madatnlp commited on
Commit
a7fb5f1
1 Parent(s): 1505add

Training in progress epoch 0

Browse files
Files changed (6) hide show
  1. README.md +52 -0
  2. config.json +50 -0
  3. special_tokens_map.json +1 -0
  4. tf_model.h5 +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +1 -0
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: madatnlp/sk-kogptv2-kormath-causal
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
+ # madatnlp/sk-kogptv2-kormath-causal
14
+
15
+ This model is a fine-tuned version of [skt/kogpt2-base-v2](https://huggingface.co/skt/kogpt2-base-v2) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: nan
18
+ - Epoch: 0
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
+ - optimizer: {'name': 'Adam', 'learning_rate': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
38
+ - training_precision: float32
39
+
40
+ ### Training results
41
+
42
+ | Train Loss | Epoch |
43
+ |:----------:|:-----:|
44
+ | nan | 0 |
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.19.1
50
+ - TensorFlow 2.8.0
51
+ - Datasets 2.2.1
52
+ - Tokenizers 0.12.1
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "skt/kogpt2-base-v2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "author": "Heewon Jeon(madjakarta@gmail.com)",
10
+ "bos_token_id": 0,
11
+ "created_date": "2021-04-28",
12
+ "embd_pdrop": 0.1,
13
+ "eos_token_id": 1,
14
+ "gradient_checkpointing": false,
15
+ "id2label": {
16
+ "0": "LABEL_0"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "layer_norm_epsilon": 1e-05,
23
+ "license": "CC-BY-NC-SA 4.0",
24
+ "model_type": "gpt2",
25
+ "n_ctx": 1024,
26
+ "n_embd": 768,
27
+ "n_head": 12,
28
+ "n_inner": null,
29
+ "n_layer": 12,
30
+ "n_positions": 1024,
31
+ "pad_token_id": 3,
32
+ "reorder_and_upcast_attn": false,
33
+ "resid_pdrop": 0.1,
34
+ "scale_attn_by_inverse_layer_idx": false,
35
+ "scale_attn_weights": true,
36
+ "summary_activation": null,
37
+ "summary_first_dropout": 0.1,
38
+ "summary_proj_to_labels": true,
39
+ "summary_type": "cls_index",
40
+ "summary_use_proj": true,
41
+ "task_specific_params": {
42
+ "text-generation": {
43
+ "do_sample": true,
44
+ "max_length": 50
45
+ }
46
+ },
47
+ "transformers_version": "4.19.1",
48
+ "use_cache": true,
49
+ "vocab_size": 51205
50
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "</s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "</s>", "mask_token": "<mask>", "additional_special_tokens": ["°", "□", "÷", "×", "‘", "○", "’", "캤", "쨰", "츌", "잌", "찗"]}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a58bddccac971176ae05c41c44713160db5dfd316a39811f8e746174b1a091
3
+ size 658153136
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "</s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "skt/kogpt2-base-v2", "tokenizer_class": "PreTrainedTokenizerFast"}