Hugging Face's logo

frankjperez
/
sft_output

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
sft
Model card Files Metrics Community
frankjperez commited on
Commit
2091fe1
·
verified ·
1 Parent(s): d3fd537

Training in progress, epoch 0

Browse files
Files changed (19) hide show
  1. adapter_config.json +32 -0
  2. adapter_model.safetensors +3 -0
  3. added_tokens.json +5 -0
  4. merges.txt +0 -0
  5. runs/Jan14_10-17-18_mad-ws-ml/events.out.tfevents.1736849845.mad-ws-ml +3 -0
  6. runs/Jan14_10-18-04_mad-ws-ml/events.out.tfevents.1736849891.mad-ws-ml +3 -0
  7. runs/Jan14_10-24-53_mad-ws-ml/events.out.tfevents.1736850296.mad-ws-ml +3 -0
  8. runs/Jan14_10-29-23_mad-ws-ml/events.out.tfevents.1736850567.mad-ws-ml +3 -0
  9. runs/Jan14_10-30-53_mad-ws-ml/events.out.tfevents.1736850655.mad-ws-ml +3 -0
  10. runs/Jan14_10-31-29_mad-ws-ml/events.out.tfevents.1736850691.mad-ws-ml +3 -0
  11. runs/Jan14_10-32-17_mad-ws-ml/events.out.tfevents.1736850746.mad-ws-ml +3 -0
  12. runs/Jan14_10-33-19_mad-ws-ml/events.out.tfevents.1736850800.mad-ws-ml +3 -0
  13. runs/Jan14_10-36-21_mad-ws-ml/events.out.tfevents.1736850983.mad-ws-ml +3 -0
  14. runs/Jan14_10-50-59_mad-ws-ml/events.out.tfevents.1736851859.mad-ws-ml +3 -0
  15. special_tokens_map.json +53 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +183 -0
  18. training_args.bin +3 -0
  19. vocab.json +0 -0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "HuggingFaceTB/SmolVLM-Instruct",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 8,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "q_proj",
27
+ "v_proj"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "use_dora": false,
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c45a043d93b362166e8575f1b52416b4f7d9232bcc041b9f9e482fe19f319198
3
+ size 10302960
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<end_of_utterance>": 49154,
3
+ "<fake_token_around_image>": 49152,
4
+ "<image>": 49153
5
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jan14_10-17-18_mad-ws-ml/events.out.tfevents.1736849845.mad-ws-ml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b67e695e2c849a019895dffaa691252206fc9389d942c33e3030af4cf94c97
3
+ size 8949
runs/Jan14_10-18-04_mad-ws-ml/events.out.tfevents.1736849891.mad-ws-ml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c1768e459cc373654d2c01db17137a58494a4fc7a07a4ecaf0f0cfb2ca9726
3
+ size 9160
runs/Jan14_10-24-53_mad-ws-ml/events.out.tfevents.1736850296.mad-ws-ml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f592817a4158d9ccb3480106cb640fe136b89c00a99b31e6699939ebb7f4d23d
3
+ size 9160
runs/Jan14_10-29-23_mad-ws-ml/events.out.tfevents.1736850567.mad-ws-ml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62af24a2b0328f22540bc449a50f01f0084d51d5b0c15a9ca9cf6b14de6c2cf7
3
+ size 8952
runs/Jan14_10-30-53_mad-ws-ml/events.out.tfevents.1736850655.mad-ws-ml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d6bea379de4058ca3a3f160f67ee0a6b2c87bacc6f06e4a4d371196215385a
3
+ size 8952
runs/Jan14_10-31-29_mad-ws-ml/events.out.tfevents.1736850691.mad-ws-ml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a97e0e013d0484ab2431342464e75f71576016fbbb4c026a99dfce8beb308e88
3
+ size 8952
runs/Jan14_10-32-17_mad-ws-ml/events.out.tfevents.1736850746.mad-ws-ml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737517a181fd05207033845ae7661efeec3593b441da8e6308683a798370df10
3
+ size 8952
runs/Jan14_10-33-19_mad-ws-ml/events.out.tfevents.1736850800.mad-ws-ml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad3aba12027687e0fea40f1bda4af9d21e08f20601ea1157d7939d629c16e1f8
3
+ size 8956
runs/Jan14_10-36-21_mad-ws-ml/events.out.tfevents.1736850983.mad-ws-ml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73019201995ce732d30493f295576a6c9769ac804e11460cd4ae3444df3c6f6a
3
+ size 8956
runs/Jan14_10-50-59_mad-ws-ml/events.out.tfevents.1736851859.mad-ws-ml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca2ffff20d51ef6e6d7fb86c07bf85efe61a50e1ec7f6c5f3bb32a4dbf404aa
3
+ size 9369
special_tokens_map.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<fake_token_around_image>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<image>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<end_of_utterance>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": {
26
+ "content": "<|im_start|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "<end_of_utterance>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": {
40
+ "content": "<|im_end|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "unk_token": {
47
+ "content": "<|endoftext|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ }
53
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "49152": {
141
+ "content": "<fake_token_around_image>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49153": {
149
+ "content": "<image>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49154": {
157
+ "content": "<end_of_utterance>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ }
164
+ },
165
+ "additional_special_tokens": [
166
+ "<fake_token_around_image>",
167
+ "<image>",
168
+ "<end_of_utterance>"
169
+ ],
170
+ "bos_token": "<|im_start|>",
171
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
172
+ "clean_up_tokenization_spaces": false,
173
+ "eos_token": "<end_of_utterance>",
174
+ "extra_special_tokens": {},
175
+ "legacy": false,
176
+ "model_max_length": 16384,
177
+ "pad_token": "<|im_end|>",
178
+ "processor_class": "Idefics3Processor",
179
+ "tokenizer_class": "GPT2Tokenizer",
180
+ "truncation_side": "left",
181
+ "unk_token": "<|endoftext|>",
182
+ "vocab_size": 49152
183
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ce1ff7956a6e7ccee4ccc89d3ecbe4894f4959b3e76e68285a6a2c6782f661
3
+ size 5624
vocab.json ADDED
The diff for this file is too large to render. See raw diff