Upload folder using huggingface_hub

README.md

@@ -18,13 +18,11 @@ model-index:
     dataset:
       name: GLUE BOOLQ
       type: glue
-      config: boolq
-      split: validation
       args: boolq
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7097859327217125
+      value: 0.7103975535168195
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the GLUE BOOLQ dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1221
-- Accuracy: 0.7098
+- Loss: 1.1407
+- Accuracy: 0.7104
 
 ## Model description
 

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.7097859327217125,
-    "eval_loss": 1.1220989227294922,
-    "eval_runtime": 6.9032,
+    "eval_accuracy": 0.7103975535168195,
+    "eval_loss": 1.1407246589660645,
+    "eval_runtime": 4.6126,
     "eval_samples": 3270,
-    "eval_samples_per_second": 473.694,
-    "eval_steps_per_second": 59.248,
-    "train_loss": 0.37518319857322563,
-    "train_runtime": 326.8151,
+    "eval_samples_per_second": 708.933,
+    "eval_steps_per_second": 88.671,
+    "train_loss": 0.38077404086872685,
+    "train_runtime": 143.3727,
     "train_samples": 9427,
-    "train_samples_per_second": 144.225,
-    "train_steps_per_second": 9.027
+    "train_samples_per_second": 328.759,
+    "train_steps_per_second": 20.576
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.7097859327217125,
-    "eval_loss": 1.1220989227294922,
-    "eval_runtime": 6.9032,
+    "eval_accuracy": 0.7103975535168195,
+    "eval_loss": 1.1407246589660645,
+    "eval_runtime": 4.6126,
     "eval_samples": 3270,
-    "eval_samples_per_second": 473.694,
-    "eval_steps_per_second": 59.248
+    "eval_samples_per_second": 708.933,
+    "eval_steps_per_second": 88.671
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e15e0a8f4da13c477a997731321b300c4e67e0affef277108b00b611b47c27d
+oid sha256:be7f2e36f176caecf8e31e394ebf5369e69b3674c887c05a212df130820e2b33
 size 433315633

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "train_loss": 0.37518319857322563,
-    "train_runtime": 326.8151,
+    "train_loss": 0.38077404086872685,
+    "train_runtime": 143.3727,
     "train_samples": 9427,
-    "train_samples_per_second": 144.225,
-    "train_steps_per_second": 9.027
+    "train_samples_per_second": 328.759,
+    "train_steps_per_second": 20.576
 }

trainer_state.json

@@ -10,41 +10,41 @@
     {
       "epoch": 0.85,
       "learning_rate": 1.6610169491525424e-05,
-      "loss": 0.6634,
+      "loss": 0.6633,
       "step": 500
     },
     {
       "epoch": 1.69,
-      "learning_rate": 1.3220338983050848e-05,
-      "loss": 0.5784,
+      "learning_rate": 1.3227118644067798e-05,
+      "loss": 0.5801,
       "step": 1000
     },
     {
       "epoch": 2.54,
-      "learning_rate": 9.830508474576272e-06,
-      "loss": 0.4113,
+      "learning_rate": 9.844067796610171e-06,
+      "loss": 0.4258,
       "step": 1500
     },
     {
       "epoch": 3.39,
-      "learning_rate": 6.440677966101695e-06,
-      "loss": 0.2685,
+      "learning_rate": 6.4542372881355944e-06,
+      "loss": 0.2802,
       "step": 2000
     },
     {
       "epoch": 4.24,
-      "learning_rate": 3.0508474576271192e-06,
-      "loss": 0.1735,
+      "learning_rate": 3.0644067796610173e-06,
+      "loss": 0.1836,
       "step": 2500
     },
     {
       "epoch": 5.0,
       "step": 2950,
       "total_flos": 3100434898598400.0,
-      "train_loss": 0.37518319857322563,
-      "train_runtime": 326.8151,
-      "train_samples_per_second": 144.225,
-      "train_steps_per_second": 9.027
+      "train_loss": 0.38077404086872685,
+      "train_runtime": 143.3727,
+      "train_samples_per_second": 328.759,
+      "train_steps_per_second": 20.576
     }
   ],
   "max_steps": 2950,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c41f5615188e374b7e0a00d54c3c74e42c1c1e8ec7c5c33fbba2a9f0aef5e36
+oid sha256:2a7317d57843de51bc3494add8422c9807a70f1ebb84b24f1d55c54896286df4
 size 3963