Commit
•
37701ae
1
Parent(s):
a5d8dba
Training in progress epoch 0
Browse files- README.md +53 -0
- config.json +46 -0
- logs/train/events.out.tfevents.1639749510.matt-TRX40-AORUS-PRO-WIFI.33131.0.v2 +3 -0
- logs/train/events.out.tfevents.1639749524.matt-TRX40-AORUS-PRO-WIFI.profile-empty +3 -0
- logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.input_pipeline.pb +3 -0
- logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.kernel_stats.pb +0 -0
- logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.memory_profile.json.gz +3 -0
- logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.overview_page.pb +3 -0
- logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.tensorflow_stats.pb +3 -0
- logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.trace.json.gz +3 -0
- logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.xplane.pb +3 -0
- logs/validation/events.out.tfevents.1639749604.matt-TRX40-AORUS-PRO-WIFI.33131.1.v2 +3 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: Rocketknight1/gbert-base-germaner
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# Rocketknight1/gbert-base-germaner
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [deepset/gbert-base](https://huggingface.co/deepset/gbert-base) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.1345
|
18 |
+
- Validation Loss: 0.0865
|
19 |
+
- Epoch: 0
|
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 |
+
- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 4176, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
|
39 |
+
- training_precision: mixed_float16
|
40 |
+
|
41 |
+
### Training results
|
42 |
+
|
43 |
+
| Train Loss | Validation Loss | Epoch |
|
44 |
+
|:----------:|:---------------:|:-----:|
|
45 |
+
| 0.1345 | 0.0865 | 0 |
|
46 |
+
|
47 |
+
|
48 |
+
### Framework versions
|
49 |
+
|
50 |
+
- Transformers 4.15.0.dev0
|
51 |
+
- TensorFlow 2.6.0
|
52 |
+
- Datasets 1.16.2.dev0
|
53 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "deepset/gbert-base",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "B-LOC",
|
13 |
+
"1": "B-ORG",
|
14 |
+
"2": "B-OTH",
|
15 |
+
"3": "B-PER",
|
16 |
+
"4": "I-LOC",
|
17 |
+
"5": "I-ORG",
|
18 |
+
"6": "I-OTH",
|
19 |
+
"7": "I-PER",
|
20 |
+
"8": "O"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"B-LOC": "0",
|
26 |
+
"B-ORG": "1",
|
27 |
+
"B-OTH": "2",
|
28 |
+
"B-PER": "3",
|
29 |
+
"I-LOC": "4",
|
30 |
+
"I-ORG": "5",
|
31 |
+
"I-OTH": "6",
|
32 |
+
"I-PER": "7",
|
33 |
+
"O": "8"
|
34 |
+
},
|
35 |
+
"layer_norm_eps": 1e-12,
|
36 |
+
"max_position_embeddings": 512,
|
37 |
+
"model_type": "bert",
|
38 |
+
"num_attention_heads": 12,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"pad_token_id": 0,
|
41 |
+
"position_embedding_type": "absolute",
|
42 |
+
"transformers_version": "4.15.0.dev0",
|
43 |
+
"type_vocab_size": 2,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 31102
|
46 |
+
}
|
logs/train/events.out.tfevents.1639749510.matt-TRX40-AORUS-PRO-WIFI.33131.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fc756013b9b3b7cb33f473165cd7d4537d485b6516dc705b7fd9b80c3092f68
|
3 |
+
size 3554976
|
logs/train/events.out.tfevents.1639749524.matt-TRX40-AORUS-PRO-WIFI.profile-empty
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3ef1d8d876bd626f72a8eefe7831f0da8ef75f2dc2101e6138a895bd9acb41
|
3 |
+
size 40
|
logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.input_pipeline.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1281122c0ad510e0d6b43dd8a3cd291e5c07d65666a0226b00ca7193fbec47f
|
3 |
+
size 2622
|
logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.kernel_stats.pb
ADDED
File without changes
|
logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.memory_profile.json.gz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e39e7ef53de0d5fb01f61dc39bbf9ce16548cf9c6bb1938fce8fb3f913a3b746
|
3 |
+
size 43422
|
logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.overview_page.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:871248fdfc40475dc26ef80927f507e70731930654fc4254f3deaa80468c610d
|
3 |
+
size 4007
|
logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.tensorflow_stats.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9fef084f546e35f7c0a117bdc167a102307f88cf84289c32aecacf235c5439a
|
3 |
+
size 6389
|
logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.trace.json.gz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:899fa5b9dfbfe036b7680b9319c438ba4b0ecc9841efe30d0a7cfc18483c3aec
|
3 |
+
size 20720
|
logs/train/plugins/profile/2021_12_17_13_58_44/matt-TRX40-AORUS-PRO-WIFI.xplane.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e95f805e072668cffedee8092a170eda46f1177fe9ab9b2488fb5e570c2f9ba7
|
3 |
+
size 940803
|
logs/validation/events.out.tfevents.1639749604.matt-TRX40-AORUS-PRO-WIFI.33131.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e422270d50603876107d1a0bb2950c7d1ba9b214557322fad753b62680366cdb
|
3 |
+
size 194
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11635a9fc84bf5dfe49d4eaa001b0bf2d7f94408e98b9b9cdf64f81e6a80c93c
|
3 |
+
size 437649452
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "deepset/gbert-base", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|