End of training
Browse files- README.md +69 -0
- config.json +34 -0
- model.safetensors +3 -0
- runs/Jul13_23-41-42_ea68994bd6cb/events.out.tfevents.1752450103.ea68994bd6cb.9476.4 +3 -0
- runs/Jul13_23-59-48_ea68994bd6cb/events.out.tfevents.1752451189.ea68994bd6cb.9476.5 +3 -0
- runs/Jul14_00-00-13_ea68994bd6cb/events.out.tfevents.1752451213.ea68994bd6cb.9476.6 +3 -0
- runs/Jul14_00-02-37_ea68994bd6cb/events.out.tfevents.1752451358.ea68994bd6cb.9476.7 +3 -0
- runs/Jul14_00-04-40_ea68994bd6cb/events.out.tfevents.1752451481.ea68994bd6cb.9476.8 +3 -0
- runs/Jul14_00-05-12_ea68994bd6cb/events.out.tfevents.1752451512.ea68994bd6cb.9476.9 +3 -0
- runs/Jul14_00-20-04_ea68994bd6cb/events.out.tfevents.1752452405.ea68994bd6cb.9476.10 +3 -0
- runs/Jul14_00-32-08_ea68994bd6cb/events.out.tfevents.1752453129.ea68994bd6cb.9476.11 +3 -0
- runs/Jul14_00-37-34_ea68994bd6cb/events.out.tfevents.1752453455.ea68994bd6cb.9476.12 +3 -0
- runs/Jul14_00-38-50_ea68994bd6cb/events.out.tfevents.1752453531.ea68994bd6cb.9476.13 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: distilbert/distilbert-base-uncased
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
+
model-index:
|
13 |
+
- name: my_awesome_wnut_model
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# my_awesome_wnut_model
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.1176
|
25 |
+
- Precision: 0.3223
|
26 |
+
- Recall: 0.2889
|
27 |
+
- F1: 0.3047
|
28 |
+
- Accuracy: 0.9671
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 2e-05
|
48 |
+
- train_batch_size: 16
|
49 |
+
- eval_batch_size: 16
|
50 |
+
- seed: 42
|
51 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- num_epochs: 3
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
+
| No log | 1.0 | 37 | 0.1255 | 0.2105 | 0.1778 | 0.1928 | 0.9676 |
|
60 |
+
| No log | 2.0 | 74 | 0.1204 | 0.2881 | 0.2519 | 0.2688 | 0.9669 |
|
61 |
+
| No log | 3.0 | 111 | 0.1176 | 0.3223 | 0.2889 | 0.3047 | 0.9671 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.48.0
|
67 |
+
- Pytorch 2.6.0+cu124
|
68 |
+
- Datasets 2.14.4
|
69 |
+
- Tokenizers 0.21.2
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "B-ENTITY",
|
14 |
+
"2": "I-ENTITY"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"B-ENTITY": 1,
|
19 |
+
"I-ENTITY": 2,
|
20 |
+
"O": 0
|
21 |
+
},
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "distilbert",
|
24 |
+
"n_heads": 12,
|
25 |
+
"n_layers": 6,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"qa_dropout": 0.1,
|
28 |
+
"seq_classif_dropout": 0.2,
|
29 |
+
"sinusoidal_pos_embds": false,
|
30 |
+
"tie_weights_": true,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.48.0",
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14367c497e71388cfebfda2c06e1c5979e87da8d76c449b6d465a3a56ee3df68
|
3 |
+
size 265473092
|
runs/Jul13_23-41-42_ea68994bd6cb/events.out.tfevents.1752450103.ea68994bd6cb.9476.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd828414142ec6a9b4258263795508b429d060ab1a082b471e3071c6f4dee1a8
|
3 |
+
size 5097
|
runs/Jul13_23-59-48_ea68994bd6cb/events.out.tfevents.1752451189.ea68994bd6cb.9476.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fabcf6ba4d122701c92572f5731893a8bd4aeea8499981c436db1e94b6db669
|
3 |
+
size 5057
|
runs/Jul14_00-00-13_ea68994bd6cb/events.out.tfevents.1752451213.ea68994bd6cb.9476.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2dcf69c824be95b820d91ffb018f5256709ac58dbb9bf3be7515278484b8588
|
3 |
+
size 5057
|
runs/Jul14_00-02-37_ea68994bd6cb/events.out.tfevents.1752451358.ea68994bd6cb.9476.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d995be99793faff7406b480d0be52c683604fc967e4b6f4ed2f34683bea1d5e2
|
3 |
+
size 5057
|
runs/Jul14_00-04-40_ea68994bd6cb/events.out.tfevents.1752451481.ea68994bd6cb.9476.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b12911eec73e135dce972593fc3bab499026eb54b08e598b2fe130c60da369e
|
3 |
+
size 5056
|
runs/Jul14_00-05-12_ea68994bd6cb/events.out.tfevents.1752451512.ea68994bd6cb.9476.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:422ccf39166d3e5f71afcbe5fb6cdd8bf9ecba3aa8e73fb66b41b739894a08c1
|
3 |
+
size 6330
|
runs/Jul14_00-20-04_ea68994bd6cb/events.out.tfevents.1752452405.ea68994bd6cb.9476.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42942cb9a0dd4f5368e079e0ba03587d0393e7e08de26e7f91760da09ff2063f
|
3 |
+
size 6370
|
runs/Jul14_00-32-08_ea68994bd6cb/events.out.tfevents.1752453129.ea68994bd6cb.9476.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b1fd4ecd7595c440a0507f80cc3557c6b712ce978d7f8245a18d0cda1b0bf32
|
3 |
+
size 6370
|
runs/Jul14_00-37-34_ea68994bd6cb/events.out.tfevents.1752453455.ea68994bd6cb.9476.12
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc2ed46416aa30479bd6e6543a14c042fb2a7069b4438097428d1a0634d2e122
|
3 |
+
size 6370
|
runs/Jul14_00-38-50_ea68994bd6cb/events.out.tfevents.1752453531.ea68994bd6cb.9476.13
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13ab305ffd6fd1c77a8461fc3c8d2ce290ebd2270025c23d3efbb88535c07ad3
|
3 |
+
size 6832
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"extra_special_tokens": {},
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f00798244c45c344061dad147cef044f59f7ffa8b0c7c653f2cda5268d1c6844
|
3 |
+
size 5368
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|