End of training

README.md

@@ -13,12 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 5.3555
-- eval_runtime: 0.0182
-- eval_samples_per_second: 55.091
-- eval_steps_per_second: 55.091
-- epoch: 50.0
-- step: 50
+- Loss: 5.3555
 
 ## Model description
 
@@ -48,6 +43,17 @@ The following hyperparameters were used during training:
 - num_epochs: 50
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0466        | 10.0  | 10   | 4.7461          |
+| 0.0213        | 20.0  | 20   | 4.9241          |
+| 0.01          | 30.0  | 30   | 5.0407          |
+| 0.0063        | 40.0  | 40   | 5.1613          |
+| 0.0043        | 50.0  | 50   | 5.3555          |
+
+
 ### Framework versions
 
 - Transformers 4.36.0

logs/events.out.tfevents.1705983419.70e47a1f5afe.42.15

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb242beabbd921fd08ac78989fe5c9c76825dbe29cfaa8cee47aab4b361be341
-size 7086
+oid sha256:957811a655eaf8eec001fcea41052a9b91275b73300e83afab73df20af70107b
+size 7434

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c839309986c2e3deebcb4dff61f0cc17ea04289c9211db54f017e6729a356c2f
+oid sha256:b682db66b454975faf7da3a053ad47ae19381e41248c218350c29f4e02d2c921
 size 435756040

trainer_state.json

@@ -77,6 +77,15 @@
       "eval_samples_per_second": 55.091,
       "eval_steps_per_second": 55.091,
       "step": 50
+    },
+    {
+      "epoch": 50.0,
+      "step": 50,
+      "total_flos": 32856154788600.0,
+      "train_loss": 0.0008505997806787491,
+      "train_runtime": 23.3473,
+      "train_samples_per_second": 19.274,
+      "train_steps_per_second": 2.142
     }
   ],
   "logging_steps": 10,