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": 5.0,
+    "epoch": 10.0,
     "eval_samples": 5000,
-    "exact_match": 56.48,
-    "f1": 66.83741494010742,
-    "train_loss": 1.1950870295239102,
-    "train_runtime": 116.2904,
+    "exact_match": 57.0,
+    "f1": 66.89460121812738,
+    "train_loss": 0.6390929455969744,
+    "train_runtime": 233.8699,
     "train_samples": 5000,
-    "train_samples_per_second": 214.979,
-    "train_steps_per_second": 6.75
+    "train_samples_per_second": 213.794,
+    "train_steps_per_second": 6.713
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:227cbc7cbb6d9ce1008447648c25b2cf48beaed0479b3240c7c42d5070b877b1
+oid sha256:257c0bd8231d77b7ed8a92f487cea47a30968fbfea9baf85295e4e6440868881
 size 5588

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f50702ab28a48bea57f726c6950493e5d002e09fc1a849f8dc20e4d1855a9aa
-size 22853456
+oid sha256:6b4f4962f1fd7eae05ed974e6d669317296158d56a21fe204a4a5143b1dcb0fa
+size 22970845

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 5.0,
+    "epoch": 10.0,
     "eval_samples": 5000,
-    "exact_match": 56.48,
-    "f1": 66.83741494010742
+    "exact_match": 57.0,
+    "f1": 66.89460121812738
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 1.1950870295239102,
-    "train_runtime": 116.2904,
+    "epoch": 10.0,
+    "train_loss": 0.6390929455969744,
+    "train_runtime": 233.8699,
     "train_samples": 5000,
-    "train_samples_per_second": 214.979,
-    "train_steps_per_second": 6.75
+    "train_samples_per_second": 213.794,
+    "train_steps_per_second": 6.713
 }

trainer_state.json

@@ -1,34 +1,46 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 785,
+  "global_step": 1570,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 3.18,
-      "learning_rate": 1.8152866242038215e-05,
-      "loss": 1.6263,
+      "learning_rate": 3.407643312101911e-05,
+      "loss": 1.5984,
       "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
+      "epoch": 6.37,
+      "learning_rate": 1.8152866242038215e-05,
+      "loss": 0.2991,
+      "step": 1000
+    },
+    {
+      "epoch": 9.55,
+      "learning_rate": 2.229299363057325e-06,
+      "loss": 0.1001,
+      "step": 1500
+    },
+    {
+      "epoch": 10.0,
+      "step": 1570,
+      "total_flos": 4899491251200000.0,
+      "train_loss": 0.6390929455969744,
+      "train_runtime": 233.8699,
+      "train_samples_per_second": 213.794,
+      "train_steps_per_second": 6.713
     }
   ],
   "logging_steps": 500,
-  "max_steps": 785,
-  "num_train_epochs": 5,
+  "max_steps": 1570,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2449745625600000.0,
+  "total_flos": 4899491251200000.0,
   "trial_name": null,
   "trial_params": null
 }