End of training
Browse files- README.md +106 -0
- config.json +64 -0
- model.safetensors +3 -0
- runs/Jun06_13-45-59_ubuntu-System-Product-Name/events.out.tfevents.1717652760.ubuntu-System-Product-Name.207770.0 +3 -0
- runs/Jun06_13-49-07_ubuntu-System-Product-Name/events.out.tfevents.1717652949.ubuntu-System-Product-Name.208270.0 +3 -0
- runs/Jun06_13-49-07_ubuntu-System-Product-Name/events.out.tfevents.1717659242.ubuntu-System-Product-Name.208270.1 +3 -0
- special_tokens_map.json +19 -0
- tokenizer.json +0 -0
- tokenizer_config.json +93 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: xlnet/xlnet-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- f1
|
8 |
+
model-index:
|
9 |
+
- name: xlnet-base-cased-airlines-news-multi-label-8-actions
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# xlnet-base-cased-airlines-news-multi-label-8-actions
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [xlnet/xlnet-base-cased](https://huggingface.co/xlnet/xlnet-base-cased) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2041
|
21 |
+
- F1: 0.9254
|
22 |
+
- Jaccard: 0.6493
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 9e-05
|
42 |
+
- train_batch_size: 32
|
43 |
+
- eval_batch_size: 32
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_steps: 150
|
48 |
+
- num_epochs: 45
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Jaccard |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
54 |
+
| No log | 1.0 | 57 | 0.4153 | 0.8352 | 0.3850 |
|
55 |
+
| No log | 2.0 | 114 | 0.3085 | 0.8357 | 0.3850 |
|
56 |
+
| No log | 3.0 | 171 | 0.2791 | 0.8685 | 0.3982 |
|
57 |
+
| No log | 4.0 | 228 | 0.2607 | 0.8726 | 0.4550 |
|
58 |
+
| No log | 5.0 | 285 | 0.2476 | 0.8898 | 0.4971 |
|
59 |
+
| No log | 6.0 | 342 | 0.2372 | 0.8933 | 0.5184 |
|
60 |
+
| No log | 7.0 | 399 | 0.2296 | 0.8986 | 0.5645 |
|
61 |
+
| No log | 8.0 | 456 | 0.2260 | 0.9049 | 0.5690 |
|
62 |
+
| 0.3101 | 9.0 | 513 | 0.2234 | 0.9047 | 0.5715 |
|
63 |
+
| 0.3101 | 10.0 | 570 | 0.2171 | 0.9149 | 0.6058 |
|
64 |
+
| 0.3101 | 11.0 | 627 | 0.2152 | 0.9123 | 0.5970 |
|
65 |
+
| 0.3101 | 12.0 | 684 | 0.2122 | 0.9141 | 0.6014 |
|
66 |
+
| 0.3101 | 13.0 | 741 | 0.2100 | 0.9197 | 0.6239 |
|
67 |
+
| 0.3101 | 14.0 | 798 | 0.2096 | 0.9163 | 0.6169 |
|
68 |
+
| 0.3101 | 15.0 | 855 | 0.2097 | 0.9202 | 0.6412 |
|
69 |
+
| 0.3101 | 16.0 | 912 | 0.2067 | 0.9231 | 0.6405 |
|
70 |
+
| 0.3101 | 17.0 | 969 | 0.2046 | 0.9230 | 0.6368 |
|
71 |
+
| 0.2256 | 18.0 | 1026 | 0.2040 | 0.9241 | 0.6486 |
|
72 |
+
| 0.2256 | 19.0 | 1083 | 0.2031 | 0.9253 | 0.6449 |
|
73 |
+
| 0.2256 | 20.0 | 1140 | 0.2022 | 0.9227 | 0.6515 |
|
74 |
+
| 0.2256 | 21.0 | 1197 | 0.2041 | 0.9240 | 0.6493 |
|
75 |
+
| 0.2256 | 22.0 | 1254 | 0.2041 | 0.9254 | 0.6493 |
|
76 |
+
| 0.2256 | 23.0 | 1311 | 0.2013 | 0.9210 | 0.6471 |
|
77 |
+
| 0.2256 | 24.0 | 1368 | 0.2013 | 0.9234 | 0.6515 |
|
78 |
+
