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": 52.43333333333333,
-    "f1": 62.43821967363908,
-    "train_loss": 1.1992795254321809,
-    "train_runtime": 116.9912,
+    "exact_match": 54.13333333333333,
+    "f1": 63.901880489999314,
+    "train_loss": 0.6003903328104222,
+    "train_runtime": 231.9146,
     "train_samples": 3000,
-    "train_samples_per_second": 256.43,
-    "train_steps_per_second": 4.017
+    "train_samples_per_second": 258.716,
+    "train_steps_per_second": 4.053
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f78182474f51de80240d435d6a112bde46d6c8477bf33e28336fe2ebaedfc2
+oid sha256:4810ed4eec1e4906c5b606e39d54a5381214a493049ba6b209c390be9b8ecdaf
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1cf87cfcce3fe5ce2dee0b3cbb0727c8f296e20f056e6cef76addd71660da8d
-size 14109976
+oid sha256:78cac92342ee14ea7282a17a5a815c667aaed4928f18779734bc9f209104e377
+size 14113500

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 3000,
-    "exact_match": 52.43333333333333,
-    "f1": 62.43821967363908
+    "exact_match": 54.13333333333333,
+    "f1": 63.901880489999314
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "train_loss": 1.1992795254321809,
-    "train_runtime": 116.9912,
+    "epoch": 20.0,
+    "train_loss": 0.6003903328104222,
+    "train_runtime": 231.9146,
     "train_samples": 3000,
-    "train_samples_per_second": 256.43,
-    "train_steps_per_second": 4.017
+    "train_samples_per_second": 258.716,
+    "train_steps_per_second": 4.053
 }

trainer_state.json

@@ -1,28 +1,34 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 470,
+  "global_step": 940,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 10.0,
-      "step": 470,
-      "total_flos": 2939694750720000.0,
-      "train_loss": 1.1992795254321809,
-      "train_runtime": 116.9912,
-      "train_samples_per_second": 256.43,
-      "train_steps_per_second": 4.017
+      "epoch": 10.64,
+      "learning_rate": 2.340425531914894e-05,
+      "loss": 1.0721,
+      "step": 500
+    },
+    {
+      "epoch": 20.0,
+      "step": 940,
+      "total_flos": 5879389501440000.0,
+      "train_loss": 0.6003903328104222,
+      "train_runtime": 231.9146,
+      "train_samples_per_second": 258.716,
+      "train_steps_per_second": 4.053
     }
   ],
   "logging_steps": 500,
-  "max_steps": 470,
-  "num_train_epochs": 10,
+  "max_steps": 940,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 2939694750720000.0,
+  "total_flos": 5879389501440000.0,
   "trial_name": null,
   "trial_params": null
 }