Baljinnyam
commited on
Commit
•
fc2c071
1
Parent(s):
e628657
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +55 -0
- pytorch_model.bin +3 -0
- runs/May06_12-22-01_bb73f3c1548f/1683375796.9767637/events.out.tfevents.1683375796.bb73f3c1548f.358.1 +3 -0
- runs/May06_12-22-01_bb73f3c1548f/events.out.tfevents.1683375796.bb73f3c1548f.358.0 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bayartsogt/mongolian-gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2ForTokenClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.0,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.0,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"finetuning_task": "ner",
|
12 |
+
"gradient_checkpointing": false,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "LOC",
|
16 |
+
"2": "MISC",
|
17 |
+
"3": "ORG",
|
18 |
+
"4": "PER"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"label2id": {
|
22 |
+
"LOC": 1,
|
23 |
+
"MISC": 2,
|
24 |
+
"O": 0,
|
25 |
+
"ORG": 3,
|
26 |
+
"PER": 4
|
27 |
+
},
|
28 |
+
"layer_norm_epsilon": 1e-05,
|
29 |
+
"model_type": "gpt2",
|
30 |
+
"n_ctx": 1024,
|
31 |
+
"n_embd": 768,
|
32 |
+
"n_head": 12,
|
33 |
+
"n_inner": null,
|
34 |
+
"n_layer": 12,
|
35 |
+
"n_positions": 1024,
|
36 |
+
"reorder_and_upcast_attn": false,
|
37 |
+
"resid_pdrop": 0.0,
|
38 |
+
"scale_attn_by_inverse_layer_idx": false,
|
39 |
+
"scale_attn_weights": true,
|
40 |
+
"summary_activation": null,
|
41 |
+
"summary_first_dropout": 0.1,
|
42 |
+
"summary_proj_to_labels": true,
|
43 |
+
"summary_type": "cls_index",
|
44 |
+
"summary_use_proj": true,
|
45 |
+
"task_specific_params": {
|
46 |
+
"text-generation": {
|
47 |
+
"do_sample": true,
|
48 |
+
"max_length": 50
|
49 |
+
}
|
50 |
+
},
|
51 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.28.1",
|
53 |
+
"use_cache": true,
|
54 |
+
"vocab_size": 50257
|
55 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9ca9092f9c16987b7926bd8f5a1be8f56cbcae63d0910e5182f20f2b34c6a18
|
3 |
+
size 510413893
|
runs/May06_12-22-01_bb73f3c1548f/1683375796.9767637/events.out.tfevents.1683375796.bb73f3c1548f.358.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f3dae2dfceb65844934ef23d1481ae02fa0bca9853dc13c228a9f65cd066bd3
|
3 |
+
size 5906
|
runs/May06_12-22-01_bb73f3c1548f/events.out.tfevents.1683375796.bb73f3c1548f.358.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:604e53f738d0f2d8f371aff630d98d8dd115fc99da0c9d3b3f2176e1d60934d5
|
3 |
+
size 5593
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "[MASK]",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "[SEP]",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": "[CLS]",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "[CLS]",
|
6 |
+
"do_lower_case": true,
|
7 |
+
"eos_token": "[SEP]",
|
8 |
+
"keep_accents": false,
|
9 |
+
"mask_token": {
|
10 |
+
"__type": "AddedToken",
|
11 |
+
"content": "[MASK]",
|
12 |
+
"lstrip": true,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"model_max_length": 512,
|
18 |
+
"pad_token": "<pad>",
|
19 |
+
"remove_space": true,
|
20 |
+
"sep_token": "[SEP]",
|
21 |
+
"tokenizer_class": "AlbertTokenizer",
|
22 |
+
"unk_token": "<unk>"
|
23 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa89d6a8d99d8406db39235d20bc85b05d2b79af5f16be28371ef654be5fbbe8
|
3 |
+
size 3579
|