End of training

README.md

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

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 63.4,
-    "f1": 73.77262733659492,
-    "train_loss": 1.6219618777011304,
-    "train_runtime": 165.6251,
+    "exact_match": 65.56666666666666,
+    "f1": 75.93060374296303,
+    "train_loss": 1.0810851401471078,
+    "train_runtime": 273.8486,
     "train_samples": 3000,
-    "train_samples_per_second": 54.34,
-    "train_steps_per_second": 0.851
+    "train_samples_per_second": 54.775,
+    "train_steps_per_second": 0.858
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ef665689044f6a1e66fbd5e20e9d9e121c1ce1f355282f6b6da4be33b5006c
+oid sha256:2cab85d2af58594514b7846f01cd583d20620cc5064a5becb223c67bbd1494bc
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a337395dabebd96d8258cb663727389215a2284f6326a9675fc999f71ddeda1a
-size 13841566
+oid sha256:dd50a260908fa943fc19dec08a82fb831491ee5246177596db2225b964265418
+size 13858090

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 63.4,
-    "f1": 73.77262733659492
+    "exact_match": 65.56666666666666,
+    "f1": 75.93060374296303
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 1.6219618777011304,
-    "train_runtime": 165.6251,
+    "epoch": 5.0,
+    "train_loss": 1.0810851401471078,
+    "train_runtime": 273.8486,
     "train_samples": 3000,
-    "train_samples_per_second": 54.34,
-    "train_steps_per_second": 0.851
+    "train_samples_per_second": 54.775,
+    "train_steps_per_second": 0.858
 }

trainer_state.json

@@ -1,28 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 141,
+  "global_step": 235,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 141,
-      "total_flos": 6268772196864000.0,
-      "train_loss": 1.6219618777011304,
-      "train_runtime": 165.6251,
-      "train_samples_per_second": 54.34,
-      "train_steps_per_second": 0.851
+      "epoch": 5.0,
+      "step": 235,
+      "total_flos": 1.044795366144e+16,
+      "train_loss": 1.0810851401471078,
+      "train_runtime": 273.8486,
+      "train_samples_per_second": 54.775,
+      "train_steps_per_second": 0.858
     }
   ],
   "logging_steps": 500,
-  "max_steps": 141,
-  "num_train_epochs": 3,
+  "max_steps": 235,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 6268772196864000.0,
+  "total_flos": 1.044795366144e+16,
   "trial_name": null,
   "trial_params": null
 }