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: 3.9143
-- eval_runtime: 0.0555
-- eval_samples_per_second: 36.051
-- eval_steps_per_second: 18.026
-- epoch: 1.0
-- step: 1
+- Loss: 3.9143
 
 ## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0044        | 1.0   | 1    | 3.9143          |
+
+
 ### Framework versions
 
 - Transformers 4.35.2

runs/Jan17_06-16-27_9e8811c6b851/events.out.tfevents.1705472195.9e8811c6b851.3247.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d3f6c3106f7b958775035e2196b75109cbb6d717df2f538cbe068d8676880c7
-size 6982
+oid sha256:4d72b91aa7736e71494ee188c2a711877df40931abc1ae2288de9b2d7f0285ed
+size 7330

trainer_state.json

@@ -21,6 +21,15 @@
       "eval_samples_per_second": 36.051,
       "eval_steps_per_second": 18.026,
       "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "step": 1,
+      "total_flos": 494250897360.0,
+      "train_loss": 1.0043808221817017,
+      "train_runtime": 26.1041,
+      "train_samples_per_second": 0.306,
+      "train_steps_per_second": 0.038
     }
   ],
   "logging_steps": 1,