End of training

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: albert-base-v2
 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 [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 69.43333333333334,
-    "f1": 79.25221934300359,
-    "train_loss": 0.7762964776221742,
-    "train_runtime": 101.5164,
+    "exact_match": 69.53333333333333,
+    "f1": 79.31930468455819,
+    "train_loss": 0.41871513204371674,
+    "train_runtime": 197.2832,
     "train_samples": 3000,
-    "train_samples_per_second": 147.759,
-    "train_steps_per_second": 2.315
+    "train_samples_per_second": 152.066,
+    "train_steps_per_second": 2.382
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f245b9584401b668d0194b26258b7c54e4cbab5f72c6afdcb40a6250b99dfb8e
+oid sha256:dd0965d3f563470f46319346d7038ec4e65efd9c85c61b754fea0b3171d83795
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026b34ded283d4ed8b02bd5f6d44f14d026a3ca3db545ddbae870b93522e8423
-size 13410828
+oid sha256:a0469941bf7a263ccfea4d74ea5f96411516ccfeaffbcb9f28ddedf5e7a4dd66
+size 13456510

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 69.43333333333334,
-    "f1": 79.25221934300359
+    "exact_match": 69.53333333333333,
+    "f1": 79.31930468455819
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 0.7762964776221742,
-    "train_runtime": 101.5164,
+    "epoch": 10.0,
+    "train_loss": 0.41871513204371674,
+    "train_runtime": 197.2832,
     "train_samples": 3000,
-    "train_samples_per_second": 147.759,
-    "train_steps_per_second": 2.315
+    "train_samples_per_second": 152.066,
+    "train_steps_per_second": 2.382
 }

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": 248442785280000.0,
-      "train_loss": 0.7762964776221742,
-      "train_runtime": 101.5164,
-      "train_samples_per_second": 147.759,
-      "train_steps_per_second": 2.315
+      "epoch": 10.0,
+      "step": 470,
+      "total_flos": 496885570560000.0,
+      "train_loss": 0.41871513204371674,
+      "train_runtime": 197.2832,
+      "train_samples_per_second": 152.066,
+      "train_steps_per_second": 2.382
     }
   ],
   "logging_steps": 500,
-  "max_steps": 235,
-  "num_train_epochs": 5,
+  "max_steps": 470,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 248442785280000.0,
+  "total_flos": 496885570560000.0,
   "trial_name": null,
   "trial_params": null
 }