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,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 65.56666666666666,
-    "f1": 75.93060374296303,
-    "train_loss": 1.0810851401471078,
-    "train_runtime": 273.8486,
+    "exact_match": 66.66666666666667,
+    "f1": 76.95180617275538,
+    "train_loss": 0.5657880417844082,
+    "train_runtime": 540.1618,
     "train_samples": 3000,
-    "train_samples_per_second": 54.775,
-    "train_steps_per_second": 0.858
+    "train_samples_per_second": 55.539,
+    "train_steps_per_second": 0.87
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cab85d2af58594514b7846f01cd583d20620cc5064a5becb223c67bbd1494bc
+oid sha256:68b06743eb1444e73c6082d6e5adb75717ebed887b12e4421107c1754933e13f
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd50a260908fa943fc19dec08a82fb831491ee5246177596db2225b964265418
-size 13858090
+oid sha256:65615ed4fe1c8c9e41a22dc324bdb4e22c39c9726ed41e382bad39176689b6a3
+size 14067254

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 65.56666666666666,
-    "f1": 75.93060374296303
+    "exact_match": 66.66666666666667,
+    "f1": 76.95180617275538
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 1.0810851401471078,
-    "train_runtime": 273.8486,
+    "epoch": 10.0,
+    "train_loss": 0.5657880417844082,
+    "train_runtime": 540.1618,
     "train_samples": 3000,
-    "train_samples_per_second": 54.775,
-    "train_steps_per_second": 0.858
+    "train_samples_per_second": 55.539,
+    "train_steps_per_second": 0.87
 }

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": 235,
+  "global_step": 470,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 5.0,
-      "step": 235,
-      "total_flos": 1.044795366144e+16,
-      "train_loss": 1.0810851401471078,
-      "train_runtime": 273.8486,
-      "train_samples_per_second": 54.775,
-      "train_steps_per_second": 0.858
+      "epoch": 10.0,
+      "step": 470,
+      "total_flos": 2.089590732288e+16,
+      "train_loss": 0.5657880417844082,
+      "train_runtime": 540.1618,
+      "train_samples_per_second": 55.539,
+      "train_steps_per_second": 0.87
     }
   ],
   "logging_steps": 500,
-  "max_steps": 235,
-  "num_train_epochs": 5,
+  "max_steps": 470,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 1.044795366144e+16,
+  "total_flos": 2.089590732288e+16,
   "trial_name": null,
   "trial_params": null
 }