hcene/Camembert-xnli
Browse files- README.md +121 -0
- config.json +39 -0
- logs/events.out.tfevents.1709397374.3876b023f36e.865.0 +3 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: mtheo/camembert-base-xnli
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
model-index:
|
11 |
+
- name: legal-data-mDEBERTa-V3-base-mnli-xnli
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# legal-data-mDEBERTa-V3-base-mnli-xnli
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [mtheo/camembert-base-xnli](https://huggingface.co/mtheo/camembert-base-xnli) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.7972
|
23 |
+
- Accuracy: 0.7706
|
24 |
+
- Precision: 0.7891
|
25 |
+
- Recall: 0.7711
|
26 |
+
- F1: 0.7697
|
27 |
+
- Ratio: 0.3154
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 20
|
48 |
+
- eval_batch_size: 20
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
53 |
+
- lr_scheduler_warmup_steps: 4
|
54 |
+
- num_epochs: 15
|
55 |
+
- label_smoothing_factor: 0.1
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Ratio |
|
60 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
|
61 |
+
| 0.9937 | 0.17 | 10 | 0.8509 | 0.6093 | 0.7022 | 0.6086 | 0.6168 | 0.1935 |
|
62 |
+
| 0.8433 | 0.34 | 20 | 0.7131 | 0.6667 | 0.6703 | 0.6687 | 0.6666 | 0.3262 |
|
63 |
+
| 0.8683 | 0.52 | 30 | 0.7101 | 0.7312 | 0.7350 | 0.7324 | 0.7324 | 0.3262 |
|
64 |
+
| 0.8536 | 0.69 | 40 | 0.7542 | 0.6989 | 0.7152 | 0.6999 | 0.7053 | 0.3011 |
|
65 |
+
| 0.7964 | 0.86 | 50 | 0.7249 | 0.7670 | 0.7773 | 0.7677 | 0.7630 | 0.3297 |
|
66 |
+
| 0.7651 | 1.03 | 60 | 0.8253 | 0.7455 | 0.7517 | 0.7465 | 0.7450 | 0.3262 |
|
67 |
+
| 0.7658 | 1.21 | 70 | 0.8282 | 0.6953 | 0.7366 | 0.6956 | 0.7030 | 0.2688 |
|
68 |
+
| 0.7297 | 1.38 | 80 | 0.8694 | 0.7634 | 0.7771 | 0.7641 | 0.7612 | 0.3226 |
|
69 |
+
| 0.7726 | 1.55 | 90 | 0.7898 | 0.7097 | 0.7112 | 0.7112 | 0.7111 | 0.3297 |
|
70 |
+
| 0.7107 | 1.72 | 100 | 0.8279 | 0.7599 | 0.7642 | 0.7608 | 0.7589 | 0.3297 |
|
71 |
+
| 0.7204 | 1.9 | 110 | 0.9353 | 0.7240 | 0.7728 | 0.7240 | 0.7279 | 0.2724 |
|
72 |
+
| 0.7241 | 2.07 | 120 | 0.7903 | 0.7527 | 0.7818 | 0.7530 | 0.7531 | 0.3011 |
|
73 |
+
| 0.6683 | 2.24 | 130 | 0.8139 | 0.7384 | 0.7931 | 0.7382 | 0.7397 | 0.2760 |
|
74 |
+
| 0.6832 | 2.41 | 140 | 0.8339 | 0.7993 | 0.8268 | 0.7996 | 0.7913 | 0.3297 |
|
75 |
+
| 0.7397 | 2.59 | 150 | 0.8309 | 0.7849 | 0.7997 | 0.7855 | 0.7801 | 0.3297 |
|
76 |
+
