sidbaines commited on
Commit
b7b2b9c
·
verified ·
1 Parent(s): 57090f2

4b scale-up control SFT checkpoint 4

Browse files
.gitattributes CHANGED
@@ -63,3 +63,4 @@ sft_4epoch/coin/checkpoint-12/tokenizer.json filter=lfs diff=lfs merge=lfs -text
63
  sft_4epoch/coin/checkpoint-24/tokenizer.json filter=lfs diff=lfs merge=lfs -text
64
  sft_4epoch/coin/checkpoint-36/tokenizer.json filter=lfs diff=lfs merge=lfs -text
65
  sft_4epoch/coin/checkpoint-48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
63
  sft_4epoch/coin/checkpoint-24/tokenizer.json filter=lfs diff=lfs merge=lfs -text
64
  sft_4epoch/coin/checkpoint-36/tokenizer.json filter=lfs diff=lfs merge=lfs -text
65
  sft_4epoch/coin/checkpoint-48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
66
+ sft_4epoch/control/checkpoint-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
sft_4epoch/control/checkpoint-4/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 -%}
sft_4epoch/control/checkpoint-4/config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token_id": 2,
21
+ "cache_implementation": "hybrid",
22
+ "dtype": "bfloat16",
23
+ "eos_token_id": 1,
24
+ "final_logit_softcapping": null,
25
+ "head_dim": 256,
26
+ "hidden_activation": "gelu_pytorch_tanh",
27
+ "hidden_size": 2560,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 10240,
30
+ "layer_types": [
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "full_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "full_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention"
65
+ ],
66
+ "max_position_embeddings": 131072,
67
+ "model_type": "gemma3_text",
68
+ "num_attention_heads": 8,
69
+ "num_hidden_layers": 34,
70
+ "num_key_value_heads": 4,
71
+ "pad_token_id": 0,
72
+ "query_pre_attn_scalar": 256,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_parameters": {
75
+ "full_attention": {
76
+ "factor": 8.0,
77
+ "rope_theta": 1000000.0,
78
+ "rope_type": "linear"
79
+ },
80
+ "sliding_attention": {
81
+ "rope_theta": 10000.0,
82
+ "rope_type": "default"
83
+ }
84
+ },
85
+ "sliding_window": 1024,
86
+ "sliding_window_pattern": 6,
87
+ "tie_word_embeddings": true,
88
+ "use_bidirectional_attention": false,
89
+ "use_cache": false,
90
+ "vocab_size": 262208
91
+ },
92
+ "tie_word_embeddings": true,
93
+ "transformers_version": "5.9.0",
94
+ "unsloth_fixed": true,
95
+ "use_cache": false,
96
+ "vision_config": {
97
+ "attention_dropout": 0.0,
98
+ "dtype": "bfloat16",
99
+ "hidden_act": "gelu_pytorch_tanh",
100
+ "hidden_size": 1152,
101
+ "image_size": 896,
102
+ "intermediate_size": 4304,
103
+ "layer_norm_eps": 1e-06,
104
+ "model_type": "siglip_vision_model",
105
+ "num_attention_heads": 16,
106
+ "num_channels": 3,
107
+ "num_hidden_layers": 27,
108
+ "patch_size": 14,
109
+ "vision_use_head": false
110
+ }
111
+ }
sft_4epoch/control/checkpoint-4/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.9.0"
13
+ }
sft_4epoch/control/checkpoint-4/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afdd602dc689e202bdc92969ff94069f087ceaef922f589917e9887f5e47e4e6
3
+ size 9942783064
sft_4epoch/control/checkpoint-4/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5ae5cf0e68b9af60509e7f43d09f9aa60d0101c8a9eb9b121b85b196a0e855c
3
+ size 15521485995
sft_4epoch/control/checkpoint-4/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessor",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
sft_4epoch/control/checkpoint-4/processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
sft_4epoch/control/checkpoint-4/pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:858c2937fa094c17736455361b52d8d60c50c8114945c6f7f01270f110767f08
3
+ size 9942970813
sft_4epoch/control/checkpoint-4/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6ae654ed628e46a69a3185a2008a760ecb6fa76a6ed8ea36091fbf51572a9dc
3
+ size 14917
