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": 49.86666666666667,
-    "f1": 59.61058102716164,
-    "train_loss": 2.3143946870844414,
-    "train_runtime": 49.5839,
+    "exact_match": 53.53333333333333,
+    "f1": 63.283542684518345,
+    "train_loss": 1.5697038366439495,
+    "train_runtime": 80.4186,
     "train_samples": 3000,
-    "train_samples_per_second": 181.511,
-    "train_steps_per_second": 5.687
+    "train_samples_per_second": 186.524,
+    "train_steps_per_second": 5.844
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec2e39b08df8c2a081fb8e5631f0856a540b5d572c8c142195a55a84002cc4e1
+oid sha256:b5ad6d9f72bf7e4a3096700a478257bc8d4a8dfed20cfb091ba8f83890913187
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1485367969b2d45f98fb1dd10711eaa35f90669a6025ce9d5baaa1cdba2cfb2
-size 14050357
+oid sha256:db9382aefdac2f83b40fe23a6f8222f14e77d5617edfeab7dd0a2b642b7de742
+size 14051098

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 49.86666666666667,
-    "f1": 59.61058102716164
+    "exact_match": 53.53333333333333,
+    "f1": 63.283542684518345
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 2.3143946870844414,
-    "train_runtime": 49.5839,
+    "epoch": 5.0,
+    "train_loss": 1.5697038366439495,
+    "train_runtime": 80.4186,
     "train_samples": 3000,
-    "train_samples_per_second": 181.511,
-    "train_steps_per_second": 5.687
+    "train_samples_per_second": 186.524,
+    "train_steps_per_second": 5.844
 }

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": 282,
+  "global_step": 470,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 282,
-      "total_flos": 881908425216000.0,
-      "train_loss": 2.3143946870844414,
-      "train_runtime": 49.5839,
-      "train_samples_per_second": 181.511,
-      "train_steps_per_second": 5.687
+      "epoch": 5.0,
+      "step": 470,
+      "total_flos": 1469847375360000.0,
+      "train_loss": 1.5697038366439495,
+      "train_runtime": 80.4186,
+      "train_samples_per_second": 186.524,
+      "train_steps_per_second": 5.844
     }
   ],
   "logging_steps": 500,
-  "max_steps": 282,
-  "num_train_epochs": 3,
+  "max_steps": 470,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 881908425216000.0,
+  "total_flos": 1469847375360000.0,
   "trial_name": null,
   "trial_params": null
 }