Plans11 commited on
Commit
590772d
·
verified ·
1 Parent(s): 0e15fbd

RESERVED Session 4 | 200,000 examples | crash-safe reservation

Browse files
Files changed (4) hide show
  1. .gitattributes +2 -0
  2. README.md +1 -1
  3. example_ledger.json +0 -0
  4. training_state.json +3 -90
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip 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
 
 
 
33
  *.zip 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
+ example_ledger.json filter=lfs diff=lfs merge=lfs -text
37
+ training_state.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -90,7 +90,7 @@ Completed sessions:
90
  3
91
 
92
  Unique examples reserved/trained:
93
- 0
94
 
95
  Unique completed examples:
96
  60,000
 
90
  3
91
 
92
  Unique examples reserved/trained:
93
+ 200,000
94
 
95
  Unique completed examples:
96
  60,000
example_ledger.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state.json CHANGED
@@ -1,90 +1,3 @@
1
- {
2
- "active_session": null,
3
- "architecture": {
4
- "adaptive_halting": true,
5
- "attention_heads": 8,
6
- "base_layers": 6,
7
- "context_length": 1096,
8
- "decoder_only": true,
9
- "head_dimension": 30,
10
- "hidden_size": 240,
11
- "intermediate_size": 1072,
12
- "max_reasoning_steps": 16,
13
- "memory_tokens": 8,
14
- "min_reasoning_steps": 2,
15
- "model_type": "nano_deep_reasoner_hypermini",
16
- "padding_aware_attention": true,
17
- "padding_query_zeroing": true,
18
- "parameter_count": 11094003,
19
- "reasoning_tokens": [
20
- "<think>",
21
- "</think>",
22
- "<thought>",
23
- "</thought>",
24
- "<reasoning>",
25
- "</reasoning>",
26
- "<answer>",
27
- "</answer>",
28
- "<question>",
29
- "</question>",
30
- "<analysis>",
31
- "</analysis>",
32
- "<tool>",
33
- "</tool>"
34
- ],
35
- "revision_head": true,
36
- "rope": true,
37
- "shared_recurrent_reasoner": true,
38
- "tied_embeddings": true,
39
- "verification_head": true,
40
- "vocab_size": 16000
41
- },
42
- "completed_sessions": 3,
43
- "current_session_examples": 20000,
44
- "dataset": "Plans11/Organized_PreTrain_1k_Context",
45
- "dataset_cursor": 60001,
46
- "dataset_fingerprint": "f81f16fb5ed873b48325febe265ee451828254504e3e8159ef926836f604845a",
47
- "global_step": 939,
48
- "last_completed_at": "2026-08-19T13:06:44.393247+00:00",
49
- "last_halt_loss": 0.8316526960849762,
50
- "last_revision_loss": 0.7080927767276763,
51
- "last_session_loss": 1.3437887360095977,
52
- "last_verify_loss": 0.6935870643138885,
53
- "max_context": 1096,
54
- "model": "Nano.Deep.Reasoner.11m-HyperMini",
55
- "optimizer_steps": 939,
56
- "seed": 1147,
57
- "session_size": 20000,
58
- "tokenizer": {
59
- "artifact_sha256": {
60
- "tokenizer.json": "9619297bcfd3ea8f40d56f991e214d166b7c3bf45aee8cabb908881adeaf6ff9",
61
- "tokenizer_config.json": "2e82dbc3e20a656b022331e8b616deb37897c4544b5c4489a598793cae589c91"
62
- },
63
- "immutable": true,
64
- "reasoning_token_ids": {
65
- "</analysis>": 15,
66
- "</answer>": 11,
67
- "</question>": 13,
68
- "</reasoning>": 9,
69
- "</think>": 5,
70
- "</thought>": 7,
71
- "</tool>": 17,
72
- "<analysis>": 14,
73
- "<answer>": 10,
74
- "<question>": 12,
75
- "<reasoning>": 8,
76
- "<think>": 4,
77
- "<thought>": 6,
78
- "<tool>": 16
79
- },
80
- "special_token_ids": {
81
- "<bos>": 1,
82
- "<eos>": 2,
83
- "<pad>": 0,
84
- "<unk>": 3
85
- },
86
- "vocab_size": 16000
87
- },
88
- "total_examples_trained": 60000,
89
- "version": 2
90
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac90c80948ccba1c639db216b41a288dc45ea42ad9aded0db4f73b9751fb7e2
3
+ size 14802574