Realgon commited on
Commit
642a5df
1 Parent(s): d3c17a0

End of training

Browse files
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: 0.7641
36
  - Accuracy: 0.9290
 
37
 
38
  ## Model description
39
 
@@ -66,14 +66,14 @@ The following hyperparameters were used during training:
66
  |:-------------:|:-----:|:-----:|:--------:|:---------------:|
67
  | 0.0369 | 1.0 | 1563 | 0.9254 | 0.5650 |
68
  | 0.0118 | 2.0 | 3126 | 0.9295 | 0.6178 |
69
- | 0.0314 | 3.0 | 4689 | 0.5877 | 0.9216 |
70
- | 0.0093 | 4.0 | 6252 | 0.6736 | 0.9212 |
71
- | 0.0043 | 5.0 | 7815 | 0.7475 | 0.9216 |
72
- | 0.0144 | 6.0 | 9378 | 0.6278 | 0.9297 |
73
- | 0.0034 | 7.0 | 10941 | 0.6739 | 0.9258 |
74
- | 0.0059 | 8.0 | 12504 | 0.6986 | 0.9310 |
75
- | 0.0 | 9.0 | 14067 | 0.7724 | 0.9277 |
76
- | 0.0038 | 10.0 | 15630 | 0.7641 | 0.9290 |
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: 0.9290
36
+ - Loss: 0.7641
37
 
38
  ## Model description
39
 
 
66
  |:-------------:|:-----:|:-----:|:--------:|:---------------:|
67
  | 0.0369 | 1.0 | 1563 | 0.9254 | 0.5650 |
68
  | 0.0118 | 2.0 | 3126 | 0.9295 | 0.6178 |
69
+ | 0.0314 | 3.0 | 4689 | 0.9216 | 0.5877 |
70
+ | 0.0093 | 4.0 | 6252 | 0.9212 | 0.6736 |
71
+ | 0.0043 | 5.0 | 7815 | 0.9216 | 0.7475 |
72
+ | 0.0144 | 6.0 | 9378 | 0.9297 | 0.6278 |
73
+ | 0.0034 | 7.0 | 10941 | 0.9258 | 0.6739 |
74
+ | 0.0059 | 8.0 | 12504 | 0.9310 | 0.6986 |
75
+ | 0.0 | 9.0 | 14067 | 0.9277 | 0.7724 |
76
+ | 0.0038 | 10.0 | 15630 | 0.9290 | 0.7641 |
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_08-20-50_HAN/events.out.tfevents.1700439660.HAN.8728.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94e518ed0ac43953d4856760103587f4bad616156ba2020fff0373e1e9921ccc
3
+ size 4609
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90dc329cd80a4133c2d9151c88bebd3d78d4b73a4cb3e2b850b1b3ea619ba475
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c501a8434cdf6b9ae760fd8a179d95ae672053509ede6f1b6a38657b2beb6f24
3
  size 4091