gentilrenard
commited on
Commit
•
c2c3b95
1
Parent(s):
5e2226d
multi-e5-small_lmd-comments_v1
Browse files- README.md +110 -0
- config.json +37 -0
- model.safetensors +3 -0
- 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
|