End of training

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: distilbert-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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-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": 14.0,
-    "f1": 20.21415093661164,
-    "train_loss": 3.7768229166666667,
-    "train_runtime": 45.2448,
+    "exact_match": 44.06666666666667,
+    "f1": 53.81229298968328,
+    "train_loss": 2.510331217447917,
+    "train_runtime": 86.3861,
     "train_samples": 3000,
-    "train_samples_per_second": 331.53,
-    "train_steps_per_second": 1.326
+    "train_samples_per_second": 347.278,
+    "train_steps_per_second": 1.389
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f996fea854c7f83cce57a5b79a6a67508af338f09e84d18d5d701d400c605c
+oid sha256:cf9af8252df187228c7d36fb5985d48984bc90bea7a9d665b09de0524c7dae30
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a2dc71fd0b1dd88f6af5c686866dd9c375efc2ec745a421ee66285c0a9f86c
-size 14384223
+oid sha256:5180325ed7d80019a21104f00ef5115fe6ebb712cc83921d2977d16c7cd69eba
+size 14076237

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 14.0,
-    "f1": 20.21415093661164
+    "exact_match": 44.06666666666667,
+    "f1": 53.81229298968328
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 3.7768229166666667,
-    "train_runtime": 45.2448,
+    "epoch": 10.0,
+    "train_loss": 2.510331217447917,
+    "train_runtime": 86.3861,
     "train_samples": 3000,
-    "train_samples_per_second": 331.53,
-    "train_steps_per_second": 1.326
+    "train_samples_per_second": 347.278,
+    "train_steps_per_second": 1.389
 }

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": 60,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 5.0,
-      "step": 60,
-      "total_flos": 1469847375360000.0,
-      "train_loss": 3.7768229166666667,
-      "train_runtime": 45.2448,
-      "train_samples_per_second": 331.53,
-      "train_steps_per_second": 1.326
+      "epoch": 10.0,
+      "step": 120,
+      "total_flos": 2939694750720000.0,
+      "train_loss": 2.510331217447917,
+      "train_runtime": 86.3861,
+      "train_samples_per_second": 347.278,
+      "train_steps_per_second": 1.389
     }
   ],
   "logging_steps": 500,
-  "max_steps": 60,
-  "num_train_epochs": 5,
+  "max_steps": 120,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 1469847375360000.0,
+  "total_flos": 2939694750720000.0,
   "trial_name": null,
   "trial_params": null
 }