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: 4.2672
-- eval_runtime: 0.0497
-- eval_samples_per_second: 40.249
-- eval_steps_per_second: 20.124
-- epoch: 1.0
-- step: 1
+- Loss: 4.2672
 
 ## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.088         | 1.0   | 1    | 4.2672          |
+
+
 ### Framework versions
 
 - Transformers 4.35.2

runs/Jan17_06-31-51_9e8811c6b851/events.out.tfevents.1705473115.9e8811c6b851.3247.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9404232f6b5e8d1b69daa077fd88f79808fe3a4515e6297065858b95ca0d6764
-size 7822
+oid sha256:ea96e0318d83b53095ec544fe983c251d3c38aa41f7ce80ed19ebdddb7b4c818
+size 8170

trainer_state.json

@@ -21,6 +21,15 @@
       "eval_samples_per_second": 40.249,
       "eval_steps_per_second": 20.124,
       "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "step": 1,
+      "total_flos": 576049352400.0,
+      "train_loss": 1.0879627466201782,
+      "train_runtime": 16.2581,
+      "train_samples_per_second": 0.492,
+      "train_steps_per_second": 0.062
     }
   ],
   "logging_steps": 1,