Training in progress, step 1000
Browse files- added_tokens.json +9 -0
- config.json +38 -0
- model.safetensors +3 -0
- special_tokens_map.json +9 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +75 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 3,
|
3 |
+
"<s>": 2,
|
4 |
+
"[CLS]": 4,
|
5 |
+
"[MASK]": 6,
|
6 |
+
"[PAD]": 0,
|
7 |
+
"[SEP]": 5,
|
8 |
+
"[UNK]": 1
|
9 |
+
}
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_fn": "swish",
|
4 |
+
"architectures": [
|
5 |
+
"RetNetForCausalLM"
|
6 |
+
],
|
7 |
+
"decoder_embed_dim": 1280,
|
8 |
+
"decoder_ffn_embed_dim": 2560,
|
9 |
+
"decoder_layers": 12,
|
10 |
+
"decoder_normalize_before": true,
|
11 |
+
"decoder_retention_heads": 8,
|
12 |
+
"decoder_value_embed_dim": 2560,
|
13 |
+
"deepnorm": false,
|
14 |
+
"drop_path_rate": 0.0,
|
15 |
+
"dropout": 0.0,
|
16 |
+
"eos_token_id": 50256,
|
17 |
+
"forward_impl": "parallel",
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"is_decoder": true,
|
20 |
+
"layernorm_embedding": true,
|
21 |
+
"layernorm_eps": 1e-06,
|
22 |
+
"model_type": "retnet",
|
23 |
+
"no_scale_embedding": false,
|
24 |
+
"output_retentions": false,
|
25 |
+
"pad_token_id": 50256,
|
26 |
+
"recurrent_chunk_size": 512,
|
27 |
+
"subln": true,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.34.0",
|
31 |
+
"unk_token_id": 50256,
|
32 |
+
"use_cache": true,
|
33 |
+
"use_ffn_rms_norm": false,
|
34 |
+
"use_glu": true,
|
35 |
+
"use_lm_decay": false,
|
36 |
+
"vocab_size": 50257,
|
37 |
+
"z_loss_coeff": 0.0
|
38 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:056916394d5842d7848ab46eaf76f5a15e0a344a90c65c22789939ff8edccf2d
|
3 |
+
size 1615784368
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d78ab344146700112cd41628ac7ce54b79c0868fe0c7c201750d8237b54dbb4
|
3 |
+
size 786216
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": true,
|
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": "</s>",
|
29 |
+
"lstrip": true,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": true,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[CLS]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "[SEP]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "[MASK]",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
}
|
59 |
+
},
|
60 |
+
"additional_special_tokens": [],
|
61 |
+
"bos_token": "<s>",
|
62 |
+
"clean_up_tokenization_spaces": true,
|
63 |
+
"cls_token": "[CLS]",
|
64 |
+
"do_lower_case": false,
|
65 |
+
"eos_token": "</s>",
|
66 |
+
"extra_ids": 0,
|
67 |
+
"legacy": true,
|
68 |
+
"mask_token": "[MASK]",
|
69 |
+
"model_max_length": 1000000000000000019884624838656,
|
70 |
+
"pad_token": "[PAD]",
|
71 |
+
"sep_token": "[SEP]",
|
72 |
+
"sp_model_kwargs": {},
|
73 |
+
"tokenizer_class": "T5Tokenizer",
|
74 |
+
"unk_token": "[UNK]"
|
75 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99b4305a08962dafa0e9bc5a994af4d018463ff14053809ec77928b08913d838
|
3 |
+
size 4027
|