End of training
Browse files- README.md +50 -26
- config.json +5 -5
- model.safetensors +2 -2
- runs/Jun05_02-36-02_1436e3d6cad1/events.out.tfevents.1717554967.1436e3d6cad1.2748.0 +3 -0
- runs/Jun05_02-36-02_1436e3d6cad1/events.out.tfevents.1717555081.1436e3d6cad1.2748.1 +3 -0
- runs/Jun05_02-36-02_1436e3d6cad1/events.out.tfevents.1717558335.1436e3d6cad1.2748.2 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -5,7 +5,6 @@ tags:
|
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- f1
|
8 |
-
- accuracy
|
9 |
model-index:
|
10 |
- name: xlnet-base-cased-airlines-news-multi-label
|
11 |
results: []
|
@@ -18,10 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [xlnet/xlnet-base-cased](https://huggingface.co/xlnet/xlnet-base-cased) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- F1: 0.
|
23 |
-
- Roc Auc: 0.
|
24 |
-
- Accuracy: 0.6116
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -40,38 +38,64 @@ More information needed
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
-
- learning_rate:
|
44 |
- train_batch_size: 12
|
45 |
- eval_batch_size: 12
|
46 |
- seed: 42
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
-
-
|
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc |
|
54 |
-
|
55 |
-
| No log | 1.0 |
|
56 |
-
| No log | 2.0 |
|
57 |
-
|
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
|
71 |
|
72 |
### Framework versions
|
73 |
|
74 |
-
- Transformers 4.41.
|
75 |
- Pytorch 2.3.0+cu121
|
76 |
-
- Datasets 2.19.
|
77 |
- Tokenizers 0.19.1
|
|
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- f1
|
|
|
8 |
model-index:
|
9 |
- name: xlnet-base-cased-airlines-news-multi-label
|
10 |
results: []
|
|
|
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: 0.2567
|
21 |
+
- F1: 0.8989
|
22 |
+
- Roc Auc: 0.6475
|
|
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 7e-05
|
42 |
- train_batch_size: 12
|
43 |
- eval_batch_size: 12
|
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: 40
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
54 |
+
| No log | 1.0 | 170 | 0.2834 | 0.8827 | 0.5576 |
|
55 |
+
| No log | 2.0 | 340 | 0.2670 | 0.8918 | 0.6102 |
|
56 |
+
| 0.2923 | 3.0 | 510 | 0.2567 | 0.8989 | 0.6475 |
|
57 |
+
| 0.2923 | 4.0 | 680 | 0.2526 | 0.8910 | 0.6685 |
|
58 |
+
| 0.2923 | 5.0 | 850 | 0.2512 | 0.8825 | 0.6352 |
|
59 |
+
| 0.2571 | 6.0 | 1020 | 0.2514 | 0.8863 | 0.6708 |
|
60 |
+
| 0.2571 | 7.0 | 1190 | 0.2454 | 0.8872 | 0.6490 |
|
61 |
+
| 0.2571 | 8.0 | 1360 | 0.2495 | 0.8884 | 0.6660 |
|
62 |
+
| 0.2468 | 9.0 | 1530 | 0.2467 | 0.8881 | 0.6725 |
|
63 |
+
| 0.2468 | 10.0 | 1700 | 0.2554 | 0.8815 | 0.6514 |
|
64 |
+
| 0.2468 | 11.0 | 1870 | 0.2474 | 0.8883 | 0.6603 |
|
65 |
+
| 0.2363 | 12.0 | 2040 | 0.2478 | 0.8912 | 0.6943 |
|
66 |
+
| 0.2363 | 13.0 | 2210 | 0.2492 | 0.8964 | 0.6976 |
|
67 |
+
| 0.2363 | 14.0 | 2380 | 0.2530 | 0.8936 | 0.7121 |
|
68 |
+
| 0.2332 | 15.0 | 2550 | 0.2497 | 0.8893 | 0.6830 |
|
69 |
+
| 0.2332 | 16.0 | 2720 | 0.2483 | 0.8922 | 0.7008 |
|
70 |
+
| 0.2332 | 17.0 | 2890 | 0.2489 | 0.8905 | 0.6782 |
|
71 |
+
| 0.23 | 18.0 | 3060 | 0.2496 | 0.8877 | 0.6927 |
|
72 |
+
| 0.23 | 19.0 | 3230 | 0.2494 | 0.8855 | 0.6652 |
|
73 |
+
| 0.23 | 20.0 | 3400 | 0.2483 | 0.8929 | 0.6903 |
|
74 |
+
| 0.2246 | 21.0 | 3570 | 0.2503 | 0.8902 | 0.6838 |
|
75 |
+
| 0.2246 | 22.0 | 3740 | 0.2506 | 0.8854 | 0.6805 |
|
76 |
+
| 0.2246 | 23.0 | 3910 | 0.2515 | 0.8900 | 0.6887 |
|
77 |
+
| 0.2214 | 24.0 | 4080 | 0.2501 | 0.8894 | 0.6773 |
