gyung commited on
Commit
a905561
·
verified ·
1 Parent(s): 712f9a8

Upload folder using huggingface_hub

Browse files
checkpoint-55/chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is true %}
150
+ {{- '<think>\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n\n</think>\n\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
checkpoint-55/config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 248046,
7
+ "image_token_id": 248056,
8
+ "model_name": "Qwen/Qwen3.5-2B",
9
+ "model_type": "qwen3_5",
10
+ "pad_token_id": 248044,
11
+ "text_config": {
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "attn_output_gate": true,
15
+ "bos_token_id": null,
16
+ "dtype": "bfloat16",
17
+ "eos_token_id": 248044,
18
+ "full_attention_interval": 4,
19
+ "head_dim": 256,
20
+ "hidden_act": "silu",
21
+ "hidden_size": 2048,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 6144,
24
+ "layer_types": [
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "full_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "full_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "full_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "full_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "full_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "full_attention"
49
+ ],
50
+ "linear_conv_kernel_dim": 4,
51
+ "linear_key_head_dim": 128,
52
+ "linear_num_key_heads": 16,
53
+ "linear_num_value_heads": 16,
54
+ "linear_value_head_dim": 128,
55
+ "mamba_ssm_dtype": "float32",
56
+ "max_position_embeddings": 262144,
57
+ "mlp_only_layers": [],
58
+ "model_type": "qwen3_5_text",
59
+ "mtp_num_hidden_layers": 1,
60
+ "mtp_use_dedicated_embeddings": false,
61
+ "num_attention_heads": 8,
62
+ "num_hidden_layers": 24,
63
+ "num_key_value_heads": 2,
64
+ "pad_token_id": null,
65
+ "partial_rotary_factor": 0.25,
66
+ "rms_norm_eps": 1e-06,
67
+ "rope_parameters": {
68
+ "mrope_interleaved": true,
69
+ "mrope_section": [
70
+ 11,
71
+ 11,
72
+ 10
73
+ ],
74
+ "partial_rotary_factor": 0.25,
75
+ "rope_theta": 10000000,
76
+ "rope_type": "default"
77
+ },
78
+ "tie_word_embeddings": true,
79
+ "use_cache": true,
80
+ "vocab_size": 248320
81
+ },
82
+ "tie_word_embeddings": true,
83
+ "transformers_version": "5.5.0",
84
+ "unsloth_version": "2026.4.8",
85
+ "use_cache": false,
86
+ "video_token_id": 248057,
87
+ "vision_config": {
88
+ "deepstack_visual_indexes": [],
89
+ "depth": 24,
90
+ "dtype": "bfloat16",
91
+ "hidden_act": "gelu_pytorch_tanh",
92
+ "hidden_size": 1024,
93
+ "in_channels": 3,
94
+ "initializer_range": 0.02,
95
+ "intermediate_size": 4096,
96
+ "model_type": "qwen3_5",
97
+ "num_heads": 16,
98
+ "num_position_embeddings": 2304,
99
+ "out_hidden_size": 2048,
100
+ "patch_size": 16,
101
+ "spatial_merge_size": 2,
102
+ "temporal_patch_size": 2
103
+ },
104
+ "vision_end_token_id": 248054,
105
+ "vision_start_token_id": 248053
106
+ }
checkpoint-55/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 248046,
5
+ 248044
6
+ ],
7
+ "pad_token_id": 248044,
8
+ "transformers_version": "5.5.0",
9
+ "use_cache": true
10
+ }
checkpoint-55/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:171e567ca6f39da1a86d8b6525c3597ec50c024f81d4055b81a8152ba29ebd18
3
+ size 4426572920
checkpoint-55/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a73ef649e98c7aa6941ef30a984ffb5d148d2efab18af6966a66c940517c8e0
3
+ size 6858879981
checkpoint-55/processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
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": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
checkpoint-55/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273ad22b3c89bffcd8d31d41b3a4f35a4e3f227292abd8cb9b2d2de2c94b6232
3
+ size 16325
checkpoint-55/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:244a3dafe58ee84bf0d61cf52ecf93f21a2025f004b82fba5b1a1abdb7010094
3
+ size 16325
checkpoint-55/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9f29aa35256c90c22f248be5d82c67127ff8ff8ee92e5859f0723b9cc3a995
3
+ size 16325
checkpoint-55/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094f72446a61fe37cd5f66de2c1a1af02ff66057d676686f2407afd788722f37
3
+ size 16325
checkpoint-55/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed5d6dbc714fdcfe26d8d251ca45c1e87ab8919065f686cfb30412dc367e63ff
3
+ size 16325
