Rocketknight1 HF staff commited on
Commit
37701ae
1 Parent(s): a5d8dba

Training in progress epoch 0

Browse files
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