End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

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,
-    "eval_samples": 2000,
-    "exact_match": 9.55,
-    "f1": 15.048311041178366,
-    "train_loss": 4.351121690538195,
-    "train_runtime": 30.007,
-    "train_samples": 3000,
-    "train_samples_per_second": 299.93,
-    "train_steps_per_second": 1.2
+    "eval_samples": 10784,
+    "exact_match": 75.1844843897824,
+    "f1": 84.01198623808155,
+    "train_loss": 1.3245489601914364,
+    "train_runtime": 732.568,
+    "train_samples": 88524,
+    "train_samples_per_second": 362.522,
+    "train_steps_per_second": 1.417
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:445c7688368a47a9373af34c72754c6baa9f210952dbbc111ee1b17a27ea1af8
+oid sha256:8f1a8815b4a31b0bf0b9ec7030d0f7f22cb8610e9e234f8183c714bfac7f798e
 size 5652

eval_results.json

@@ -1,6 +1,6 @@
 {
     "epoch": 3.0,
-    "eval_samples": 2000,
-    "exact_match": 9.55,
-    "f1": 15.048311041178366
+    "eval_samples": 10784,
+    "exact_match": 75.1844843897824,
+    "f1": 84.01198623808155
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 4.351121690538195,
-    "train_runtime": 30.007,
-    "train_samples": 3000,
-    "train_samples_per_second": 299.93,
-    "train_steps_per_second": 1.2
+    "train_loss": 1.3245489601914364,
+    "train_runtime": 732.568,
+    "train_samples": 88524,
+    "train_samples_per_second": 362.522,
+    "train_steps_per_second": 1.417
 }

trainer_state.json

@@ -3,26 +3,38 @@
   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 36,
+  "global_step": 1038,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.5915221579961463e-05,
+      "loss": 1.6863,
+      "step": 500
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.8304431599229288e-06,
+      "loss": 0.9928,
+      "step": 1000
+    },
     {
       "epoch": 3.0,
-      "step": 36,
-      "total_flos": 881908425216000.0,
-      "train_loss": 4.351121690538195,
-      "train_runtime": 30.007,
-      "train_samples_per_second": 299.93,
-      "train_steps_per_second": 1.2
+      "step": 1038,
+      "total_flos": 2.602335381127373e+16,
+      "train_loss": 1.3245489601914364,
+      "train_runtime": 732.568,
+      "train_samples_per_second": 362.522,
+      "train_steps_per_second": 1.417
     }
   ],
   "logging_steps": 500,
-  "max_steps": 36,
+  "max_steps": 1038,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 881908425216000.0,
+  "total_flos": 2.602335381127373e+16,
   "trial_name": null,
   "trial_params": null
 }