checkpoint-55/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03592e430c05ca680c73fef4cc130f0470e32dbb019f85ae4abdeae205f19727
3
+ size 16325
checkpoint-55/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c941d50874e595c2d28cd152e55beb3b8ffee575ac35a356135cc537ba94ca5a
3
+ size 16325
checkpoint-55/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91714d462a3ef168563ff7bca05e9c4fd8bea7d039f09e4df15873f0ca9a9511
3
+ size 16325
checkpoint-55/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13b8110f0ee8946add717c79db3bd3bfce711aef8f7d01e7824d0092d5589c23
3
+ size 1465
checkpoint-55/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
checkpoint-55/tokenizer_config.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": false,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "padding_side": "right",
25
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
26
+ "processor_class": "Qwen3VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "TokenizersBackend",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>",
33
+ "added_tokens_decoder": {
34
+ "248044": {
35
+ "content": "<|endoftext|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ "248045": {
43
+ "content": "<|im_start|>",
44
+ "single_word": false,
45
+ "lstrip": false,
46
+ "rstrip": false,
47
+ "normalized": false,
48
+ "special": true
49
+ },
50
+ "248046": {
51
+ "content": "<|im_end|>",
52
+ "single_word": false,
53
+ "lstrip": false,
54
+ "rstrip": false,
55
+ "normalized": false,
56
+ "special": true
57
+ },
58
+ "248047": {
59
+ "content": "<|object_ref_start|>",
60
+ "single_word": false,
61
+ "lstrip": false,
62
+ "rstrip": false,
63
+ "normalized": false,
64
+ "special": true
65
+ },
66
+ "248048": {
67
+ "content": "<|object_ref_end|>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ "248049": {
75
+ "content": "<|box_start|>",
76
+ "single_word": false,
77
+ "lstrip": false,
78
+ "rstrip": false,
79
+ "normalized": false,
80
+ "special": true
81
+ },
82
+ "248050": {
83
+ "content": "<|box_end|>",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": false,
88
+ "special": true
89
+ },
90
+ "248051": {
91
+ "content": "<|quad_start|>",
92
+ "single_word": false,
93
+ "lstrip": false,
94
+ "rstrip": false,
95
+ "normalized": false,
96
+ "special": true
97
+ },
98
+ "248052": {
99
+ "content": "<|quad_end|>",
100
+ "single_word": false,
101
+ "lstrip": false,
102
+ "rstrip": false,
103
+ "normalized": false,
104
+ "special": true
105
+ },
106
+ "248053": {
107
+ "content": "<|vision_start|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ "248054": {
115
+ "content": "<|vision_end|>",
116
+ "single_word": false,
117
+ "lstrip": false,
118
+ "rstrip": false,
119
+ "normalized": false,
120
+ "special": true
121
+ },
122
+ "248055": {
123
+ "content": "<|vision_pad|>",
124
+ "single_word": false,
125
+ "lstrip": false,
126
+ "rstrip": false,
127
+ "normalized": false,
128
+ "special": true
129
+ },
130
+ "248056": {
131
+ "content": "<|image_pad|>",
132
+ "single_word": false,
133
+ "lstrip": false,
134
+ "rstrip": false,
135
+ "normalized": false,
136
+ "special": true
137
+ },
138
+ "248057": {
139
+ "content": "<|video_pad|>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": true
145
+ },
146
+ "248058": {
147
+ "content": "<tool_call>",
148
+ "single_word": false,
149
+ "lstrip": false,
150
+ "rstrip": false,
151
+ "normalized": false,
152
+ "special": false
153
+ },
154
+ "248059": {
155
+ "content": "</tool_call>",
156
+ "single_word": false,
157
+ "lstrip": false,
158
+ "rstrip": false,
159
+ "normalized": false,
160
+ "special": false
161
+ },
162
+ "248060": {
163
+ "content": "<|fim_prefix|>",
164
+ "single_word": false,
165
+ "lstrip": false,
166
+ "rstrip": false,
167
+ "normalized": false,
168
+ "special": false
169
+ },
170
+ "248061": {
171
+ "content": "<|fim_middle|>",
172
+ "single_word": false,
173
+ "lstrip": false,
174
+ "rstrip": false,
175
+ "normalized": false,
176
+ "special": false
177
+ },
178
+ "248062": {
179
+ "content": "<|fim_suffix|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": false
185
+ },
186
+ "248063": {
187
+ "content": "<|fim_pad|>",
188
+ "single_word": false,
189
+ "lstrip": false,
190
+ "rstrip": false,
191
+ "normalized": false,
192
+ "special": false
193
+ },
194
+ "248064": {
195
+ "content": "<|repo_name|>",
196
+ "single_word": false,
