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": 5000,
-    "exact_match": 26.26,
-    "f1": 37.96865231481615,
-    "train_loss": 0.3752000265483615,
-    "train_runtime": 1847.2329,
+    "exact_match": 55.94,
+    "f1": 66.02639589699918,
+    "train_loss": 1.745846888062301,
+    "train_runtime": 73.1405,
     "train_samples": 5000,
-    "train_samples_per_second": 270.675,
-    "train_steps_per_second": 4.277
+    "train_samples_per_second": 205.085,
+    "train_steps_per_second": 6.44
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66362bd91a0319d4356bb2c1c86fc9093cef45c6105ddb804a520d1b1f81b3d3
+oid sha256:88e4c8f49b6f7b9ed5d11d1a5aa56a4a013deaacd9ffe43772410d84301ac4c5
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270cf96fc867a2a49749b6cb84de525c6441fe6b38efa5c1ba35f9ec3640a80f
-size 23332316
+oid sha256:6a21b7e29fc101babf47022be93e4bc5edbc45a50588f7444588e52dbd5bbd03
+size 22834956

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 100.0,
+    "epoch": 3.0,
     "eval_samples": 5000,
-    "exact_match": 26.26,
-    "f1": 37.96865231481615
+    "exact_match": 55.94,
+    "f1": 66.02639589699918
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 100.0,
-    "train_loss": 0.3752000265483615,
-    "train_runtime": 1847.2329,
+    "epoch": 3.0,
+    "train_loss": 1.745846888062301,
+    "train_runtime": 73.1405,
     "train_samples": 5000,
-    "train_samples_per_second": 270.675,
-    "train_steps_per_second": 4.277
+    "train_samples_per_second": 205.085,
+    "train_steps_per_second": 6.44
 }

trainer_state.json

@@ -1,118 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 100.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 7900,
+  "global_step": 471,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 6.33,
-      "learning_rate": 4.683544303797468e-05,
-      "loss": 1.1738,
-      "step": 500
-    },
-    {
-      "epoch": 12.66,
-      "learning_rate": 4.367088607594937e-05,
-      "loss": 0.1263,
-      "step": 1000
-    },
-    {
-      "epoch": 18.99,
-      "learning_rate": 4.050632911392405e-05,
-      "loss": 0.0547,
-      "step": 1500
-    },
-    {
-      "epoch": 25.32,
-      "learning_rate": 3.7341772151898736e-05,
-      "loss": 0.0303,
-      "step": 2000
-    },
-    {
-      "epoch": 31.65,
-      "learning_rate": 3.4177215189873416e-05,
-      "loss": 0.0218,
-      "step": 2500
-    },
-    {
-      "epoch": 37.97,
-      "learning_rate": 3.10126582278481e-05,
-      "loss": 0.0211,
-      "step": 3000
-    },
-    {
-      "epoch": 44.3,
-      "learning_rate": 2.7848101265822786e-05,
-      "loss": 0.0274,
-      "step": 3500
-    },
-    {
-      "epoch": 50.63,
-      "learning_rate": 2.468354430379747e-05,
-      "loss": 0.0399,
-      "step": 4000
-    },
-    {
-      "epoch": 56.96,
-      "learning_rate": 2.1518987341772153e-05,
-      "loss": 0.0601,
-      "step": 4500
-    },
-    {
-      "epoch": 63.29,
-      "learning_rate": 1.8354430379746836e-05,
-      "loss": 0.1468,
-      "step": 5000
-    },
-    {
-      "epoch": 69.62,
-      "learning_rate": 1.5189873417721521e-05,
-      "loss": 0.403,
-      "step": 5500
-    },
-    {
-      "epoch": 75.95,
-      "learning_rate": 1.2025316455696203e-05,
-      "loss": 0.5652,
-      "step": 6000
-    },
-    {
-      "epoch": 82.28,
-      "learning_rate": 8.860759493670886e-06,
-      "loss": 0.6874,
-      "step": 6500
-    },
-    {
-      "epoch": 88.61,
-      "learning_rate": 5.69620253164557e-06,
-      "loss": 0.764,
-      "step": 7000
-    },
-    {
-      "epoch": 94.94,
-      "learning_rate": 2.531645569620253e-06,
-      "loss": 1.0024,
-      "step": 7500
-    },
-    {
-      "epoch": 100.0,
-      "step": 7900,
-      "total_flos": 4.8994912512e+16,
-      "train_loss": 0.3752000265483615,
-      "train_runtime": 1847.2329,
-      "train_samples_per_second": 270.675,
-      "train_steps_per_second": 4.277
+      "epoch": 3.0,
+      "step": 471,
+      "total_flos": 1469847375360000.0,
+      "train_loss": 1.745846888062301,
+      "train_runtime": 73.1405,
+      "train_samples_per_second": 205.085,
+      "train_steps_per_second": 6.44
     }
   ],
   "logging_steps": 500,
-  "max_steps": 7900,
-  "num_train_epochs": 100,
+  "max_steps": 471,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 4.8994912512e+16,
+  "total_flos": 1469847375360000.0,
   "trial_name": null,
   "trial_params": null
 }