| 0.6945 | 2.76 | 160 | 0.7860 | 0.7240 | 0.7259 | 0.7253 | 0.7247 | 0.3297 |
|
77 |
+
| 0.7067 | 2.93 | 170 | 0.7046 | 0.7957 | 0.8152 | 0.7962 | 0.7898 | 0.3297 |
|
78 |
+
| 0.6759 | 3.1 | 180 | 0.7465 | 0.7634 | 0.7703 | 0.7643 | 0.7611 | 0.3297 |
|
79 |
+
| 0.6673 | 3.28 | 190 | 0.8461 | 0.8029 | 0.8234 | 0.8033 | 0.7972 | 0.3297 |
|
80 |
+
| 0.6748 | 3.45 | 200 | 0.8701 | 0.8065 | 0.8354 | 0.8068 | 0.7987 | 0.3297 |
|
81 |
+
| 0.7638 | 3.62 | 210 | 0.7501 | 0.8136 | 0.8521 | 0.8138 | 0.8043 | 0.3297 |
|
82 |
+
| 0.6426 | 3.79 | 220 | 0.7165 | 0.8100 | 0.8379 | 0.8103 | 0.8029 | 0.3297 |
|
83 |
+
| 0.6569 | 3.97 | 230 | 0.7244 | 0.8100 | 0.8415 | 0.8103 | 0.8020 | 0.3297 |
|
84 |
+
| 0.7068 | 4.14 | 240 | 0.7448 | 0.8100 | 0.8499 | 0.8102 | 0.8000 | 0.3297 |
|
85 |
+
| 0.6544 | 4.31 | 250 | 0.8241 | 0.8065 | 0.8476 | 0.8066 | 0.7957 | 0.3297 |
|
86 |
+
| 0.6261 | 4.48 | 260 | 0.8409 | 0.7634 | 0.7692 | 0.7643 | 0.7617 | 0.3297 |
|
87 |
+
| 0.6428 | 4.66 | 270 | 0.7887 | 0.7491 | 0.7528 | 0.7501 | 0.7484 | 0.3297 |
|
88 |
+
| 0.657 | 4.83 | 280 | 0.7534 | 0.7706 | 0.7791 | 0.7714 | 0.7677 | 0.3297 |
|
89 |
+
| 0.6895 | 5.0 | 290 | 0.7863 | 0.8100 | 0.8379 | 0.8103 | 0.8029 | 0.3297 |
|
90 |
+
| 0.6422 | 5.17 | 300 | 0.7908 | 0.8136 | 0.8439 | 0.8139 | 0.8062 | 0.3297 |
|
91 |
+
| 0.5933 | 5.34 | 310 | 0.8330 | 0.7885 | 0.8031 | 0.7891 | 0.7869 | 0.3226 |
|
92 |
+
| 0.5863 | 5.52 | 320 | 0.8494 | 0.7527 | 0.7598 | 0.7536 | 0.7535 | 0.3226 |
|
93 |
+
| 0.6787 | 5.69 | 330 | 0.7748 | 0.7742 | 0.7823 | 0.7750 | 0.7716 | 0.3297 |
|
94 |
+
| 0.6761 | 5.86 | 340 | 0.7256 | 0.7814 | 0.7929 | 0.7820 | 0.7775 | 0.3297 |
|
95 |
+
| 0.6974 | 6.03 | 350 | 0.7711 | 0.8029 | 0.8208 | 0.8033 | 0.7980 | 0.3297 |
|
96 |
+
| 0.6083 | 6.21 | 360 | 0.8435 | 0.7993 | 0.8191 | 0.7997 | 0.7951 | 0.3262 |
|
97 |
+
| 0.5897 | 6.38 | 370 | 0.8773 | 0.7849 | 0.8124 | 0.7852 | 0.7831 | 0.3118 |
|
98 |
+
| 0.6076 | 6.55 | 380 | 0.8255 | 0.7634 | 0.7683 | 0.7644 | 0.7623 | 0.3297 |
|
99 |
+
| 0.6709 | 6.72 | 390 | 0.7865 | 0.7527 | 0.7551 | 0.7538 | 0.7530 | 0.3297 |
|
100 |
+
| 0.7063 | 6.9 | 400 | 0.7898 | 0.8029 | 0.8234 | 0.8033 | 0.7972 | 0.3297 |
|
101 |
+
| 0.6804 | 7.07 | 410 | 0.7804 | 0.7921 | 0.8152 | 0.7925 | 0.7848 | 0.3297 |
|
102 |
+
| 0.6227 | 7.24 | 420 | 0.7515 | 0.7706 | 0.7778 | 0.7714 | 0.7683 | 0.3297 |
|
103 |
+
| 0.6482 | 7.41 | 430 | 0.7758 | 0.7670 | 0.7725 | 0.7679 | 0.7656 | 0.3297 |
