End of training
Browse files- README.md +73 -0
- config.json +75 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-multilingual-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: results
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# results
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.5702
|
24 |
+
- Accuracy: 0.7894
|
25 |
+
- Precision: 0.7913
|
26 |
+
- Recall: 0.7040
|
27 |
+
- F1: 0.7144
|
28 |
+
- Hamming Loss: 0.2106
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 1e-05
|
48 |
+
- train_batch_size: 16
|
49 |
+
- eval_batch_size: 32
|
50 |
+
- seed: 42
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- num_epochs: 8
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Hamming Loss |
|
58 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|:------------:|
|
59 |
+
| 1.435 | 1.0 | 1744 | 1.2662 | 0.5627 | 0.6403 | 0.4392 | 0.4707 | 0.4373 |
|
60 |
+
| 1.19 | 2.0 | 3488 | 1.0175 | 0.6358 | 0.6749 | 0.5311 | 0.5571 | 0.3642 |
|
61 |
+
| 0.9496 | 3.0 | 5232 | 0.8298 | 0.6934 | 0.7166 | 0.5916 | 0.6132 | 0.3066 |
|
62 |
+
| 0.8226 | 4.0 | 6976 | 0.7224 | 0.7306 | 0.7447 | 0.6371 | 0.6561 | 0.2694 |
|
63 |
+
| 0.7113 | 5.0 | 8720 | 0.6609 | 0.7514 | 0.7628 | 0.6583 | 0.6742 | 0.2486 |
|
64 |
+
| 0.6497 | 6.0 | 10464 | 0.6153 | 0.7724 | 0.7717 | 0.6904 | 0.6980 | 0.2276 |
|
65 |
+
| 0.5997 | 7.0 | 12208 | 0.5822 | 0.7863 | 0.7945 | 0.6967 | 0.7105 | 0.2137 |
|
66 |
+
| 0.571 | 8.0 | 13952 | 0.5702 | 0.7894 | 0.7913 | 0.7040 | 0.7144 | 0.2106 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.32.0
|
72 |
+
- Pytorch 2.0.1+cu118
|
73 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-multilingual-cased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"BertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"attention_probs_dropout_prob": 0.1,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"dim": 768,
|
11 |
+
"dropout": 0.1,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dim": 3072,
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0",
|
18 |
+
"1": "LABEL_1",
|
19 |
+
"2": "LABEL_2",
|
20 |
+
"3": "LABEL_3",
|
21 |
+
"4": "LABEL_4",
|
22 |
+
"5": "LABEL_5",
|
23 |
+
"6": "LABEL_6",
|
24 |
+
"7": "LABEL_7",
|
25 |
+
"8": "LABEL_8",
|
26 |
+
"9": "LABEL_9",
|
27 |
+
"10": "LABEL_10",
|
28 |
+
"11": "LABEL_11",
|
29 |
+
"12": "LABEL_12",
|
30 |
+
"13": "LABEL_13",
|
31 |
+
"14": "LABEL_14",
|
32 |
+
"15": "LABEL_15",
|
33 |
+
"16": "LABEL_16"
|
34 |
+
},
|
35 |
+
"initializer_range": 0.02,
|
36 |
+
"intermediate_size": 3072,
|
37 |
+
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1,
|
40 |
+
"LABEL_10": 10,
|
41 |
+
"LABEL_11": 11,
|
42 |
+
"LABEL_12": 12,
|
43 |
+
"LABEL_13": 13,
|
44 |
+
"LABEL_14": 14,
|
45 |
+
"LABEL_15": 15,
|
46 |
+
"LABEL_16": 16,
|
47 |
+
"LABEL_2": 2,
|
48 |
+
"LABEL_3": 3,
|
49 |
+
"LABEL_4": 4,
|
50 |
+
"LABEL_5": 5,
|
51 |
+
"LABEL_6": 6,
|
52 |
+
"LABEL_7": 7,
|
53 |
+
"LABEL_8": 8,
|
54 |
+
"LABEL_9": 9
|
55 |
+
},
|
56 |
+
"layer_norm_eps": 1e-12,
|
57 |
+
"max_position_embeddings": 512,
|
58 |
+
"model_type": "bert",
|
59 |
+
"n_heads": 12,
|
60 |
+
"n_layers": 6,
|
61 |
+
"num_attention_heads": 12,
|
62 |
+
"num_hidden_layers": 12,
|
63 |
+
"output_past": true,
|
64 |
+
"pad_token_id": 0,
|
65 |
+
"position_embedding_type": "absolute",
|
66 |
+
"qa_dropout": 0.1,
|
67 |
+
"seq_classif_dropout": 0.2,
|
68 |
+
"sinusoidal_pos_embds": false,
|
69 |
+
"tie_weights_": true,
|
70 |
+
"torch_dtype": "float32",
|
71 |
+
"transformers_version": "4.32.0",
|
72 |
+
"type_vocab_size": 2,
|
73 |
+
"use_cache": true,
|
74 |
+
"vocab_size": 119547
|
75 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a849a5b2949605589be0557b54853783698c1b9f3b12d433b7758fb42fb63e7
|
3 |
+
size 709171433
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d82f0d5b7c498660217383e8681cc5445f60b5d675f5c667d81d5bf04b205568
|
3 |
+
size 4027
|