|
78 |
+
| 0.2214 | 25.0 | 4250 | 0.2528 | 0.8878 | 0.6870 |
|
79 |
+
| 0.2214 | 26.0 | 4420 | 0.2519 | 0.8918 | 0.6895 |
|
80 |
+
| 0.2203 | 27.0 | 4590 | 0.2558 | 0.8897 | 0.6830 |
|
81 |
+
| 0.2203 | 28.0 | 4760 | 0.2554 | 0.8919 | 0.6952 |
|
82 |
+
| 0.2203 | 29.0 | 4930 | 0.2537 | 0.8957 | 0.7025 |
|
83 |
+
| 0.2193 | 30.0 | 5100 | 0.2513 | 0.8951 | 0.7025 |
|
84 |
+
| 0.2193 | 31.0 | 5270 | 0.2565 | 0.8946 | 0.7130 |
|
85 |
+
| 0.2193 | 32.0 | 5440 | 0.2542 | 0.8935 | 0.6960 |
|
86 |
+
| 0.2178 | 33.0 | 5610 | 0.2545 | 0.8970 | 0.7090 |
|
87 |
+
| 0.2178 | 34.0 | 5780 | 0.2546 | 0.8960 | 0.7138 |
|
88 |
+
| 0.2178 | 35.0 | 5950 | 0.2550 | 0.8942 | 0.7073 |
|
89 |
+
| 0.2173 | 36.0 | 6120 | 0.2545 | 0.8942 | 0.7073 |
|
90 |
+
| 0.2173 | 37.0 | 6290 | 0.2537 | 0.8925 | 0.7008 |
|
91 |
+
| 0.2173 | 38.0 | 6460 | 0.2541 | 0.8942 | 0.7073 |
|
92 |
+
| 0.2164 | 39.0 | 6630 | 0.2537 | 0.8940 | 0.7016 |
|
93 |
+
| 0.2164 | 40.0 | 6800 | 0.2540 | 0.8942 | 0.7073 |
|
94 |
|
95 |
|
96 |
### Framework versions
|
97 |
|
98 |
+
- Transformers 4.41.1
|
99 |
- Pytorch 2.3.0+cu121
|
100 |
+
- Datasets 2.19.2
|
101 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -16,8 +16,8 @@
|
|
16 |
"ff_activation": "gelu",
|
17 |
"id2label": {
|
18 |
"0": "capacity expansion",
|
19 |
-
"1": "
|
20 |
-
"2": "
|
21 |
"3": "merger & acquisition and finance investments",
|
22 |
"4": "outsourcing and alliance",
|
23 |
"5": "product introductions and improvements"
|
@@ -25,8 +25,8 @@
|
|
25 |
"initializer_range": 0.02,
|
26 |
"label2id": {
|
27 |
"capacity expansion": 0,
|
28 |
-
"
|
29 |
-
"
|
30 |
"merger & acquisition and finance investments": 3,
|
31 |
"outsourcing and alliance": 4,
|
32 |
"product introductions and improvements": 5
|
@@ -52,7 +52,7 @@
|
|
52 |
}
|
53 |
},
|
54 |
"torch_dtype": "float32",
|
55 |
-
"transformers_version": "4.41.
|
56 |
"untie_r": true,
|
57 |
"use_mems_eval": true,
|
58 |
"use_mems_train": false,
|
|
|
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": "product introductions and improvements"
|
|
|
25 |
"initializer_range": 0.02,
|
26 |
"label2id": {
|
27 |
"capacity expansion": 0,
|
28 |
+
"legal action": 1,
|
29 |
+
"market expansion": 2,
|
30 |
"merger & acquisition and finance investments": 3,
|
31 |
"outsourcing and alliance": 4,
|
32 |
"product introductions and improvements": 5
|
|
|
52 |
}
|
53 |
},
|
54 |
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.41.1",
|
56 |
"untie_r": true,
|
57 |
"use_mems_eval": true,
|
58 |
"use_mems_train": false,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b9ad9948a9cfaba13c052badec77c7f44deef2dc91d4a8efdd1094a6e9b94d8
|
3 |
+
size 470064528
|
runs/Jun05_02-36-02_1436e3d6cad1/events.out.tfevents.1717554967.1436e3d6cad1.2748.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cc900bcf8750852ad916f50b0c8f79069d009f63f51a8c49c335799bd9ce3e7
|
3 |
+
size 5694
|
runs/Jun05_02-36-02_1436e3d6cad1/events.out.tfevents.1717555081.1436e3d6cad1.2748.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93fbf85e5c03afd592d0e47470cb070fde102e46c84a0fcf690ad8b9da5c4a61
|
3 |
+
size 23511
|
runs/Jun05_02-36-02_1436e3d6cad1/events.out.tfevents.1717558335.1436e3d6cad1.2748.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5895e147048b7b13c0d210af4502bfca3cc8ea710448f5d0f597818a7ed0c38f
|
3 |
+
size 456
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d70d2216f2f14075027e3c0686caaf9ba1a2c7918a492712e1312be498515af
|
3 |
size 5176
|