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": 53.3,
-    "f1": 63.04894189678107,
-    "train_loss": 0.24828063900272052,
-    "train_runtime": 821.3881,
+    "exact_match": 14.3,
+    "f1": 20.29190806017442,
+    "train_loss": 3.7479913499620228,
+    "train_runtime": 31.8766,
     "train_samples": 3000,
-    "train_samples_per_second": 365.235,
-    "train_steps_per_second": 1.461
+    "train_samples_per_second": 282.339,
+    "train_steps_per_second": 2.259
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41494cb31750bbcc5327a27ef9dfb1a2d79e849f13442ab514c631b99c26b799
+oid sha256:4110e6d91b4190181ef6936a2db1c1499ffbbd54e0e2828edaab63bae609d818
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bfa2f94dbfa1f1809eda0f1549268165ae69d4d98f3afddf526747a4e1e7ebf
-size 14255468
+oid sha256:7771c77c6579ae9e2557400522441f7a14bc92ec10b0f8d2c6240137f41dcbbc
+size 14355145

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 100.0,
+    "epoch": 3.0,
     "eval_samples": 3000,
-    "exact_match": 53.3,
-    "f1": 63.04894189678107
+    "exact_match": 14.3,
+    "f1": 20.29190806017442
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 100.0,
-    "train_loss": 0.24828063900272052,
-    "train_runtime": 821.3881,
+    "epoch": 3.0,
+    "train_loss": 3.7479913499620228,
+    "train_runtime": 31.8766,
     "train_samples": 3000,
-    "train_samples_per_second": 365.235,
-    "train_steps_per_second": 1.461
+    "train_samples_per_second": 282.339,
+    "train_steps_per_second": 2.259
 }

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": 0.5848,
-      "step": 500
-    },
-    {
-      "epoch": 83.33,
-      "learning_rate": 8.333333333333334e-06,
-      "loss": 0.0094,
-      "step": 1000
-    },
-    {
-      "epoch": 100.0,
-      "step": 1200,
-      "total_flos": 2.93969475072e+16,
-      "train_loss": 0.24828063900272052,
-      "train_runtime": 821.3881,
-      "train_samples_per_second": 365.235,
-      "train_steps_per_second": 1.461
+      "epoch": 3.0,
+      "step": 72,
+      "total_flos": 881908425216000.0,
+      "train_loss": 3.7479913499620228,
+      "train_runtime": 31.8766,
+      "train_samples_per_second": 282.339,
+      "train_steps_per_second": 2.259
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1200,
-  "num_train_epochs": 100,
+  "max_steps": 72,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 2.93969475072e+16,
+  "total_flos": 881908425216000.0,
   "trial_name": null,
   "trial_params": null
 }