Hugging Face's logo

veronica-girolimetti
/
outputs

TensorBoard
Safetensors
Model card Files Metrics Community
veronica-girolimetti commited on
Commit
afe321d
•
1 Parent(s): a2356f7

Training in progress, step 280

Browse files
Files changed (10) hide show
  1. adapter_config.json +5 -5
  2. adapter_model.safetensors +2 -2
  3. added_tokens.json +19 -0
  4. runs/Oct17_08-49-06_5a7df1c8e84f/events.out.tfevents.1729154962.5a7df1c8e84f.613.0 +3 -0
  5. runs/Oct17_08-52-07_5a7df1c8e84f/events.out.tfevents.1729155141.5a7df1c8e84f.613.1 +3 -0
  6. runs/Oct17_08-55-21_5a7df1c8e84f/events.out.tfevents.1729155337.5a7df1c8e84f.613.2 +3 -0
  7. special_tokens_map.json +43 -2
  8. tokenizer.model +2 -2
  9. tokenizer_config.json +159 -8
  10. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "BioMistral/BioMistral-7B-DARE",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "down_proj",
24
  "q_proj",
 
25
  "up_proj",
26
- "k_proj",
27
- "gate_proj",
28
- "o_proj",
29
- "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "epfl-llm/meditron-7b",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "k_proj",
24
+ "gate_proj",
25
  "down_proj",
26
  "q_proj",
27
+ "v_proj",
28
  "up_proj",
29
+ "o_proj"
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:384b727e05dcb73ef0739a09c0be55081e380976b12378330cc6753b272d8c09
3
- size 5368770952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3623ddf42e9cfd77baf050555f85fe23b185192292437ca55d5dd9f7583fab81
3
+ size 5117112704
added_tokens.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<CLS>": 32000,
3
+ "<EOD>": 32002,
4
+ "<MASK>": 32003,
5
+ "<PAD>": 32004,
6
+ "<SEP>": 32001,
7
+ "[/bib]": 32010,
8
+ "[/bib_ref]": 32006,
9
+ "[/fig]": 32012,
10
+ "[/fig_ref]": 32008,
11
+ "[/formula]": 32016,
12
+ "[/table]": 32014,
13
+ "[bib]": 32009,
14
+ "[bib_ref]": 32005,
15
+ "[fig]": 32011,
16
+ "[fig_ref]": 32007,
17
+ "[formula]": 32015,
18
+ "[table]": 32013
19
+ }
runs/Oct17_08-49-06_5a7df1c8e84f/events.out.tfevents.1729154962.5a7df1c8e84f.613.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d31b1733d8af0ffbe3ea1a63966943179f8207b5dd4c74269b774f45273b0d
3
+ size 5933
runs/Oct17_08-52-07_5a7df1c8e84f/events.out.tfevents.1729155141.5a7df1c8e84f.613.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d5c24cae1f6ca1ba82199fc171d6c3bf221ca8e7ce8f8625ca6fee3822d92d6
3
+ size 5933
runs/Oct17_08-55-21_5a7df1c8e84f/events.out.tfevents.1729155337.5a7df1c8e84f.613.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd8ce48380c85e3e0d27b9b27efac3d7c5343b69b724c5d5624f894a0502014
3
+ size 11930
special_tokens_map.json CHANGED
@@ -1,7 +1,28 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
 
 
 
 
 
 
 
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
@@ -9,15 +30,35 @@
9
  "eos_token": {
10
  "content": "</s>",
11
  "lstrip": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<unk>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
20
- "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "[bib_ref]",
4
+ "[/bib_ref]",
5
+ "[fig_ref]",
6
+ "[/fig_ref]",
7
+ "[bib]",
8
+ "[/bib]",
9
+ "[fig]",
10
+ "[/fig]",
11
+ "[table]",
12
+ "[/table]",
13
+ "[formula]",
14
+ "[/formula]"
15
+ ],
16
  "bos_token": {
17
  "content": "<s>",
18
  "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "cls_token": {
24
+ "content": "<CLS>",
25
+ "lstrip": false,
26
  "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
 
