velaa commited on
Commit
4042536
·
1 Parent(s): 5fed8ba

End of training

Browse files
README.md CHANGED
@@ -9,20 +9,7 @@ metrics:
9
  - accuracy
10
  model-index:
11
  - name: opt-125m-finetuned-mnli
12
- results:
13
- - task:
14
- name: Text Classification
15
- type: text-classification
16
- dataset:
17
- name: glue
18
- type: glue
19
- config: mnli
20
- split: validation_matched
21
- args: mnli
22
- metrics:
23
- - name: Accuracy
24
- type: accuracy
25
- value: 0.34111054508405503
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.2230
36
- - Accuracy: 0.3411
37
 
38
  ## Model description
39
 
@@ -64,16 +51,16 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | 1.2506 | 1.0 | 1 | 1.2157 | 0.3374 |
68
- | 0.7567 | 2.0 | 2 | 1.2243 | 0.3364 |
69
- | 0.5481 | 3.0 | 3 | 1.2259 | 0.3371 |
70
- | 0.4338 | 4.0 | 4 | 1.2238 | 0.3391 |
71
- | 0.3292 | 5.0 | 5 | 1.2230 | 0.3411 |
72
 
73
 
74
  ### Framework versions
75
 
76
- - Transformers 4.35.2
77
  - Pytorch 2.1.0+cu118
78
  - Datasets 2.15.0
79
  - Tokenizers 0.15.0
 
9
  - accuracy
10
  model-index:
11
  - name: opt-125m-finetuned-mnli
12
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
19
 
20
  This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the glue dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.2083
23
+ - Accuracy: 0.3321
24
 
25
  ## Model description
26
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 1.2018 | 1.0 | 1 | 1.2117 | 0.3312 |
55
+ | 1.237 | 2.0 | 2 | 1.2083 | 0.3321 |
56
+ | 1.2323 | 3.0 | 3 | 1.2057 | 0.3317 |
57
+ | 1.1903 | 4.0 | 4 | 1.2041 | 0.3317 |
58
+ | 1.1866 | 5.0 | 5 | 1.2032 | 0.3317 |
59
 
60
 
61
  ### Framework versions
62
 
63
+ - Transformers 4.36.0.dev0
64
  - Pytorch 2.1.0+cu118
65
  - Datasets 2.15.0
66
  - Tokenizers 0.15.0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c7f42be0c39cc97201a15161a1234b1cc69712eb3ec6c98df28bad5dc102dd7
3
  size 2365968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e649329902db1f9b974706d77cc276fa0430745497bba11f4903ea03eecefc
3
  size 2365968
runs/Dec03_00-37-44_e58bb28c2f23/events.out.tfevents.1701564175.e58bb28c2f23.6904.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:274b53207be3b6d2a1a56acec28baf6f8664bd29c1f8401b5d9aceec8dc18c93
3
+ size 405