End of training

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: albert-base-v2
 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 [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 3000,
-    "exact_match": 68.26666666666667,
-    "f1": 78.38905109442426,
-    "train_loss": 0.7833234786987304,
-    "train_runtime": 167.423,
+    "exact_match": 67.9,
+    "f1": 77.83883701177933,
+    "train_loss": 0.38943036397298175,
+    "train_runtime": 329.0245,
     "train_samples": 3000,
-    "train_samples_per_second": 179.187,
-    "train_steps_per_second": 0.717
+    "train_samples_per_second": 182.357,
+    "train_steps_per_second": 0.729
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda1b4922f51f05acbe00291cb4bc0b89564898901550c66bbc18e87110c9a3e
+oid sha256:b98ffa5349c0eff3e8f76032b48d1417a6ebbe2c3b081c98881f17190725557f
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d11d629d760516118885e652f2fca2608d49adc757b2eb5b17c82a4a1dc0361d
-size 13452701
+oid sha256:17e1412e546dbb567042247344ac270a21072da18a34caaedd52a0f22b7b8e6f
+size 13471437

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 3000,
-    "exact_match": 68.26666666666667,
-    "f1": 78.38905109442426
+    "exact_match": 67.9,
+    "f1": 77.83883701177933
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "train_loss": 0.7833234786987304,
-    "train_runtime": 167.423,
+    "epoch": 20.0,
+    "train_loss": 0.38943036397298175,
+    "train_runtime": 329.0245,
     "train_samples": 3000,
-    "train_samples_per_second": 179.187,
-    "train_steps_per_second": 0.717
+    "train_samples_per_second": 182.357,
+    "train_steps_per_second": 0.729
 }

trainer_state.json

@@ -1,28 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 10.0,
-      "step": 120,
-      "total_flos": 496885570560000.0,
-      "train_loss": 0.7833234786987304,
-      "train_runtime": 167.423,
-      "train_samples_per_second": 179.187,
-      "train_steps_per_second": 0.717
+      "epoch": 20.0,
+      "step": 240,
+      "total_flos": 993771141120000.0,
+      "train_loss": 0.38943036397298175,
+      "train_runtime": 329.0245,
+      "train_samples_per_second": 182.357,
+      "train_steps_per_second": 0.729
     }
   ],
   "logging_steps": 500,
-  "max_steps": 120,
-  "num_train_epochs": 10,
+  "max_steps": 240,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 496885570560000.0,
+  "total_flos": 993771141120000.0,
   "trial_name": null,
   "trial_params": null
 }