Hugging Face's logo

kurogane
/
ModernBERT_Japanese_MT_Bench_test

Safetensors
Japanese
modernbert
Model card Files Community
kurogane commited on
Commit
4e265d4
·
verified ·
1 Parent(s): 2b84747

Upload 10 files

Browse files
Files changed (10) hide show
  1. config.json +54 -0
  2. dataset_dict_float.pkl +3 -0
  3. log_epochs.json +138 -0
  4. log_epochs.png +0 -0
  5. model.safetensors +3 -0
  6. special_tokens_map.json +51 -0
  7. tokenizer.json +0 -0
  8. tokenizer.model +3 -0
  9. tokenizer_config.json +171 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sbintuitions/modernbert-ja-130m",
3
+ "architectures": [
4
+ "ModernBertForScoring"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "cls",
13
+ "cls_token_id": 6,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 2,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 512,
23
+ "id2label": {
24
+ "0": "LABEL_0"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 2048,
29
+ "label2id": {
30
+ "LABEL_0": 0
31
+ },
32
+ "layer_norm_eps": 1e-05,
33
+ "local_attention": 128,
34
+ "local_rope_theta": 10000.0,
35
+ "max_position_embeddings": 8192,
36
+ "mlp_bias": false,
37
+ "mlp_dropout": 0.0,
38
+ "model_type": "modernbert",
39
+ "norm_bias": false,
40
+ "norm_eps": 1e-05,
41
+ "num_attention_heads": 8,
42
+ "num_hidden_layers": 19,
43
+ "pad_token_id": 3,
44
+ "position_embedding_type": "rope",
45
+ "problem_type": "regression",
46
+ "reference_compile": false,
47
+ "repad_logits_with_grad": false,
48
+ "sep_token_id": 4,
49
+ "sparse_pred_ignore_index": -100,
50
+ "sparse_prediction": false,
51
+ "torch_dtype": "bfloat16",
52
+ "transformers_version": "4.48.3",
53
+ "vocab_size": 102400
54
+ }
dataset_dict_float.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd3a0c993c263843aff8ea282607fca17aef9719d3e4e0f5e0bf9a563ca8113a
3
+ size 116830328
log_epochs.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_mae": [
3
+ 0.17266634106636047,
4
+ 0.1580764204263687,
5
+ 0.12138129025697708,
6
+ 0.20911525189876556,
7
+ 0.13156601786613464,
8
+ 0.21507295966148376,
9
+ 0.14059017598628998,
10
+ 0.10728383809328079,
11
+ 0.1066611260175705,
12
+ 0.09842122346162796,
13
+ 0.10877804458141327,
14
+ 0.09843869507312775,
15
+ 0.09856921434402466,
16
+ 0.10013321042060852,
17
+ 0.09610398858785629,
18
+ 0.09528868645429611,
19
+ 0.09609043598175049,
20
+ 0.09504454582929611,
21
+ 0.09461775422096252,
22
+ 0.09538693726062775,
23
+ 0.09486550092697144,
24
+ 0.09502706676721573,
25
+ 0.09564735740423203,
26
+ 0.09563229233026505,
27
+ 0.09536463767290115,
28
+ 0.09554819762706757,
29
+ 0.09549544751644135,
30
+ 0.09565941989421844,
31
+ 0.09550147503614426,
32
+ 0.09589602053165436,
33
+ 0.09597408771514893,
34
+ 0.09559731930494308
35
+ ],
36
+ "eval_mse": [
37
+ 0.0507173128426075,
38
+ 0.04139243811368942,
39
+ 0.02957291156053543,
40
+ 0.0648992508649826,
41
+ 0.02996584214270115,
42
+ 0.06873928010463715,
43
+ 0.03262793645262718,
44
+ 0.02407955564558506,
45
+ 0.023550204932689667,
46
+ 0.019672002643346786,
47
+ 0.02080916427075863,
48
+ 0.018793340772390366,
49
+ 0.017699001356959343,
50
+ 0.020223593339323997,
51
+ 0.0172074306756258,
52
+ 0.01772039383649826,
53
+ 0.01798297092318535,
54
+ 0.017709195613861084,
55
+ 0.01745619811117649,
56
+ 0.017487283796072006,
57
+ 0.017418190836906433,
58
+ 0.017374927178025246,
59
+ 0.017170023173093796,
60
+ 0.01734360121190548,
61
+ 0.017127346247434616,
62
+ 0.017153076827526093,
63
+ 0.017261626198887825,
64
+ 0.017204392701387405,
65
+ 0.01731843128800392,
66
+ 0.01728595420718193,
67
+ 0.017363164573907852,
68
+ 0.017249830067157745
69
+ ],
70
+ "eval_loss": [
71
+ 0.0507173053920269,
72
+ 0.04139243811368942,
73
+ 0.029572907835245132,
74
+ 0.0648992508649826,
75
+ 0.02996584214270115,
76
+ 0.06873928010463715,
77
+ 0.03262793645262718,
78
+ 0.02407955564558506,
79
+ 0.023550206795334816,
80
+ 0.019672002643346786,
81
+ 0.02080916427075863,
82
+ 0.018793340772390366,
83
+ 0.017699001356959343,
84
+ 0.020223593339323997,
85
+ 0.0172074306756258,
86
+ 0.01772039383649826,
87
+ 0.01798297092318535,
88
+ 0.017709195613861084,
89
+ 0.01745619811117649,
90
+ 0.017487281933426857,
91
+ 0.017418190836906433,
92
+ 0.017374925315380096,
93
+ 0.017170023173093796,
94
+ 0.01734360121190548,
95
+ 0.017127346247434616,
96
+ 0.017153076827526093,
97
+ 0.017261626198887825,
98
+ 0.017204392701387405,
99
+ 0.01731843128800392,
100
+ 0.01728595420718193,
101
