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": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 9.333333333333334,
-    "f1": 14.467623210820486,
-    "train_loss": 4.351121690538195,
-    "train_runtime": 29.6764,
+    "exact_match": 14.0,
+    "f1": 20.21415093661164,
+    "train_loss": 3.7768229166666667,
+    "train_runtime": 45.2448,
     "train_samples": 3000,
-    "train_samples_per_second": 303.272,
-    "train_steps_per_second": 1.213
+    "train_samples_per_second": 331.53,
+    "train_steps_per_second": 1.326
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51c8883aff3f1da4c3347b9cab131bc71b9aff4c0806b779b6279cf0f12b1591
+oid sha256:d0f996fea854c7f83cce57a5b79a6a67508af338f09e84d18d5d701d400c605c
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:712e1b60dc69e369d446b9cab4e9b3a4d8e1674aee0ebe8bbfde1fc436e15c52
-size 14416993
+oid sha256:70a2dc71fd0b1dd88f6af5c686866dd9c375efc2ec745a421ee66285c0a9f86c
+size 14384223

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 9.333333333333334,
-    "f1": 14.467623210820486
+    "exact_match": 14.0,
+    "f1": 20.21415093661164
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 4.351121690538195,
-    "train_runtime": 29.6764,
+    "epoch": 5.0,
+    "train_loss": 3.7768229166666667,
+    "train_runtime": 45.2448,
     "train_samples": 3000,
-    "train_samples_per_second": 303.272,
-    "train_steps_per_second": 1.213
+    "train_samples_per_second": 331.53,
+    "train_steps_per_second": 1.326
 }

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": 36,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 36,
-      "total_flos": 881908425216000.0,
-      "train_loss": 4.351121690538195,
-      "train_runtime": 29.6764,
-      "train_samples_per_second": 303.272,
-      "train_steps_per_second": 1.213
+      "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
     }
   ],
   "logging_steps": 500,
-  "max_steps": 36,
-  "num_train_epochs": 3,
+  "max_steps": 60,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 881908425216000.0,
+  "total_flos": 1469847375360000.0,
   "trial_name": null,
   "trial_params": null
 }