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: 4.3916
-- eval_runtime: 0.0226
-- eval_samples_per_second: 88.586
-- eval_steps_per_second: 44.293
-- epoch: 1.0
-- step: 1
+- Loss: 4.3916
 
 ## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.1082        | 1.0   | 1    | 4.3916          |
+
+
 ### Framework versions
 
 - Transformers 4.35.2

runs/Jan17_06-36-29_9e8811c6b851/events.out.tfevents.1705473392.9e8811c6b851.3247.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9933290ae2d2c0cbd47dd30a8efee264de6d2599800ee6c1ccea9460a6fa58e
-size 7822
+oid sha256:1ede52348a2e83537d9aac3ddb420a32ac9868d64b779de80482767d83640f8f
+size 8170

trainer_state.json

@@ -21,6 +21,15 @@
       "eval_samples_per_second": 88.586,
       "eval_steps_per_second": 44.293,
       "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "step": 1,
+      "total_flos": 576049352400.0,
+      "train_loss": 1.108170986175537,
+      "train_runtime": 16.482,
+      "train_samples_per_second": 0.485,
+      "train_steps_per_second": 0.061
     }
   ],
   "logging_steps": 1,