Rocketknight1 HF staff commited on
Commit
efccc88
1 Parent(s): 8105eab

Training in progress epoch 0

Browse files
README.md CHANGED
@@ -14,13 +14,13 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.0342
18
- - Validation Loss: 0.0595
19
- - Train Precision: 0.9240
20
- - Train Recall: 0.9328
21
- - Train F1: 0.9284
22
- - Train Accuracy: 0.9830
23
- - Epoch: 2
24
 
25
  ## Model description
26
 
@@ -46,14 +46,12 @@ The following hyperparameters were used during training:
46
 
47
  | Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
48
  |:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
49
- | 0.1933 | 0.0697 | 0.9065 | 0.9236 | 0.9149 | 0.9803 | 0 |
50
- | 0.0541 | 0.0601 | 0.9210 | 0.9311 | 0.9260 | 0.9824 | 1 |
51
- | 0.0342 | 0.0595 | 0.9240 | 0.9328 | 0.9284 | 0.9830 | 2 |
52
 
53
 
54
  ### Framework versions
55
 
56
- - Transformers 4.16.0.dev0
57
  - TensorFlow 2.8.0-rc0
58
- - Datasets 1.17.0
59
  - Tokenizers 0.11.0
 
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.1901
18
+ - Validation Loss: 0.0718
19
+ - Train Precision: 0.9022
20
+ - Train Recall: 0.9228
21
+ - Train F1: 0.9124
22
+ - Train Accuracy: 0.9801
23
+ - Epoch: 0
24
 
25
  ## Model description
26
 
 
46
 
47
  | Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
48
  |:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
49
+ | 0.1901 | 0.0718 | 0.9022 | 0.9228 | 0.9124 | 0.9801 | 0 |
 
 
50
 
51
 
52
  ### Framework versions
53
 
54
+ - Transformers 4.19.0.dev0
55
  - TensorFlow 2.8.0-rc0
56
+ - Datasets 2.1.1.dev0
57
  - Tokenizers 0.11.0
config.json CHANGED
@@ -40,6 +40,6 @@
40
  "seq_classif_dropout": 0.2,
41
  "sinusoidal_pos_embds": false,
42
  "tie_weights_": true,
43
- "transformers_version": "4.16.0.dev0",
44
  "vocab_size": 30522
45
  }
 
40
  "seq_classif_dropout": 0.2,
41
  "sinusoidal_pos_embds": false,
42
  "tie_weights_": true,
43
+ "transformers_version": "4.19.0.dev0",
44
  "vocab_size": 30522
45
  }
logs/train/events.out.tfevents.1651768451.matt-TRX40-AORUS-PRO-WIFI.89159.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3ed1d3121bbc7f45cfeb42689db86586affbc81a902124a423113667ed21501
3
+ size 1609860
logs/validation/events.out.tfevents.1651768488.matt-TRX40-AORUS-PRO-WIFI.89159.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6814f8e2e5dd04b1db3c2f1a83e76c242c2edb05a9f5d61bc0e37dea2933753
3
+ size 194
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2beb13d1eb4ce4c1f2fab0e88b6b3b8dd0306414ff08ac8207214d5da68af9f
3
  size 265606504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f52c5ee5994ac36c51d0e6970eb9293835c4b6ac1765f9990ebea5af2221073
3
  size 265606504