erikhenriksson
commited on
Commit
•
9f296c7
1
Parent(s):
7b0cce2
Upload 4 files
Browse files- config.json +82 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
- training_metadata.json +7 -0
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "MT",
|
15 |
+
"1": "LY",
|
16 |
+
"2": "SP",
|
17 |
+
"3": "ID",
|
18 |
+
"4": "NA",
|
19 |
+
"5": "HI",
|
20 |
+
"6": "IN",
|
21 |
+
"7": "OP",
|
22 |
+
"8": "IP",
|
23 |
+
"9": "it",
|
24 |
+
"10": "ne",
|
25 |
+
"11": "sr",
|
26 |
+
"12": "nb",
|
27 |
+
"13": "re",
|
28 |
+
"14": "en",
|
29 |
+
"15": "ra",
|
30 |
+
"16": "dtp",
|
31 |
+
"17": "fi",
|
32 |
+
"18": "lt",
|
33 |
+
"19": "rv",
|
34 |
+
"20": "ob",
|
35 |
+
"21": "rs",
|
36 |
+
"22": "av",
|
37 |
+
"23": "ds",
|
38 |
+
"24": "ed"
|
39 |
+
},
|
40 |
+
"initializer_range": 0.02,
|
41 |
+
"intermediate_size": 4096,
|
42 |
+
"label2id": {
|
43 |
+
"HI": 5,
|
44 |
+
"ID": 3,
|
45 |
+
"IN": 6,
|
46 |
+
"IP": 8,
|
47 |
+
"LY": 1,
|
48 |
+
"MT": 0,
|
49 |
+
"NA": 4,
|
50 |
+
"OP": 7,
|
51 |
+
"SP": 2,
|
52 |
+
"av": 22,
|
53 |
+
"ds": 23,
|
54 |
+
"dtp": 16,
|
55 |
+
"ed": 24,
|
56 |
+
"en": 14,
|
57 |
+
"fi": 17,
|
58 |
+
"it": 9,
|
59 |
+
"lt": 18,
|
60 |
+
"nb": 12,
|
61 |
+
"ne": 10,
|
62 |
+
"ob": 20,
|
63 |
+
"ra": 15,
|
64 |
+
"re": 13,
|
65 |
+
"rs": 21,
|
66 |
+
"rv": 19,
|
67 |
+
"sr": 11
|
68 |
+
},
|
69 |
+
"layer_norm_eps": 1e-05,
|
70 |
+
"max_position_embeddings": 514,
|
71 |
+
"model_type": "xlm-roberta",
|
72 |
+
"num_attention_heads": 16,
|
73 |
+
"num_hidden_layers": 24,
|
74 |
+
"output_past": true,
|
75 |
+
"pad_token_id": 1,
|
76 |
+
"position_embedding_type": "absolute",
|
77 |
+
"torch_dtype": "bfloat16",
|
78 |
+
"transformers_version": "4.39.3",
|
79 |
+
"type_vocab_size": 1,
|
80 |
+
"use_cache": true,
|
81 |
+
"vocab_size": 250002
|
82 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:688d9075d2d72268cec7662e316b2ee17d8757f3ec004f3ad1ba186c604ca49d
|
3 |
+
size 1119880626
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebf403c952a10b2c8536d4787b9c94e81a9be354ce8e46705c1ed18a2600a9d8
|
3 |
+
size 5048
|
training_metadata.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"batch_size": 8,
|
3 |
+
"learning_rate": 3e-05,
|
4 |
+
"warmup_ratio": 0.05,
|
5 |
+
"stopped_epoch": 21,
|
6 |
+
"total_epochs": 30,
|
7 |
+
}
|