End of training

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: bert-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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 5000,
-    "exact_match": 61.92,
-    "f1": 71.73903036462997,
-    "train_loss": 1.3744957796327628,
-    "train_runtime": 129.2666,
+    "exact_match": 63.04,
+    "f1": 72.7227629774702,
+    "train_loss": 0.9167267234462082,
+    "train_runtime": 215.6037,
     "train_samples": 5000,
-    "train_samples_per_second": 116.039,
-    "train_steps_per_second": 3.644
+    "train_samples_per_second": 115.953,
+    "train_steps_per_second": 3.641
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f40dc6c969dc97f99d4457518802ea3fd3849b9127d7763d1d0cab49f0af0fd
+oid sha256:5d553cf4574a4e9be4e65ad1f80904cdc8c8b0ab5936ff145353b91eeaf6fcfb
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea2f532462c760f6c27d21337b3cabd1ecdf0f4bd44aa85cf898e6b8ef4aa21
-size 22776039
+oid sha256:c2d524a01fe642f32844cbfbe43476f8742f66853135d3436c57d1f7f1552982
+size 22748312

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 5000,
-    "exact_match": 61.92,
-    "f1": 71.73903036462997
+    "exact_match": 63.04,
+    "f1": 72.7227629774702
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 1.3744957796327628,
-    "train_runtime": 129.2666,
+    "epoch": 5.0,
+    "train_loss": 0.9167267234462082,
+    "train_runtime": 215.6037,
     "train_samples": 5000,
-    "train_samples_per_second": 116.039,
-    "train_steps_per_second": 3.644
+    "train_samples_per_second": 115.953,
+    "train_steps_per_second": 3.641
 }

trainer_state.json

@@ -1,28 +1,34 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 471,
+  "global_step": 785,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 471,
-      "total_flos": 2939588513280000.0,
-      "train_loss": 1.3744957796327628,
-      "train_runtime": 129.2666,
-      "train_samples_per_second": 116.039,
-      "train_steps_per_second": 3.644
+      "epoch": 3.18,
+      "learning_rate": 1.8152866242038215e-05,
+      "loss": 1.2876,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "step": 785,
+      "total_flos": 4899314188800000.0,
+      "train_loss": 0.9167267234462082,
+      "train_runtime": 215.6037,
+      "train_samples_per_second": 115.953,
+      "train_steps_per_second": 3.641
     }
   ],
   "logging_steps": 500,
-  "max_steps": 471,
-  "num_train_epochs": 3,
+  "max_steps": 785,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 2939588513280000.0,
+  "total_flos": 4899314188800000.0,
   "trial_name": null,
   "trial_params": null
 }