197
+ "lstrip": false,
198
+ "rstrip": false,
199
+ "normalized": false,
200
+ "special": false
201
+ },
202
+ "248065": {
203
+ "content": "<|file_sep|>",
204
+ "single_word": false,
205
+ "lstrip": false,
206
+ "rstrip": false,
207
+ "normalized": false,
208
+ "special": false
209
+ },
210
+ "248066": {
211
+ "content": "<tool_response>",
212
+ "single_word": false,
213
+ "lstrip": false,
214
+ "rstrip": false,
215
+ "normalized": false,
216
+ "special": false
217
+ },
218
+ "248067": {
219
+ "content": "</tool_response>",
220
+ "single_word": false,
221
+ "lstrip": false,
222
+ "rstrip": false,
223
+ "normalized": false,
224
+ "special": false
225
+ },
226
+ "248068": {
227
+ "content": "<think>",
228
+ "single_word": false,
229
+ "lstrip": false,
230
+ "rstrip": false,
231
+ "normalized": false,
232
+ "special": false
233
+ },
234
+ "248069": {
235
+ "content": "</think>",
236
+ "single_word": false,
237
+ "lstrip": false,
238
+ "rstrip": false,
239
+ "normalized": false,
240
+ "special": false
241
+ },
242
+ "248070": {
243
+ "content": "<|audio_start|>",
244
+ "single_word": false,
245
+ "lstrip": false,
246
+ "rstrip": false,
247
+ "normalized": false,
248
+ "special": true
249
+ },
250
+ "248071": {
251
+ "content": "<|audio_end|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ "248072": {
259
+ "content": "<tts_pad>",
260
+ "single_word": false,
261
+ "lstrip": false,
262
+ "rstrip": false,
263
+ "normalized": false,
264
+ "special": true
265
+ },
266
+ "248073": {
267
+ "content": "<tts_text_bos>",
268
+ "single_word": false,
269
+ "lstrip": false,
270
+ "rstrip": false,
271
+ "normalized": false,
272
+ "special": true
273
+ },
274
+ "248074": {
275
+ "content": "<tts_text_eod>",
276
+ "single_word": false,
277
+ "lstrip": false,
278
+ "rstrip": false,
279
+ "normalized": false,
280
+ "special": true
281
+ },
282
+ "248075": {
283
+ "content": "<tts_text_bos_single>",
284
+ "single_word": false,
285
+ "lstrip": false,
286
+ "rstrip": false,
287
+ "normalized": false,
288
+ "special": true
289
+ },
290
+ "248076": {
291
+ "content": "<|audio_pad|>",
292
+ "single_word": false,
293
+ "lstrip": false,
294
+ "rstrip": false,
295
+ "normalized": false,
296
+ "special": true
297
+ }
298
+ }
299
+ }
checkpoint-55/trainer_state.json ADDED
@@ -0,0 +1,419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 55,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01818181818181818,
14
+ "grad_norm": 3.65625,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.9540231227874756,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.03636363636363636,
21
+ "grad_norm": 3.90625,
22
+ "learning_rate": 5e-06,
23
+ "loss": 0.9547070860862732,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.05454545454545454,
28
+ "grad_norm": 1.4765625,
29
+ "learning_rate": 1e-05,
30
+ "loss": 0.6905241012573242,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.07272727272727272,
35
+ "grad_norm": 1.828125,
36
+ "learning_rate": 1.5000000000000002e-05,
37
+ "loss": 0.738600492477417,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.09090909090909091,
42
+ "grad_norm": 0.96875,
43
+ "learning_rate": 2e-05,
44
+ "loss": 0.6457145810127258,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.10909090909090909,
49
+ "grad_norm": 0.78515625,
50
+ "learning_rate": 1.9995608365087945e-05,
51
+ "loss": 0.579596757888794,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.12727272727272726,
56
+ "grad_norm": 0.578125,
57
+ "learning_rate": 1.9982437317643218e-05,
58
+ "loss": 0.5202184319496155,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.14545454545454545,
63
+ "grad_norm": 0.396484375,
64
+ "learning_rate": 1.996049842615217e-05,
65
+ "loss": 0.519447386264801,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.16363636363636364,
70
+ "grad_norm": 0.41015625,
71
+ "learning_rate": 1.992981096013517e-05,
72
+ "loss": 0.4847332239151001,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.18181818181818182,
77
+ "grad_norm": 0.333984375,
78
+ "learning_rate": 1.9890401873221642e-05,
79
+ "loss": 0.4574339687824249,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.2,
84
+ "grad_norm": 0.35546875,
85
+ "learning_rate": 1.984230577947597e-05,
86
+ "loss": 0.5035643577575684,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.21818181818181817,
