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": 68.83333333333333,
-    "f1": 79.17591999568613,
-    "train_loss": 0.3617458444960574,
-    "train_runtime": 216.5737,
+    "exact_match": 67.6,
+    "f1": 77.98001410061255,
+    "train_loss": 0.20614639479429164,
+    "train_runtime": 429.6446,
     "train_samples": 3000,
-    "train_samples_per_second": 138.521,
-    "train_steps_per_second": 4.34
+    "train_samples_per_second": 139.65,
+    "train_steps_per_second": 4.376
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10a59deee26bc53a4b1bfbcd4c175f77919dcdce208eedefe41f5a424d19b28
+oid sha256:4b3207b354104ae2aa7322b0e77c14a354007e7a43bd391df0c632e053c8bfd7
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc323de3db5a627f1b03e8ebb643c4237fadecda10144a1f11f1fc0cccd6f57
-size 13413491
+oid sha256:ed67c57fcb4a38c9f758f5a71a7447f48c31bb3dd85f06aff1a867da2121d29e
+size 13489570

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 3000,
-    "exact_match": 68.83333333333333,
-    "f1": 79.17591999568613
+    "exact_match": 67.6,
+    "f1": 77.98001410061255
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "train_loss": 0.3617458444960574,
-    "train_runtime": 216.5737,
+    "epoch": 20.0,
+    "train_loss": 0.20614639479429164,
+    "train_runtime": 429.6446,
     "train_samples": 3000,
-    "train_samples_per_second": 138.521,
-    "train_steps_per_second": 4.34
+    "train_samples_per_second": 139.65,
+    "train_steps_per_second": 4.376
 }

trainer_state.json

@@ -1,34 +1,46 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 940,
+  "global_step": 1880,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 5.32,
-      "learning_rate": 2.340425531914894e-05,
-      "loss": 0.6488,
+      "learning_rate": 3.670212765957447e-05,
+      "loss": 0.6754,
       "step": 500
     },
     {
-      "epoch": 10.0,
-      "step": 940,
-      "total_flos": 496885570560000.0,
-      "train_loss": 0.3617458444960574,
-      "train_runtime": 216.5737,
-      "train_samples_per_second": 138.521,
-      "train_steps_per_second": 4.34
+      "epoch": 10.64,
+      "learning_rate": 2.340425531914894e-05,
+      "loss": 0.0842,
+      "step": 1000
+    },
+    {
+      "epoch": 15.96,
+      "learning_rate": 1.0106382978723404e-05,
+      "loss": 0.0137,
+      "step": 1500
+    },
+    {
+      "epoch": 20.0,
+      "step": 1880,
+      "total_flos": 993771141120000.0,
+      "train_loss": 0.20614639479429164,
+      "train_runtime": 429.6446,
+      "train_samples_per_second": 139.65,
+      "train_steps_per_second": 4.376
     }
   ],
   "logging_steps": 500,
-  "max_steps": 940,
-  "num_train_epochs": 10,
+  "max_steps": 1880,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 496885570560000.0,
+  "total_flos": 993771141120000.0,
   "trial_name": null,
   "trial_params": null
 }