+ 0.017363166436553,
102
+ 0.017249828204512596
103
+ ],
104
+ "loss": [
105
+ 0.121,
106
+ 0.0891,
107
+ 0.0789,
108
+ 0.1049,
109
+ 0.0505,
110
+ 0.0245,
111
+ 0.0176,
112
+ 0.0115,
113
+ 0.0096,
114
+ 0.0089,
115
+ 0.0079,
116
+ 0.005,
117
+ 0.0036,
118
+ 0.0029,
119
+ 0.0034,
120
+ 0.0012,
121
+ 0.0015,
122
+ 0.0008,
123
+ 0.0009,
124
+ 0.0003,
125
+ 0.0002,
126
+ 0.0001,
127
+ 0.0001,
128
+ 0.0001,
129
+ 0.0,
130
+ 0.0,
131
+ 0.0,
132
+ 0.0,
133
+ 0.0,
134
+ 0.0,
135
+ 0.0,
136
+ 0.0
137
+ ]
138
+ }
log_epochs.png ADDED
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9620185adb3e032b355bf88958ba060e04678e9e0c17d7958ce80a4aa97dd1f1
3
+ size 264819850
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<cls>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "<sep>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
3
+ size 1831879
tokenizer_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_dummy_prefix_space": false,
4
+ "add_eos_token": true,
5
+ "add_prefix_space": false,
6
+ "added_tokens_decoder": {
7
+ "0": {
8
+ "content": "<unk>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false,
13
+ "special": true
14
+ },
15
+ "1": {
16
+ "content": "<s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false,
21
+ "special": true
22
+ },
23
+ "2": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false,
29
+ "special": true
30
+ },
31
+ "3": {
32
+ "content": "<pad>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false,
37
+ "special": true
38
+ },
39
+ "4": {
40
+ "content": "<sep>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false,
45
+ "special": true
46
+ },
47
+ "5": {
48
+ "content": "<mask>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false,
53
+ "special": true
54
+ },
55
+ "6": {
56
+ "content": "<cls>",
57
+ "lstrip": false,
58
+ "normalized": false,
59
+ "rstrip": false,
60
+ "single_word": false,
61
+ "special": true
62
+ },
63
+ "7": {
64
+ "content": "<|system|>",
65
+ "lstrip": false,
66
+ "normalized": false,
67
+ "rstrip": false,
68
+ "single_word": false,
69
+ "special": false
70
+ },
71
+ "8": {
72
+ "content": "<|assistant|>",
73
+ "lstrip": false,
74
+ "normalized": false,
75
+ "rstrip": false,
76
+ "single_word": false,
77
+ "special": false
78
+ },
79
+ "9": {
80
+ "content": "<|user|>",
81
+ "lstrip": false,
82
+ "normalized": false,
83
+ "rstrip": false,
84
+ "single_word": false,
85
+ "special": false
86
+ },
87
+ "10": {
88
+ "content": "<|available_tools|>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false,
93
+ "special": false
94
+ },
95
+ "11": {
96
+ "content": "<|tool_calls|>",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false,
101
+ "special": false
102
+ },
103
+ "12": {
104
+ "content": "<|tool_results|>",
105
+ "lstrip": false,
106
+ "normalized": false,
107
+ "rstrip": false,
108
+ "single_word": false,
109
+ "special": false
110
+ },
111
+ "13": {
112
+ "content": "<|code|>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false,
117
+ "special": false
118
+ },
119
+ "14": {
120
+ "content": "<|file|>",
121
+ "lstrip": false,
122
+ "normalized": false,
123
+ "rstrip": false,
124
+ "single_word": false,
125
+ "special": false
126
+ },
127
+ "102397": {
128
+ "content": "<|prefix|>",
129
+ "lstrip": false,
130
+ "normalized": false,
131
+ "rstrip": false,
132
+ "single_word": false,
133
+ "special": false
134
+ },
135
+ "102398": {
136
+ "content": "<|suffix|>",
137
+ "lstrip": false,
138
+ "normalized": false,
139
+ "rstrip": false,
140
+ "single_word": false,
141
+ "special": false
142
+ },
143
+ "102399": {
144
+ "content": "<|middle|>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false,
149
+ "special": false
150
+ }
151
+ },
152
+ "bos_token": "<s>",
153
+ "clean_up_tokenization_spaces": false,
154
+ "cls_token": "<cls>",
155
+ "do_lower_case": false,
156
+ "eos_token": "</s>",
157
+ "extra_ids": 0,
158
+ "extra_special_tokens": {},
159
+ "keep_accents": true,
160
+ "legacy": false,
161
+ "mask_token": "<mask>",
162
+ "model_max_length": 1000000000000000019884624838656,
163
+ "pad_token": "<pad>",
164
+ "padding_side": "right",
165
+ "sep_token": "<sep>",
166
+ "sp_model_kwargs": {},
167
+ "spaces_between_special_tokens": false,
168
+ "tokenizer_class": "LlamaTokenizer",
169
+ "unk_token": "<unk>",
170
+ "use_default_system_prompt": false
171
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21cd18dfccd620200c5c32055b02624b0d8e6f21c5a4666da30b3ec1d42e40be
3
+ size 5368