End of training

README.md

@@ -4,6 +4,8 @@ license: apache-2.0
 base_model: albert/albert-base-v2
 tags:
 - generated_from_trainer
+datasets:
+- squad
 model-index:
 - name: squad_albert_finetuned2
   results: []
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # squad_albert_finetuned2
 
-This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
+This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -602,20 +602,20 @@
     "epoch": 1.0,
     "eval_exact_match": 13.0,
     "eval_f1": 22.02673682526624,
-    "eval_runtime": 3.405,
+    "eval_runtime": 3.4116,
     "eval_samples": 100,
-    "eval_samples_per_second": 29.368,
-    "eval_steps_per_second": 3.818,
+    "eval_samples_per_second": 29.312,
+    "eval_steps_per_second": 3.811,
     "predict_samples_tr": 100,
     "test_exact_match": 33.0,
     "test_f1": 43.51652920179235,
-    "test_runtime": 3.1882,
-    "test_samples_per_second": 31.365,
-    "test_steps_per_second": 4.077,
+    "test_runtime": 3.1834,
+    "test_samples_per_second": 31.413,
+    "test_steps_per_second": 4.084,
     "total_flos": 1656285235200.0,
     "train_loss": 0.0,
-    "train_runtime": 1.684,
+    "train_runtime": 1.5301,
     "train_samples": 100,
-    "train_samples_per_second": 59.381,
-    "train_steps_per_second": 29.691
+    "train_samples_per_second": 65.355,
+    "train_steps_per_second": 32.677
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "eval_exact_match": 13.0,
     "eval_f1": 22.02673682526624,
-    "eval_runtime": 3.405,
+    "eval_runtime": 3.4116,
     "eval_samples": 100,
-    "eval_samples_per_second": 29.368,
-    "eval_steps_per_second": 3.818
+    "eval_samples_per_second": 29.312,
+    "eval_steps_per_second": 3.811
 }

predict_tr_results.json

@@ -2,7 +2,7 @@
     "predict_samples_tr": 100,
     "test_exact_match": 33.0,
     "test_f1": 43.51652920179235,
-    "test_runtime": 3.1882,
-    "test_samples_per_second": 31.365,
-    "test_steps_per_second": 4.077
+    "test_runtime": 3.1834,
+    "test_samples_per_second": 31.413,
+    "test_steps_per_second": 4.084
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 1656285235200.0,
     "train_loss": 0.0,
-    "train_runtime": 1.684,
+    "train_runtime": 1.5301,
     "train_samples": 100,
-    "train_samples_per_second": 59.381,
-    "train_steps_per_second": 29.691
+    "train_samples_per_second": 65.355,
+    "train_steps_per_second": 32.677
 }

trainer_state.json

@@ -13,9 +13,9 @@
       "step": 50,
       "total_flos": 1656285235200.0,
       "train_loss": 0.0,
-      "train_runtime": 1.684,
-      "train_samples_per_second": 59.381,
-      "train_steps_per_second": 29.691
+      "train_runtime": 1.5301,
+      "train_samples_per_second": 65.355,
+      "train_steps_per_second": 32.677
     }
   ],
   "logging_steps": 500,