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": 5000,
-    "exact_match": 41.04,
-    "f1": 52.204443710543785,
-    "train_loss": 3.0070706685384114,
-    "train_runtime": 122.9618,
+    "exact_match": 54.7,
+    "f1": 65.28162437242771,
+    "train_loss": 2.1884329223632815,
+    "train_runtime": 219.3477,
     "train_samples": 5000,
-    "train_samples_per_second": 121.989,
-    "train_steps_per_second": 0.488
+    "train_samples_per_second": 113.974,
+    "train_steps_per_second": 0.456
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a8faeb17d6700282e0433bd20d12f060b5026dc3729080a6f3feb4a612936d
+oid sha256:4707f93b4753847457839c795eeb5bd6f21a62ae56bbb8e4788510de6fc12fd3
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680db1c5e66e56840b3d9031e79bd2145f82728d53811cb3876e4c00eb74e5b3
-size 22841996
+oid sha256:1bab8180feb903e5f46d52b6b94335797c1a34e5b2b55b3f1630bd16dd030770
+size 22757324

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 5000,
-    "exact_match": 41.04,
-    "f1": 52.204443710543785
+    "exact_match": 54.7,
+    "f1": 65.28162437242771
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 3.0070706685384114,
-    "train_runtime": 122.9618,
+    "epoch": 5.0,
+    "train_loss": 2.1884329223632815,
+    "train_runtime": 219.3477,
     "train_samples": 5000,
-    "train_samples_per_second": 121.989,
-    "train_steps_per_second": 0.488
+    "train_samples_per_second": 113.974,
+    "train_steps_per_second": 0.456
 }

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": 60,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 60,
-      "total_flos": 2939588513280000.0,
-      "train_loss": 3.0070706685384114,
-      "train_runtime": 122.9618,
-      "train_samples_per_second": 121.989,
-      "train_steps_per_second": 0.488
+      "epoch": 5.0,
+      "step": 100,
+      "total_flos": 4899314188800000.0,
+      "train_loss": 2.1884329223632815,
+      "train_runtime": 219.3477,
+      "train_samples_per_second": 113.974,
+      "train_steps_per_second": 0.456
     }
   ],
   "logging_steps": 500,
-  "max_steps": 60,
-  "num_train_epochs": 3,
+  "max_steps": 100,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 2939588513280000.0,
+  "total_flos": 4899314188800000.0,
   "trial_name": null,
   "trial_params": null
 }