hilco commited on
Commit
10f56ae
1 Parent(s): 9a9e88f

Finished training.

Browse files
Files changed (3) hide show
  1. README.md +11 -11
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  args: irony
24
  metrics:
25
  - type: accuracy
26
- value: 0.675392670157068
27
  name: accuracy
28
  ---
29
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
34
 
35
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the tweet_eval dataset.
36
  It achieves the following results on the evaluation set:
37
- - accuracy: 0.6754
38
 
39
  ## Model description
40
 
@@ -65,15 +65,15 @@ The following hyperparameters were used during training:
65
 
66
  | accuracy | train_loss | epoch |
67
  |:--------:|:----------:|:-----:|
68
- | 0.5173 | None | 0 |
69
- | 0.6084 | 0.6735 | 0 |
70
- | 0.6084 | 0.6186 | 1 |
71
- | 0.6649 | 0.5837 | 2 |
72
- | 0.6764 | 0.5616 | 3 |
73
- | 0.6743 | 0.5366 | 4 |
74
- | 0.6471 | 0.5275 | 5 |
75
- | 0.6775 | 0.5065 | 6 |
76
- | 0.6754 | 0.4976 | 7 |
77
 
78
 
79
  ### Framework versions
 
23
  args: irony
24
  metrics:
25
  - type: accuracy
26
+ value: 0.6774869109947644
27
  name: accuracy
28
  ---
29
 
 
34
 
35
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the tweet_eval dataset.
36
  It achieves the following results on the evaluation set:
37
+ - accuracy: 0.6775
38
 
39
  ## Model description
40
 
 
65
 
66
  | accuracy | train_loss | epoch |
67
  |:--------:|:----------:|:-----:|
68
+ | 0.4921 | None | 0 |
69
+ | 0.6105 | 0.6719 | 0 |
70
+ | 0.6136 | 0.6217 | 1 |
71
+ | 0.6733 | 0.5822 | 2 |
72
+ | 0.6775 | 0.5562 | 3 |
73
+ | 0.6723 | 0.5319 | 4 |
74
+ | 0.6450 | 0.5167 | 5 |
75
+ | 0.6764 | 0.5046 | 6 |
76
+ | 0.6775 | 0.4967 | 7 |
77
 
78
 
79
  ### Framework versions
adapter_config.json CHANGED
@@ -19,8 +19,8 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "v_lin",
23
- "q_lin"
24
  ],
25
  "task_type": "SEQ_CLS",
26
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "q_lin",
23
+ "v_lin"
24
  ],
25
  "task_type": "SEQ_CLS",
26
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54276ed62ed04ff430f05e81bb9e738e56caba79e5380e568d733bcddc12b1d0
3
  size 2446056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e13d500c1b78c0dfe22710c13bf2d30cd91c6e6f04c2652fdb90cc0863d3431
3
  size 2446056