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": 14.3,
-    "f1": 20.29190806017442,
-    "train_loss": 3.7479913499620228,
-    "train_runtime": 32.8699,
+    "exact_match": 39.3,
+    "f1": 48.66561298612545,
+    "train_loss": 2.9127347310384115,
+    "train_runtime": 51.0676,
     "train_samples": 3000,
-    "train_samples_per_second": 273.807,
-    "train_steps_per_second": 2.19
+    "train_samples_per_second": 293.728,
+    "train_steps_per_second": 2.35
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88de45f5b7bcc3bc1ff4914575da066c3cc9a24174482b8e7c59ca6eab05e889
+oid sha256:8c7da3f47648138a19acd72a86976cdabedff9aa63dc1b5961e321ec9376d10b
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7771c77c6579ae9e2557400522441f7a14bc92ec10b0f8d2c6240137f41dcbbc
-size 14355145
+oid sha256:eddec2fcc17848d4a430663ff8cf09815b9acabdb7a916954dafedbf74ed72d7
+size 14154496

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 14.3,
-    "f1": 20.29190806017442
+    "exact_match": 39.3,
+    "f1": 48.66561298612545
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 3.7479913499620228,
-    "train_runtime": 32.8699,
+    "epoch": 5.0,
+    "train_loss": 2.9127347310384115,
+    "train_runtime": 51.0676,
     "train_samples": 3000,
-    "train_samples_per_second": 273.807,
-    "train_steps_per_second": 2.19
+    "train_samples_per_second": 293.728,
+    "train_steps_per_second": 2.35
 }

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": 72,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 72,
-      "total_flos": 881908425216000.0,
-      "train_loss": 3.7479913499620228,
-      "train_runtime": 32.8699,
-      "train_samples_per_second": 273.807,
-      "train_steps_per_second": 2.19
+      "epoch": 5.0,
+      "step": 120,
+      "total_flos": 1469847375360000.0,
+      "train_loss": 2.9127347310384115,
+      "train_runtime": 51.0676,
+      "train_samples_per_second": 293.728,
+      "train_steps_per_second": 2.35
     }
   ],
   "logging_steps": 500,
-  "max_steps": 72,
-  "num_train_epochs": 3,
+  "max_steps": 120,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 881908425216000.0,
+  "total_flos": 1469847375360000.0,
   "trial_name": null,
   "trial_params": null
 }