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": 20.0,
+    "epoch": 3.0,
     "eval_samples": 3000,
-    "exact_match": 61.733333333333334,
-    "f1": 71.7971731355904,
-    "train_loss": 0.3228585179815901,
-    "train_runtime": 543.0246,
+    "exact_match": 9.333333333333334,
+    "f1": 14.467623210820486,
+    "train_loss": 4.351121690538195,
+    "train_runtime": 29.6764,
     "train_samples": 3000,
-    "train_samples_per_second": 110.492,
-    "train_steps_per_second": 3.462
+    "train_samples_per_second": 303.272,
+    "train_steps_per_second": 1.213
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f50dde618352b5ed3d003e54055fbe33a5b7907552c5b322cada60b9dbf2cd59
+oid sha256:51c8883aff3f1da4c3347b9cab131bc71b9aff4c0806b779b6279cf0f12b1591
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:622e6d7361d204c5d517c04211e9ff7bf526064d115a46f9132880a4bfc3c5c2
-size 14134944
+oid sha256:712e1b60dc69e369d446b9cab4e9b3a4d8e1674aee0ebe8bbfde1fc436e15c52
+size 14416993

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 20.0,
+    "epoch": 3.0,
     "eval_samples": 3000,
-    "exact_match": 61.733333333333334,
-    "f1": 71.7971731355904
+    "exact_match": 9.333333333333334,
+    "f1": 14.467623210820486
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 20.0,
-    "train_loss": 0.3228585179815901,
-    "train_runtime": 543.0246,
+    "epoch": 3.0,
+    "train_loss": 4.351121690538195,
+    "train_runtime": 29.6764,
     "train_samples": 3000,
-    "train_samples_per_second": 110.492,
-    "train_steps_per_second": 3.462
+    "train_samples_per_second": 303.272,
+    "train_steps_per_second": 1.213
 }

trainer_state.json

@@ -1,46 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1880,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 5.32,
-      "learning_rate": 3.670212765957447e-05,
-      "loss": 1.0779,
-      "step": 500
-    },
-    {
-      "epoch": 10.64,
-      "learning_rate": 2.340425531914894e-05,
-      "loss": 0.0968,
-      "step": 1000
-    },
-    {
-      "epoch": 15.96,
-      "learning_rate": 1.0106382978723404e-05,
-      "loss": 0.0322,
-      "step": 1500
-    },
-    {
-      "epoch": 20.0,
-      "step": 1880,
-      "total_flos": 1.175835405312e+16,
-      "train_loss": 0.3228585179815901,
-      "train_runtime": 543.0246,
-      "train_samples_per_second": 110.492,
-      "train_steps_per_second": 3.462
+      "epoch": 3.0,
+      "step": 36,
+      "total_flos": 881908425216000.0,
+      "train_loss": 4.351121690538195,
+      "train_runtime": 29.6764,
+      "train_samples_per_second": 303.272,
+      "train_steps_per_second": 1.213
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1880,
-  "num_train_epochs": 20,
+  "max_steps": 36,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 1.175835405312e+16,
+  "total_flos": 881908425216000.0,
   "trial_name": null,
   "trial_params": null
 }