End of training

README.md

@@ -15,7 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.2773
+- eval_loss: 4.2773
+- eval_runtime: 0.0648
+- eval_samples_per_second: 30.874
+- eval_steps_per_second: 15.437
+- epoch: 1.0
+- step: 1
 
 ## Model description
 
@@ -45,13 +50,6 @@ The following hyperparameters were used during training:
 - num_epochs: 1
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.0902        | 1.0   | 1    | 4.2773          |
-
-
 ### Framework versions
 
 - Transformers 4.35.2

runs/Jan17_07-03-37_9e8811c6b851/events.out.tfevents.1705475024.9e8811c6b851.3247.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ffde13aae5e968d8087a1d4e8f98780c80d6896b766f292a1c66b40b961c694
+size 7822

trainer_state.json

@@ -17,19 +17,10 @@
     {
       "epoch": 1.0,
       "eval_loss": 4.27725887298584,
-      "eval_runtime": 0.0285,
-      "eval_samples_per_second": 70.132,
-      "eval_steps_per_second": 35.066,
+      "eval_runtime": 0.0648,
+      "eval_samples_per_second": 30.874,
+      "eval_steps_per_second": 15.437,
       "step": 1
-    },
-    {
-      "epoch": 1.0,
-      "step": 1,
-      "total_flos": 576049352400.0,
-      "train_loss": 1.0902321338653564,
-      "train_runtime": 6.8218,
-      "train_samples_per_second": 1.173,
-      "train_steps_per_second": 0.147
     }
   ],
   "logging_steps": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c72fc3f38d98cc547f525276b85de336d66fc629ebc4813f4cef0c71327bbd15
+oid sha256:21bafcad3f9c59888faef07c61f3e3aa60532b2d9ed02dd791605896705b4331
 size 4600