Hugging Face's logo

luigisaetta
/
sentiment_ita

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
luigisaetta commited on
Commit
d151a08
•
1 Parent(s): 792c12b

sentiment_ita

Browse files
Files changed (5) hide show
  1. README.md +54 -30
  2. model.safetensors +1 -1
  3. runs/Nov25_13-40-25_31107af71a91/events.out.tfevents.1700919629.31107af71a91.6393.0 +3 -0
  4. tokenizer.json +2 -16
  5. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.6697530864197531
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [neuraly/bert-base-italian-cased-sentiment](https://huggingface.co/neuraly/bert-base-italian-cased-sentiment) on the tweet_sentiment_multilingual dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 2.7883
36
- - Accuracy: 0.6698
37
 
38
  ## Model description
39
 
@@ -52,9 +52,9 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 4e-05
56
- - train_batch_size: 16
57
- - eval_batch_size: 16
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
@@ -65,30 +65,54 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 1.4695 | 0.57 | 100 | 1.0286 | 0.6173 |
69
- | 0.7416 | 1.15 | 200 | 0.7852 | 0.6451 |
70
- | 0.6165 | 1.72 | 300 | 0.7865 | 0.6574 |
71
- | 0.5304 | 2.3 | 400 | 0.8629 | 0.6821 |
72
- | 0.4296 | 2.87 | 500 | 0.8318 | 0.6914 |
73
- | 0.282 | 3.45 | 600 | 1.0587 | 0.6914 |
74
- | 0.2344 | 4.02 | 700 | 1.3293 | 0.6574 |
75
- | 0.1327 | 4.6 | 800 | 1.5493 | 0.6728 |
76
- | 0.1603 | 5.17 | 900 | 1.8099 | 0.6605 |
77
- | 0.1048 | 5.75 | 1000 | 1.7567 | 0.6698 |
78
- | 0.086 | 6.32 | 1100 | 2.1221 | 0.6574 |
79
- | 0.0439 | 6.9 | 1200 | 2.1960 | 0.6821 |
80
- | 0.0224 | 7.47 | 1300 | 2.3251 | 0.6821 |
81
- | 0.0205 | 8.05 | 1400 | 2.4668 | 0.6790 |
82
- | 0.0195 | 8.62 | 1500 | 2.4558 | 0.6728 |
83
- | 0.0137 | 9.2 | 1600 | 2.7194 | 0.6698 |
84
- | 0.0046 | 9.77 | 1700 | 2.7665 | 0.6728 |
85
- | 0.0163 | 10.34 | 1800 | 2.7496 | 0.6574 |
86
- | 0.0059 | 10.92 | 1900 | 2.6633 | 0.6667 |
87
- | 0.0059 | 11.49 | 2000 | 2.7200 | 0.6636 |
88
- | 0.0035 | 12.07 | 2100 | 2.8186 | 0.6636 |
89
- | 0.0002 | 12.64 | 2200 | 2.8109 | 0.6636 |
90
- | 0.0001 | 13.22 | 2300 | 2.8181 | 0.6667 |
91
- | 0.0015 | 13.79 | 2400 | 2.7883 | 0.6698 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92
 
