End of training

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: distilbert-base-uncased
 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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 100.0,
+    "epoch": 3.0,
     "eval_samples": 3000,
-    "exact_match": 53.96666666666667,
-    "f1": 63.66874539606777,
-    "train_loss": 0.16586235642433167,
-    "train_runtime": 943.4087,
+    "exact_match": 33.666666666666664,
+    "f1": 42.75238381408002,
+    "train_loss": 3.122912900667664,
+    "train_runtime": 39.0267,
     "train_samples": 3000,
-    "train_samples_per_second": 317.996,
-    "train_steps_per_second": 2.544
+    "train_samples_per_second": 230.612,
+    "train_steps_per_second": 3.613
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba64574df4882a77546859e4a99e3473eaed1a5e9b8fdc4081e85b938f82213
+oid sha256:45f7754020a34ee3e18daf22b0eef4c202ad1c6bbccab97a5416ff38944ff169
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef5ef606b8f778e3fae8ae13ac62316f979367d2f73770a3a630a58574e45f7
-size 14170084
+oid sha256:7f448708de085c99e8ea367abba636773c1bc67c1942315670e86358f9966759
+size 14164954

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 100.0,
+    "epoch": 3.0,
     "eval_samples": 3000,
-    "exact_match": 53.96666666666667,
-    "f1": 63.66874539606777
+    "exact_match": 33.666666666666664,
+    "f1": 42.75238381408002
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 100.0,
-    "train_loss": 0.16586235642433167,
-    "train_runtime": 943.4087,
+    "epoch": 3.0,
+    "train_loss": 3.122912900667664,
+    "train_runtime": 39.0267,
     "train_samples": 3000,
-    "train_samples_per_second": 317.996,
-    "train_steps_per_second": 2.544
+    "train_samples_per_second": 230.612,
+    "train_steps_per_second": 3.613
 }

trainer_state.json

@@ -1,52 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 100.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 2400,
+  "global_step": 141,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 20.83,
-      "learning_rate": 3.958333333333333e-05,
-      "loss": 0.7576,
-      "step": 500
-    },
-    {
-      "epoch": 41.67,
-      "learning_rate": 2.916666666666667e-05,
-      "loss": 0.0249,
-      "step": 1000
-    },
-    {
-      "epoch": 62.5,
-      "learning_rate": 1.8750000000000002e-05,
-      "loss": 0.0074,
-      "step": 1500
-    },
-    {
-      "epoch": 83.33,
-      "learning_rate": 8.333333333333334e-06,
-      "loss": 0.0038,
-      "step": 2000
-    },
-    {
-      "epoch": 100.0,
-      "step": 2400,
-      "total_flos": 2.93969475072e+16,
-      "train_loss": 0.16586235642433167,
-      "train_runtime": 943.4087,
-      "train_samples_per_second": 317.996,
-      "train_steps_per_second": 2.544
+      "epoch": 3.0,
+      "step": 141,
+      "total_flos": 881908425216000.0,
+      "train_loss": 3.122912900667664,
+      "train_runtime": 39.0267,
+      "train_samples_per_second": 230.612,
+      "train_steps_per_second": 3.613
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2400,
-  "num_train_epochs": 100,
+  "max_steps": 141,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 2.93969475072e+16,
+  "total_flos": 881908425216000.0,
   "trial_name": null,
   "trial_params": null
 }