End of training

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: bert-large-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-large-uncased](https://huggingface.co/bert-large-uncased) on the None dataset.
+This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 5000,
-    "exact_match": 68.34,
-    "f1": 78.06079471771494,
-    "train_loss": 0.619562873840332,
-    "train_runtime": 793.7478,
+    "exact_match": 69.28,
+    "f1": 78.44328977753698,
+    "train_loss": 0.31375922679901125,
+    "train_runtime": 1596.9354,
     "train_samples": 5000,
-    "train_samples_per_second": 62.992,
-    "train_steps_per_second": 0.504
+    "train_samples_per_second": 62.62,
+    "train_steps_per_second": 0.501
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d22717b457d4aa61f5166aaf2e8dc810385cb93e68385c063bd04ce57e99a1b
+oid sha256:6dc34696aabf84796982adf7ceaf54365331bf70ad16fbd11939940917e71ac9
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ae6ba3e4308eb42e2bc549ab3e3b967e91ead419e1a2d043ab18a66276b963
-size 22563542
+oid sha256:bc55abb7ecfa5b6c55a9c7644fa47bb213132c8869b1b5eaaf73be137fd73723
+size 22545765

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 5000,
-    "exact_match": 68.34,
-    "f1": 78.06079471771494
+    "exact_match": 69.28,
+    "f1": 78.44328977753698
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "train_loss": 0.619562873840332,
-    "train_runtime": 793.7478,
+    "epoch": 20.0,
+    "train_loss": 0.31375922679901125,
+    "train_runtime": 1596.9354,
     "train_samples": 5000,
-    "train_samples_per_second": 62.992,
-    "train_steps_per_second": 0.504
+    "train_samples_per_second": 62.62,
+    "train_steps_per_second": 0.501
 }

trainer_state.json

@@ -1,28 +1,34 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 10.0,
-      "step": 400,
-      "total_flos": 3.48265122048e+16,
-      "train_loss": 0.619562873840332,
-      "train_runtime": 793.7478,
-      "train_samples_per_second": 62.992,
-      "train_steps_per_second": 0.504
+      "epoch": 12.5,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.4898,
+      "step": 500
+    },
+    {
+      "epoch": 20.0,
+      "step": 800,
+      "total_flos": 6.96530244096e+16,
+      "train_loss": 0.31375922679901125,
+      "train_runtime": 1596.9354,
+      "train_samples_per_second": 62.62,
+      "train_steps_per_second": 0.501
     }
   ],
   "logging_steps": 500,
-  "max_steps": 400,
-  "num_train_epochs": 10,
+  "max_steps": 800,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 3.48265122048e+16,
+  "total_flos": 6.96530244096e+16,
   "trial_name": null,
   "trial_params": null
 }