93
 
94
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6975308641975309
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [neuraly/bert-base-italian-cased-sentiment](https://huggingface.co/neuraly/bert-base-italian-cased-sentiment) on the tweet_sentiment_multilingual dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 2.6373
36
+ - Accuracy: 0.6975
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 2e-05
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.7447 | 0.29 | 100 | 1.3167 | 0.6173 |
69
+ | 1.0082 | 0.58 | 200 | 0.9060 | 0.6296 |
70
+ | 0.7784 | 0.86 | 300 | 0.7883 | 0.6481 |
71
+ | 0.6812 | 1.15 | 400 | 0.7989 | 0.6667 |
72
+ | 0.5648 | 1.44 | 500 | 0.8325 | 0.6728 |
73
+ | 0.5937 | 1.73 | 600 | 0.7558 | 0.7222 |
74
+ | 0.6003 | 2.02 | 700 | 0.7908 | 0.6944 |
75
+ | 0.3699 | 2.31 | 800 | 1.0595 | 0.7099 |
76
+ | 0.4165 | 2.59 | 900 | 0.8819 | 0.6852 |
77
+ | 0.419 | 2.88 | 1000 | 0.8979 | 0.6852 |
78
+ | 0.2812 | 3.17 | 1100 | 1.2963 | 0.6852 |
79
+ | 0.1934 | 3.46 | 1200 | 1.6792 | 0.6728 |
80
+ | 0.2119 | 3.75 | 1300 | 1.7649 | 0.6759 |
81
+ | 0.2201 | 4.03 | 1400 | 1.7034 | 0.6852 |
82
+ | 0.0836 | 4.32 | 1500 | 1.8075 | 0.6759 |
83
+ | 0.1281 | 4.61 | 1600 | 1.7611 | 0.6636 |
84
+ | 0.1111 | 4.9 | 1700 | 1.8872 | 0.6728 |
85
+ | 0.0488 | 5.19 | 1800 | 2.0455 | 0.6790 |
86
+ | 0.0902 | 5.48 | 1900 | 1.9040 | 0.7006 |
87
+ | 0.0204 | 5.76 | 2000 | 2.1793 | 0.6790 |
88
+ | 0.0478 | 6.05 | 2100 | 2.1681 | 0.6636 |
89
+ | 0.0226 | 6.34 | 2200 | 2.1877 | 0.6944 |
90
+ | 0.008 | 6.63 | 2300 | 2.1935 | 0.7068 |
91
+ | 0.0116 | 6.92 | 2400 | 2.3427 | 0.6852 |
92
+ | 0.0236 | 7.2 | 2500 | 2.4266 | 0.6698 |
93
+ | 0.0091 | 7.49 | 2600 | 2.2203 | 0.7130 |
94
+ | 0.0075 | 7.78 | 2700 | 2.2581 | 0.7130 |
95
+ | 0.0102 | 8.07 | 2800 | 2.2857 | 0.7037 |
96
+ | 0.0031 | 8.36 | 2900 | 2.4401 | 0.6790 |
97
+ | 0.0063 | 8.65 | 3000 | 2.3777 | 0.6883 |
98
+ | 0.0086 | 8.93 | 3100 | 2.4918 | 0.6852 |
99
+ | 0.0051 | 9.22 | 3200 | 2.4327 | 0.6944 |
100
+ | 0.0133 | 9.51 | 3300 | 2.4651 | 0.6883 |
101
+ | 0.0121 | 9.8 | 3400 | 2.5034 | 0.6975 |
102
+ | 0.0081 | 10.09 | 3500 | 2.5176 | 0.6944 |
103
+ | 0.0001 | 10.37 | 3600 | 2.5281 | 0.7068 |
104
+ | 0.0016 | 10.66 | 3700 | 2.5443 | 0.6975 |
105
+ | 0.0001 | 10.95 | 3800 | 2.6249 | 0.7006 |
106
+ | 0.0001 | 11.24 | 3900 | 2.5790 | 0.6821 |
107
+ | 0.0001 | 11.53 | 4000 | 2.6509 | 0.6914 |
108
+ | 0.0001 | 11.82 | 4100 | 2.5943 | 0.6944 |
109
+ | 0.014 | 12.1 | 4200 | 2.5885 | 0.6975 |
110
+ | 0.0001 | 12.39 | 4300 | 2.6308 | 0.6944 |
111
+ | 0.0001 | 12.68 | 4400 | 2.6134 | 0.6883 |
112
+ | 0.0024 | 12.97 | 4500 | 2.6108 | 0.6975 |
113
+ | 0.0004 | 13.26 | 4600 | 2.6135 | 0.6944 |
114
+ | 0.0028 | 13.54 | 4700 | 2.6475 | 0.7006 |
115
+ | 0.0001 | 13.83 | 4800 | 2.6373 | 0.6975 |
116
 
117
 
118
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:881d634f31853bacd1703c1e3109407d213e550f08b275ad892b52bfeafb97df
3
  size 442815492
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd2a889d1dc44e567877e7eb1a509f984bc1a4b5726f3af9f5e9b9c44241963
3
  size 442815492
runs/Nov25_13-40-25_31107af71a91/events.out.tfevents.1700919629.31107af71a91.6393.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33ae25093a75e5cd997788b8a69bd4c174add64a2dbdd7f78e4296e4ccc1e966
3
+ size 27799
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 512
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 0,
16
- "pad_type_id": 0,
17
- "pad_token": "[PAD]"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ffc2db6e0634a2c337ecdb0ec1817026893fa5b01f5c747c1fb0e048779c7a5
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d5b5e7247daf9bf48a935c94ae2326ef7c7edd1763c3a06aeacd87c3f2c9e8
3
  size 4155