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": 3.0,
+    "epoch": 5.0,
     "eval_samples": 5000,
-    "exact_match": 55.94,
-    "f1": 66.02639589699918,
-    "train_loss": 1.745847276821258,
-    "train_runtime": 72.8357,
+    "exact_match": 56.48,
+    "f1": 66.83741494010742,
+    "train_loss": 1.1950870295239102,
+    "train_runtime": 116.2904,
     "train_samples": 5000,
-    "train_samples_per_second": 205.943,
-    "train_steps_per_second": 6.467
+    "train_samples_per_second": 214.979,
+    "train_steps_per_second": 6.75
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fede8eea72f810ac4bacbc6c15745df8d0b258eb8efb4aec1faa3cfba727ef0
+oid sha256:227cbc7cbb6d9ce1008447648c25b2cf48beaed0479b3240c7c42d5070b877b1
 size 5588

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6690b5edfc80d9dd9816fa96a6e681647b10fdfa5d6446d620f3e8d12ef48b08
-size 22836828
+oid sha256:0f50702ab28a48bea57f726c6950493e5d002e09fc1a849f8dc20e4d1855a9aa
+size 22853456

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 3.0,
+    "epoch": 5.0,
     "eval_samples": 5000,
-    "exact_match": 55.94,
-    "f1": 66.02639589699918
+    "exact_match": 56.48,
+    "f1": 66.83741494010742
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 1.745847276821258,
-    "train_runtime": 72.8357,
+    "epoch": 5.0,
+    "train_loss": 1.1950870295239102,
+    "train_runtime": 116.2904,
     "train_samples": 5000,
-    "train_samples_per_second": 205.943,
-    "train_steps_per_second": 6.467
+    "train_samples_per_second": 214.979,
+    "train_steps_per_second": 6.75
 }

trainer_state.json

@@ -1,28 +1,34 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 471,
+  "global_step": 785,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 471,
-      "total_flos": 1469847375360000.0,
-      "train_loss": 1.745847276821258,
-      "train_runtime": 72.8357,
-      "train_samples_per_second": 205.943,
-      "train_steps_per_second": 6.467
+      "epoch": 3.18,
+      "learning_rate": 1.8152866242038215e-05,
+      "loss": 1.6263,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "step": 785,
+      "total_flos": 2449745625600000.0,
+      "train_loss": 1.1950870295239102,
+      "train_runtime": 116.2904,
+      "train_samples_per_second": 214.979,
+      "train_steps_per_second": 6.75
     }
   ],
   "logging_steps": 500,
-  "max_steps": 471,
-  "num_train_epochs": 3,
+  "max_steps": 785,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1469847375360000.0,
+  "total_flos": 2449745625600000.0,
   "trial_name": null,
   "trial_params": null
 }