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": 100.0,
+    "epoch": 3.0,
     "eval_samples": 3000,
-    "exact_match": 69.0,
-    "f1": 78.89666079356367,
-    "train_loss": 0.08420621717969577,
-    "train_runtime": 1629.8221,
+    "exact_match": 68.56666666666666,
+    "f1": 78.31093544823585,
+    "train_loss": 1.5496142705281575,
+    "train_runtime": 55.38,
     "train_samples": 3000,
-    "train_samples_per_second": 184.069,
-    "train_steps_per_second": 0.736
+    "train_samples_per_second": 162.513,
+    "train_steps_per_second": 1.3
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4623367a901eddc57d675a066a6f9ad4d0713b876fdaba747336b4e82e84dbb3
+oid sha256:27e96aa596383a62b53fd4c3ceeb13e8f24294281671bceac6b94fc330804d03
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf66bf79f75e61369aa6297120c187c19df5dd5a9c8f553d34cbd37d7d679be
-size 13453266
+oid sha256:b806aa658647d9bf8f5b76bb7f27e6f1a6fd65b396c9fd2187599b49a899dbe1
+size 13531727

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 100.0,
+    "epoch": 3.0,
     "eval_samples": 3000,
-    "exact_match": 69.0,
-    "f1": 78.89666079356367
+    "exact_match": 68.56666666666666,
+    "f1": 78.31093544823585
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 100.0,
-    "train_loss": 0.08420621717969577,
-    "train_runtime": 1629.8221,
+    "epoch": 3.0,
+    "train_loss": 1.5496142705281575,
+    "train_runtime": 55.38,
     "train_samples": 3000,
-    "train_samples_per_second": 184.069,
-    "train_steps_per_second": 0.736
+    "train_samples_per_second": 162.513,
+    "train_steps_per_second": 1.3
 }

trainer_state.json

@@ -1,40 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 100.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1200,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 41.67,
-      "learning_rate": 2.916666666666667e-05,
-      "loss": 0.1992,
-      "step": 500
-    },
-    {
-      "epoch": 83.33,
-      "learning_rate": 8.333333333333334e-06,
-      "loss": 0.0023,
-      "step": 1000
-    },
-    {
-      "epoch": 100.0,
-      "step": 1200,
-      "total_flos": 4968855705600000.0,
-      "train_loss": 0.08420621717969577,
-      "train_runtime": 1629.8221,
-      "train_samples_per_second": 184.069,
-      "train_steps_per_second": 0.736
+      "epoch": 3.0,
+      "step": 72,
+      "total_flos": 149065671168000.0,
+      "train_loss": 1.5496142705281575,
+      "train_runtime": 55.38,
+      "train_samples_per_second": 162.513,
+      "train_steps_per_second": 1.3
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1200,
-  "num_train_epochs": 100,
+  "max_steps": 72,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 4968855705600000.0,
+  "total_flos": 149065671168000.0,
   "trial_name": null,
   "trial_params": null
 }