Upload folder using huggingface_hub

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6425992779783394
+      value: 0.6787003610108303
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2055
-- Accuracy: 0.6426
+- Loss: 1.7714
+- Accuracy: 0.6787
 
 ## Model description
 
@@ -53,7 +53,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
+- 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": 5.0,
-    "eval_accuracy": 0.6425992779783394,
-    "eval_loss": 3.205474376678467,
-    "eval_runtime": 0.5373,
+    "eval_accuracy": 0.6787003610108303,
+    "eval_loss": 1.771389365196228,
+    "eval_runtime": 0.7069,
     "eval_samples": 277,
-    "eval_samples_per_second": 515.583,
-    "eval_steps_per_second": 65.146,
-    "train_loss": 0.3344010169689472,
-    "train_runtime": 98.9629,
+    "eval_samples_per_second": 391.849,
+    "eval_steps_per_second": 49.512,
+    "train_loss": 0.3118787203079615,
+    "train_runtime": 82.0111,
     "train_samples": 2490,
-    "train_samples_per_second": 125.805,
-    "train_steps_per_second": 15.763
+    "train_samples_per_second": 151.809,
+    "train_steps_per_second": 9.511
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.6425992779783394,
-    "eval_loss": 3.205474376678467,
-    "eval_runtime": 0.5373,
+    "eval_accuracy": 0.6787003610108303,
+    "eval_loss": 1.771389365196228,
+    "eval_runtime": 0.7069,
     "eval_samples": 277,
-    "eval_samples_per_second": 515.583,
-    "eval_steps_per_second": 65.146
+    "eval_samples_per_second": 391.849,
+    "eval_steps_per_second": 49.512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cb641be82ca0f1ccfb4f61fe42542d9659f201169ff773b587f2a936c8dfb1a
+oid sha256:781808a175754627018579d28acc8bfdd46b49fe2ebba66f729431a19f617612
 size 501029729

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "train_loss": 0.3344010169689472,
-    "train_runtime": 98.9629,
+    "train_loss": 0.3118787203079615,
+    "train_runtime": 82.0111,
     "train_samples": 2490,
-    "train_samples_per_second": 125.805,
-    "train_steps_per_second": 15.763
+    "train_samples_per_second": 151.809,
+    "train_steps_per_second": 9.511
 }

trainer_state.json

@@ -2,40 +2,28 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 5.0,
-  "global_step": 1560,
+  "global_step": 780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 1.6,
-      "learning_rate": 1.3589743589743592e-05,
-      "loss": 0.6095,
-      "step": 500
-    },
     {
       "epoch": 3.21,
-      "learning_rate": 7.17948717948718e-06,
-      "loss": 0.3272,
-      "step": 1000
-    },
-    {
-      "epoch": 4.81,
-      "learning_rate": 7.692307692307694e-07,
-      "loss": 0.0972,
-      "step": 1500
+      "learning_rate": 7.282051282051282e-06,
+      "loss": 0.4533,
+      "step": 500
     },
     {
       "epoch": 5.0,
-      "step": 1560,
+      "step": 780,
       "total_flos": 813286136217600.0,
-      "train_loss": 0.3344010169689472,
-      "train_runtime": 98.9629,
-      "train_samples_per_second": 125.805,
-      "train_steps_per_second": 15.763
+      "train_loss": 0.3118787203079615,
+      "train_runtime": 82.0111,
+      "train_samples_per_second": 151.809,
+      "train_steps_per_second": 9.511
     }
   ],
-  "max_steps": 1560,
+  "max_steps": 780,
   "num_train_epochs": 5,
   "total_flos": 813286136217600.0,
   "trial_name": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b7acb9d14b816ffeacb7e2beaba2d6037a7bff441ba00c7df1b155086660724
+oid sha256:1da5bc24ce2ee57a0ae282557258fdf6c887a02ea72d1c5da88e78847d79679b
 size 3963