Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +36 -0
- autotrain-data/train/.nfs1a84977ae50b87e800000057 +3 -0
- autotrain-data/validation/.nfsd5f3174aceaff3e800000058 +3 -0
- checkpoint-61270/config.json +0 -0
- checkpoint-61270/model.safetensors +3 -0
- checkpoint-61270/optimizer.pt +3 -0
- checkpoint-61270/rng_state.pth +3 -0
- checkpoint-61270/scheduler.pt +3 -0
- checkpoint-61270/trainer_state.json +0 -0
- checkpoint-61270/training_args.bin +3 -0
- config.json +0 -0
- model.safetensors +3 -0
- runs/Jan21_17-17-06_ccc0389.campuscluster.illinois.edu/events.out.tfevents.1737501446.ccc0389.campuscluster.illinois.edu.3804449.0 +2 -2
- runs/Jan21_17-17-06_ccc0389.campuscluster.illinois.edu/events.out.tfevents.1737510605.ccc0389.campuscluster.illinois.edu.3804449.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
autotrain-data/train/.nfs1a84977ae50b87e800000057 filter=lfs diff=lfs merge=lfs -text
|
37 |
+
autotrain-data/validation/.nfsd5f3174aceaff3e800000058 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: dbmdz/bert-base-german-europeana-uncased
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Text Classification
|
14 |
+
|
15 |
+
## Validation Metrics
|
16 |
+
loss: 6.590800762176514
|
17 |
+
|
18 |
+
f1_macro: 0.008138962923889539
|
19 |
+
|
20 |
+
f1_micro: 0.07204093712409065
|
21 |
+
|
22 |
+
f1_weighted: 0.043525754606176574
|
23 |
+
|
24 |
+
precision_macro: 0.0073795359485093765
|
25 |
+
|
26 |
+
precision_micro: 0.07204093712409065
|
27 |
+
|
28 |
+
precision_weighted: 0.035906260666633036
|
29 |
+
|
30 |
+
recall_macro: 0.013094065506618197
|
31 |
+
|
32 |
+
recall_micro: 0.07204093712409065
|
33 |
+
|
34 |
+
recall_weighted: 0.07204093712409065
|
35 |
+
|
36 |
+
accuracy: 0.07204093712409065
|
autotrain-data/train/.nfs1a84977ae50b87e800000057
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a1b9fc99960801e0a5cba26230a89b25098c8bcfe3fb24c1d1e3a863a9a8c0f
|
3 |
+
size 218815136
|
autotrain-data/validation/.nfsd5f3174aceaff3e800000058
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2af8db9c302d3e6f66b1fc094854bfb755a4e7f7572f9c902196be89a59b86c7
|
3 |
+
size 62766352
|
checkpoint-61270/config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-61270/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b479167469d00f17fd72ae93424dd2cb9fa5dfbc773776690ee4eb3184d98f26
|
3 |
+
size 509143688
|
checkpoint-61270/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6036dc587846b54a7965e06bc3f65811074fd5bbb1a7596b8d4a747fced409f
|
3 |
+
size 1018408442
|
checkpoint-61270/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8aa2c24ad9231344aaa0fa083b976e2a2fb3958d6446a0b252605a00dfbd0036
|
3 |
+
size 14244
|
checkpoint-61270/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c30e4ad8ca47c24040bfc599158500a19b05b7f83c950cfe0e63643f321a07f
|
3 |
+
size 1064
|
checkpoint-61270/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-61270/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fc0870ddd2ffdbdd04e39f2530855526de0fc4c05ab27f4be5e820aa086ae23
|
3 |
+
size 5368
|
config.json
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:b479167469d00f17fd72ae93424dd2cb9fa5dfbc773776690ee4eb3184d98f26
|
3 |
+
size 509143688
|
runs/Jan21_17-17-06_ccc0389.campuscluster.illinois.edu/events.out.tfevents.1737501446.ccc0389.campuscluster.illinois.edu.3804449.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5119d9e08d23ebed0564fc8a8394a24e196953d30644deca1391a68c0f17414d
|
3 |
+
size 2018340
|
runs/Jan21_17-17-06_ccc0389.campuscluster.illinois.edu/events.out.tfevents.1737510605.ccc0389.campuscluster.illinois.edu.3804449.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9513ef79e37878e002c6b3727bb5f1cd31d6ee40f4cf3bd1e1a09a4ae699e5b2
|
3 |
+
size 936
|
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 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
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 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"max_len": 512,
|
51 |
+
"model_max_length": 512,
|
52 |
+
"never_split": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"strip_accents": null,
|
56 |
+
"tokenize_chinese_chars": true,
|
57 |
+
"tokenizer_class": "BertTokenizer",
|
58 |
+
"unk_token": "[UNK]"
|
59 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fc0870ddd2ffdbdd04e39f2530855526de0fc4c05ab27f4be5e820aa086ae23
|
3 |
+
size 5368
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "bert-base-german-europeana-uncased-dnb/autotrain-data",
|
3 |
+
"model": "dbmdz/bert-base-german-europeana-uncased",
|
4 |
+
"lr": 3e-05,
|
5 |
+
"epochs": 25,
|
6 |
+
"max_seq_length": 100,
|
7 |
+
"batch_size": 16,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 2,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "bert-base-german-europeana-uncased-dnb",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "jimfhahn",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|