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": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 64.2,
-    "f1": 74.31179260848076,
-    "train_loss": 2.188524670071072,
-    "train_runtime": 54.4098,
+    "exact_match": 68.96666666666667,
+    "f1": 78.38604997749991,
+    "train_loss": 1.5239224751790366,
+    "train_runtime": 89.6311,
     "train_samples": 3000,
-    "train_samples_per_second": 165.411,
-    "train_steps_per_second": 0.662
+    "train_samples_per_second": 167.353,
+    "train_steps_per_second": 0.669
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8885ffd4ecc33bd503c0f8a9a0020a0f7bade75a2380de2544b287f02ce1cc7
+oid sha256:91e030a2325775960460cdef2319fbb5d53cf540343531f96079b47bb5b6da88
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b82a97ed87fdc47a92d9f9cc868907de41476cd54d137c4eec77a44457560143
-size 13662949
+oid sha256:da1f53009f4ec37156f905192aa448403cee30dd54ca95782e25ad495172a541
+size 13563366

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 64.2,
-    "f1": 74.31179260848076
+    "exact_match": 68.96666666666667,
+    "f1": 78.38604997749991
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 2.188524670071072,
-    "train_runtime": 54.4098,
+    "epoch": 5.0,
+    "train_loss": 1.5239224751790366,
+    "train_runtime": 89.6311,
     "train_samples": 3000,
-    "train_samples_per_second": 165.411,
-    "train_steps_per_second": 0.662
+    "train_samples_per_second": 167.353,
+    "train_steps_per_second": 0.669
 }

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": 36,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 36,
-      "total_flos": 149065671168000.0,
-      "train_loss": 2.188524670071072,
-      "train_runtime": 54.4098,
-      "train_samples_per_second": 165.411,
-      "train_steps_per_second": 0.662
+      "epoch": 5.0,
+      "step": 60,
+      "total_flos": 248442785280000.0,
+      "train_loss": 1.5239224751790366,
+      "train_runtime": 89.6311,
+      "train_samples_per_second": 167.353,
+      "train_steps_per_second": 0.669
     }
   ],
   "logging_steps": 500,
-  "max_steps": 36,
-  "num_train_epochs": 3,
+  "max_steps": 60,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 149065671168000.0,
+  "total_flos": 248442785280000.0,
   "trial_name": null,
   "trial_params": null
 }