_name": null,
   "trial_params": null
 }