91
+ "grad_norm": 0.34765625,
92
+ "learning_rate": 1.9785564922995042e-05,
93
+ "loss": 0.4525945782661438,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.23636363636363636,
98
+ "grad_norm": 0.29296875,
99
+ "learning_rate": 1.972022914080411e-05,
100
+ "loss": 0.42145389318466187,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.2545454545454545,
105
+ "grad_norm": 0.287109375,
106
+ "learning_rate": 1.964635581908359e-05,
107
+ "loss": 0.4275360107421875,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.2727272727272727,
112
+ "grad_norm": 0.294921875,
113
+ "learning_rate": 1.9564009842765225e-05,
114
+ "loss": 0.41398945450782776,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.2909090909090909,
119
+ "grad_norm": 0.3046875,
120
+ "learning_rate": 1.9473263538541916e-05,
121
+ "loss": 0.436551570892334,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.3090909090909091,
126
+ "grad_norm": 0.28125,
127
+ "learning_rate": 1.9374196611341212e-05,
128
+ "loss": 0.45138514041900635,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.32727272727272727,
133
+ "grad_norm": 0.275390625,
134
+ "learning_rate": 1.9266896074318335e-05,
135
+ "loss": 0.43172961473464966,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.34545454545454546,
140
+ "grad_norm": 0.2890625,
141
+ "learning_rate": 1.9151456172430186e-05,
142
+ "loss": 0.4228370785713196,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.36363636363636365,
147
+ "grad_norm": 0.27734375,
148
+ "learning_rate": 1.9027978299657436e-05,
149
+ "loss": 0.41701316833496094,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.38181818181818183,
154
+ "grad_norm": 0.265625,
155
+ "learning_rate": 1.8896570909947477e-05,
156
+ "loss": 0.4082438051700592,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.4,
161
+ "grad_norm": 0.255859375,
162
+ "learning_rate": 1.875734942195637e-05,
163
+ "loss": 0.40878307819366455,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.41818181818181815,
168
+ "grad_norm": 0.279296875,
169
+ "learning_rate": 1.8610436117673557e-05,
170
+ "loss": 0.4113834798336029,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.43636363636363634,
175
+ "grad_norm": 0.2734375,
176
+ "learning_rate": 1.845596003501826e-05,
177
+ "loss": 0.3875882029533386,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.45454545454545453,
182
+ "grad_norm": 0.265625,
183
+ "learning_rate": 1.829405685450202e-05,
184
+ "loss": 0.37104856967926025,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.4727272727272727,
189
+ "grad_norm": 0.27734375,
190
+ "learning_rate": 1.8124868780056814e-05,
191
+ "loss": 0.4169103503227234,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.4909090909090909,
196
+ "grad_norm": 0.26171875,
197
+ "learning_rate": 1.7948544414133534e-05,
198
+ "loss": 0.39792633056640625,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.509090909090909,
203
+ "grad_norm": 0.26953125,
204
+ "learning_rate": 1.7765238627180424e-05,
205
+ "loss": 0.4081586003303528,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.5272727272727272,
210
+ "grad_norm": 0.28125,
211
+ "learning_rate": 1.7575112421616203e-05,
212
+ "loss": 0.4401257038116455,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.5454545454545454,
217
+ "grad_norm": 0.287109375,
218
+ "learning_rate": 1.7378332790417275e-05,
219
+ "loss": 0.4105204641819,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.5636363636363636,
224
+ "grad_norm": 0.28125,
225
+ "learning_rate": 1.717507257044331e-05,
226
+ "loss": 0.42984315752983093,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.5818181818181818,
231
+ "grad_norm": 0.251953125,
232
+ "learning_rate": 1.6965510290629973e-05,
233
+ "loss": 0.39207223057746887,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.6,
238
+ "grad_norm": 0.265625,
239
+ "learning_rate": 1.6749830015182106e-05,
240
+ "loss": 0.42477482557296753,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.6181818181818182,
245
+ "grad_norm": 0.251953125,
246
+ "learning_rate": 1.6528221181905217e-05,
247
+ "loss": 0.35220205783843994,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.6363636363636364,
252
+ "grad_norm": 0.26953125,
253
+ "learning_rate": 1.6300878435817115e-05,
254
+ "loss": 0.38372600078582764,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.6545454545454545,
