Training in progress, step 500
Browse files- README.md +61 -61
- config.json +24 -24
- model.safetensors +1 -1
- runs/Jul02_12-43-52_Asus/events.out.tfevents.1719920634.Asus.5096.0 +3 -0
- special_tokens_map.json +7 -7
- tokenizer_config.json +55 -55
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,61 +1,61 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
base_model: distilbert-base-uncased
|
4 |
-
tags:
|
5 |
-
- generated_from_trainer
|
6 |
-
model-index:
|
7 |
-
- name: SQuAD_qa_model_PT
|
8 |
-
results: []
|
9 |
-
---
|
10 |
-
|
11 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
-
should probably proofread and complete it, then remove this comment. -->
|
13 |
-
|
14 |
-
# SQuAD_qa_model_PT
|
15 |
-
|
16 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
-
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 1.5221
|
19 |
-
|
20 |
-
## Model description
|
21 |
-
|
22 |
-
More information needed
|
23 |
-
|
24 |
-
## Intended uses & limitations
|
25 |
-
|
26 |
-
More information needed
|
27 |
-
|
28 |
-
## Training and evaluation data
|
29 |
-
|
30 |
-
More information needed
|
31 |
-
|
32 |
-
## Training procedure
|
33 |
-
|
34 |
-
### Training hyperparameters
|
35 |
-
|
36 |
-
The following hyperparameters were used during training:
|
37 |
-
- learning_rate: 2e-05
|
38 |
-
- train_batch_size: 16
|
39 |
-
- eval_batch_size: 16
|
40 |
-
- seed: 42
|
41 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
-
- lr_scheduler_type: linear
|
43 |
-
- num_epochs: 5
|
44 |
-
|
45 |
-
### Training results
|
46 |
-
|
47 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
-
| No log | 1.0 | 300 | 2.1407 |
|
50 |
-
| 2.7542 | 2.0 | 600 | 1.5523 |
|
51 |
-
| 2.7542 | 3.0 | 900 | 1.4745 |
|
52 |
-
| 1.2751 | 4.0 | 1200 | 1.4890 |
|
53 |
-
| 0.8489 | 5.0 | 1500 | 1.5221 |
|
54 |
-
|
55 |
-
|
56 |
-
### Framework versions
|
57 |
-
|
58 |
-
- Transformers 4.38.1
|
59 |
-
- Pytorch 2.2.1+cu118
|
60 |
-
- Datasets 2.17.1
|
61 |
-
- Tokenizers 0.15.2
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: SQuAD_qa_model_PT
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# SQuAD_qa_model_PT
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.5221
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 16
|
39 |
+
- eval_batch_size: 16
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 5
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 300 | 2.1407 |
|
50 |
+
| 2.7542 | 2.0 | 600 | 1.5523 |
|
51 |
+
| 2.7542 | 3.0 | 900 | 1.4745 |
|
52 |
+
| 1.2751 | 4.0 | 1200 | 1.4890 |
|
53 |
+
| 0.8489 | 5.0 | 1500 | 1.5221 |
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- Transformers 4.38.1
|
59 |
+
- Pytorch 2.2.1+cu118
|
60 |
+
- Datasets 2.17.1
|
61 |
+
- Tokenizers 0.15.2
|
config.json
CHANGED
@@ -1,24 +1,24 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
-
"activation": "gelu",
|
4 |
-
"architectures": [
|
5 |
-
"DistilBertForQuestionAnswering"
|
6 |
-
],
|
7 |
-
"attention_dropout": 0.1,
|
8 |
-
"dim": 768,
|
9 |
-
"dropout": 0.1,
|
10 |
-
"hidden_dim": 3072,
|
11 |
-
"initializer_range": 0.02,
|
12 |
-
"max_position_embeddings": 512,
|
13 |
-
"model_type": "distilbert",
|
14 |
-
"n_heads": 12,
|
15 |
-
"n_layers": 6,
|
16 |
-
"pad_token_id": 0,
|
17 |
-
"qa_dropout": 0.1,
|
18 |
-
"seq_classif_dropout": 0.2,
|
19 |
-
"sinusoidal_pos_embds": false,
|
20 |
-
"tie_weights_": true,
|
21 |
-
"torch_dtype": "float32",
|
22 |
-
"transformers_version": "4.38.1",
|
23 |
-
"vocab_size": 30522
|
24 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForQuestionAnswering"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": false,
|
20 |
+
"tie_weights_": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.38.1",
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 265470032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6d37644f297a618a46279e5b3aa5c911dbe2b8e63443b71e44438bdb4ec2a5c
|
3 |
size 265470032
|
runs/Jul02_12-43-52_Asus/events.out.tfevents.1719920634.Asus.5096.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e6ee335f9a623bdba730553986ba0032cdcb0259615f929f1f88d84b0159508
|
3 |
+
size 4922
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
-
"mask_token": "[MASK]",
|
4 |
-
"pad_token": "[PAD]",
|
5 |
-
"sep_token": "[SEP]",
|
6 |
-
"unk_token": "[UNK]"
|
7 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer_config.json
CHANGED
@@ -1,55 +1,55 @@
|
|
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": true,
|
45 |
-
"cls_token": "[CLS]",
|
46 |
-
"do_lower_case": true,
|
47 |
-
"mask_token": "[MASK]",
|
48 |
-
"model_max_length": 512,
|
49 |
-
"pad_token": "[PAD]",
|
50 |
-
"sep_token": "[SEP]",
|
51 |
-
"strip_accents": null,
|
52 |
-
"tokenize_chinese_chars": true,
|
53 |
-
"tokenizer_class": "DistilBertTokenizer",
|
54 |
-
"unk_token": "[UNK]"
|
55 |
-
}
|
|
|
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": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6856661812c83c3eaf4e197d565c2b604020c8e6e1af52b9331d22fd1a022a6e
|
3 |
size 4856
|