End of training
Browse files- README.md +106 -0
- config.json +62 -0
- model.safetensors +3 -0
- runs/Jun06_18-41-24_ubuntu-System-Product-Name/events.out.tfevents.1717670493.ubuntu-System-Product-Name.279897.0 +3 -0
- runs/Jun06_18-43-45_ubuntu-System-Product-Name/events.out.tfevents.1717670628.ubuntu-System-Product-Name.279897.1 +3 -0
- runs/Jun06_18-43-45_ubuntu-System-Product-Name/events.out.tfevents.1717678069.ubuntu-System-Product-Name.279897.2 +3 -0
- runs/Jun06_21-00-03_ubuntu-System-Product-Name/events.out.tfevents.1717678805.ubuntu-System-Product-Name.403909.0 +3 -0
- runs/Jun06_21-00-03_ubuntu-System-Product-Name/events.out.tfevents.1717682219.ubuntu-System-Product-Name.403909.1 +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-7-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-7-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: 0.2151
|
21 |
+
- F1: 0.9188
|
22 |
+
- Jaccard: 0.6316
|
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: 0.0001
|
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 | 0.4002 | 0.8330 | 0.4071 |
|
55 |
+
| No log | 2.0 | 114 | 0.3221 | 0.8443 | 0.4115 |
|
56 |
+
| No log | 3.0 | 171 | 0.2836 | 0.8703 | 0.4565 |
|
57 |
+
| No log | 4.0 | 228 | 0.2654 | 0.8731 | 0.4786 |
|
58 |
+
| No log | 5.0 | 285 | 0.2478 | 0.8825 | 0.5288 |
|
59 |
+
| No log | 6.0 | 342 | 0.2410 | 0.8925 | 0.5395 |
|
60 |
+
| No log | 7.0 | 399 | 0.2337 | 0.8990 | 0.5830 |
|
61 |
+
| No log | 8.0 | 456 | 0.2313 | 0.8997 | 0.5586 |
|
62 |
+
| 0.3113 | 9.0 | 513 | 0.2287 | 0.8974 | 0.5579 |
|
63 |
+
| 0.3113 | 10.0 | 570 | 0.2242 | 0.9037 | 0.6080 |
|
64 |
+
| 0.3113 | 11.0 | 627 | 0.2215 | 0.9036 | 0.5911 |
|
65 |
+
| 0.3113 | 12.0 | 684 | 0.2209 | 0.9072 | 0.5977 |
|
66 |
+
| 0.3113 | 13.0 | 741 | 0.2192 | 0.9093 | 0.6169 |
|
67 |
+
| 0.3113 | 14.0 | 798 | 0.2193 | 0.9076 | 0.6125 |
|
68 |
+
| 0.3113 | 15.0 | 855 | 0.2206 | 0.9067 | 0.6257 |
|
69 |
+
| 0.3113 | 16.0 | 912 | 0.2166 | 0.9121 | 0.6265 |
|
70 |
+
| 0.3113 | 17.0 | 969 | 0.2151 | 0.9188 | 0.6316 |
|
71 |
+
| 0.2282 | 18.0 | 1026 | 0.2143 | 0.9107 | 0.6279 |
|
72 |
+
| 0.2282 | 19.0 | 1083 | 0.2132 | 0.9105 | 0.6346 |
|
73 |
+
| 0.2282 | 20.0 | 1140 | 0.2132 | 0.9106 | 0.6279 |
|
74 |
+
| 0.2282 | 21.0 | 1197 | 0.2174 | 0.9122 | 0.6243 |
|
75 |
+
| 0.2282 | 22.0 | 1254 | 0.2161 | 0.9139 | 0.6221 |
|
76 |
+
| 0.2282 | 23.0 | 1311 | 0.2127 | 0.9119 | 0.6287 |
|
77 |
+
| 0.2282 | 24.0 | 1368 | 0.2129 | 0.9119 | 0.6353 |
|
78 |
+
| 0.2282 | 25.0 | 1425 | 0.2112 | 0.9147 | 0.6324 |
|
79 |
+
| 0.2282 | 26.0 | 1482 | 0.2122 | 0.9129 | 0.6386 |
|
80 |
+
| 0.2142 | 27.0 | 1539 | 0.2126 | 0.9146 | 0.6272 |
|
81 |
+
| 0.2142 | 28.0 | 1596 | 0.2114 | 0.9144 | 0.6331 |
|
82 |
+
| 0.2142 | 29.0 | 1653 | 0.2109 | 0.9159 | 0.6434 |
|
83 |
+
| 0.2142 | 30.0 | 1710 | 0.2102 | 0.9165 | 0.6479 |
|
84 |
+
| 0.2142 | 31.0 | 1767 | 0.2120 | 0.9114 | 0.6397 |
|
85 |
+
| 0.2142 | 32.0 | 1824 | 0.2110 | 0.9125 | 0.6405 |
|
86 |
+
| 0.2142 | 33.0 | 1881 | 0.2111 | 0.9093 | 0.625 |
|
87 |
+
| 0.2142 | 34.0 | 1938 | 0.2110 | 0.9109 | 0.6243 |
|
88 |
+
| 0.2142 | 35.0 | 1995 | 0.2111 | 0.9110 | 0.6324 |
|
89 |
+
| 0.2084 | 36.0 | 2052 | 0.2127 | 0.9141 | 0.6394 |
|
90 |
+
| 0.2084 | 37.0 | 2109 | 0.2112 | 0.9098 | 0.6265 |
|
91 |
+
| 0.2084 | 38.0 | 2166 | 0.2109 | 0.9112 | 0.6309 |
|
92 |
+
