drzo commited on
Commit
76a0a98
·
verified ·
1 Parent(s): fd59b69

Training update: run 400, 500 iters, cache_key=ci

Browse files
Files changed (3) hide show
  1. README.md +4 -4
  2. pytorch_model.bin +1 -1
  3. training_metadata.json +11 -11
README.md CHANGED
@@ -25,10 +25,10 @@ capabilities inspired by cognitive science and AGI research.
25
 
26
  ## Training Details
27
 
28
- - **Checkpoint ID**: ckpt_20260504_141407_2500_22deff1b_9470fbb7
29
- - **Training Iteration**: 2500
30
- - **Validation Loss**: 0.14673430055379869
31
- - **Quality Score**: 384000.70257747936
32
 
33
  ## Echo Self Features
34
 
 
25
 
26
  ## Training Details
27
 
28
+ - **Checkpoint ID**: ckpt_20260504_201009_3000_22deff1b_9470fbb7
29
+ - **Training Iteration**: 3000
30
+ - **Validation Loss**: 0.033119172342121604
31
+ - **Quality Score**: 460800.76150449156
32
 
33
  ## Echo Self Features
34
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f0dddba4d8488dc868c1c190ce075275081a90c16f1180fd8d2ef099fb11324
3
  size 51464851
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ddf2bf41843001463b7a85b9008f1278b027ddd9cc42a01bf4cf01366804997
3
  size 51464851
training_metadata.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "checkpoint_id": "ckpt_20260504_141407_2500_22deff1b_9470fbb7",
3
- "created_at": "2026-05-04T14:14:07.921963",
4
- "iteration": 2500,
5
  "epoch": 0,
6
  "train_loss": 0.0,
7
- "val_loss": 0.14673430055379869,
8
- "learning_rate": 6.9972e-05,
9
  "model_config": {
10
  "n_layer": 4,
11
  "n_head": 4,
@@ -36,10 +36,10 @@
36
  "block_size": 1024
37
  },
38
  "metrics": {
39
- "val_loss": 0.14673430055379869,
40
  "connection_ratio": 1.0,
41
- "tokens_processed": 5120000,
42
- "training_speed_iters_per_sec": 0.0819106067942122
43
  },
44
  "tags": [
45
  "phase_adaptive_mastery",
@@ -49,7 +49,7 @@
49
  "introspection"
50
  ],
51
  "parent_checkpoint": null,
52
- "notes": "Training checkpoint at iteration 2500 (resumed from iteration 2000) | Phase: adaptive_mastery",
53
- "file_size_mb": 249.29106044769287,
54
- "quality_score": 384000.70257747936
55
  }
 
1
  {
2
+ "checkpoint_id": "ckpt_20260504_201009_3000_22deff1b_9470fbb7",
3
+ "created_at": "2026-05-04T20:10:09.215305",
4
+ "iteration": 3000,
5
  "epoch": 0,
6
  "train_loss": 0.0,
7
+ "val_loss": 0.033119172342121604,
8
+ "learning_rate": 8.397199999999999e-05,
9
  "model_config": {
10
  "n_layer": 4,
11
  "n_head": 4,
 
36
  "block_size": 1024
37
  },
38
  "metrics": {
39
+ "val_loss": 0.033119172342121604,
40
  "connection_ratio": 1.0,
41
+ "tokens_processed": 6144000,
42
+ "training_speed_iters_per_sec": 0.08614363683723561
43
  },
44
  "tags": [
45
  "phase_adaptive_mastery",
 
49
  "introspection"
50
  ],
51
  "parent_checkpoint": null,
52
+ "notes": "Training checkpoint at iteration 3000 (resumed from iteration 2500) | Phase: adaptive_mastery",
53
+ "file_size_mb": 250.30978298187256,
54
+ "quality_score": 460800.76150449156
55
  }