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": 10.0,
+    "epoch": 20.0,
     "eval_samples": 5000,
-    "exact_match": 59.58,
-    "f1": 69.71960105711858,
-    "train_loss": 1.2581602478027343,
-    "train_runtime": 413.243,
+    "exact_match": 60.42,
+    "f1": 70.74697155317126,
+    "train_loss": 0.6378796005249023,
+    "train_runtime": 703.9199,
     "train_samples": 5000,
-    "train_samples_per_second": 120.994,
-    "train_steps_per_second": 0.484
+    "train_samples_per_second": 142.062,
+    "train_steps_per_second": 0.568
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e604a3d57f8c0e7d4e3b20a1684e254a6ed551ed9c978f83e0da6fb59f5a8a61
+oid sha256:9052152341dd06ff95dae32a6d0919c339c2305dbf17ecc196e067ab82bb93a7
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae9f7bfa4e5b405e38b8ee97a5724923387c9936987caa3d8fc562c50b6fbf41
-size 22804353
+oid sha256:e5b5fc8c31057d93f337bfdc1c35c06016f331d8518c543f81fdc0f8d947c830
+size 23177500

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 5000,
-    "exact_match": 59.58,
-    "f1": 69.71960105711858
+    "exact_match": 60.42,
+    "f1": 70.74697155317126
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "train_loss": 1.2581602478027343,
-    "train_runtime": 413.243,
+    "epoch": 20.0,
+    "train_loss": 0.6378796005249023,
+    "train_runtime": 703.9199,
     "train_samples": 5000,
-    "train_samples_per_second": 120.994,
-    "train_steps_per_second": 0.484
+    "train_samples_per_second": 142.062,
+    "train_steps_per_second": 0.568
 }

trainer_state.json

@@ -1,28 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 10.0,
-      "step": 200,
-      "total_flos": 9798628377600000.0,
-      "train_loss": 1.2581602478027343,
-      "train_runtime": 413.243,
-      "train_samples_per_second": 120.994,
-      "train_steps_per_second": 0.484
+      "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
     }
   ],
   "logging_steps": 500,
-  "max_steps": 200,
-  "num_train_epochs": 10,
+  "max_steps": 400,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 9798628377600000.0,
+  "total_flos": 1.95972567552e+16,
   "trial_name": null,
   "trial_params": null
 }