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: 4.0122
-- eval_runtime: 0.0303
-- eval_samples_per_second: 65.996
-- eval_steps_per_second: 32.998
-- epoch: 1.0
-- step: 1
+- Loss: 4.0122
 
 ## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9982        | 1.0   | 1    | 4.0122          |
+
+
 ### Framework versions
 
 - Transformers 4.35.2

runs/Jan17_06-28-03_9e8811c6b851/events.out.tfevents.1705472886.9e8811c6b851.3247.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf379022868d7e84e6e61fe4f20ec9102bb38d3e6b0865dff18009222a05e6d1
-size 6940
+oid sha256:d2cb75a5a091b0a6d16b5d3bcc3a3346223beb5507439ebaa431fb134de2845b
+size 7288

trainer_state.json

@@ -21,6 +21,15 @@
       "eval_samples_per_second": 65.996,
       "eval_steps_per_second": 32.998,
       "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "step": 1,
+      "total_flos": 584109418464.0,
+      "train_loss": 0.9981689453125,
+      "train_runtime": 19.7049,
+      "train_samples_per_second": 0.406,
+      "train_steps_per_second": 0.051
     }
   ],
   "logging_steps": 1,