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: 4.3336
-- eval_runtime: 0.036
-- eval_samples_per_second: 55.487
-- eval_steps_per_second: 27.744
-- epoch: 1.0
-- step: 1
+- Loss: 4.3336
 
 ## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.1037        | 1.0   | 1    | 4.3336          |
+
+
 ### Framework versions
 
 - Transformers 4.35.2

runs/Jan17_06-57-58_9e8811c6b851/events.out.tfevents.1705474681.9e8811c6b851.3247.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19efd81999941d31f2d83755bf8fb67fea3cf70836d4a28e7fe6b3ce90d052d6
-size 7822
+oid sha256:4c87cc69313d8cdaee799e4491b10c33d989beb924720623913bcf5882528875
+size 8170

trainer_state.json

@@ -21,6 +21,15 @@
       "eval_samples_per_second": 55.487,
       "eval_steps_per_second": 27.744,
       "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "step": 1,
+      "total_flos": 576049352400.0,
+      "train_loss": 1.1036854982376099,
+      "train_runtime": 21.068,
+      "train_samples_per_second": 0.38,
+      "train_steps_per_second": 0.047
     }
   ],
   "logging_steps": 1,