gentilrenard commited on
Commit
c2c3b95
1 Parent(s): 5e2226d

multi-e5-small_lmd-comments_v1

Browse files
Files changed (4) hide show
  1. README.md +110 -0
  2. config.json +37 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: intfloat/multilingual-e5-small
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - f1
8
+ - accuracy
9
+ model-index:
10
+ - name: multi-e5-small_lmd-comments_v1
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # multi-e5-small_lmd-comments_v1
18
+
19
+ This model is a fine-tuned version of [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.9808
22
+ - F1: 0.7036
23
+ - Accuracy: 0.7122
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 2
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
55
+ | 1.0969 | 0.04 | 100 | 1.0991 | 0.4109 | 0.4964 |
56
+ | 1.0764 | 0.08 | 200 | 1.0768 | 0.5217 | 0.5971 |
57
+ | 0.955 | 0.12 | 300 | 0.9313 | 0.5802 | 0.6691 |
58
+ | 0.8137 | 0.17 | 400 | 0.8927 | 0.5864 | 0.6475 |
59
+ | 0.7837 | 0.21 | 500 | 0.8711 | 0.6238 | 0.6475 |
60
+ | 0.7234 | 0.25 | 600 | 0.9953 | 0.5641 | 0.6475 |
61
+ | 0.6983 | 0.29 | 700 | 0.9111 | 0.6226 | 0.6475 |
62
+ | 0.6574 | 0.33 | 800 | 0.8557 | 0.6686 | 0.6835 |
63
+ | 0.6653 | 0.37 | 900 | 0.7925 | 0.7087 | 0.7122 |
64
+ | 0.6444 | 0.41 | 1000 | 0.8338 | 0.7056 | 0.7122 |
65
+ | 0.6155 | 0.46 | 1100 | 0.8339 | 0.7257 | 0.7338 |
66
+ | 0.5726 | 0.5 | 1200 | 0.8078 | 0.7140 | 0.7194 |
67
+ | 0.6279 | 0.54 | 1300 | 0.9534 | 0.6917 | 0.7050 |
68
+ | 0.6083 | 0.58 | 1400 | 0.9515 | 0.6914 | 0.7050 |
69
+ | 0.5525 | 0.62 | 1500 | 0.9281 | 0.6846 | 0.7050 |
70
+ | 0.6849 | 0.66 | 1600 | 0.8352 | 0.6917 | 0.7050 |
71
+ | 0.5924 | 0.7 | 1700 | 1.0702 | 0.6602 | 0.6906 |
72
+ | 0.5614 | 0.75 | 1800 | 0.9689 | 0.6801 | 0.6978 |
73
+ | 0.5936 | 0.79 | 1900 | 1.0179 | 0.6896 | 0.7050 |
74
+ | 0.5582 | 0.83 | 2000 | 0.8858 | 0.7320 | 0.7410 |
75
+ | 0.5479 | 0.87 | 2100 | 0.9373 | 0.7030 | 0.7122 |
76
+ | 0.6278 | 0.91 | 2200 | 0.8694 | 0.6858 | 0.6978 |
77
+ | 0.4819 | 0.95 | 2300 | 0.9440 | 0.7074 | 0.7194 |
78
+ | 0.5425 | 0.99 | 2400 | 1.0661 | 0.6765 | 0.6906 |
79
+ | 0.5804 | 1.04 | 2500 | 0.8904 | 0.7189 | 0.7266 |
80
+ | 0.5025 | 1.08 | 2600 | 1.0105 | 0.6886 | 0.7050 |
81
+ | 0.5148 | 1.12 | 2700 | 0.9934 | 0.7076 | 0.7194 |
82
+ | 0.5359 | 1.16 | 2800 | 0.9249 | 0.7291 | 0.7410 |
83
+ | 0.5002 | 1.2 | 2900 | 0.7503 | 0.7047 | 0.7050 |
84
+ | 0.4563 | 1.24 | 3000 | 0.8149 | 0.7230 | 0.7266 |
85
+ | 0.4837 | 1.28 | 3100 | 0.8956 | 0.7125 | 0.7194 |
86
+ | 0.4486 | 1.33 | 3200 | 0.9013 | 0.7110 | 0.7194 |
87
+ | 0.4721 | 1.37 | 3300 | 1.0545 | 0.7142 | 0.7266 |
88
+ | 0.5482 | 1.41 | 3400 | 1.0139 | 0.7014 | 0.7122 |
89
+ | 0.4488 | 1.45 | 3500 | 0.9427 | 0.7162 | 0.7266 |
90
+ | 0.4859 | 1.49 | 3600 | 1.1337 | 0.7074 | 0.7194 |
91
+ | 0.504 | 1.53 | 3700 | 1.0299 | 0.7178 | 0.7266 |
92
+ | 0.4555 | 1.57 | 3800 | 0.8830 | 0.7273 | 0.7338 |
93
+ | 0.502 | 1.62 | 3900 | 1.0340 | 0.7142 | 0.7266 |
94
+ | 0.5131 | 1.66 | 4000 | 1.0997 | 0.7031 | 0.7194 |
95
+ | 0.5208 | 1.7 | 4100 | 1.0845 | 0.7025 | 0.7194 |
96
+ | 0.4329 | 1.74 | 4200 | 1.0553 | 0.7132 | 0.7266 |
97
+ | 0.4612 | 1.78 | 4300 | 1.0458 | 0.7074 | 0.7194 |
98
+ | 0.4857 | 1.82 | 4400 | 0.9425 | 0.7120 | 0.7194 |
99
+ | 0.4986 | 1.86 | 4500 | 0.9965 | 0.7237 | 0.7338 |
100
+ | 0.4066 | 1.91 | 4600 | 0.9520 | 0.7041 | 0.7122 |
101
+ | 0.4638 | 1.95 | 4700 | 0.9558 | 0.6979 | 0.7050 |
102
+ | 0.4541 | 1.99 | 4800 | 0.9808 | 0.7036 | 0.7122 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - Transformers 4.38.1
108
+ - Pytorch 2.1.2
109
+ - Datasets 2.1.0
110
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "intfloat/multilingual-e5-small",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1536,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "tokenizer_class": "XLMRobertaTokenizer",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.38.1",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 250037
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3944d39bd4625b103cbb80326df8dbfe8fe15106b10440ca0e82ca479e39f13e
3
+ size 470643204
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ade1cdc794601d6ea9cd9ef3f8970ee77bc5cde95e5de33b5b150e776851a2e7
3
+ size 4856