ghostdivisio
commited on
Commit
•
4e88166
1
Parent(s):
2802947
End of training
Browse files- README.md +146 -0
- config.json +25 -0
- model.safetensors +3 -0
- runs/May29_10-14-55_4497ee5e0d2f/events.out.tfevents.1716978062.4497ee5e0d2f.402.0 +3 -0
- runs/May29_10-22-22_4497ee5e0d2f/events.out.tfevents.1716978149.4497ee5e0d2f.402.1 +3 -0
- runs/May29_10-23-19_4497ee5e0d2f/events.out.tfevents.1716978204.4497ee5e0d2f.402.2 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: prajjwal1/bert-tiny
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: bert-tiny-finetuned-squad
|
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 |
+
# bert-tiny-finetuned-squad
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.1478
|
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: 90
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 29 | 0.8724 |
|
50 |
+
| No log | 2.0 | 58 | 0.7989 |
|
51 |
+
| No log | 3.0 | 87 | 0.7316 |
|
52 |
+
| No log | 4.0 | 116 | 0.6691 |
|
53 |
+
| No log | 5.0 | 145 | 0.6121 |
|
54 |
+
| No log | 6.0 | 174 | 0.5597 |
|
55 |
+
| No log | 7.0 | 203 | 0.5121 |
|
56 |
+
| No log | 8.0 | 232 | 0.4690 |
|
57 |
+
| No log | 9.0 | 261 | 0.4300 |
|
58 |
+
| No log | 10.0 | 290 | 0.3950 |
|
59 |
+
| No log | 11.0 | 319 | 0.3637 |
|
60 |
+
| No log | 12.0 | 348 | 0.3358 |
|
61 |
+
| No log | 13.0 | 377 | 0.3110 |
|
62 |
+
| No log | 14.0 | 406 | 0.2891 |
|
63 |
+
| No log | 15.0 | 435 | 0.2697 |
|
64 |
+
| No log | 16.0 | 464 | 0.2527 |
|
65 |
+
| No log | 17.0 | 493 | 0.2379 |
|
66 |
+
| 0.5621 | 18.0 | 522 | 0.2247 |
|
67 |
+
| 0.5621 | 19.0 | 551 | 0.2134 |
|
68 |
+
| 0.5621 | 20.0 | 580 | 0.2035 |
|
69 |
+
| 0.5621 | 21.0 | 609 | 0.1955 |
|
70 |
+
| 0.5621 | 22.0 | 638 | 0.1886 |
|
71 |
+
| 0.5621 | 23.0 | 667 | 0.1829 |
|
72 |
+
| 0.5621 | 24.0 | 696 | 0.1776 |
|
73 |
+
| 0.5621 | 25.0 | 725 | 0.1731 |
|
74 |
+
| 0.5621 | 26.0 | 754 | 0.1694 |
|
75 |
+
| 0.5621 | 27.0 | 783 | 0.1662 |
|
76 |
+
| 0.5621 | 28.0 | 812 | 0.1635 |
|
77 |
+
| 0.5621 | 29.0 | 841 | 0.1614 |
|
78 |
+
| 0.5621 | 30.0 | 870 | 0.1597 |
|
79 |
+
| 0.5621 | 31.0 | 899 | 0.1582 |
|
80 |
+
| 0.5621 | 32.0 | 928 | 0.1570 |
|
81 |
+
| 0.5621 | 33.0 | 957 | 0.1561 |
|
82 |
+
| 0.5621 | 34.0 | 986 | 0.1551 |
|
83 |
+
| 0.1726 | 35.0 | 1015 | 0.1545 |
|
84 |
+
| 0.1726 | 36.0 | 1044 | 0.1537 |
|
85 |
+
| 0.1726 | 37.0 | 1073 | 0.1532 |
|
86 |
+
| 0.1726 | 38.0 | 1102 | 0.1528 |
|
87 |
+
| 0.1726 | 39.0 | 1131 | 0.1523 |
|
88 |
+
| 0.1726 | 40.0 | 1160 | 0.1519 |
|
89 |
+
| 0.1726 | 41.0 | 1189 | 0.1516 |
|
90 |
+
| 0.1726 | 42.0 | 1218 | 0.1512 |
|
91 |
+
| 0.1726 | 43.0 | 1247 | 0.1510 |
|
92 |
+
| 0.1726 | 44.0 | 1276 | 0.1507 |
|
93 |
+
| 0.1726 | 45.0 | 1305 | 0.1505 |
|
94 |
+
| 0.1726 | 46.0 | 1334 | 0.1503 |
|
95 |
+
| 0.1726 | 47.0 | 1363 | 0.1502 |
|
96 |
+
| 0.1726 | 48.0 | 1392 | 0.1500 |
|
97 |
+
| 0.1726 | 49.0 | 1421 | 0.1499 |
|
98 |
+
| 0.1726 | 50.0 | 1450 | 0.1497 |
|
99 |
+
| 0.1726 | 51.0 | 1479 | 0.1496 |
|
100 |
+
| 0.1271 | 52.0 | 1508 | 0.1496 |
|
101 |
+
| 0.1271 | 53.0 | 1537 | 0.1494 |
|
102 |
+
