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": 20.0,
+    "epoch": 50.0,
     "eval_samples": 5000,
-    "exact_match": 60.42,
-    "f1": 70.74697155317126,
-    "train_loss": 0.6378796005249023,
-    "train_runtime": 703.9199,
+    "exact_match": 62.22,
+    "f1": 71.95882328661979,
+    "train_loss": 0.25276324987411497,
+    "train_runtime": 1413.9494,
     "train_samples": 5000,
-    "train_samples_per_second": 142.062,
-    "train_steps_per_second": 0.568
+    "train_samples_per_second": 176.81,
+    "train_steps_per_second": 0.707
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9052152341dd06ff95dae32a6d0919c339c2305dbf17ecc196e067ab82bb93a7
+oid sha256:02786a2b8aa31481648ebb5d7d75d824eacfc2bc64318620127cdd232f9dc33b
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5b5fc8c31057d93f337bfdc1c35c06016f331d8518c543f81fdc0f8d947c830
-size 23177500
+oid sha256:9dd2c89529276e53a056a5cf5c51956d5c29915008e2c2bd400e554208e678b7
+size 23209136

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 20.0,
+    "epoch": 50.0,
     "eval_samples": 5000,
-    "exact_match": 60.42,
-    "f1": 70.74697155317126
+    "exact_match": 62.22,
+    "f1": 71.95882328661979
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 20.0,
-    "train_loss": 0.6378796005249023,
-    "train_runtime": 703.9199,
+    "epoch": 50.0,
+    "train_loss": 0.25276324987411497,
+    "train_runtime": 1413.9494,
     "train_samples": 5000,
-    "train_samples_per_second": 142.062,
-    "train_steps_per_second": 0.568
+    "train_samples_per_second": 176.81,
+    "train_steps_per_second": 0.707
 }

trainer_state.json

@@ -1,28 +1,40 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.0,
+  "epoch": 50.0,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 20.0,
-      "step": 400,
-      "total_flos": 1.95972567552e+16,
-      "train_loss": 0.6378796005249023,
-      "train_runtime": 703.9199,
-      "train_samples_per_second": 142.062,
-      "train_steps_per_second": 0.568
+      "epoch": 25.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4919,
+      "step": 500
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 0.0,
+      "loss": 0.0136,
+      "step": 1000
+    },
+    {
+      "epoch": 50.0,
+      "step": 1000,
+      "total_flos": 4.8993141888e+16,
+      "train_loss": 0.25276324987411497,
+      "train_runtime": 1413.9494,
+      "train_samples_per_second": 176.81,
+      "train_steps_per_second": 0.707
     }
   ],
   "logging_steps": 500,
-  "max_steps": 400,
-  "num_train_epochs": 20,
+  "max_steps": 1000,
+  "num_train_epochs": 50,
   "save_steps": 500,
-  "total_flos": 1.95972567552e+16,
+  "total_flos": 4.8993141888e+16,
   "trial_name": null,
   "trial_params": null
 }