End of training

README.md

@@ -15,12 +15,7 @@ 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:
-- eval_loss: 4.3147
-- eval_runtime: 0.0269
-- eval_samples_per_second: 74.475
-- eval_steps_per_second: 37.237
-- epoch: 1.0
-- step: 1
+- Loss: 4.3147
 
 ## Model description
 
@@ -50,6 +45,13 @@ The following hyperparameters were used during training:
 - num_epochs: 1
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.092         | 1.0   | 1    | 4.3147          |
+
+
 ### Framework versions
 
 - Transformers 4.35.2

runs/Jan17_06-34-08_9e8811c6b851/events.out.tfevents.1705473251.9e8811c6b851.3247.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc100354794e53f4a83680a44b2a7cd1d132e83515e2a94f451351054edb6907
-size 7822
+oid sha256:5eda29b5081a5fce361772eb73720f13256c94ece7b18691c770d316ea2a1641
+size 8170

trainer_state.json

@@ -21,6 +21,15 @@
       "eval_samples_per_second": 74.475,
       "eval_steps_per_second": 37.237,
       "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "step": 1,
+      "total_flos": 576049352400.0,
+      "train_loss": 1.0920077562332153,
+      "train_runtime": 16.4422,
+      "train_samples_per_second": 0.487,
+      "train_steps_per_second": 0.061
     }
   ],
   "logging_steps": 1,