| 0.1271 | 54.0 | 1566 | 0.1493 |
|
103 |
+
| 0.1271 | 55.0 | 1595 | 0.1492 |
|
104 |
+
| 0.1271 | 56.0 | 1624 | 0.1491 |
|
105 |
+
| 0.1271 | 57.0 | 1653 | 0.1490 |
|
106 |
+
| 0.1271 | 58.0 | 1682 | 0.1490 |
|
107 |
+
| 0.1271 | 59.0 | 1711 | 0.1489 |
|
108 |
+
| 0.1271 | 60.0 | 1740 | 0.1489 |
|
109 |
+
| 0.1271 | 61.0 | 1769 | 0.1488 |
|
110 |
+
| 0.1271 | 62.0 | 1798 | 0.1487 |
|
111 |
+
| 0.1271 | 63.0 | 1827 | 0.1487 |
|
112 |
+
| 0.1271 | 64.0 | 1856 | 0.1486 |
|
113 |
+
| 0.1271 | 65.0 | 1885 | 0.1486 |
|
114 |
+
| 0.1271 | 66.0 | 1914 | 0.1485 |
|
115 |
+
| 0.1271 | 67.0 | 1943 | 0.1485 |
|
116 |
+
| 0.1271 | 68.0 | 1972 | 0.1484 |
|
117 |
+
| 0.1216 | 69.0 | 2001 | 0.1484 |
|
118 |
+
| 0.1216 | 70.0 | 2030 | 0.1483 |
|
119 |
+
| 0.1216 | 71.0 | 2059 | 0.1483 |
|
120 |
+
| 0.1216 | 72.0 | 2088 | 0.1482 |
|
121 |
+
| 0.1216 | 73.0 | 2117 | 0.1483 |
|
122 |
+
| 0.1216 | 74.0 | 2146 | 0.1482 |
|
123 |
+
| 0.1216 | 75.0 | 2175 | 0.1481 |
|
124 |
+
| 0.1216 | 76.0 | 2204 | 0.1481 |
|
125 |
+
| 0.1216 | 77.0 | 2233 | 0.1481 |
|
126 |
+
| 0.1216 | 78.0 | 2262 | 0.1480 |
|
127 |
+
| 0.1216 | 79.0 | 2291 | 0.1480 |
|
128 |
+
| 0.1216 | 80.0 | 2320 | 0.1479 |
|
129 |
+
| 0.1216 | 81.0 | 2349 | 0.1479 |
|
130 |
+
| 0.1216 | 82.0 | 2378 | 0.1479 |
|
131 |
+
| 0.1216 | 83.0 | 2407 | 0.1479 |
|
132 |
+
| 0.1216 | 84.0 | 2436 | 0.1479 |
|
133 |
+
| 0.1216 | 85.0 | 2465 | 0.1479 |
|
134 |
+
| 0.1216 | 86.0 | 2494 | 0.1478 |
|
135 |
+
| 0.1151 | 87.0 | 2523 | 0.1478 |
|
136 |
+
| 0.1151 | 88.0 | 2552 | 0.1478 |
|
137 |
+
| 0.1151 | 89.0 | 2581 | 0.1478 |
|
138 |
+
| 0.1151 | 90.0 | 2610 | 0.1478 |
|
139 |
+
|
140 |
+
|
141 |
+
### Framework versions
|
142 |
+
|
143 |
+
- Transformers 4.41.1
|
144 |
+
- Pytorch 2.3.0+cu121
|
145 |
+
- Datasets 2.19.1
|
146 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "prajjwal1/bert-tiny",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 128,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 512,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 2,
|
17 |
+
"num_hidden_layers": 2,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.41.1",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b30a8cea4983f46782c2e8a87af00752a80e9496de63b39772098cf6a6c7b7cb
|
3 |
+
size 17483080
|
runs/May29_10-14-55_4497ee5e0d2f/events.out.tfevents.1716978062.4497ee5e0d2f.402.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6906672580ebc0cbc7f84b035f721b20c19c68531c614ff533f9c29d9dc46d67
|
3 |
+
size 5891
|
runs/May29_10-22-22_4497ee5e0d2f/events.out.tfevents.1716978149.4497ee5e0d2f.402.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:264535974c68eeb0d41501933de730f9f1e13048d851ee823754614cb57d3f0d
|
3 |
+
size 13421
|
runs/May29_10-23-19_4497ee5e0d2f/events.out.tfevents.1716978204.4497ee5e0d2f.402.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f726198a6f6a18860994d10f877c8ef878c4bfabedb7f309f0412af7fb0bf64
|
3 |
+
size 30610
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3035315be1c50daccaa02f6522e884364abca37840b42f873ddf6b7c259cc5e3
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|