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": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 57.266666666666666,
-    "f1": 67.84344433055534,
-    "train_loss": 1.7998744883435838,
-    "train_runtime": 81.9809,
+    "exact_match": 59.833333333333336,
+    "f1": 70.03211784220984,
+    "train_loss": 1.1987541036402924,
+    "train_runtime": 134.4633,
     "train_samples": 3000,
-    "train_samples_per_second": 109.782,
-    "train_steps_per_second": 3.44
+    "train_samples_per_second": 111.555,
+    "train_steps_per_second": 3.495
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27451d6951fb404d5440d8d3363762b82df73750de7c34ca5e845d8504f89b2
+oid sha256:c73e84d41f55176f4e92b8b00f9968583df48d9f0a08dd985ba6d2b254105b0c
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2c5ac444b5491f784848e0410b6e8d7854067bca925e32756bd90da36bad51
-size 13984380
+oid sha256:d07b786ffc7919ed87d80ead8801cead36f449e8a34eae0918a5277c29fe4210
+size 14101165

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 57.266666666666666,
-    "f1": 67.84344433055534
+    "exact_match": 59.833333333333336,
+    "f1": 70.03211784220984
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 1.7998744883435838,
-    "train_runtime": 81.9809,
+    "epoch": 5.0,
+    "train_loss": 1.1987541036402924,
+    "train_runtime": 134.4633,
     "train_samples": 3000,
-    "train_samples_per_second": 109.782,
-    "train_steps_per_second": 3.44
+    "train_samples_per_second": 111.555,
+    "train_steps_per_second": 3.495
 }

trainer_state.json

@@ -1,28 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 282,
+  "global_step": 470,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 282,
-      "total_flos": 1763753107968000.0,
-      "train_loss": 1.7998744883435838,
-      "train_runtime": 81.9809,
-      "train_samples_per_second": 109.782,
-      "train_steps_per_second": 3.44
+      "epoch": 5.0,
+      "step": 470,
+      "total_flos": 2939588513280000.0,
+      "train_loss": 1.1987541036402924,
+      "train_runtime": 134.4633,
+      "train_samples_per_second": 111.555,
+      "train_steps_per_second": 3.495
     }
   ],
   "logging_steps": 500,
-  "max_steps": 282,
-  "num_train_epochs": 3,
+  "max_steps": 470,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1763753107968000.0,
+  "total_flos": 2939588513280000.0,
   "trial_name": null,
   "trial_params": null
 }