Training in progress, step 500
Browse files- config.json +5 -5
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jul18_01-09-48_fe084eaf0329/events.out.tfevents.1721265051.fe084eaf0329.29414.0 +3 -0
- runs/Jul18_01-11-52_fe084eaf0329/events.out.tfevents.1721265118.fe084eaf0329.30009.0 +3 -0
- runs/Jul18_01-12-59_fe084eaf0329/events.out.tfevents.1721265209.fe084eaf0329.30334.0 +3 -0
- runs/Jul18_01-14-07_fe084eaf0329/events.out.tfevents.1721265254.fe084eaf0329.30664.0 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +2 -2
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
CHANGED
@@ -4,14 +4,14 @@
|
|
4 |
],
|
5 |
"attention_probs_dropout_prob": 0.1,
|
6 |
"bos_token_id": 0,
|
|
|
7 |
"eos_token_id": 2,
|
8 |
-
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 256,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 1024,
|
14 |
-
"layer_norm_eps": 1e-
|
15 |
"max_position_embeddings": 128,
|
16 |
"model_type": "roberta",
|
17 |
"num_attention_heads": 4,
|
@@ -19,8 +19,8 @@
|
|
19 |
"pad_token_id": 1,
|
20 |
"position_embedding_type": "absolute",
|
21 |
"torch_dtype": "float32",
|
22 |
-
"transformers_version": "4.
|
23 |
-
"type_vocab_size":
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 50265
|
26 |
-
}
|
|
|
4 |
],
|
5 |
"attention_probs_dropout_prob": 0.1,
|
6 |
"bos_token_id": 0,
|
7 |
+
"classifier_dropout": null,
|
8 |
"eos_token_id": 2,
|
|
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 256,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 1024,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
"max_position_embeddings": 128,
|
16 |
"model_type": "roberta",
|
17 |
"num_attention_heads": 4,
|
|
|
19 |
"pad_token_id": 1,
|
20 |
"position_embedding_type": "absolute",
|
21 |
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.42.4",
|
23 |
+
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 50265
|
26 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0105db47ed9fbfe3d7774d06dd0ad9e117ed2e52d03375119524fe3fb3c9ee3
|
3 |
+
size 90005100
|
runs/Jul18_01-09-48_fe084eaf0329/events.out.tfevents.1721265051.fe084eaf0329.29414.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b64baa320ae27a38fc004f3cca96cd4ccd5100d5522dae688c742313a1b66a1c
|
3 |
+
size 4749
|
runs/Jul18_01-11-52_fe084eaf0329/events.out.tfevents.1721265118.fe084eaf0329.30009.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2ed0b3e3806c536951000129098b906d99c55d8bd7a8cbe4f5d55b7aed0ab8b
|
3 |
+
size 4749
|
runs/Jul18_01-12-59_fe084eaf0329/events.out.tfevents.1721265209.fe084eaf0329.30334.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0073f25837c52cca762f41a15e73e44f0f63aa4ad63bc2aea4f94b2e944e1405
|
3 |
+
size 4749
|
runs/Jul18_01-14-07_fe084eaf0329/events.out.tfevents.1721265254.fe084eaf0329.30664.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31d619da90785cef674456c8b71ffad124ed38a61f40f0464a9d132bbef1caf9
|
3 |
+
size 4961
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
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": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
CHANGED
@@ -43,7 +43,7 @@
|
|
43 |
"id": 4,
|
44 |
"content": "<mask>",
|
45 |
"single_word": false,
|
46 |
-
"lstrip":
|
47 |
"rstrip": false,
|
48 |
"normalized": false,
|
49 |
"special": true
|
@@ -59,7 +59,7 @@
|
|
59 |
"post_processor": {
|
60 |
"type": "ByteLevel",
|
61 |
"add_prefix_space": true,
|
62 |
-
"trim_offsets":
|
63 |
"use_regex": true
|
64 |
},
|
65 |
"decoder": {
|
|
|
43 |
"id": 4,
|
44 |
"content": "<mask>",
|
45 |
"single_word": false,
|
46 |
+
"lstrip": true,
|
47 |
"rstrip": false,
|
48 |
"normalized": false,
|
49 |
"special": true
|
|
|
59 |
"post_processor": {
|
60 |
"type": "ByteLevel",
|
61 |
"add_prefix_space": true,
|
62 |
+
"trim_offsets": true,
|
63 |
"use_regex": true
|
64 |
},
|
65 |
"decoder": {
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1f2196f8bb1c72cdb770a21b2a58f1a7bc6df8a2f5bd8f8664030d8d677a88c
|
3 |
+
size 5176
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|