Hugging Face's logo

joelniklaus
/
test-optimized

Image-to-Text
Transformers
Safetensors
gemma3
Generated from Trainer
trl
sft
text-generation-inference
Model card Files
xet
Community
joelniklaus HF Staff commited on
Commit
842bfaa
·
verified ·
1 Parent(s): b87910a

Training in progress, step 2, checkpoint

Browse files
Files changed (27) hide show
  1. .gitattributes +1 -0
  2. last-checkpoint/added_tokens.json +3 -0
  3. last-checkpoint/chat_template.jinja +47 -0
  4. last-checkpoint/config.json +125 -0
  5. last-checkpoint/generation_config.json +14 -0
  6. last-checkpoint/model-00001-of-00012.safetensors +3 -0
  7. last-checkpoint/model-00002-of-00012.safetensors +3 -0
  8. last-checkpoint/model-00003-of-00012.safetensors +3 -0
  9. last-checkpoint/model-00004-of-00012.safetensors +3 -0
  10. last-checkpoint/model-00005-of-00012.safetensors +3 -0
  11. last-checkpoint/model-00006-of-00012.safetensors +3 -0
  12. last-checkpoint/model-00007-of-00012.safetensors +3 -0
  13. last-checkpoint/model-00008-of-00012.safetensors +3 -0
  14. last-checkpoint/model-00009-of-00012.safetensors +3 -0
  15. last-checkpoint/model-00010-of-00012.safetensors +3 -0
  16. last-checkpoint/model-00011-of-00012.safetensors +3 -0
  17. last-checkpoint/model-00012-of-00012.safetensors +3 -0
  18. last-checkpoint/model.safetensors.index.json +0 -0
  19. last-checkpoint/optimizer.pt +3 -0
  20. last-checkpoint/rng_state.pth +3 -0
  21. last-checkpoint/scheduler.pt +3 -0
  22. last-checkpoint/special_tokens_map.json +33 -0
  23. last-checkpoint/tokenizer.json +3 -0
  24. last-checkpoint/tokenizer.model +3 -0
  25. last-checkpoint/tokenizer_config.json +0 -0
  26. last-checkpoint/trainer_state.json +33 -0
  27. last-checkpoint/training_args.bin +3 -0
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
last-checkpoint/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
last-checkpoint/chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
47
+ {%- endif -%}
last-checkpoint/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "dtype": "bfloat16",
8
+ "eoi_token_index": 256000,
9
+ "eos_token_id": 1,
10
+ "image_token_index": 262144,
11
+ "initializer_range": 0.02,
12
+ "mm_tokens_per_image": 256,
13
+ "model_type": "gemma3",
14
+ "pad_token_id": 0,
15
+ "text_config": {
16
+ "_sliding_window_pattern": 6,
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "attn_logit_softcapping": null,
20
+ "dtype": "bfloat16",
21
+ "final_logit_softcapping": null,
22
+ "head_dim": 128,
23
+ "hidden_activation": "gelu_pytorch_tanh",
24
+ "hidden_size": 5376,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 21504,
27
+ "layer_types": [
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "full_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "full_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "full_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "full_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "full_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "sliding_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "full_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "sliding_attention",
85
+ "sliding_attention",
86
+ "sliding_attention",
87
+ "full_attention",
88
+ "sliding_attention",
89
+ "sliding_attention"
90
+ ],
91
+ "max_position_embeddings": 131072,
92
+ "model_type": "gemma3_text",
93
+ "num_attention_heads": 32,
94
+ "num_hidden_layers": 62,
95
+ "num_key_value_heads": 16,
96
+ "query_pre_attn_scalar": 168,
97
+ "rms_norm_eps": 1e-06,
98
+ "rope_local_base_freq": 10000.0,
99
+ "rope_scaling": {
100
+ "factor": 8.0,
101
+ "rope_type": "linear"
102
+ },
103
+ "rope_theta": 1000000.0,
104
+ "sliding_window": 1024,
105
+ "use_bidirectional_attention": false,
106
+ "use_cache": true,
107
+ "vocab_size": 262208
108
+ },
109
+ "transformers_version": "4.57.3",
110
+ "vision_config": {
111
+ "attention_dropout": 0.0,
112
+ "dtype": "bfloat16",
113
+ "hidden_act": "gelu_pytorch_tanh",
114
+ "hidden_size": 1152,
115
+ "image_size": 896,
116
+ "intermediate_size": 4304,
117
+ "layer_norm_eps": 1e-06,
118
+ "model_type": "siglip_vision_model",
119
+ "num_attention_heads": 16,
120
+ "num_channels": 3,
121
+ "num_hidden_layers": 27,
122
+ "patch_size": 14,
123
+ "vision_use_head": false
124
+ }
125
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 1,
8
+ 106
9
+ ],
10
+ "pad_token_id": 0,
11
+ "top_k": 64,
12
+ "top_p": 0.95,
13
+ "transformers_version": "4.57.3"
14
+ }
last-checkpoint/model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c647dfacc1e54d271be56139f731285c28184f708eeb430d000f51df630c3a07
3
+ size 4854573696
last-checkpoint/model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5189d8550baafcbbad4c36610da4cf70e869b76a5f608f85f9cbcf9efcb99075
3
+ size 4954792944
last-checkpoint/model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d06bd8f73f2708cc8570ec76a2d29c024e8ed74291b5e485fe9c53894f1543fa
3
+ size 4954792976
last-checkpoint/model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d286319bd3e24214ff0d36b736f25bf13239e50edbcb0bd9c0e665c3eda1cda6
3
+ size 4954793016
last-checkpoint/model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a03c4b67435bd87b14c59984fdc02976a1907cea7c6577e2f416cd507d4a27f
3
+ size 4954793016
last-checkpoint/model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25cb928b2d2e9e3fee98274c550de42439926013422d566d461f86cf903948b
3
+ size 4954793016
last-checkpoint/model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3196e79fd1b8a5b6bce49b0a5c9771296e9dbe6817cfa1e9f95d0925c23aded3
3
+ size 4954793016
last-checkpoint/model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4b9e4fa0dd33240dbd69ba2e7aa6e82b04e0a2f94e402c92733646027be21be
3
+ size 4954793016
last-checkpoint/model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c832f37d7924e9415cc037b4a73a5ee15e275c32f8ce0a0d3ab4ebaf9e9764
3
+ size 4954793016
last-checkpoint/model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2649115da495e4a30931f2246b3dadf3e1a0309f5e034d1dd1e71c6d77f3b206
3
+ size 4954793016
last-checkpoint/model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c24a159b0c5627e4b73fb99d5ac22831894e6c9c54350e6786444119e42df9
3
+ size 4954793016
last-checkpoint/model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e43d0df432fb1d2c8579b9b00a5dd229f3fc0ca9b165cd7a410a125fb49bf4
3
+ size 462476696
last-checkpoint/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8bd0002935d699caf7043bd1f75ee693119aa474315f0e1d16f1e8a02e42ab
3
+ size 108038095650
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e77b3705002784ffe4e0c22b2b8722ae2d7710c6f824e5193c3861902144216
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:426e4bff8e6d6d20581b3490b21650e219696e00914362a438fc0a74add37214
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
last-checkpoint/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
last-checkpoint/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 1000,
7
+ "global_step": 2,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 10,
13
+ "max_steps": 2,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 1,
16
+ "save_steps": 1000,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": true
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 799274736844800.0,
30
+ "train_batch_size": 2,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871a7e51c014cbb3b547dbdc26ceaa9b4a8862d3049eb46748d73ec98234a864
3
+ size 6008