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": 20.0,
+    "epoch": 50.0,
     "eval_samples": 3000,
-    "exact_match": 48.666666666666664,
-    "f1": 58.93108771704041,
-    "train_loss": 1.3183675130208334,
-    "train_runtime": 168.5498,
+    "exact_match": 51.56666666666667,
+    "f1": 61.20209643312287,
+    "train_loss": 0.5075189057985942,
+    "train_runtime": 413.5077,
     "train_samples": 3000,
-    "train_samples_per_second": 355.978,
-    "train_steps_per_second": 1.424
+    "train_samples_per_second": 362.75,
+    "train_steps_per_second": 1.451
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a902c5f029aee6f99c6a6450a5cfef382b9c5f42f3b3b214eeb9c912250ca911
+oid sha256:9f73842d78186e4627e15b8da431dc54bf9e092314127c8477eec236b8697cb6
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc5cdbd56896604fbaa911e47f92c0a83ce8a1e7a99408858344ab17cccceaef
-size 14136346
+oid sha256:2761a80eb4ea611c586d8610ae8ce9bd336d0306736189cb8cd0bb4c64dc8961
+size 14227253

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 20.0,
+    "epoch": 50.0,
     "eval_samples": 3000,
-    "exact_match": 48.666666666666664,
-    "f1": 58.93108771704041
+    "exact_match": 51.56666666666667,
+    "f1": 61.20209643312287
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 20.0,
-    "train_loss": 1.3183675130208334,
-    "train_runtime": 168.5498,
+    "epoch": 50.0,
+    "train_loss": 0.5075189057985942,
+    "train_runtime": 413.5077,
     "train_samples": 3000,
-    "train_samples_per_second": 355.978,
-    "train_steps_per_second": 1.424
+    "train_samples_per_second": 362.75,
+    "train_steps_per_second": 1.451
 }

trainer_state.json

@@ -1,28 +1,34 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.0,
+  "epoch": 50.0,
   "eval_steps": 500,
-  "global_step": 240,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 20.0,
-      "step": 240,
-      "total_flos": 5879389501440000.0,
-      "train_loss": 1.3183675130208334,
-      "train_runtime": 168.5498,
-      "train_samples_per_second": 355.978,
-      "train_steps_per_second": 1.424
+      "epoch": 41.67,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6047,
+      "step": 500
+    },
+    {
+      "epoch": 50.0,
+      "step": 600,
+      "total_flos": 1.46984737536e+16,
+      "train_loss": 0.5075189057985942,
+      "train_runtime": 413.5077,
+      "train_samples_per_second": 362.75,
+      "train_steps_per_second": 1.451
     }
   ],
   "logging_steps": 500,
-  "max_steps": 240,
-  "num_train_epochs": 20,
+  "max_steps": 600,
+  "num_train_epochs": 50,
   "save_steps": 500,
-  "total_flos": 5879389501440000.0,
+  "total_flos": 1.46984737536e+16,
   "trial_name": null,
   "trial_params": null
 }