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": 3.0,
+    "epoch": 5.0,
     "eval_samples": 5000,
-    "exact_match": 64.94,
-    "f1": 74.88256878240358,
-    "train_loss": 1.7362415313720703,
-    "train_runtime": 240.9993,
+    "exact_match": 65.68,
+    "f1": 76.0006601247389,
+    "train_loss": 1.093597183227539,
+    "train_runtime": 399.8372,
     "train_samples": 5000,
-    "train_samples_per_second": 62.241,
-    "train_steps_per_second": 0.498
+    "train_samples_per_second": 62.525,
+    "train_steps_per_second": 0.5
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79802b2d38e0625bbb14c3acd3fc2717abc0f0b822b17aac8ecb8715343ac2f3
+oid sha256:1c18f8e7ce609fcb7f5cece5f9af488f87bad0ed008cab5b3474cd51d8afb3fd
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5435916da9a8e8964bea4d4429a6cdad4f297265ac33dae971608c0d874226de
-size 22481960
+oid sha256:e9be45d43403e97984aaba2595c11c44400055b40223f61b868252f48cdaa900
+size 22460373

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 5000,
-    "exact_match": 64.94,
-    "f1": 74.88256878240358
+    "exact_match": 65.68,
+    "f1": 76.0006601247389
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 1.7362415313720703,
-    "train_runtime": 240.9993,
+    "epoch": 5.0,
+    "train_loss": 1.093597183227539,
+    "train_runtime": 399.8372,
     "train_samples": 5000,
-    "train_samples_per_second": 62.241,
-    "train_steps_per_second": 0.498
+    "train_samples_per_second": 62.525,
+    "train_steps_per_second": 0.5
 }

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": 120,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 120,
-      "total_flos": 1.044795366144e+16,
-      "train_loss": 1.7362415313720703,
-      "train_runtime": 240.9993,
-      "train_samples_per_second": 62.241,
-      "train_steps_per_second": 0.498
+      "epoch": 5.0,
+      "step": 200,
+      "total_flos": 1.74132561024e+16,
+      "train_loss": 1.093597183227539,
+      "train_runtime": 399.8372,
+      "train_samples_per_second": 62.525,
+      "train_steps_per_second": 0.5
     }
   ],
   "logging_steps": 500,
-  "max_steps": 120,
-  "num_train_epochs": 3,
+  "max_steps": 200,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.044795366144e+16,
+  "total_flos": 1.74132561024e+16,
   "trial_name": null,
   "trial_params": null
 }