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": 51.4,
-    "f1": 61.80132735813969,
-    "train_loss": 2.202923583984375,
-    "train_runtime": 90.231,
+    "exact_match": 55.53333333333333,
+    "f1": 65.96783081998758,
+    "train_loss": 1.2132312774658203,
+    "train_runtime": 177.4882,
     "train_samples": 3000,
-    "train_samples_per_second": 166.24,
-    "train_steps_per_second": 1.33
+    "train_samples_per_second": 169.025,
+    "train_steps_per_second": 1.352
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6133e2830387b5855ef3e60bb9972535deca578b899f163c60140ed43063358b
+oid sha256:275c983112aa7798c90fd01b66495c299b934e1672e6ea925c1b22df404a111a
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f399189608612fd60d52294bdf8e6410d929b1a75150bbac5de47a0342ae73
-size 13988199
+oid sha256:d493f82275909c0b4890919d9bb255868a43e2bb5fb9ac154c4121b15f429b8f
+size 14068360

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 51.4,
-    "f1": 61.80132735813969
+    "exact_match": 55.53333333333333,
+    "f1": 65.96783081998758
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 2.202923583984375,
-    "train_runtime": 90.231,
+    "epoch": 10.0,
+    "train_loss": 1.2132312774658203,
+    "train_runtime": 177.4882,
     "train_samples": 3000,
-    "train_samples_per_second": 166.24,
-    "train_steps_per_second": 1.33
+    "train_samples_per_second": 169.025,
+    "train_steps_per_second": 1.352
 }

trainer_state.json

@@ -1,28 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 5.0,
-      "step": 120,
-      "total_flos": 2939588513280000.0,
-      "train_loss": 2.202923583984375,
-      "train_runtime": 90.231,
-      "train_samples_per_second": 166.24,
-      "train_steps_per_second": 1.33
+      "epoch": 10.0,
+      "step": 240,
+      "total_flos": 5879177026560000.0,
+      "train_loss": 1.2132312774658203,
+      "train_runtime": 177.4882,
+      "train_samples_per_second": 169.025,
+      "train_steps_per_second": 1.352
     }
   ],
   "logging_steps": 500,
-  "max_steps": 120,
-  "num_train_epochs": 5,
+  "max_steps": 240,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2939588513280000.0,
+  "total_flos": 5879177026560000.0,
   "trial_name": null,
   "trial_params": null
 }