PaulTran commited on
Commit
c4a5ce4
1 Parent(s): 253d3f0

Training in progress, step 1000

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/phobert-large",
3
+ "architectures": [
4
+ "RobertaForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 258,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "tokenizer_class": "PhobertTokenizer",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.35.0",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 64001
29
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41c36329edb0940079a4610c497726b628c66773d2215e844753112a2ba6880
3
+ size 1476705404
runs/Nov08_17-27-26_cbd66e0f02cd/events.out.tfevents.1699464769.cbd66e0f02cd.508.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd21760d0c578d300f2ff6d36d07864b7cf8389423051f143a13897f0b30575
3
+ size 4317
runs/Nov08_17-33-09_cbd66e0f02cd/events.out.tfevents.1699464799.cbd66e0f02cd.508.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:107b22bdb64c676ce287b847a99942378351d1db42021d32ae4cae7a562cbf34
3
+ size 4315
runs/Nov08_17-33-44_cbd66e0f02cd/events.out.tfevents.1699464830.cbd66e0f02cd.508.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8db1644ebeb0a634dd2b43e3d22b62edb7c78b7a4c454580af256f0602f734e
3
+ size 4315
runs/Nov08_17-37-12_cbd66e0f02cd/events.out.tfevents.1699465036.cbd66e0f02cd.3511.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053121e0cda03a9a9af731977eee1e890d181653513063001d18d80b8d65abe9
3
+ size 4315
runs/Nov08_17-38-50_cbd66e0f02cd/events.out.tfevents.1699465141.cbd66e0f02cd.3511.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aae0b441595bb976673ec6971dc6ce78b08d8f33059da5160f4d77b7b902938a
3
+ size 4184
runs/Nov08_17-40-34_cbd66e0f02cd/events.out.tfevents.1699465237.cbd66e0f02cd.4598.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa30d3e732db66c6e40f544eecc16264adb04a5da565eff99a3aeb8b95e3df9
3
+ size 5598
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 256,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "PhobertTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188fa2db0d5370f6e6f7d2a4f1a9e3dc1c32f08ae3d3312228262f15eea1b1b4
3
+ size 4600
vocab.txt ADDED
The diff for this file is too large to render. See raw diff