259
+ "grad_norm": 0.265625,
260
+ "learning_rate": 1.6068001458185934e-05,
261
+ "loss": 0.3893311023712158,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.6727272727272727,
266
+ "grad_norm": 0.271484375,
267
+ "learning_rate": 1.5829794791144723e-05,
268
+ "loss": 0.3897112309932709,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.6909090909090909,
273
+ "grad_norm": 0.267578125,
274
+ "learning_rate": 1.5586467658036526e-05,
275
+ "loss": 0.3875298798084259,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.7090909090909091,
280
+ "grad_norm": 0.2470703125,
281
+ "learning_rate": 1.533823377964791e-05,
282
+ "loss": 0.3694135248661041,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.7272727272727273,
287
+ "grad_norm": 0.279296875,
288
+ "learning_rate": 1.5085311186492206e-05,
289
+ "loss": 0.41407889127731323,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.7454545454545455,
294
+ "grad_norm": 0.26171875,
295
+ "learning_rate": 1.482792202730745e-05,
296
+ "loss": 0.3905969262123108,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.7636363636363637,
301
+ "grad_norm": 0.251953125,
302
+ "learning_rate": 1.4566292373937133e-05,
303
+ "loss": 0.3897048234939575,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.7818181818181819,
308
+ "grad_norm": 0.255859375,
309
+ "learning_rate": 1.4300652022765207e-05,
310
+ "loss": 0.3396158218383789,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.8,
315
+ "grad_norm": 0.275390625,
316
+ "learning_rate": 1.4031234292879726e-05,
317
+ "loss": 0.3982832729816437,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.8181818181818182,
322
+ "grad_norm": 0.27734375,
323
+ "learning_rate": 1.3758275821142382e-05,
324
+ "loss": 0.39318445324897766,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.8363636363636363,
329
+ "grad_norm": 0.24609375,
330
+ "learning_rate": 1.348201635434399e-05,
331
+ "loss": 0.39158475399017334,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.8545454545454545,
336
+ "grad_norm": 0.25390625,
337
+ "learning_rate": 1.3202698538628376e-05,
338
+ "loss": 0.4073805809020996,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.8727272727272727,
343
+ "grad_norm": 0.267578125,
344
+ "learning_rate": 1.292056770636976e-05,
345
+ "loss": 0.4243454337120056,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.8909090909090909,
350
+ "grad_norm": 0.263671875,
351
+ "learning_rate": 1.2635871660690677e-05,
352
+ "loss": 0.4044433832168579,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.9090909090909091,
357
+ "grad_norm": 0.279296875,
358
+ "learning_rate": 1.234886045780984e-05,
359
+ "loss": 0.4086686670780182,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.9272727272727272,
364
+ "grad_norm": 0.251953125,
365
+ "learning_rate": 1.2059786187410984e-05,
366
+ "loss": 0.39805901050567627,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.9454545454545454,
371
+ "grad_norm": 0.251953125,
372
+ "learning_rate": 1.176890275122573e-05,
373
+ "loss": 0.3601215183734894,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.9636363636363636,
378
+ "grad_norm": 0.251953125,
379
+ "learning_rate": 1.1476465640024814e-05,
380
+ "loss": 0.3588330149650574,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.9818181818181818,
385
+ "grad_norm": 0.275390625,
386
+ "learning_rate": 1.1182731709213658e-05,
387
+ "loss": 0.4134596586227417,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 1.0,
392
+ "grad_norm": 0.2490234375,
393
+ "learning_rate": 1.0887958953229349e-05,
394
+ "loss": 0.3795488774776459,
395
+ "step": 55
396
+ }
397
+ ],
398
+ "logging_steps": 1,
399
+ "max_steps": 110,
400
+ "num_input_tokens_seen": 0,
401
+ "num_train_epochs": 2,
402
+ "save_steps": 100,
403
+ "stateful_callbacks": {
404
+ "TrainerControl": {
405
+ "args": {
406
+ "should_epoch_stop": false,
407
+ "should_evaluate": false,
408
+ "should_log": false,
409
+ "should_save": true,
410
+ "should_training_stop": false
411
+ },
412
+ "attributes": {}
413
+ }
414
+ },
415
+ "total_flos": 7.363187175325696e+16,
416
+ "train_batch_size": 8,
417
+ "trial_name": null,
418
+ "trial_params": null
419
+ }
checkpoint-55/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afa5819f1597cbd762508051924dea8b456aa3e46e0a9907c18879d6e428e7d
3
+ size 5777