End of training

README.md

@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7047
 - Accuracy: 0.9289
+- Loss: 0.7047
 
 ## Model description
 
@@ -66,14 +66,14 @@ The following hyperparameters were used during training:
 |:-------------:|:-----:|:-----:|:--------:|:---------------:|
 | 0.0355        | 1.0   | 1563  | 0.9217   | 0.5841          |
 | 0.0049        | 2.0   | 3126  | 0.9265   | 0.5822          |
-| 0.0273        | 3.0   | 4689  | 0.5829   | 0.9264          |
-| 0.0186        | 4.0   | 6252  | 0.6172   | 0.9261          |
-| 0.0188        | 5.0   | 7815  | 0.5887   | 0.9224          |
-| 0.0066        | 6.0   | 9378  | 0.5949   | 0.9265          |
-| 0.0           | 7.0   | 10941 | 0.6716   | 0.9268          |
-| 0.0024        | 8.0   | 12504 | 0.6961   | 0.9284          |
-| 0.0           | 9.0   | 14067 | 0.7182   | 0.9267          |
-| 0.0           | 10.0  | 15630 | 0.7047   | 0.9289          |
+| 0.0273        | 3.0   | 4689  | 0.9264   | 0.5829          |
+| 0.0186        | 4.0   | 6252  | 0.9261   | 0.6172          |
+| 0.0188        | 5.0   | 7815  | 0.9224   | 0.5887          |
+| 0.0066        | 6.0   | 9378  | 0.9265   | 0.5949          |
+| 0.0           | 7.0   | 10941 | 0.9268   | 0.6716          |
+| 0.0024        | 8.0   | 12504 | 0.9284   | 0.6961          |
+| 0.0           | 9.0   | 14067 | 0.9267   | 0.7182          |
+| 0.0           | 10.0  | 15630 | 0.9289   | 0.7047          |
 
 
 ### Framework versions

config.json

@@ -22,7 +22,6 @@
   "n_heads": 12,
   "n_layers": 6,
   "pad_token_id": 0,
-  "problem_type": "single_label_classification",
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,

runs/Nov20_08-20-35_HAN/events.out.tfevents.1700439643.HAN.8728.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45385082decd194ebaf31aa566f5bf03ff7c8d6ab305e7648dabc9c0c4d9efc0
+size 4609

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1723ae6cfb67e588ad0282f38d96a0351d2ef3d657cb99d5184598497bc1afff
+oid sha256:855f925b84bfeab512ba62b9402c007ebaa49f8e594b4d3fa380fc9f15273cb8
 size 4091