Plans11 commited on
Commit
bfed34a
·
verified ·
1 Parent(s): 227da3e

HyperMini Session 1 complete | 20,000 examples | loss=4.194006

Browse files
Files changed (6) hide show
  1. README.md +5 -5
  2. example_ledger.json +14 -7
  3. model.safetensors +1 -1
  4. optimizer.pt +2 -2
  5. rng_state.pt +2 -2
  6. training_state.json +0 -0
README.md CHANGED
@@ -87,16 +87,16 @@ before resume.
87
  ## Current state
88
 
89
  Completed sessions:
90
- 0
91
 
92
  Unique examples reserved/trained:
93
- 20,000
94
 
95
  Unique completed examples:
96
- 0
97
 
98
  Global optimizer steps:
99
- 0
100
 
101
  Last session loss:
102
- None
 
87
  ## Current state
88
 
89
  Completed sessions:
90
+ 1
91
 
92
  Unique examples reserved/trained:
93
+ 0
94
 
95
  Unique completed examples:
96
+ 20,000
97
 
98
  Global optimizer steps:
99
+ 313
100
 
101
  Last session loss:
102
+ 4.194005527544022
example_ledger.json CHANGED
@@ -1,10 +1,5 @@
1
  {
2
- "consumed_hashes": [],
3
- "dataset": "Plans11/Organized_PreTrain_1k_Context",
4
- "hash_algorithm": "sha256",
5
- "max_context": 1096,
6
- "model": "Nano.Deep.Reasoner.11m-HyperMini",
7
- "reserved_hashes": [
8
  "0002cd024fab39975c82ac4bd97c4094c14b53e078c2b116dcd87d58cf87593d",
9
  "0007b117544ae123a7307db66235d42b85c93f5e8e535a0f735e355496366985",
10
  "000a011e97f4f47b77b2e43c2dd291566528d0116f57d4c02bae9b5cb9c3c94c",
@@ -20006,7 +20001,19 @@
20006
  "ffff908c820212a44b0ac770676a4beac9a562755e94bb52def0f3a293a8c058",
20007
  "ffffe4418acd7862689a36e80bd15167290d5aa047296816411a57b063d7c135"
20008
  ],
 
 
 
 
 
20009
  "session_size": 20000,
20010
- "sessions": [],
 
 
 
 
 
 
 
20011
  "version": 2
20012
  }
 
1
  {
2
+ "consumed_hashes": [
 
 
 
 
 
3
  "0002cd024fab39975c82ac4bd97c4094c14b53e078c2b116dcd87d58cf87593d",
4
  "0007b117544ae123a7307db66235d42b85c93f5e8e535a0f735e355496366985",
5
  "000a011e97f4f47b77b2e43c2dd291566528d0116f57d4c02bae9b5cb9c3c94c",
 
20001
  "ffff908c820212a44b0ac770676a4beac9a562755e94bb52def0f3a293a8c058",
20002
  "ffffe4418acd7862689a36e80bd15167290d5aa047296816411a57b063d7c135"
20003
  ],
20004
+ "dataset": "Plans11/Organized_PreTrain_1k_Context",
20005
+ "hash_algorithm": "sha256",
20006
+ "max_context": 1096,
20007
+ "model": "Nano.Deep.Reasoner.11m-HyperMini",
20008
+ "reserved_hashes": [],
20009
  "session_size": 20000,
20010
+ "sessions": [
20011
+ {
20012
+ "completed_at": "2026-08-19T12:18:32.261418+00:00",
20013
+ "examples": 20000,
20014
+ "loss": 4.194005527544022,
20015
+ "session": 1
20016
+ }
20017
+ ],
20018
  "version": 2
20019
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7395c7c3b61893cadfa369d36f78a12f61c3c844856821b5cd88ccf24b9b0971
3
  size 59742900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fcb150d81f420d4b23f1dd41b788fa08690a101efa16592385fbf6ddeb91bb3
3
  size 59742900
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d493a143ff47266f40b916d678f4bce6de34ba3c9592c59d1f92078ab1b7c9de
3
- size 1721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d08607602e4c713dfe2d7e9b5036a7a69022d1309253058a25018cab1d32ba87
3
+ size 88811659
rng_state.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55c3041a7be4d734bf7df211c94ad7620ecd54feff1b53e73c11c884179f2879
3
- size 10931
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a888e035cc770d8b2fee0c18eb61da249fc04689737c80f0d613730774a75d0b
3
+ size 10995
training_state.json CHANGED
The diff for this file is too large to render. See raw diff