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": 5.0,
-    "eval_samples": 5000,
-    "exact_match": 68.2,
-    "f1": 78.04105325561898,
-    "train_loss": 0.7782299186609969,
-    "train_runtime": 451.7161,
-    "train_samples": 5000,
-    "train_samples_per_second": 55.344,
-    "train_steps_per_second": 0.874
+    "epoch": 10.0,
+    "eval_samples": 3000,
+    "exact_match": 66.66666666666667,
+    "f1": 76.95180617275538,
+    "train_loss": 0.5657880417844082,
+    "train_runtime": 541.9228,
+    "train_samples": 3000,
+    "train_samples_per_second": 55.358,
+    "train_steps_per_second": 0.867
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dc8c93e96be7e6a00460047830327a8c1a8d996178e304451d56f3e9823311b
+oid sha256:8104c83d3b93778cc91e9d179978285a54187a54d8372d34cdcd93a8c6812e0d
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e34c7f461af7f5b898941e802aebf0733d05f3de7d614c105884c073dea92c
-size 22511101
+oid sha256:65615ed4fe1c8c9e41a22dc324bdb4e22c39c9726ed41e382bad39176689b6a3
+size 14067254

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 5.0,
-    "eval_samples": 5000,
-    "exact_match": 68.2,
-    "f1": 78.04105325561898
+    "epoch": 10.0,
+    "eval_samples": 3000,
+    "exact_match": 66.66666666666667,
+    "f1": 76.95180617275538
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 0.7782299186609969,
-    "train_runtime": 451.7161,
-    "train_samples": 5000,
-    "train_samples_per_second": 55.344,
-    "train_steps_per_second": 0.874
+    "epoch": 10.0,
+    "train_loss": 0.5657880417844082,
+    "train_runtime": 541.9228,
+    "train_samples": 3000,
+    "train_samples_per_second": 55.358,
+    "train_steps_per_second": 0.867
 }

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": 395,
+  "global_step": 470,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 5.0,
-      "step": 395,
-      "total_flos": 1.74132561024e+16,
-      "train_loss": 0.7782299186609969,
-      "train_runtime": 451.7161,
-      "train_samples_per_second": 55.344,
-      "train_steps_per_second": 0.874
+      "epoch": 10.0,
+      "step": 470,
+      "total_flos": 2.089590732288e+16,
+      "train_loss": 0.5657880417844082,
+      "train_runtime": 541.9228,
+      "train_samples_per_second": 55.358,
+      "train_steps_per_second": 0.867
     }
   ],
   "logging_steps": 500,
-  "max_steps": 395,
-  "num_train_epochs": 5,
+  "max_steps": 470,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 1.74132561024e+16,
+  "total_flos": 2.089590732288e+16,
   "trial_name": null,
   "trial_params": null
 }