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": 70.7,
-    "f1": 80.77159516855934,
-    "train_loss": 0.9721946986854499,
-    "train_runtime": 70.3514,
+    "exact_match": 71.46666666666667,
+    "f1": 80.70165088524692,
+    "train_loss": 0.6540570847531583,
+    "train_runtime": 109.2106,
     "train_samples": 3000,
-    "train_samples_per_second": 127.929,
-    "train_steps_per_second": 4.008
+    "train_samples_per_second": 137.349,
+    "train_steps_per_second": 4.304
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e86867e39d1269ba816e624e5cf804173942ad3422e6eeb5d1e35f9d2971cc98
+oid sha256:30bf497c8f1d3b0b97d8bda8f659df3c60f82e6b1c22399160ef4e9cb0ff45f3
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe6c2d52b6e438e6a53b1ab025c2334b4e5bf4ad43f6b9245331eecce06dcbd
-size 13436925
+oid sha256:c80fa9b6a90ff70ce0275553d0d7596167d0287fdde2ff3fa1eb71c10daaf630
+size 13413679

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 3000,
-    "exact_match": 70.7,
-    "f1": 80.77159516855934
+    "exact_match": 71.46666666666667,
+    "f1": 80.70165088524692
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 0.9721946986854499,
-    "train_runtime": 70.3514,
+    "epoch": 5.0,
+    "train_loss": 0.6540570847531583,
+    "train_runtime": 109.2106,
     "train_samples": 3000,
-    "train_samples_per_second": 127.929,
-    "train_steps_per_second": 4.008
+    "train_samples_per_second": 137.349,
+    "train_steps_per_second": 4.304
 }

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": 282,
+  "global_step": 470,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 282,
-      "total_flos": 149065671168000.0,
-      "train_loss": 0.9721946986854499,
-      "train_runtime": 70.3514,
-      "train_samples_per_second": 127.929,
-      "train_steps_per_second": 4.008
+      "epoch": 5.0,
+      "step": 470,
+      "total_flos": 248442785280000.0,
+      "train_loss": 0.6540570847531583,
+      "train_runtime": 109.2106,
+      "train_samples_per_second": 137.349,
+      "train_steps_per_second": 4.304
     }
   ],
   "logging_steps": 500,
-  "max_steps": 282,
-  "num_train_epochs": 3,
+  "max_steps": 470,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 149065671168000.0,
+  "total_flos": 248442785280000.0,
   "trial_name": null,
   "trial_params": null
 }