30
  "eos_token": {
31
  "content": "</s>",
32
  "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "mask_token": {
38
+ "content": "<MASK>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "pad_token": {
45
+ "content": "<PAD>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ },
51
+ "sep_token": {
52
+ "content": "<SEP>",
53
+ "lstrip": false,
54
  "normalized": false,
55
  "rstrip": false,
56
  "single_word": false
57
  },
 
58
  "unk_token": {
59
  "content": "<unk>",
60
  "lstrip": false,
61
+ "normalized": true,
62
  "rstrip": false,
63
  "single_word": false
64
  }
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
- size 493443
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
8
  "lstrip": false,
9
- "normalized": false,
10
  "rstrip": false,
11
  "single_word": false,
12
  "special": true
@@ -14,7 +14,7 @@
14
  "1": {
15
  "content": "<s>",
16
  "lstrip": false,
17
- "normalized": false,
18
  "rstrip": false,
19
  "single_word": false,
20
  "special": true
@@ -22,21 +22,172 @@
22
  "2": {
23
  "content": "</s>",
24
  "lstrip": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  "normalized": false,
26
  "rstrip": false,
27
  "single_word": false,
28
  "special": true
29
  }
30
  },
31
- "additional_special_tokens": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  "bos_token": "<s>",
33
- "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
34
  "clean_up_tokenization_spaces": false,
 
35
  "eos_token": "</s>",
36
- "legacy": true,
37
- "model_max_length": 32768,
38
- "pad_token": "<unk>",
 
39
  "padding_side": "right",
 
40
  "sp_model_kwargs": {},
41
  "spaces_between_special_tokens": false,
42
  "tokenizer_class": "LlamaTokenizer",
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
8
  "lstrip": false,
9
+ "normalized": true,
10
  "rstrip": false,
11
  "single_word": false,
12
  "special": true
 
14
  "1": {
15
  "content": "<s>",
16
  "lstrip": false,
17
+ "normalized": true,
18
  "rstrip": false,
19
  "single_word": false,
20
  "special": true
 
22
  "2": {
23
  "content": "</s>",
24
  "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<CLS>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<SEP>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<EOD>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<MASK>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<PAD>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "[bib_ref]",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "[/bib_ref]",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "[fig_ref]",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "[/fig_ref]",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "[bib]",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "[/bib]",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "[fig]",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "[/fig]",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "32013": {
135
+ "content": "[table]",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "32014": {
143
+ "content": "[/table]",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "32015": {
151
+ "content": "[formula]",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "32016": {
159
+ "content": "[/formula]",
160
+ "lstrip": false,
161
  "normalized": false,
162
  "rstrip": false,
163
  "single_word": false,
164
  "special": true
165
  }
166
  },
167
+ "additional_special_tokens": [
168
+ "[bib_ref]",
169
+ "[/bib_ref]",
170
+ "[fig_ref]",
171
+ "[/fig_ref]",
172
+ "[bib]",
173
+ "[/bib]",
174
+ "[fig]",
175
+ "[/fig]",
176
+ "[table]",
177
+ "[/table]",
178
+ "[formula]",
179
+ "[/formula]"
180
+ ],
181
  "bos_token": "<s>",
 
182
  "clean_up_tokenization_spaces": false,
183
+ "cls_token": "<CLS>",
184
  "eos_token": "</s>",
185
+ "legacy": false,
186
+ "mask_token": "<MASK>",
187
+ "model_max_length": 4096,
188
+ "pad_token": "<PAD>",
189
  "padding_side": "right",
190
+ "sep_token": "<SEP>",
191
  "sp_model_kwargs": {},
192
  "spaces_between_special_tokens": false,
193
  "tokenizer_class": "LlamaTokenizer",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed8985a3e13456185287842fb82455c0643a9c165ae63641112815ec718511d8
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9906bf4e163fe8a7af412354fc7aae2bd1c2e974f8139abafce6fdfaae2f822e
3
  size 5432