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": 10.0,
+    "epoch": 20.0,
     "eval_samples": 3000,
-    "exact_match": 44.06666666666667,
-    "f1": 53.81229298968328,
-    "train_loss": 2.510331217447917,
-    "train_runtime": 86.3861,
+    "exact_match": 48.666666666666664,
+    "f1": 58.93108771704041,
+    "train_loss": 1.3183675130208334,
+    "train_runtime": 166.1295,
     "train_samples": 3000,
-    "train_samples_per_second": 347.278,
-    "train_steps_per_second": 1.389
+    "train_samples_per_second": 361.164,
+    "train_steps_per_second": 1.445
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf9af8252df187228c7d36fb5985d48984bc90bea7a9d665b09de0524c7dae30
+oid sha256:35f7d7c0517615ca36986a4c68cda841df658a7b906c1ba8cfce1ba7d5ea0494
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5180325ed7d80019a21104f00ef5115fe6ebb712cc83921d2977d16c7cd69eba
-size 14076237
+oid sha256:bc5cdbd56896604fbaa911e47f92c0a83ce8a1e7a99408858344ab17cccceaef
+size 14136346

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 3000,
-    "exact_match": 44.06666666666667,
-    "f1": 53.81229298968328
+    "exact_match": 48.666666666666664,
+    "f1": 58.93108771704041
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "train_loss": 2.510331217447917,
-    "train_runtime": 86.3861,
+    "epoch": 20.0,
+    "train_loss": 1.3183675130208334,
+    "train_runtime": 166.1295,
     "train_samples": 3000,
-    "train_samples_per_second": 347.278,
-    "train_steps_per_second": 1.389
+    "train_samples_per_second": 361.164,
+    "train_steps_per_second": 1.445
 }

trainer_state.json

@@ -1,28 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 10.0,
-      "step": 120,
-      "total_flos": 2939694750720000.0,
-      "train_loss": 2.510331217447917,
-      "train_runtime": 86.3861,
-      "train_samples_per_second": 347.278,
-      "train_steps_per_second": 1.389
+      "epoch": 20.0,
+      "step": 240,
+      "total_flos": 5879389501440000.0,
+      "train_loss": 1.3183675130208334,
+      "train_runtime": 166.1295,
+      "train_samples_per_second": 361.164,
+      "train_steps_per_second": 1.445
     }
   ],
   "logging_steps": 500,
-  "max_steps": 120,
-  "num_train_epochs": 10,
+  "max_steps": 240,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 2939694750720000.0,
+  "total_flos": 5879389501440000.0,
   "trial_name": null,
   "trial_params": null
 }