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: 4.4291
-- eval_runtime: 0.0319
-- eval_samples_per_second: 62.736
-- eval_steps_per_second: 31.368
-- epoch: 1.0
-- step: 1
+- Loss: 4.4291
 
 ## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.081         | 1.0   | 1    | 4.4291          |
+
+
 ### Framework versions
 
 - Transformers 4.35.2

runs/Jan17_06-45-41_9e8811c6b851/events.out.tfevents.1705473944.9e8811c6b851.3247.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f62377a2c8c88e9fc07a59a1bb2b7beed138e9c5cccb5986f9f3aa0f776bc160
-size 7822
+oid sha256:6ca0637005d2a3e062f5017c38d0a1bcbd7a8c067fbb182d645c9c3fb90036e8
+size 8170

trainer_state.json

@@ -21,6 +21,15 @@
       "eval_samples_per_second": 62.736,
       "eval_steps_per_second": 31.368,
       "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "step": 1,
+      "total_flos": 576049352400.0,
+      "train_loss": 1.0810490846633911,
+      "train_runtime": 20.9434,
+      "train_samples_per_second": 0.382,
+      "train_steps_per_second": 0.048
     }
   ],
   "logging_steps": 1,