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": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 17.9,
-    "f1": 25.631270409710442,
-    "train_loss": 3.889862484402127,
-    "train_runtime": 51.5185,
+    "exact_match": 39.93333333333333,
+    "f1": 50.14867522598639,
+    "train_loss": 3.0218854268391926,
+    "train_runtime": 81.6525,
     "train_samples": 3000,
-    "train_samples_per_second": 174.695,
-    "train_steps_per_second": 0.699
+    "train_samples_per_second": 183.705,
+    "train_steps_per_second": 0.735
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef199f188cf5ae97840cb9371cec085d36eab003f414e916c89082b136ba91d7
+oid sha256:4db8c208c865d94c3b907e2d4c20516e55b01181b1ae32b6d814a95b8cdc2256
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d64a4d53ec417ef1268f3e5434ba12da1de8378c366a37f10451075c60d547b6
-size 14213032
+oid sha256:64b8d7bc61038af9b4d045c1ba5ca7a251c5836c1f1ac63c3e5269190dc0747e
+size 13993522

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 17.9,
-    "f1": 25.631270409710442
+    "exact_match": 39.93333333333333,
+    "f1": 50.14867522598639
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 3.889862484402127,
-    "train_runtime": 51.5185,
+    "epoch": 5.0,
+    "train_loss": 3.0218854268391926,
+    "train_runtime": 81.6525,
     "train_samples": 3000,
-    "train_samples_per_second": 174.695,
-    "train_steps_per_second": 0.699
+    "train_samples_per_second": 183.705,
+    "train_steps_per_second": 0.735
 }

trainer_state.json

@@ -1,28 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 36,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 36,
-      "total_flos": 1763753107968000.0,
-      "train_loss": 3.889862484402127,
-      "train_runtime": 51.5185,
-      "train_samples_per_second": 174.695,
-      "train_steps_per_second": 0.699
+      "epoch": 5.0,
+      "step": 60,
+      "total_flos": 2939588513280000.0,
+      "train_loss": 3.0218854268391926,
+      "train_runtime": 81.6525,
+      "train_samples_per_second": 183.705,
+      "train_steps_per_second": 0.735
     }
   ],
   "logging_steps": 500,
-  "max_steps": 36,
-  "num_train_epochs": 3,
+  "max_steps": 60,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1763753107968000.0,
+  "total_flos": 2939588513280000.0,
   "trial_name": null,
   "trial_params": null
 }