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": 50.0,
+    "epoch": 3.0,
     "eval_samples": 5000,
-    "exact_match": 34.92,
-    "f1": 47.79389306204009,
-    "train_loss": 0.4468785848435323,
-    "train_runtime": 2136.4763,
+    "exact_match": 64.94,
+    "f1": 74.88256878240358,
+    "train_loss": 1.7362415313720703,
+    "train_runtime": 240.9993,
     "train_samples": 5000,
-    "train_samples_per_second": 117.015,
-    "train_steps_per_second": 3.674
+    "train_samples_per_second": 62.241,
+    "train_steps_per_second": 0.498
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95bdff34edcf1b619422dd081958b538f4912da5430f12817e638bacd4ac122c
+oid sha256:79802b2d38e0625bbb14c3acd3fc2717abc0f0b822b17aac8ecb8715343ac2f3
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a994ec4ce88bef3058d6401482c9e7ebc3b7bf5a0f22ee54e47429201c59ebd
-size 23040916
+oid sha256:5435916da9a8e8964bea4d4429a6cdad4f297265ac33dae971608c0d874226de
+size 22481960

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 50.0,
+    "epoch": 3.0,
     "eval_samples": 5000,
-    "exact_match": 34.92,
-    "f1": 47.79389306204009
+    "exact_match": 64.94,
+    "f1": 74.88256878240358
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 50.0,
-    "train_loss": 0.4468785848435323,
-    "train_runtime": 2136.4763,
+    "epoch": 3.0,
+    "train_loss": 1.7362415313720703,
+    "train_runtime": 240.9993,
     "train_samples": 5000,
-    "train_samples_per_second": 117.015,
-    "train_steps_per_second": 3.674
+    "train_samples_per_second": 62.241,
+    "train_steps_per_second": 0.498
 }

trainer_state.json

@@ -1,118 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 50.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 7850,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.18,
-      "learning_rate": 4.681528662420383e-05,
-      "loss": 1.2838,
-      "step": 500
-    },
-    {
-      "epoch": 6.37,
-      "learning_rate": 4.3630573248407646e-05,
-      "loss": 0.2252,
-      "step": 1000
-    },
-    {
-      "epoch": 9.55,
-      "learning_rate": 4.044585987261147e-05,
-      "loss": 0.1119,
-      "step": 1500
-    },
-    {
-      "epoch": 12.74,
-      "learning_rate": 3.7261146496815283e-05,
-      "loss": 0.066,
-      "step": 2000
-    },
-    {
-      "epoch": 15.92,
-      "learning_rate": 3.407643312101911e-05,
-      "loss": 0.0493,
-      "step": 2500
-    },
-    {
-      "epoch": 19.11,
-      "learning_rate": 3.089171974522293e-05,
-      "loss": 0.041,
-      "step": 3000
-    },
-    {
-      "epoch": 22.29,
-      "learning_rate": 2.7707006369426753e-05,
-      "loss": 0.0492,
-      "step": 3500
-    },
-    {
-      "epoch": 25.48,
-      "learning_rate": 2.4522292993630575e-05,
-      "loss": 0.0654,
-      "step": 4000
-    },
-    {
-      "epoch": 28.66,
-      "learning_rate": 2.1337579617834397e-05,
-      "loss": 0.0816,
-      "step": 4500
-    },
-    {
-      "epoch": 31.85,
-      "learning_rate": 1.8152866242038215e-05,
-      "loss": 0.1484,
-      "step": 5000
-    },
-    {
-      "epoch": 35.03,
-      "learning_rate": 1.4968152866242039e-05,
-      "loss": 0.3258,
-      "step": 5500
-    },
-    {
-      "epoch": 38.22,
-      "learning_rate": 1.178343949044586e-05,
-      "loss": 0.6468,
-      "step": 6000
-    },
-    {
-      "epoch": 41.4,
-      "learning_rate": 8.598726114649681e-06,
-      "loss": 0.7716,
-      "step": 6500
-    },
-    {
-      "epoch": 44.59,
-      "learning_rate": 5.414012738853504e-06,
-      "loss": 1.0718,
-      "step": 7000
-    },
-    {
-      "epoch": 47.77,
-      "learning_rate": 2.229299363057325e-06,
-      "loss": 1.2439,
-      "step": 7500
-    },
-    {
-      "epoch": 50.0,
-      "step": 7850,
-      "total_flos": 4.8993141888e+16,
-      "train_loss": 0.4468785848435323,
-      "train_runtime": 2136.4763,
-      "train_samples_per_second": 117.015,
-      "train_steps_per_second": 3.674
+      "epoch": 3.0,
+      "step": 120,
+      "total_flos": 1.044795366144e+16,
+      "train_loss": 1.7362415313720703,
+      "train_runtime": 240.9993,
+      "train_samples_per_second": 62.241,
+      "train_steps_per_second": 0.498
     }
   ],
   "logging_steps": 500,
-  "max_steps": 7850,
-  "num_train_epochs": 50,
+  "max_steps": 120,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 4.8993141888e+16,
+  "total_flos": 1.044795366144e+16,
   "trial_name": null,
   "trial_params": null
 }