Hugging Face's logo

Ericu950
/
Stoicheia-tagger-parser

Token Classification
Transformers
Safetensors
Ancient Greek (to 1453)
char_bert_joint
ancient-greek
classical-philology
character-level
masked-diffusion
dependency-parsing
pos-tagging
lemmatization
custom_code
Model card Files
xet
 Community
Stoicheia-tagger-parser
File size: 2,155 Bytes
cd8ae16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
{
  "cfg": {
    "kfold_dir": "kfold",
    "attn": "sdpa",
    "T": 2048,
    "W": 384,
    "micro_batch": 2,
    "eval_micro": 8,
    "lr_enc": 0.0001,
    "lr_head": 0.0008,
    "llrd": 1.0,
    "wd": 0.01,
    "clip": 1.0,
    "warmup_frac": 0.1,
    "epochs": 60,
    "patience": 8,
    "pool": "mean",
    "head_dropout": 0.33,
    "parse_dropout": 0.33,
    "w_xpos": 1.0,
    "w_script": 1.0,
    "w_upos": 0.2,
    "w_flat": 1.0,
    "use_cap": true,
    "scalar_mix": true,
    "d_arc": 500,
    "d_rel": 150,
    "w_parse": 1.0,
    "log_every": 10,
    "ckpt": "best.pt",
    "name": "joint_docclean_f0_s0",
    "seed": 0,
    "fold": 0,
    "out_dir": "joint_docclean_f0_s0"
  },
  "tcfg": {
    "pool": "mean",
    "head_dropout": 0.33,
    "w_xpos": 1.0,
    "w_flat": 1.0,
    "w_script": 1.0,
    "w_upos": 0.2,
    "use_cap": true,
    "scalar_mix": true
  },
  "pcfg": {
    "d_arc": 500,
    "d_rel": 150,
    "dropout": 0.33,
    "n_labels": 24
  },
  "pretrain_cfg": {
    "name": "gcb_doc_clean",
    "seed": 0,
    "d_model": 1024,
    "depth": 32,
    "char_window": 256,
    "attn": "flex",
    "compile": true,
    "qk_norm": true,
    "seq_len": 8192,
    "micro_batch": 4,
    "grad_accum": 2,
    "lr": 0.0003,
    "wd": 0.1,
    "clip": 1.0,
    "warmup_frac": 0.04,
    "decay_frac": 0.4,
    "tier_weights": [
      1.0,
      1.0,
      0.3
    ],
    "lam": 0.1,
    "total_steps": 120000,
    "hard_max_steps": 1000000,
    "num_workers": 16,
    "log_every": 20,
    "ckpt_every": 2000,
    "eval_every_ckpt": true,
    "eval_n": 256,
    "out_dir": "gcb_doc_clean",
    "anneal_phases": [
      [
        0.5,
        [
          1.0,
          1.0,
          0.3
        ]
      ],
      [
        0.9,
        [
          1.0,
          1.0,
          0.0
        ]
      ],
      [
        1.0,
        [
          1.0,
          0.0,
          0.0
        ]
      ]
    ]
  },
  "epoch": 53,
  "dev": {
    "epoch": 53,
    "xpos_exact": 0.924,
    "lemma_script": 0.9343,
    "upos": 0.9675,
    "uas": 0.8939,
    "las": 0.8367,
    "n_words": 145653,
    "score": 0.9156
  },
  "_source_checkpoint": "best.pt"
}