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": 5000,
-    "exact_match": 15.38,
-    "f1": 21.930776458284956,
-    "train_loss": 3.737274678548177,
-    "train_runtime": 76.8952,
+    "exact_match": 42.8,
+    "f1": 53.12557533001562,
+    "train_loss": 2.859217224121094,
+    "train_runtime": 123.9942,
     "train_samples": 5000,
-    "train_samples_per_second": 195.071,
-    "train_steps_per_second": 0.78
+    "train_samples_per_second": 201.622,
+    "train_steps_per_second": 0.806
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30231df9ec3139aaf926968164cc03e8532646ba3ce58b8ee9f40195f0ce42c8
+oid sha256:aa167e02ac780bb944b9315cee4620d61ed7bdca97dfacdca468e17a08a73c0d
 size 5588

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cbe588cdef23e5896fe91154e98b43872e9757939c180444f27297cf8632b11
-size 23506986
+oid sha256:70038db594c4473d8778a9fdca8e88b2192f40fb5133a7b2d5c5853a841b12ef
+size 22999531

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 5000,
-    "exact_match": 15.38,
-    "f1": 21.930776458284956
+    "exact_match": 42.8,
+    "f1": 53.12557533001562
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 3.737274678548177,
-    "train_runtime": 76.8952,
+    "epoch": 5.0,
+    "train_loss": 2.859217224121094,
+    "train_runtime": 123.9942,
     "train_samples": 5000,
-    "train_samples_per_second": 195.071,
-    "train_steps_per_second": 0.78
+    "train_samples_per_second": 201.622,
+    "train_steps_per_second": 0.806
 }

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": 60,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 60,
-      "total_flos": 1469847375360000.0,
-      "train_loss": 3.737274678548177,
-      "train_runtime": 76.8952,
-      "train_samples_per_second": 195.071,
-      "train_steps_per_second": 0.78
+      "epoch": 5.0,
+      "step": 100,
+      "total_flos": 2449745625600000.0,
+      "train_loss": 2.859217224121094,
+      "train_runtime": 123.9942,
+      "train_samples_per_second": 201.622,
+      "train_steps_per_second": 0.806
     }
   ],
   "logging_steps": 500,
-  "max_steps": 60,
-  "num_train_epochs": 3,
+  "max_steps": 100,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1469847375360000.0,
+  "total_flos": 2449745625600000.0,
   "trial_name": null,
   "trial_params": null
 }