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": 59.7,
-    "f1": 69.87047070681501,
-    "train_loss": 1.686978497082674,
-    "train_runtime": 105.3178,
+    "exact_match": 61.48,
+    "f1": 71.87791395508978,
+    "train_loss": 1.1596815664556963,
+    "train_runtime": 169.407,
     "train_samples": 5000,
-    "train_samples_per_second": 142.426,
-    "train_steps_per_second": 2.25
+    "train_samples_per_second": 147.574,
+    "train_steps_per_second": 2.332
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:899fdba252d778354c225f8e7f4fa341d401b33c0985b2c101f08cd1bbc85ba3
+oid sha256:fd911f98856fb1c15532b0b9898de14cc06164d501fc3f3b4f585db57dd902ad
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afc1cfe88e006fc074e06db5966fce1be065452d5cd9f72523611e9f504cf112
-size 22644197
+oid sha256:6df02f82341428618e78b94cabbc9fceabc47d63bf78ba4650e4587a59cd6938
+size 22859124

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 5000,
-    "exact_match": 59.7,
-    "f1": 69.87047070681501
+    "exact_match": 61.48,
+    "f1": 71.87791395508978
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 1.686978497082674,
-    "train_runtime": 105.3178,
+    "epoch": 5.0,
+    "train_loss": 1.1596815664556963,
+    "train_runtime": 169.407,
     "train_samples": 5000,
-    "train_samples_per_second": 142.426,
-    "train_steps_per_second": 2.25
+    "train_samples_per_second": 147.574,
+    "train_steps_per_second": 2.332
 }

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": 237,
+  "global_step": 395,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 237,
-      "total_flos": 2939588513280000.0,
-      "train_loss": 1.686978497082674,
-      "train_runtime": 105.3178,
-      "train_samples_per_second": 142.426,
-      "train_steps_per_second": 2.25
+      "epoch": 5.0,
+      "step": 395,
+      "total_flos": 4899314188800000.0,
+      "train_loss": 1.1596815664556963,
+      "train_runtime": 169.407,
+      "train_samples_per_second": 147.574,
+      "train_steps_per_second": 2.332
     }
   ],
   "logging_steps": 500,
-  "max_steps": 237,
-  "num_train_epochs": 3,
+  "max_steps": 395,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 2939588513280000.0,
+  "total_flos": 4899314188800000.0,
   "trial_name": null,
   "trial_params": null
 }