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": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 59.833333333333336,
-    "f1": 70.03211784220984,
-    "train_loss": 1.1987541036402924,
-    "train_runtime": 134.4633,
+    "exact_match": 60.2,
+    "f1": 70.56217910315665,
+    "train_loss": 0.6274924014477019,
+    "train_runtime": 267.6611,
     "train_samples": 3000,
-    "train_samples_per_second": 111.555,
-    "train_steps_per_second": 3.495
+    "train_samples_per_second": 112.082,
+    "train_steps_per_second": 3.512
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c73e84d41f55176f4e92b8b00f9968583df48d9f0a08dd985ba6d2b254105b0c
+oid sha256:30dc4bfdecc4f8bda46f12340afa0f3283ef9640136a6ed75059db7badcb250f
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d07b786ffc7919ed87d80ead8801cead36f449e8a34eae0918a5277c29fe4210
-size 14101165
+oid sha256:4e7b0af6c461862f9cef77ac33fe3cfcd3bdf5ba7424558b09e2b39755aad680
+size 14082921

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 59.833333333333336,
-    "f1": 70.03211784220984
+    "exact_match": 60.2,
+    "f1": 70.56217910315665
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 1.1987541036402924,
-    "train_runtime": 134.4633,
+    "epoch": 10.0,
+    "train_loss": 0.6274924014477019,
+    "train_runtime": 267.6611,
     "train_samples": 3000,
-    "train_samples_per_second": 111.555,
-    "train_steps_per_second": 3.495
+    "train_samples_per_second": 112.082,
+    "train_steps_per_second": 3.512
 }

trainer_state.json

@@ -1,28 +1,34 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 470,
+  "global_step": 940,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 5.0,
-      "step": 470,
-      "total_flos": 2939588513280000.0,
-      "train_loss": 1.1987541036402924,
-      "train_runtime": 134.4633,
-      "train_samples_per_second": 111.555,
-      "train_steps_per_second": 3.495
+      "epoch": 5.32,
+      "learning_rate": 2.340425531914894e-05,
+      "loss": 1.1006,
+      "step": 500
+    },
+    {
+      "epoch": 10.0,
+      "step": 940,
+      "total_flos": 5879177026560000.0,
+      "train_loss": 0.6274924014477019,
+      "train_runtime": 267.6611,
+      "train_samples_per_second": 112.082,
+      "train_steps_per_second": 3.512
     }
   ],
   "logging_steps": 500,
-  "max_steps": 470,
-  "num_train_epochs": 5,
+  "max_steps": 940,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2939588513280000.0,
+  "total_flos": 5879177026560000.0,
   "trial_name": null,
   "trial_params": null
 }