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": 45.6375,
+    "exact_match": 42.8,
+    "f1": 53.12557533001562,
+    "train_loss": 2.859217224121094,
+    "train_runtime": 73.9374,
     "train_samples": 5000,
-    "train_samples_per_second": 328.677,
-    "train_steps_per_second": 1.315
+    "train_samples_per_second": 338.124,
+    "train_steps_per_second": 1.352
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98798d11dd0cdecae302e736d5a9515adb5ead3dc44e56684fff7d3c9ce849c9
+oid sha256:4564febfe1f53ae18f66da04c6f4c5652a34f54ef148853be8c4e759923eb57f
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac251bbb2f244b349586525dbf4b3d6dbb0b63367cdec64d3db6dd2f02562724
-size 23506813
+oid sha256:a3a75753c8031177117ea174e61ab4e5c4889e60ad57499b2a3042808bf1cde5
+size 22998191

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": 45.6375,
+    "epoch": 5.0,
+    "train_loss": 2.859217224121094,
+    "train_runtime": 73.9374,
     "train_samples": 5000,
-    "train_samples_per_second": 328.677,
-    "train_steps_per_second": 1.315
+    "train_samples_per_second": 338.124,
+    "train_steps_per_second": 1.352
 }

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": 45.6375,
-      "train_samples_per_second": 328.677,
-      "train_steps_per_second": 1.315
+      "epoch": 5.0,
+      "step": 100,
+      "total_flos": 2449745625600000.0,
+      "train_loss": 2.859217224121094,
+      "train_runtime": 73.9374,
+      "train_samples_per_second": 338.124,
+      "train_steps_per_second": 1.352
     }
   ],
   "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
 }