| 0.2256 | 25.0 | 1425 | 0.2015 | 0.9234 | 0.6397 |
|
79 |
+
| 0.2256 | 26.0 | 1482 | 0.1999 | 0.9235 | 0.6574 |
|
80 |
+
| 0.2117 | 27.0 | 1539 | 0.2000 | 0.9237 | 0.6523 |
|
81 |
+
| 0.2117 | 28.0 | 1596 | 0.1998 | 0.9239 | 0.6361 |
|
82 |
+
| 0.2117 | 29.0 | 1653 | 0.1987 | 0.9211 | 0.6442 |
|
83 |
+
| 0.2117 | 30.0 | 1710 | 0.1988 | 0.9230 | 0.6530 |
|
84 |
+
| 0.2117 | 31.0 | 1767 | 0.1997 | 0.9235 | 0.6589 |
|
85 |
+
| 0.2117 | 32.0 | 1824 | 0.1995 | 0.9228 | 0.6582 |
|
86 |
+
| 0.2117 | 33.0 | 1881 | 0.1982 | 0.9197 | 0.6434 |
|
87 |
+
| 0.2117 | 34.0 | 1938 | 0.1983 | 0.9209 | 0.6508 |
|
88 |
+
| 0.2117 | 35.0 | 1995 | 0.1985 | 0.9217 | 0.6538 |
|
89 |
+
| 0.2057 | 36.0 | 2052 | 0.1993 | 0.9247 | 0.6597 |
|
90 |
+
| 0.2057 | 37.0 | 2109 | 0.1981 | 0.9217 | 0.6538 |
|
91 |
+
| 0.2057 | 38.0 | 2166 | 0.1977 | 0.9238 | 0.6597 |
|
92 |
+
| 0.2057 | 39.0 | 2223 | 0.1974 | 0.9229 | 0.6560 |
|
93 |
+
| 0.2057 | 40.0 | 2280 | 0.1978 | 0.9223 | 0.6538 |
|
94 |
+
| 0.2057 | 41.0 | 2337 | 0.1976 | 0.9217 | 0.6538 |
|
95 |
+
| 0.2057 | 42.0 | 2394 | 0.1976 | 0.9229 | 0.6552 |
|
96 |
+
| 0.2057 | 43.0 | 2451 | 0.1975 | 0.9229 | 0.6552 |
|
97 |
+
| 0.2023 | 44.0 | 2508 | 0.1975 | 0.9229 | 0.6552 |
|
98 |
+
| 0.2023 | 45.0 | 2565 | 0.1975 | 0.9223 | 0.6538 |
|
99 |
+
|
100 |
+
|
101 |
+
### Framework versions
|
102 |
+
|
103 |
+
- Transformers 4.41.1
|
104 |
+
- Pytorch 2.3.0+cu121
|
105 |
+
- Datasets 2.19.1
|
106 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlnet/xlnet-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"XLNetForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attn_type": "bi",
|
7 |
+
"bi_data": false,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"clamp_len": -1,
|
10 |
+
"d_head": 64,
|
11 |
+
"d_inner": 3072,
|
12 |
+
"d_model": 768,
|
13 |
+
"dropout": 0.1,
|
14 |
+
"end_n_top": 5,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"ff_activation": "gelu",
|
17 |
+
"id2label": {
|
18 |
+
"0": "capacity expansion",
|
19 |
+
"1": "legal action",
|
20 |
+
"2": "market expansion",
|
21 |
+
"3": "marketing",
|
22 |
+
"4": "merger & acquisition and finance investments",
|
23 |
+
"5": "outsourcing and alliance",
|
24 |
+
"6": "pricing",
|
25 |
+
"7": "product introductions and improvements"
|
26 |
+
},
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"label2id": {
|
29 |
+
"capacity expansion": 0,
|
30 |
+
"legal action": 1,
|
31 |
+
"market expansion": 2,
|
32 |
+
"marketing": 3,
|
33 |
+
"merger & acquisition and finance investments": 4,
|
34 |
+
"outsourcing and alliance": 5,
|
35 |
+
"pricing": 6,
|
36 |
+
"product introductions and improvements": 7
|
37 |
+
},
|
38 |
+
"layer_norm_eps": 1e-12,
|
39 |
+
"mem_len": null,
|
40 |
+
"model_type": "xlnet",
|
41 |
+
"n_head": 12,
|
42 |
+
"n_layer": 12,
|
43 |
+
"pad_token_id": 5,
|
44 |
+
"problem_type": "multi_label_classification",
|
45 |
+
"reuse_len": null,