|
104 |
+
| 0.6072 | 7.59 | 440 | 0.8077 | 0.7706 | 0.7792 | 0.7714 | 0.7693 | 0.3262 |
|
105 |
+
| 0.5695 | 7.76 | 450 | 0.8460 | 0.7921 | 0.8068 | 0.7926 | 0.7892 | 0.3262 |
|
106 |
+
| 0.6097 | 7.93 | 460 | 0.7856 | 0.7993 | 0.8191 | 0.7997 | 0.7951 | 0.3262 |
|
107 |
+
| 0.5591 | 8.1 | 470 | 0.7812 | 0.8136 | 0.8447 | 0.8138 | 0.8074 | 0.3262 |
|
108 |
+
| 0.5573 | 8.28 | 480 | 0.7249 | 0.7849 | 0.7930 | 0.7857 | 0.7828 | 0.3297 |
|
109 |
+
| 0.6128 | 8.45 | 490 | 0.7245 | 0.7921 | 0.8006 | 0.7928 | 0.7901 | 0.3297 |
|
110 |
+
| 0.6072 | 8.62 | 500 | 0.7732 | 0.7885 | 0.8038 | 0.7891 | 0.7852 | 0.3262 |
|
111 |
+
| 0.6276 | 8.79 | 510 | 0.8017 | 0.7885 | 0.8038 | 0.7891 | 0.7852 | 0.3262 |
|
112 |
+
| 0.647 | 8.97 | 520 | 0.7998 | 0.7885 | 0.8038 | 0.7891 | 0.7852 | 0.3262 |
|
113 |
+
| 0.5924 | 9.14 | 530 | 0.7972 | 0.7706 | 0.7891 | 0.7711 | 0.7697 | 0.3154 |
|
114 |
+
|
115 |
+
|
116 |
+
### Framework versions
|
117 |
+
|
118 |
+
- Transformers 4.39.0.dev0
|
119 |
+
- Pytorch 2.1.0+cu121
|
120 |
+
- Datasets 2.18.0
|
121 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mtheo/camembert-base-xnli",
|
3 |
+
"architectures": [
|
4 |
+
"CamembertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 5,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 6,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "entailment",
|
16 |
+
"1": "neutral",
|
17 |
+
"2": "contradiction"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"contradiction": 2,
|
23 |
+
"entailment": 0,
|
24 |
+
"neutral": 1
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-05,
|
27 |
+
"max_position_embeddings": 514,
|
28 |
+
"model_type": "camembert",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"output_past": true,
|
32 |
+
"pad_token_id": 1,
|
33 |
+
"position_embedding_type": "absolute",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.39.0.dev0",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 32178
|
39 |
+
}
|
logs/events.out.tfevents.1709397374.3876b023f36e.865.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b39a2ec51f6d10569219d616529708bcf665d21e455d203e5ee765c2aabdf9d
|
3 |
+
size 44524
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6533a6a80775f845dfcf9f99bb96929d63dc0ace1ce66976af95bd104d9612c
|
3 |
+
size 443052636
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bff2ea34f511004577040efc219afd075aae1792750405805bfb85761e3422d7
|
3 |
+
size 4920
|