sherelyn912
commited on
Commit
•
1af233e
1
Parent(s):
73610c4
End of training
Browse files- README.md +70 -0
- config.json +112 -0
- model.safetensors +3 -0
- runs/Apr13_03-31-16_5bd0ca79381f/events.out.tfevents.1712979077.5bd0ca79381f.453.0 +3 -0
- special_tokens_map.json +19 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +93 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: xlnet/xlnet-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: emotional-xlnet
|
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 |
+
# emotional-xlnet
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [xlnet/xlnet-base-cased](https://huggingface.co/xlnet/xlnet-base-cased) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 2.9968
|
24 |
+
- Accuracy: 0.3875
|
25 |
+
- F1: 0.3676
|
26 |
+
- Precision: 0.3990
|
27 |
+
- Recall: 0.3875
|
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: 16
|
48 |
+
- eval_batch_size: 16
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 10
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
58 |
+
| 2.4746 | 1.0 | 270 | 2.3530 | 0.3085 | 0.2878 | 0.4138 | 0.3085 |
|
59 |
+
| 0.8581 | 2.0 | 540 | 2.1600 | 0.3466 | 0.3310 | 0.3603 | 0.3466 |
|
60 |
+
| 0.2628 | 3.0 | 810 | 2.3594 | 0.3575 | 0.3519 | 0.4060 | 0.3575 |
|
61 |
+
| 0.0791 | 4.0 | 1080 | 2.7493 | 0.3793 | 0.3643 | 0.3901 | 0.3793 |
|
62 |
+
| 0.0292 | 5.0 | 1350 | 2.9968 | 0.3875 | 0.3676 | 0.3990 | 0.3875 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.39.3
|
68 |
+
- Pytorch 2.2.1+cu121
|
69 |
+
- Datasets 2.18.0
|
70 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "serenity",
|
19 |
+
"1": "joy",
|
20 |
+
"10": "terror",
|
21 |
+
"11": "awe",
|
22 |
+
"12": "distraction",
|
23 |
+
"13": "surprise",
|
24 |
+
"14": "amazement",
|
25 |
+
"15": "disapproval",
|
26 |
+
"16": "pensiveness",
|
27 |
+
"17": "sadness",
|
28 |
+
"18": "grief",
|
29 |
+
"19": "remorse",
|
30 |
+
"2": "ecstasy",
|
31 |
+
"20": "boredom",
|
32 |
+
"21": "disgust",
|
33 |
+
"22": "loathing",
|
34 |
+
"23": "contempt",
|
35 |
+
"24": "annoyance",
|
36 |
+
"25": "anger",
|
37 |
+
"26": "rage",
|
38 |
+
"27": "aggressiveness",
|
39 |
+
"28": "interest",
|
40 |
+
"29": "anticipation",
|
41 |
+
"3": "love",
|
42 |
+
"30": "vigilance",
|
43 |
+
"31": "optimism",
|
44 |
+
"4": "acceptance",
|
45 |
+
"5": "trust",
|
46 |
+
"6": "admiration",
|
47 |
+
"7": "submission",
|
48 |
+
"8": "apprehension",
|
49 |
+
"9": "fear"
|
50 |
+
},
|
51 |
+
"initializer_range": 0.02,
|
52 |
+
"label2id": {
|
53 |
+
"acceptance": 4,
|
54 |
+
"admiration": 6,
|
55 |
+
"aggressiveness": 27,
|
56 |
+
"amazement": 14,
|
57 |
+
"anger": 25,
|
58 |
+
"annoyance": 24,
|
59 |
+
"anticipation": 29,
|
60 |
+
"apprehension": 8,
|
61 |
+
"awe": 11,
|
62 |
+
"boredom": 20,
|
63 |
+
"contempt": 23,
|
64 |
+
"disapproval": 15,
|
65 |
+
"disgust": 21,
|
66 |
+
"distraction": 12,
|
67 |
+
"ecstasy": 2,
|
68 |
+
"fear": 9,
|
69 |
+
"grief": 18,
|
70 |
+
"interest": 28,
|
71 |
+
"joy": 1,
|
72 |
+
"loathing": 22,
|
73 |
+
"love": 3,
|
74 |
+
"optimism": 31,
|
75 |
+
"pensiveness": 16,
|
76 |
+
"rage": 26,
|
77 |
+
"remorse": 19,
|
78 |
+
"sadness": 17,
|
79 |
+
"serenity": 0,
|
80 |
+
"submission": 7,
|
81 |
+
"surprise": 13,
|
82 |
+
"terror": 10,
|
83 |
+
"trust": 5,
|
84 |
+
"vigilance": 30
|
85 |
+
},
|
86 |
+
"layer_norm_eps": 1e-12,
|
87 |
+
"mem_len": null,
|
88 |
+
"model_type": "xlnet",
|
89 |
+
"n_head": 12,
|
90 |
+
"n_layer": 12,
|
91 |
+
"pad_token_id": 5,
|
92 |
+
"problem_type": "single_label_classification",
|
93 |
+
"reuse_len": null,
|
94 |
+
"same_length": false,
|
95 |
+
"start_n_top": 5,
|
96 |
+
"summary_activation": "tanh",
|
97 |
+
"summary_last_dropout": 0.1,
|
98 |
+
"summary_type": "last",
|
99 |
+
"summary_use_proj": true,
|
100 |
+
"task_specific_params": {
|
101 |
+
"text-generation": {
|
102 |
+
"do_sample": true,
|
103 |
+
"max_length": 250
|
104 |
+
}
|
105 |
+
},
|
106 |
+
"torch_dtype": "float32",
|
107 |
+
"transformers_version": "4.39.3",
|
108 |
+
"untie_r": true,
|
109 |
+
"use_mems_eval": true,
|
110 |
+
"use_mems_train": false,
|
111 |
+
"vocab_size": 32000
|
112 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:029dd9e5624c6093f3890bbc8ed1f40bbf23d03f659256995e91d81d9d5858c3
|
3 |
+
size 469356888
|
runs/Apr13_03-31-16_5bd0ca79381f/events.out.tfevents.1712979077.5bd0ca79381f.453.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79e49c47d071327279f2a5c6a8debeccd2bf63396a6f45ac5ef08f42e5362e72
|
3 |
+
size 9972
|
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 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
|
3 |
+
size 798011
|
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 sha256:355ac68396a7dd8911a4f38ff07d3224d80ad30f462b9cd1d74c965e26544833
|
3 |
+
size 4920
|