add model

README.md

@@ -21,7 +21,7 @@ model_index:
     metric:
       name: Accuracy
       type: accuracy
-      value: 0.43661971830985913
+      value: 0.5633802816901409
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7083
-- Accuracy: 0.4366
+- Loss: 0.6898
+- Accuracy: 0.5634
 
 ## Model description
 
@@ -52,7 +52,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.43661971830985913,
-    "eval_loss": 0.7083150744438171,
-    "eval_runtime": 0.3695,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6897721290588379,
+    "eval_runtime": 0.3684,
     "eval_samples": 71,
-    "eval_samples_per_second": 192.154,
-    "eval_steps_per_second": 24.358,
-    "train_loss": 0.7118758201599121,
-    "train_runtime": 29.8471,
+    "eval_samples_per_second": 192.717,
+    "eval_steps_per_second": 24.429,
+    "train_loss": 0.7106883525848389,
+    "train_runtime": 30.3399,
     "train_samples": 635,
-    "train_samples_per_second": 85.1,
-    "train_steps_per_second": 2.68
+    "train_samples_per_second": 83.718,
+    "train_steps_per_second": 5.274
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.43661971830985913,
-    "eval_loss": 0.7083150744438171,
-    "eval_runtime": 0.3695,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6897721290588379,
+    "eval_runtime": 0.3684,
     "eval_samples": 71,
-    "eval_samples_per_second": 192.154,
-    "eval_steps_per_second": 24.358
+    "eval_samples_per_second": 192.717,
+    "eval_steps_per_second": 24.429
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72aa754f30d527572866f65631831dd1ac8ca634865161cdd2eafe60495bb084
+oid sha256:76738bf5d41349aef5380b1b6cf0cf43458f92dbfd0d90ff6bafe43b56ab872e
 size 46755537

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "train_loss": 0.7118758201599121,
-    "train_runtime": 29.8471,
+    "train_loss": 0.7106883525848389,
+    "train_runtime": 30.3399,
     "train_samples": 635,
-    "train_samples_per_second": 85.1,
-    "train_steps_per_second": 2.68
+    "train_samples_per_second": 83.718,
+    "train_steps_per_second": 5.274
 }

trainer_state.json

@@ -2,22 +2,22 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 4.0,
-  "global_step": 80,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 4.0,
-      "step": 80,
+      "step": 160,
       "total_flos": 15175294617600.0,
-      "train_loss": 0.7118758201599121,
-      "train_runtime": 29.8471,
-      "train_samples_per_second": 85.1,
-      "train_steps_per_second": 2.68
+      "train_loss": 0.7106883525848389,
+      "train_runtime": 30.3399,
+      "train_samples_per_second": 83.718,
+      "train_steps_per_second": 5.274
     }
   ],
-  "max_steps": 80,
+  "max_steps": 160,
   "num_train_epochs": 4,
   "total_flos": 15175294617600.0,
   "trial_name": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88188319793dcb1cdbb8866aa84daceea3fbf0084cce61388fcde675f5cbd888
+oid sha256:a0a2fb8602a3ca6cfc2c99949d345edf962d967e8ba319836ecfbcb69ccd28dd
 size 2607