End of training
Browse files- README.md +108 -0
- config.json +41 -0
- logs/events.out.tfevents.1729783251.5d702f840c7d.337.3 +3 -0
- logs/events.out.tfevents.1729783459.5d702f840c7d.337.4 +3 -0
- logs/events.out.tfevents.1729784153.5d702f840c7d.337.5 +3 -0
- logs/events.out.tfevents.1729786982.5d702f840c7d.337.6 +3 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: roberta-base
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: topicclassify_roberta-base_ng
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# topicclassify_roberta-base_ng
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.6365
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 8
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 500
|
45 |
+
- num_epochs: 50
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| No log | 1.0 | 8 | 2.3860 |
|
52 |
+
| 2.4191 | 2.0 | 16 | 2.3819 |
|
53 |
+
| 2.3782 | 3.0 | 24 | 2.3747 |
|
54 |
+
| 2.3916 | 4.0 | 32 | 2.3645 |
|
55 |
+
| 2.3684 | 5.0 | 40 | 2.3507 |
|
56 |
+
| 2.3684 | 6.0 | 48 | 2.3336 |
|
57 |
+
| 2.3351 | 7.0 | 56 | 2.3078 |
|
58 |
+
| 2.3004 | 8.0 | 64 | 2.2660 |
|
59 |
+
| 2.2395 | 9.0 | 72 | 2.1492 |
|
60 |
+
| 2.1171 | 10.0 | 80 | 2.0108 |
|
61 |
+
| 2.1171 | 11.0 | 88 | 1.9561 |
|
62 |
+
| 1.9637 | 12.0 | 96 | 1.8987 |
|
63 |
+
| 1.8614 | 13.0 | 104 | 1.8365 |
|
64 |
+
| 1.5772 | 14.0 | 112 | 1.7732 |
|
65 |
+
| 1.3709 | 15.0 | 120 | 1.7141 |
|
66 |
+
| 1.3709 | 16.0 | 128 | 1.6833 |
|
67 |
+
| 1.0789 | 17.0 | 136 | 1.6628 |
|
68 |
+
| 0.8387 | 18.0 | 144 | 1.6431 |
|
69 |
+
| 0.6901 | 19.0 | 152 | 1.6693 |
|
70 |
+
| 0.5079 | 20.0 | 160 | 1.6365 |
|
71 |
+
| 0.5079 | 21.0 | 168 | 1.6810 |
|
72 |
+
| 0.3348 | 22.0 | 176 | 1.7289 |
|
73 |
+
| 0.2514 | 23.0 | 184 | 1.7938 |
|
74 |
+
| 0.1799 | 24.0 | 192 | 1.8653 |
|
75 |
+
| 0.136 | 25.0 | 200 | 1.8664 |
|
76 |
+
| 0.136 | 26.0 | 208 | 2.0561 |
|
77 |
+
| 0.0884 | 27.0 | 216 | 1.9570 |
|
78 |
+
| 0.0572 | 28.0 | 224 | 2.0407 |
|
79 |
+
| 0.0482 | 29.0 | 232 | 2.0549 |
|
80 |
+
| 0.0287 | 30.0 | 240 | 2.1033 |
|
81 |
+
| 0.0287 | 31.0 | 248 | 2.1545 |
|
82 |
+
| 0.0203 | 32.0 | 256 | 2.2210 |
|
83 |
+
| 0.0138 | 33.0 | 264 | 2.2864 |
|
84 |
+
| 0.011 | 34.0 | 272 | 2.3884 |
|
85 |
+
| 0.0097 | 35.0 | 280 | 2.4863 |
|
86 |
+
| 0.0097 | 36.0 | 288 | 2.4634 |
|
87 |
+
| 0.0084 | 37.0 | 296 | 2.4587 |
|
88 |
+
| 0.0073 | 38.0 | 304 | 2.4804 |
|
89 |
+
| 0.0063 | 39.0 | 312 | 2.5137 |
|
90 |
+
| 0.0061 | 40.0 | 320 | 2.5542 |
|
91 |
+
| 0.0061 | 41.0 | 328 | 2.5758 |
|
92 |
+
| 0.0055 | 42.0 | 336 | 2.5782 |
|
93 |
+
| 0.0051 | 43.0 | 344 | 2.5991 |
|
94 |
+
| 0.0048 | 44.0 | 352 | 2.6235 |
|
95 |
+
| 0.0042 | 45.0 | 360 | 2.6597 |
|
96 |
+
| 0.0042 | 46.0 | 368 | 2.6941 |
|
97 |
+
| 0.0039 | 47.0 | 376 | 2.7132 |
|
98 |
+
| 0.0037 | 48.0 | 384 | 2.6993 |
|
99 |
+
| 0.0033 | 49.0 | 392 | 2.7146 |
|
100 |
+
| 0.0033 | 50.0 | 400 | 2.7414 |
|
101 |
+
|
102 |
+
|
103 |
+
### Framework versions
|
104 |
+
|
105 |
+
- Transformers 4.46.0
|
106 |
+
- Pytorch 2.5.0+cu121
|
107 |
+
- Datasets 3.0.2
|
108 |
+
- Tokenizers 0.20.1
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "Animal encounter and experience",
|
15 |
+
"1": "Activity experience",
|
16 |
+
"2": "Natural scene",
|
17 |
+
"3": "Weather",
|
18 |
+
"4": "Diving training",
|
19 |
+
"5": "Travel-experience related photography",
|
20 |
+
"6": "Natural impact",
|
21 |
+
"7": "Local narrative",
|
22 |
+
"8": "Travel experience",
|
23 |
+
"9": "Dining experience",
|
24 |
+
"10": "Holiday vibe"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"layer_norm_eps": 1e-05,
|
29 |
+
"max_position_embeddings": 514,
|
30 |
+
"model_type": "roberta",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"pad_token_id": 1,
|
34 |
+
"position_embedding_type": "absolute",
|
35 |
+
"problem_type": "single_label_classification",
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.46.0",
|
38 |
+
"type_vocab_size": 1,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 50265
|
41 |
+
}
|
logs/events.out.tfevents.1729783251.5d702f840c7d.337.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38bbeb3582da308754c50c17224f6b9a804c390ef6e1035b1fd6be6ecff0adcf
|
3 |
+
size 7875
|
logs/events.out.tfevents.1729783459.5d702f840c7d.337.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff869545a98db29bb2a3c6e466a29b6455ce433aef5da87f55e3dd44a8c942fb
|
3 |
+
size 10034
|
logs/events.out.tfevents.1729784153.5d702f840c7d.337.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54f641f0892a7d98c0cd1c0ab3c145fa2f7e3e0746c32b58c488bfc6118d64f1
|
3 |
+
size 27591
|
logs/events.out.tfevents.1729786982.5d702f840c7d.337.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7ef22e60b8926eb38ac7ba9c944d6be3608129bd40d48182f941d239801c6fe
|
3 |
+
size 311
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de651e89fb476ffbed3263bf992e508b8adb7a9e3705934477ac909a6efd43f7
|
3 |
+
size 498640508
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": false,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17e641d0a23ea8bdeedd6351db7cf8c697ddc0470a3f3c94fb574aeb444b6b6d
|
3 |
+
size 5304
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|