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": 5000,
-    "exact_match": 63.04,
-    "f1": 72.7227629774702,
-    "train_loss": 0.9167267234462082,
-    "train_runtime": 215.6037,
+    "exact_match": 63.44,
+    "f1": 73.23936492780788,
+    "train_loss": 0.4993326762679276,
+    "train_runtime": 435.4109,
     "train_samples": 5000,
-    "train_samples_per_second": 115.953,
-    "train_steps_per_second": 3.641
+    "train_samples_per_second": 114.834,
+    "train_steps_per_second": 3.606
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d553cf4574a4e9be4e65ad1f80904cdc8c8b0ab5936ff145353b91eeaf6fcfb
+oid sha256:582307e537606fc7e95a67ea720b3d66dd8e91c37fbb1573b9a4ef95e35bbb25
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d524a01fe642f32844cbfbe43476f8742f66853135d3436c57d1f7f1552982
-size 22748312
+oid sha256:86fc5bb73d9f87545c3a6e4966872b53b6774b98e346fb7ef856261fc86ba95b
+size 23075256

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 5000,
-    "exact_match": 63.04,
-    "f1": 72.7227629774702
+    "exact_match": 63.44,
+    "f1": 73.23936492780788
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 0.9167267234462082,
-    "train_runtime": 215.6037,
+    "epoch": 10.0,
+    "train_loss": 0.4993326762679276,
+    "train_runtime": 435.4109,
     "train_samples": 5000,
-    "train_samples_per_second": 115.953,
-    "train_steps_per_second": 3.641
+    "train_samples_per_second": 114.834,
+    "train_steps_per_second": 3.606
 }

trainer_state.json

@@ -1,34 +1,46 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 785,
+  "global_step": 1570,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 3.18,
-      "learning_rate": 1.8152866242038215e-05,
-      "loss": 1.2876,
+      "learning_rate": 3.407643312101911e-05,
+      "loss": 1.2801,
       "step": 500
     },
     {
-      "epoch": 5.0,
-      "step": 785,
-      "total_flos": 4899314188800000.0,
-      "train_loss": 0.9167267234462082,
-      "train_runtime": 215.6037,
-      "train_samples_per_second": 115.953,
-      "train_steps_per_second": 3.641
+      "epoch": 6.37,
+      "learning_rate": 1.8152866242038215e-05,
+      "loss": 0.2111,
+      "step": 1000
+    },
+    {
+      "epoch": 9.55,
+      "learning_rate": 2.229299363057325e-06,
+      "loss": 0.0713,
+      "step": 1500
+    },
+    {
+      "epoch": 10.0,
+      "step": 1570,
+      "total_flos": 9798628377600000.0,
+      "train_loss": 0.4993326762679276,
+      "train_runtime": 435.4109,
+      "train_samples_per_second": 114.834,
+      "train_steps_per_second": 3.606
     }
   ],
   "logging_steps": 500,
-  "max_steps": 785,
-  "num_train_epochs": 5,
+  "max_steps": 1570,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 4899314188800000.0,
+  "total_flos": 9798628377600000.0,
   "trial_name": null,
   "trial_params": null
 }