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: 4.0211
-- eval_runtime: 0.0298
-- eval_samples_per_second: 67.051
-- eval_steps_per_second: 33.525
-- epoch: 1.0
-- step: 1
+- Loss: 4.0211
 
 ## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0194        | 1.0   | 1    | 4.0211          |
+
+
 ### Framework versions
 
 - Transformers 4.35.2

runs/Jan17_06-30-10_9e8811c6b851/events.out.tfevents.1705473013.9e8811c6b851.3247.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9f23082bb6494e75b1d21a892398363058a09f81277f8d056e306abbac168ea
-size 6940
+oid sha256:c159f6559f911b06e762a3d9a649519e63e454c196c52b929fbba50ab95d9970
+size 7288

trainer_state.json

@@ -21,6 +21,15 @@
       "eval_samples_per_second": 67.051,
       "eval_steps_per_second": 33.525,
       "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "step": 1,
+      "total_flos": 584109418464.0,
+      "train_loss": 1.0194010734558105,
+      "train_runtime": 15.5881,
+      "train_samples_per_second": 0.513,
+      "train_steps_per_second": 0.064
     }
   ],
   "logging_steps": 1,