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": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 70.03333333333333,
-    "f1": 79.65547885978339,
-    "train_loss": 1.0535087585449219,
-    "train_runtime": 92.4038,
+    "exact_match": 68.46666666666667,
+    "f1": 78.53700891077818,
+    "train_loss": 0.5349376042683919,
+    "train_runtime": 176.0119,
     "train_samples": 3000,
-    "train_samples_per_second": 162.331,
-    "train_steps_per_second": 1.299
+    "train_samples_per_second": 170.443,
+    "train_steps_per_second": 1.364
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8929cf9f9d82f7d221291393f1c9c8641dcb27daeb9a15a403212f483cbe21e6
+oid sha256:055187e21a4cb3904c0aeead21d48e6380a9ba61af8132f958ebb52f4a3db65d
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41181dbcaf0b37cc8629086de6a44b4489822079041548a40e3088d91f39ea48
-size 13452643
+oid sha256:920ba717dada51390a042a763d638bac35ccb2dbea1ce86f039c9e47259d2d08
+size 13502248

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 3000,
-    "exact_match": 70.03333333333333,
-    "f1": 79.65547885978339
+    "exact_match": 68.46666666666667,
+    "f1": 78.53700891077818
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 1.0535087585449219,
-    "train_runtime": 92.4038,
+    "epoch": 10.0,
+    "train_loss": 0.5349376042683919,
+    "train_runtime": 176.0119,
     "train_samples": 3000,
-    "train_samples_per_second": 162.331,
-    "train_steps_per_second": 1.299
+    "train_samples_per_second": 170.443,
+    "train_steps_per_second": 1.364
 }

trainer_state.json

@@ -1,28 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 10.0,
   "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": 5.0,
-      "step": 120,
-      "total_flos": 248442785280000.0,
-      "train_loss": 1.0535087585449219,
-      "train_runtime": 92.4038,
-      "train_samples_per_second": 162.331,
-      "train_steps_per_second": 1.299
+      "epoch": 10.0,
+      "step": 240,
+      "total_flos": 496885570560000.0,
+      "train_loss": 0.5349376042683919,
+      "train_runtime": 176.0119,
+      "train_samples_per_second": 170.443,
+      "train_steps_per_second": 1.364
     }
   ],
   "logging_steps": 500,
-  "max_steps": 120,
-  "num_train_epochs": 5,
+  "max_steps": 240,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 248442785280000.0,
+  "total_flos": 496885570560000.0,
   "trial_name": null,
   "trial_params": null
 }