| 0.2084 | 39.0 | 2223 | 0.2109 | 0.9137 | 0.6405 |
|
93 |
+
| 0.2084 | 40.0 | 2280 | 0.2111 | 0.9122 | 0.6346 |
|
94 |
+
| 0.2084 | 41.0 | 2337 | 0.2111 | 0.9111 | 0.6368 |
|
95 |
+
| 0.2084 | 42.0 | 2394 | 0.2113 | 0.9099 | 0.6279 |
|
96 |
+
| 0.2084 | 43.0 | 2451 | 0.2112 | 0.9105 | 0.6324 |
|
97 |
+
| 0.2054 | 44.0 | 2508 | 0.2111 | 0.9105 | 0.6287 |
|
98 |
+
| 0.2054 | 45.0 | 2565 | 0.2110 | 0.9089 | 0.6221 |
|
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 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "merger & acquisition and finance investments",
|
22 |
+
"4": "outsourcing and alliance",
|
23 |
+
"5": "pricing",
|
24 |
+
"6": "product introductions and improvements"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"label2id": {
|
28 |
+
"capacity expansion": 0,
|
29 |
+
"legal action": 1,
|
30 |
+
"market expansion": 2,
|
31 |
+
"merger & acquisition and finance investments": 3,
|
32 |
+
"outsourcing and alliance": 4,
|
33 |
+
"pricing": 5,
|
34 |
+
"product introductions and improvements": 6
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"mem_len": null,
|
38 |
+
"model_type": "xlnet",
|
39 |
+
"n_head": 12,
|
40 |
+
"n_layer": 12,
|
41 |
+
"pad_token_id": 5,
|
42 |
+
"problem_type": "multi_label_classification",
|
43 |
+
"reuse_len": null,
|
44 |
+
"same_length": false,
|
45 |
+
"start_n_top": 5,
|
46 |
+
"summary_activation": "tanh",
|
47 |
+
"summary_last_dropout": 0.1,
|
48 |
+
"summary_type": "last",
|
49 |
+
"summary_use_proj": true,
|
50 |
+
"task_specific_params": {
|
51 |
+
"text-generation": {
|
52 |
+
"do_sample": true,
|
53 |
+
"max_length": 250
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.41.1",
|
58 |
+
"untie_r": true,
|
59 |
+
"use_mems_eval": true,
|
60 |
+
"use_mems_train": false,
|
61 |
+
"vocab_size": 32000
|
62 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4215b834d445b1c6d743d668f41c3bac85d8a6bab5e1686cffdd2fac115ab9d
|
3 |
+
size 470067604
|
runs/Jun06_18-41-24_ubuntu-System-Product-Name/events.out.tfevents.1717670493.ubuntu-System-Product-Name.279897.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:268637e44299238bdc3d5bf1804d3e22c4aa76323f91d3fc57e579d507939995
|
3 |
+
size 6134
|
runs/Jun06_18-43-45_ubuntu-System-Product-Name/events.out.tfevents.1717670628.ubuntu-System-Product-Name.279897.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5362e2e2820547603ca0ea4e798476682efd3fc3c248043effa88364b06dbbe
|
3 |
+
size 45235
|
runs/Jun06_18-43-45_ubuntu-System-Product-Name/events.out.tfevents.1717678069.ubuntu-System-Product-Name.279897.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15c22ce9b4592c6f407ae97b223ca5660b1ddbdc07b058138d0985599d50a9c1
|
3 |
+
size 824
|
runs/Jun06_21-00-03_ubuntu-System-Product-Name/events.out.tfevents.1717678805.ubuntu-System-Product-Name.403909.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec31a8eba0a1e25acf4ff9de986f60c99d42a495e17e8098fe03bf673da7568c
|
3 |
+
size 23729
|
runs/Jun06_21-00-03_ubuntu-System-Product-Name/events.out.tfevents.1717682219.ubuntu-System-Product-Name.403909.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e974f3f9f93700c857f4b9ce743928c7867d229202593690321d645f971389e2
|
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 sha256:4de54c13429d8c5e9d4a0285bfa9dca95addccd06147000344d2d4421efb6fda
|
3 |
+
size 5176
|