jonaskoenig commited on
Commit
afee651
1 Parent(s): e8aff9f

Training in progress epoch 0

Browse files
Files changed (3) hide show
  1. README.md +7 -14
  2. config.json +57 -58
  3. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,11 +14,9 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.0230
18
- - Train Binary Crossentropy: 0.3795
19
- - Validation Loss: 0.0217
20
- - Validation Binary Crossentropy: 0.3411
21
- - Epoch: 5
22
 
23
  ## Model description
24
 
@@ -37,19 +35,14 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - optimizer: {'name': 'Adam', 'learning_rate': 4e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
41
  - training_precision: float32
42
 
43
  ### Training results
44
 
45
- | Train Loss | Train Binary Crossentropy | Validation Loss | Validation Binary Crossentropy | Epoch |
46
- |:----------:|:-------------------------:|:---------------:|:------------------------------:|:-----:|
47
- | 0.0607 | 0.6194 | 0.0411 | 0.6178 | 0 |
48
- | 0.0385 | 0.6219 | 0.0341 | 0.6174 | 1 |
49
- | 0.0319 | 0.5539 | 0.0290 | 0.5115 | 2 |
50
- | 0.0279 | 0.4860 | 0.0257 | 0.4198 | 3 |
51
- | 0.0252 | 0.4284 | 0.0236 | 0.3984 | 4 |
52
- | 0.0230 | 0.3795 | 0.0217 | 0.3411 | 5 |
53
 
54
 
55
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.0487
18
+ - Train Binary Crossentropy: 0.6401
19
+ - Epoch: 0
 
 
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - optimizer: {'name': 'Adam', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
39
  - training_precision: float32
40
 
41
  ### Training results
42
 
43
+ | Train Loss | Train Binary Crossentropy | Epoch |
44
+ |:----------:|:-------------------------:|:-----:|
45
+ | 0.0487 | 0.6401 | 0 |
 
 
 
 
 
46
 
47
 
48
  ### Framework versions
config.json CHANGED
@@ -10,67 +10,66 @@
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 256,
12
  "id2label": {
13
- "0": "admiration",
14
- "1": "amusement",
15
- "10": "disapproval",
16
- "11": "disgust",
17
- "12": "embarrassment",
18
- "13": "excitement",
19
- "14": "fear",
20
- "15": "gratitude",
21
- "16": "grief",
22
- "17": "joy",
23
- "18": "love",
24
- "19": "nervousness",
25
- "2": "anger",
26
- "20": "optimism",
27
- "21": "pride",
28
- "22": "realization",
29
- "23": "relief",
30
- "24": "remorse",
31
- "25": "sadness",
32
- "26": "surprise",
33
- "27": "neutral",
34
- "3": "annoyance",
35
- "4": "approval",
36
- "5": "caring",
37
- "6": "confusion",
38
- "7": "curiosity",
39
- "8": "desire",
40
- "9": "disappointment"
41
- },
42
  "initializer_range": 0.02,
43
  "intermediate_size": 1024,
44
  "label2id": {
45
- "admiration": 0,
46
- "amusement": 1,
47
- "anger": 2,
48
- "annoyance": 3,
49
- "approval": 4,
50
- "caring": 5,
51
- "confusion": 6,
52
- "curiosity": 7,
53
- "desire": 8,
54
- "disappointment": 9,
55
- "disapproval": 10,
56
- "disgust": 11,
57
- "embarrassment": 12,
58
- "excitement": 13,
59
- "fear": 14,
60
- "gratitude": 15,
61
- "grief": 16,
62
- "joy": 17,
63
- "love": 18,
64
- "nervousness": 19,
65
- "neutral": 27,
66
- "optimism": 20,
67
- "pride": 21,
68
- "realization": 22,
69
- "relief": 23,
70
- "remorse": 24,
71
- "sadness": 25,
72
- "surprise": 26,
73
- "neutral": 27
74
  },
75
  "layer_norm_eps": 1e-12,
76
  "max_position_embeddings": 512,
 
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 256,
12
  "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12",
26
+ "13": "LABEL_13",
27
+ "14": "LABEL_14",
28
+ "15": "LABEL_15",
29
+ "16": "LABEL_16",
30
+ "17": "LABEL_17",
31
+ "18": "LABEL_18",
32
+ "19": "LABEL_19",
33
+ "20": "LABEL_20",
34
+ "21": "LABEL_21",
35
+ "22": "LABEL_22",
36
+ "23": "LABEL_23",
37
+ "24": "LABEL_24",
38
+ "25": "LABEL_25",
39
+ "26": "LABEL_26",
40
+ "27": "LABEL_27"
41
+ },
42
  "initializer_range": 0.02,
43
  "intermediate_size": 1024,
44
  "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1,
47
+ "LABEL_10": 10,
48
+ "LABEL_11": 11,
49
+ "LABEL_12": 12,
50
+ "LABEL_13": 13,
51
+ "LABEL_14": 14,
52
+ "LABEL_15": 15,
53
+ "LABEL_16": 16,
54
+ "LABEL_17": 17,
55
+ "LABEL_18": 18,
56
+ "LABEL_19": 19,
57
+ "LABEL_2": 2,
58
+ "LABEL_20": 20,
59
+ "LABEL_21": 21,
60
+ "LABEL_22": 22,
61
+ "LABEL_23": 23,
62
+ "LABEL_24": 24,
63
+ "LABEL_25": 25,
64
+ "LABEL_26": 26,
65
+ "LABEL_27": 27,
66
+ "LABEL_3": 3,
67
+ "LABEL_4": 4,
68
+ "LABEL_5": 5,
69
+ "LABEL_6": 6,
70
+ "LABEL_7": 7,
71
+ "LABEL_8": 8,
72
+ "LABEL_9": 9
 
73
  },
74
  "layer_norm_eps": 1e-12,
75
  "max_position_embeddings": 512,
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d352b498685b35b17374cafd396f6b33a9b6a4800f5b82db3c0a4a8eb7dba14
3
  size 51177784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c2deccc09f6176bbe28ef24fc4d09c734ccee544adbdc59a041081be0e060e
3
  size 51177784