End of training

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: bert-large-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-large-uncased](https://huggingface.co/bert-large-uncased) on the None dataset.
+This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-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": 65.33333333333333,
-    "f1": 75.53040749041759,
-    "train_loss": 1.3561742255028257,
-    "train_runtime": 201.2091,
+    "exact_match": 67.93333333333334,
+    "f1": 77.72615073637355,
+    "train_loss": 0.8829002867353724,
+    "train_runtime": 329.6971,
     "train_samples": 3000,
-    "train_samples_per_second": 44.73,
-    "train_steps_per_second": 1.402
+    "train_samples_per_second": 45.496,
+    "train_steps_per_second": 1.426
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65fa218cb552d3042096e9a62289ae1ccab4c8c0577012b02669b3c54d4ae1e3
+oid sha256:52d10610d2dbda47810ec0e88c845b59efd7ea20818907375a7b0a0c65210321
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e06574c62ad947e8cf9ed2283dae9b0e7609d0692b817f3635106e5001c47a
-size 13778063
+oid sha256:88e9173c6a56dc2d8a2be7f2b7947a7e91ad5fadadd77e43394edcebee93f726
+size 13842730

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 65.33333333333333,
-    "f1": 75.53040749041759
+    "exact_match": 67.93333333333334,
+    "f1": 77.72615073637355
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 1.3561742255028257,
-    "train_runtime": 201.2091,
+    "epoch": 5.0,
+    "train_loss": 0.8829002867353724,
+    "train_runtime": 329.6971,
     "train_samples": 3000,
-    "train_samples_per_second": 44.73,
-    "train_steps_per_second": 1.402
+    "train_samples_per_second": 45.496,
+    "train_steps_per_second": 1.426
 }

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": 6268772196864000.0,
-      "train_loss": 1.3561742255028257,
-      "train_runtime": 201.2091,
-      "train_samples_per_second": 44.73,
-      "train_steps_per_second": 1.402
+      "epoch": 5.0,
+      "step": 470,
+      "total_flos": 1.044795366144e+16,
+      "train_loss": 0.8829002867353724,
+      "train_runtime": 329.6971,
+      "train_samples_per_second": 45.496,
+      "train_steps_per_second": 1.426
     }
   ],
   "logging_steps": 500,
-  "max_steps": 282,
-  "num_train_epochs": 3,
+  "max_steps": 470,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 6268772196864000.0,
+  "total_flos": 1.044795366144e+16,
   "trial_name": null,
   "trial_params": null
 }