|
46 |
+
"same_length": false,
|
47 |
+
"start_n_top": 5,
|
48 |
+
"summary_activation": "tanh",
|
49 |
+
"summary_last_dropout": 0.1,
|
50 |
+
"summary_type": "last",
|
51 |
+
"summary_use_proj": true,
|
52 |
+
"task_specific_params": {
|
53 |
+
"text-generation": {
|
54 |
+
"do_sample": true,
|
55 |
+
"max_length": 250
|
56 |
+
}
|
57 |
+
},
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.41.1",
|
60 |
+
"untie_r": true,
|
61 |
+
"use_mems_eval": true,
|
62 |
+
"use_mems_train": false,
|
63 |
+
"vocab_size": 32000
|
64 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22ff4ffbc7ee9c735a78bf26c072db3d0327772ca0ed9efccd9a33b9318e1fe3
|
3 |
+
size 469283056
|
runs/Jun06_13-45-59_ubuntu-System-Product-Name/events.out.tfevents.1717652760.ubuntu-System-Product-Name.207770.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2cfdf81b5757068112257e895fe3db6dfa93b2a59d99a24ab59926cc791e03f
|
3 |
+
size 5815
|
runs/Jun06_13-49-07_ubuntu-System-Product-Name/events.out.tfevents.1717652949.ubuntu-System-Product-Name.208270.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d748b532526cd57bca8b8f229e2a77d76fea6b1cca66ca5742bc30ba7c74d3c
|
3 |
+
size 23770
|
runs/Jun06_13-49-07_ubuntu-System-Product-Name/events.out.tfevents.1717659242.ubuntu-System-Product-Name.208270.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9df00da145461bfc5fe832f9dec190a43d1a753356a969d9ea757d4f4f6047a9
|
3 |
+
size 456
|
special_tokens_map.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<eop>",
|
4 |
+
"<eod>"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<cls>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"content": "<mask>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "<sep>",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<cls>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "<sep>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "<pad>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "<mask>",
|
53 |
+
"lstrip": true,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "<eod>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"8": {
|
68 |
+
"content": "<eop>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
}
|
75 |
+
},
|
76 |
+
"additional_special_tokens": [
|
77 |
+
"<eop>",
|
78 |
+
"<eod>"
|
79 |
+
],
|
80 |
+
"bos_token": "<s>",
|
81 |
+
"clean_up_tokenization_spaces": true,
|
82 |
+
"cls_token": "<cls>",
|
83 |
+
"do_lower_case": false,
|
84 |
+
"eos_token": "</s>",
|
85 |
+
"keep_accents": false,
|
86 |
+
"mask_token": "<mask>",
|
87 |
+
"model_max_length": 1000000000000000019884624838656,
|
88 |
+
"pad_token": "<pad>",
|
89 |
+
"remove_space": true,
|
90 |
+
"sep_token": "<sep>",
|
91 |
+
"tokenizer_class": "XLNetTokenizer",
|
92 |
+
"unk_token": "<unk>"
|
93 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c5fa58c1bc75aebf108a9ccd57244d79b829c7930f3d61559f2f34da372d073
|
3 |
+
size 5176
|