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": 54.166666666666664,
-    "f1": 64.12697846015462,
-    "train_loss": 0.8370751482375125,
-    "train_runtime": 154.8812,
+    "exact_match": 56.46666666666667,
+    "f1": 65.69798974381443,
+    "train_loss": 0.4279018166217398,
+    "train_runtime": 303.9253,
     "train_samples": 3000,
-    "train_samples_per_second": 193.697,
-    "train_steps_per_second": 6.069
+    "train_samples_per_second": 197.417,
+    "train_steps_per_second": 6.186
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce5d39599c6b93caec2237a1e4db6a87cd7fcbc0323e0f22b5652501eea9de8a
+oid sha256:b05c8907dfc280bd1c1e1e817267322e98030804d0488d1fdd3fb33e2b44b7fe
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5ed5e61243535ff4955375d06ea43a2e05949b5ca7358091b7242a30a8570e2
-size 14110407
+oid sha256:cd412c736e41e466d98fd5b5e4084e176a1136bfb43b240de8217cee79037206
+size 14228580

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 3000,
-    "exact_match": 54.166666666666664,
-    "f1": 64.12697846015462
+    "exact_match": 56.46666666666667,
+    "f1": 65.69798974381443
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "train_loss": 0.8370751482375125,
-    "train_runtime": 154.8812,
+    "epoch": 20.0,
+    "train_loss": 0.4279018166217398,
+    "train_runtime": 303.9253,
     "train_samples": 3000,
-    "train_samples_per_second": 193.697,
-    "train_steps_per_second": 6.069
+    "train_samples_per_second": 197.417,
+    "train_steps_per_second": 6.186
 }

trainer_state.json

@@ -1,34 +1,46 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 940,
+  "global_step": 1880,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 5.32,
-      "learning_rate": 2.340425531914894e-05,
-      "loss": 1.4252,
+      "learning_rate": 3.670212765957447e-05,
+      "loss": 1.4055,
       "step": 500
     },
     {
-      "epoch": 10.0,
-      "step": 940,
-      "total_flos": 2939694750720000.0,
-      "train_loss": 0.8370751482375125,
-      "train_runtime": 154.8812,
-      "train_samples_per_second": 193.697,
-      "train_steps_per_second": 6.069
+      "epoch": 10.64,
+      "learning_rate": 2.340425531914894e-05,
+      "loss": 0.1477,
+      "step": 1000
+    },
+    {
+      "epoch": 15.96,
+      "learning_rate": 1.0106382978723404e-05,
+      "loss": 0.0432,
+      "step": 1500
+    },
+    {
+      "epoch": 20.0,
+      "step": 1880,
+      "total_flos": 5879389501440000.0,
+      "train_loss": 0.4279018166217398,
+      "train_runtime": 303.9253,
+      "train_samples_per_second": 197.417,
+      "train_steps_per_second": 6.186
     }
   ],
   "logging_steps": 500,
-  "max_steps": 940,
-  "num_train_epochs": 10,
+  "max_steps": 1880,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 2939694750720000.0,
+  "total_flos": 5879389501440000.0,
   "trial_name": null,
   "trial_params": null
 }