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": 56.8,
-    "f1": 66.82949852318735,
-    "train_loss": 1.581298178814827,
-    "train_runtime": 105.6881,
+    "exact_match": 57.9,
+    "f1": 68.29356952960427,
+    "train_loss": 0.8431574395362367,
+    "train_runtime": 207.7697,
     "train_samples": 3000,
-    "train_samples_per_second": 141.927,
-    "train_steps_per_second": 2.224
+    "train_samples_per_second": 144.391,
+    "train_steps_per_second": 2.262
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54d6f8651fccacfe2c1b70696f553dda46f815f7eb9d77628c2a3a3111f8cbee
+oid sha256:f9693899242c922d9426f4ef9bfb511d8e0cb6abdd88a8c8e3dd4c665c3a6777
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e192c79650550dc8a839465d094c7e231783f46298f465788c94b5662117eb
-size 13984069
+oid sha256:0eb0b92ab764d996c08df8d1432896a80f9410e4628c75f5f2b472ead9a9e69a
+size 14163554

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 56.8,
-    "f1": 66.82949852318735
+    "exact_match": 57.9,
+    "f1": 68.29356952960427
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 1.581298178814827,
-    "train_runtime": 105.6881,
+    "epoch": 10.0,
+    "train_loss": 0.8431574395362367,
+    "train_runtime": 207.7697,
     "train_samples": 3000,
-    "train_samples_per_second": 141.927,
-    "train_steps_per_second": 2.224
+    "train_samples_per_second": 144.391,
+    "train_steps_per_second": 2.262
 }

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": 235,
+  "global_step": 470,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 5.0,
-      "step": 235,
-      "total_flos": 2939588513280000.0,
-      "train_loss": 1.581298178814827,
-      "train_runtime": 105.6881,
-      "train_samples_per_second": 141.927,
-      "train_steps_per_second": 2.224
+      "epoch": 10.0,
+      "step": 470,
+      "total_flos": 5879177026560000.0,
+      "train_loss": 0.8431574395362367,
+      "train_runtime": 207.7697,
+      "train_samples_per_second": 144.391,
+      "train_steps_per_second": 2.262
     }
   ],
   "logging_steps": 500,
-  "max_steps": 235,
-  "num_train_epochs": 5,
+  "max_steps": 470,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2939588513280000.0,
+  "total_flos": 5879177026560000.0,
   "trial_name": null,
   "trial_params": null
 }