Hugging Face's logo

rdz-falcon
/
SignMotionGPT-Sentence-v6

Safetensors
Model card Files
xet
 Community
rdz-falcon commited on
Commit
0fec24c
·
verified ·
1 Parent(s): c305e66

stage2 epoch 2 step 2992

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. stage2/chat_template.jinja +89 -0
  3. stage2/config.json +63 -0
  4. stage2/generation_config.json +13 -0
  5. stage2/model.safetensors +3 -0
  6. stage2/optimizer.pt +3 -0
  7. stage2/scheduler.pt +3 -0
  8. stage2/tokenizer.json +3 -0
  9. stage2/tokenizer_config.json +22 -0
  10. stage2/trainable_token_rows.pt +3 -0
  11. stage2/training_state.json +41 -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
  stage1/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
  stage1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ stage2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
stage2/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
stage2/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 40960,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "pad_token_id": 151669,
52
+ "rms_norm_eps": 1e-06,
53
+ "rope_parameters": {
54
+ "rope_theta": 1000000,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_window": null,
58
+ "tie_word_embeddings": true,
59
+ "transformers_version": "5.5.0",
60
+ "use_cache": true,
61
+ "use_sliding_window": false,
62
+ "vocab_size": 152184
63
+ }
stage2/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.5.0"
13
+ }
stage2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b09205d71b2b47e48ea943bd8aa88aa2ab204482f8b50ffc149b5568c42be8b5
3
+ size 1192643000
stage2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81bbf566a652350195dc1e5f46b9dea745196c5edc3b8bd1e3e876cb6852a2e3
3
+ size 2385476043
stage2/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb0dfecd85f25cc8e3d924ea4bd0145b90cc684d9a2f869c153e9e3c3f235cf8
3
+ size 1465
stage2/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83aeb3f17fb5cab1d6e356ac8419435d4d79b537e9986b5e4d375849ac61e49a
3
+ size 11516814
stage2/tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<M_START>",
10
+ "<M_END>",
11
+ "<M_MASK>",
12
+ "<|LEN_SHORT|>",
13
+ "<|LEN_MEDIUM|>",
14
+ "<|LEN_LONG|>"
15
+ ],
16
+ "is_local": false,
17
+ "model_max_length": 131072,
18
+ "pad_token": "<PAD>",
19
+ "split_special_tokens": false,
20
+ "tokenizer_class": "Qwen2Tokenizer",
21
+ "unk_token": null
22
+ }
stage2/trainable_token_rows.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a2d5de98dd9aecf63e72371aaa1aae473e26c4354904d8fa018f89f463e74e
3
+ size 2117389
stage2/training_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "stage": "stage2",
3
+ "label": "latest",
4
+ "epoch_completed": 2,
5
+ "total_epochs": 40,
6
+ "avg_loss": 2.5099431818181817,
7
+ "val_loss": 2.610505773774674,
8
+ "global_step": 2992,
9
+ "motion_token_count": 514,
10
+ "training_meta": {
11
+ "strategy": "full_finetune",
12
+ "model_name": "Qwen/Qwen3-0.6B",
13
+ "materialize_template_augmentation": true
14
+ },
15
+ "stage_summary": {
16
+ "train_loss": 2.5099431818181817,
17
+ "train_sentence_loss": 2.5099431818181817,
18
+ "train_plain_ce_sentence": 2.5099431818181817,
19
+ "train_smoothed_motion_avg": 0.0,
20
+ "train_replay_loss": 0.0,
21
+ "train_plain_ce_replay": 0.0,
22
+ "train_denoise_loss": 0.0,
23
+ "train_plain_ce_denoise": 0.0,
24
+ "train_motion_exact_acc": 0.1700125178284784,
25
+ "train_motion_near_acc": 0.20118459718051873,
26
+ "replay_step_fraction": 0.0,
27
+ "val_loss": 2.610505773774674,
28
+ "val_motion_exact_acc": 0.15297534624767856,
29
+ "val_motion_near_acc": 0.17797220443524175,
30
+ "val_num_samples": 11956,
31
+ "val_coverage_loss_0_00_0_25": 2.4676196481299213,
32
+ "val_coverage_loss_0_25_0_50": 2.598003075372955,
33
+ "val_coverage_loss_0_50_0_75": 2.6296353357919253,
34
+ "val_coverage_loss_0_75_1_00": 2.612093786678404,
35
+ "val_length_loss_long": 2.482314931556196,
36
+ "val_length_loss_medium": 2.607876040529476,
37
+ "val_length_loss_short": 2.6484359596805995,
38
+ "val_worst_group_loss": 2.6484359596805995
39
+ },
40
+ "saved_at": "2026-04-18T14:13:49.233616Z"
41
+ }