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": 43.06,
-    "f1": 53.618746262295474,
-    "train_loss": 2.885350290934245,
-    "train_runtime": 83.8882,
+    "exact_match": 52.26,
+    "f1": 62.58034876294766,
+    "train_loss": 2.077248229980469,
+    "train_runtime": 134.9317,
     "train_samples": 5000,
-    "train_samples_per_second": 178.81,
-    "train_steps_per_second": 1.43
+    "train_samples_per_second": 185.279,
+    "train_steps_per_second": 1.482
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e34056bf27991072a1449390dcae51e12e177000b669ebf7b5ada9992fee424
+oid sha256:5b6753784ab048176f0cd0536de542b42e0055eb958dee0172500b5929e820d0
 size 5588

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cef250ff0822a071831145d0d9a1e2fbe3d92b857134e6ccb6ef04f41e128404
-size 23049810
+oid sha256:69eed0ed657f5c33a2db92a12b724aa1d2df5565e5c114f2424b27b2c302f8d2
+size 22829472

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 5000,
-    "exact_match": 43.06,
-    "f1": 53.618746262295474
+    "exact_match": 52.26,
+    "f1": 62.58034876294766
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 2.885350290934245,
-    "train_runtime": 83.8882,
+    "epoch": 5.0,
+    "train_loss": 2.077248229980469,
+    "train_runtime": 134.9317,
     "train_samples": 5000,
-    "train_samples_per_second": 178.81,
-    "train_steps_per_second": 1.43
+    "train_samples_per_second": 185.279,
+    "train_steps_per_second": 1.482
 }

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": 120,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 120,
-      "total_flos": 1469847375360000.0,
-      "train_loss": 2.885350290934245,
-      "train_runtime": 83.8882,
-      "train_samples_per_second": 178.81,
-      "train_steps_per_second": 1.43
+      "epoch": 5.0,
+      "step": 200,
+      "total_flos": 2449745625600000.0,
+      "train_loss": 2.077248229980469,
+      "train_runtime": 134.9317,
+      "train_samples_per_second": 185.279,
+      "train_steps_per_second": 1.482
     }
   ],
   "logging_steps": 500,
-  "max_steps": 120,
-  "num_train_epochs": 3,
+  "max_steps": 200,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1469847375360000.0,
+  "total_flos": 2449745625600000.0,
   "trial_name": null,
   "trial_params": null
 }