Baljinnyam commited on
Commit
78b6b97
1 Parent(s): 92d1f95

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForTokenClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "finetuning_task": "ner",
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "LOC",
15
+ "2": "MISC",
16
+ "3": "ORG",
17
+ "4": "PER"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LOC": 1,
22
+ "MISC": 2,
23
+ "O": 0,
24
+ "ORG": 3,
25
+ "PER": 4
26
+ },
27
+ "layer_norm_epsilon": 1e-05,
28
+ "model_type": "gpt2",
29
+ "n_ctx": 1024,
30
+ "n_embd": 768,
31
+ "n_head": 12,
32
+ "n_inner": null,
33
+ "n_layer": 12,
34
+ "n_positions": 1024,
35
+ "reorder_and_upcast_attn": false,
36
+ "resid_pdrop": 0.1,
37
+ "scale_attn_by_inverse_layer_idx": false,
38
+ "scale_attn_weights": true,
39
+ "summary_activation": null,
40
+ "summary_first_dropout": 0.1,
41
+ "summary_proj_to_labels": true,
42
+ "summary_type": "cls_index",
43
+ "summary_use_proj": true,
44
+ "task_specific_params": {
45
+ "text-generation": {
46
+ "do_sample": true,
47
+ "max_length": 50
48
+ }
49
+ },
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.28.1",
52
+ "use_cache": true,
53
+ "vocab_size": 50258
54
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1635b953b1b478ac46e6df85f11b241ccdc7682f0511d0ca8127b90c2f36c3e
3
+ size 510416965
runs/May03_01-46-45_3e0dba33dae4/1683078410.3404202/events.out.tfevents.1683078410.3e0dba33dae4.499.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:410137369c084f027021862d3d5eeaa61dd8589d6adc609e2725021d3fbc5e99
3
+ size 5852
runs/May03_01-46-45_3e0dba33dae4/events.out.tfevents.1683078410.3e0dba33dae4.499.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6974763697b2140b64c8db82dcfbae1edbbfd84c58aaa76d58f0af9d2a2bd7f
3
+ size 5057
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2d4941551e2f60924575065277a023071d01b3d19e568413e37f71fcf88f085
3
+ size 3515
vocab.json ADDED
The diff for this file is too large to render. See raw diff