End of training
Browse files- README.md +9 -9
- config.json +0 -1
- runs/Nov20_08-21-08_HAN/events.out.tfevents.1700439678.HAN.8728.10 +3 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.7584
|
36 |
- Accuracy: 0.9273
|
|
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -66,14 +66,14 @@ The following hyperparameters were used during training:
|
|
66 |
|:-------------:|:-----:|:-----:|:--------:|:---------------:|
|
67 |
| 0.0209 | 1.0 | 1563 | 0.9263 | 0.5386 |
|
68 |
| 0.0 | 2.0 | 3126 | 0.9284 | 0.6249 |
|
69 |
-
| 0.016 | 3.0 | 4689 | 0.
|
70 |
-
| 0.0125 | 4.0 | 6252 | 0.
|
71 |
-
| 0.0032 | 5.0 | 7815 | 0.
|
72 |
-
| 0.0139 | 6.0 | 9378 | 0.
|
73 |
-
| 0.0001 | 7.0 | 10941 | 0.
|
74 |
-
| 0.0 | 8.0 | 12504 | 0.
|
75 |
-
| 0.0132 | 9.0 | 14067 | 0.
|
76 |
-
| 0.0 | 10.0 | 15630 | 0.
|
77 |
|
78 |
|
79 |
### Framework versions
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
|
34 |
It achieves the following results on the evaluation set:
|
|
|
35 |
- Accuracy: 0.9273
|
36 |
+
- Loss: 0.7584
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
66 |
|:-------------:|:-----:|:-----:|:--------:|:---------------:|
|
67 |
| 0.0209 | 1.0 | 1563 | 0.9263 | 0.5386 |
|
68 |
| 0.0 | 2.0 | 3126 | 0.9284 | 0.6249 |
|
69 |
+
| 0.016 | 3.0 | 4689 | 0.9166 | 0.6532 |
|
70 |
+
| 0.0125 | 4.0 | 6252 | 0.9198 | 0.6454 |
|
71 |
+
| 0.0032 | 5.0 | 7815 | 0.9264 | 0.6582 |
|
72 |
+
| 0.0139 | 6.0 | 9378 | 0.9260 | 0.6766 |
|
73 |
+
| 0.0001 | 7.0 | 10941 | 0.9283 | 0.7319 |
|
74 |
+
| 0.0 | 8.0 | 12504 | 0.9269 | 0.7658 |
|
75 |
+
| 0.0132 | 9.0 | 14067 | 0.9266 | 0.7416 |
|
76 |
+
| 0.0 | 10.0 | 15630 | 0.9273 | 0.7584 |
|
77 |
|
78 |
|
79 |
### Framework versions
|
config.json
CHANGED
@@ -22,7 +22,6 @@
|
|
22 |
"n_heads": 12,
|
23 |
"n_layers": 6,
|
24 |
"pad_token_id": 0,
|
25 |
-
"problem_type": "single_label_classification",
|
26 |
"qa_dropout": 0.1,
|
27 |
"seq_classif_dropout": 0.2,
|
28 |
"sinusoidal_pos_embds": false,
|
|
|
22 |
"n_heads": 12,
|
23 |
"n_layers": 6,
|
24 |
"pad_token_id": 0,
|
|
|
25 |
"qa_dropout": 0.1,
|
26 |
"seq_classif_dropout": 0.2,
|
27 |
"sinusoidal_pos_embds": false,
|
runs/Nov20_08-21-08_HAN/events.out.tfevents.1700439678.HAN.8728.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f97659c837b6465df4caf335112d623408b491ad0a12793001288e8b5795771
|
3 |
+
size 4612
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9528c02646de77e2b3aa5823bb3c82d0bc8b87be3ea67b702767f5c79bd7c14
|
3 |
+
size 4155
|