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": 5000,
-    "exact_match": 55.56,
-    "f1": 65.99798795371326,
-    "train_loss": 0.8420210005361822,
-    "train_runtime": 308.0717,
+    "exact_match": 57.48,
+    "f1": 67.27900000737974,
+    "train_loss": 0.42836274300949484,
+    "train_runtime": 610.7019,
     "train_samples": 5000,
-    "train_samples_per_second": 162.3,
-    "train_steps_per_second": 2.564
+    "train_samples_per_second": 163.746,
+    "train_steps_per_second": 2.587
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0882b92f28d2d31a25520efc044eec984b7d9186d76ac0b65b2d0b7c8d2aeca4
+oid sha256:244e22ac7033fa836c3458d4f82cbb001bff5a49ff85c86a4ccbab550a1e12ed
 size 5588

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3683846b046cd910c858ffd8d44c05d145630f4a56c1c01c92c0d4bdc4a64b5
-size 23054658
+oid sha256:37621a1b662c8e9d8baa5d910705b9709910050bc95850e3e81f1944ee468d83
+size 23107507

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 5000,
-    "exact_match": 55.56,
-    "f1": 65.99798795371326
+    "exact_match": 57.48,
+    "f1": 67.27900000737974
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "train_loss": 0.8420210005361822,
-    "train_runtime": 308.0717,
+    "epoch": 20.0,
+    "train_loss": 0.42836274300949484,
+    "train_runtime": 610.7019,
     "train_samples": 5000,
-    "train_samples_per_second": 162.3,
-    "train_steps_per_second": 2.564
+    "train_samples_per_second": 163.746,
+    "train_steps_per_second": 2.587
 }

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": 790,
+  "global_step": 1580,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 6.33,
-      "learning_rate": 1.8354430379746836e-05,
-      "loss": 1.2199,
+      "learning_rate": 3.4177215189873416e-05,
+      "loss": 1.1909,
       "step": 500
     },
     {
-      "epoch": 10.0,
-      "step": 790,
-      "total_flos": 4899491251200000.0,
-      "train_loss": 0.8420210005361822,
-      "train_runtime": 308.0717,
-      "train_samples_per_second": 162.3,
-      "train_steps_per_second": 2.564
+      "epoch": 12.66,
+      "learning_rate": 1.8354430379746836e-05,
+      "loss": 0.1219,
+      "step": 1000
+    },
+    {
+      "epoch": 18.99,
+      "learning_rate": 2.531645569620253e-06,
+      "loss": 0.0375,
+      "step": 1500
+    },
+    {
+      "epoch": 20.0,
+      "step": 1580,
+      "total_flos": 9798982502400000.0,
+      "train_loss": 0.42836274300949484,
+      "train_runtime": 610.7019,
+      "train_samples_per_second": 163.746,
+      "train_steps_per_second": 2.587
     }
   ],
   "logging_steps": 500,
-  "max_steps": 790,
-  "num_train_epochs": 10,
+  "max_steps": 1580,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 4899491251200000.0,
+  "total_flos": 9798982502400000.0,
   "trial_name": null,
   "trial_params": null
 }