sft_4epoch/control/checkpoint-4/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aca90864f21237f3b2ef7719c284655f031e849a610ff91881a6d9e258037405
3
+ size 14917
sft_4epoch/control/checkpoint-4/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc25ede503d6f6adf77ae1c226ca09b3ff68c3472bc530c6fdf8dfeb20cb3590
3
+ size 1465
sft_4epoch/control/checkpoint-4/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
3
+ size 33384567
sft_4epoch/control/checkpoint-4/tokenizer_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "boi_token": "<start_of_image>",
4
+ "bos_token": "<bos>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eoi_token": "<end_of_image>",
7
+ "eos_token": "<eos>",
8
+ "image_token": "<image_soft_token>",
9
+ "is_local": true,
10
+ "local_files_only": false,
11
+ "mask_token": "<mask>",
12
+ "model_max_length": 131072,
13
+ "model_specific_special_tokens": {
14
+ "boi_token": "<start_of_image>",
15
+ "eoi_token": "<end_of_image>",
16
+ "image_token": "<image_soft_token>"
17
+ },
18
+ "pad_token": "<pad>",
19
+ "padding_side": "left",
20
+ "processor_class": "Gemma3Processor",
21
+ "sp_model_kwargs": null,
22
+ "spaces_between_special_tokens": false,
23
+ "tokenizer_class": "GemmaTokenizer",
24
+ "unk_token": "<unk>",
25
+ "use_default_system_prompt": false
26
+ }
sft_4epoch/control/checkpoint-4/tokens_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"total": 8388608, "trainable": 5229996}
sft_4epoch/control/checkpoint-4/trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.0071111111111111115,
6
+ "eval_steps": 500,
7
+ "global_step": 4,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0017777777777777779,
14
+ "grad_norm": 2.875,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.09912109375,
17
+ "memory/device_reserved (GiB)": 40.7,
18
+ "memory/max_active (GiB)": 34.07,
19
+ "memory/max_allocated (GiB)": 34.07,
20
+ "ppl": 3.00153,
21
+ "step": 1,
22
+ "tokens/total": 2097152,
23
+ "tokens/train_per_sec_per_gpu": 631.15,
24
+ "tokens/trainable": 1319329
25
+ },
26
+ {
27
+ "epoch": 0.0035555555555555557,
28
+ "grad_norm": 2.890625,
29
+ "learning_rate": 3.3333333333333333e-06,
30
+ "loss": 1.0859375,
31
+ "memory/device_reserved (GiB)": 47.77,
32
+ "memory/max_active (GiB)": 41.3,
33
+ "memory/max_allocated (GiB)": 41.3,
34
+ "ppl": 2.96222,
35
+ "step": 2,
36
+ "tokens/total": 4194304,
37
+ "tokens/train_per_sec_per_gpu": 616.0,
38
+ "tokens/trainable": 2628278
39
+ },
40
+ {
41
+ "epoch": 0.005333333333333333,
42
+ "grad_norm": 2.578125,
43
+ "learning_rate": 6.666666666666667e-06,
44
+ "loss": 1.0758056640625,
45
+ "memory/device_reserved (GiB)": 47.77,
46
+ "memory/max_active (GiB)": 41.3,
47
+ "memory/max_allocated (GiB)": 41.3,
48
+ "ppl": 2.93235,
49
+ "step": 3,
50
+ "tokens/total": 6291456,
51
+ "tokens/train_per_sec_per_gpu": 655.05,
52
+ "tokens/trainable": 3948806
53
+ },
54
+ {
55
+ "epoch": 0.0071111111111111115,
56
+ "grad_norm": 1.71875,
57
+ "learning_rate": 1e-05,
58
+ "loss": 1.0162353515625,
59
+ "memory/device_reserved (GiB)": 47.77,
60
+ "memory/max_active (GiB)": 41.3,
61
+ "memory/max_allocated (GiB)": 41.3,
62
+ "ppl": 2.76277,
63
+ "step": 4,
64
+ "tokens/total": 8388608,
65
+ "tokens/train_per_sec_per_gpu": 598.59,
66
+ "tokens/trainable": 5229996
67
+ }
68
+ ],
69
+ "logging_steps": 1,
70
+ "max_steps": 48,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 1,
73
+ "save_steps": 500,
74
+ "stateful_callbacks": {
75
+ "TrainerControl": {
76
+ "args": {
77
+ "should_epoch_stop": false,
78
+ "should_evaluate": false,
79
+ "should_log": false,
80
+ "should_save": true,
81
+ "should_training_stop": false
82
+ },
83
+ "attributes": {}
84
+ }
85
+ },
86
+ "total_flos": 1.8240734696046592e+17,
87
+ "train_batch_size": 8,
88
+ "trial_name": null,
89
+ "trial_params": null
90
+ }
sft_4epoch/control/checkpoint-4/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86036685f74c9b56ba03469e3541a7e7b5fb88833612f5f84a8c12343ddc38b4
3
+ size 8913