drzo commited on
Commit
247c616
·
verified ·
1 Parent(s): d8f5ec2

Training update: run 362, 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 +10 -10
README.md CHANGED
@@ -25,10 +25,10 @@ capabilities inspired by cognitive science and AGI research.
25
 
26
  ## Training Details
27
 
28
- - **Checkpoint ID**: ckpt_20260425_020902_17000_22deff1b_9470fbb7
29
- - **Training Iteration**: 17000
30
- - **Validation Loss**: 0.0004727929548971588
31
- - **Quality Score**: 2611200.7804933703
32
 
33
  ## Echo Self Features
34
 
 
25
 
26
  ## Training Details
27
 
28
+ - **Checkpoint ID**: ckpt_20260425_080703_17500_22deff1b_9470fbb7
29
+ - **Training Iteration**: 17500
30
+ - **Validation Loss**: 0.00011886571933246159
31
+ - **Quality Score**: 2688000.781412786
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 sha256:888ad461b9f3566f2c6ebff4df7239803a41ecb20fc349fa27611142af4fe75f
3
  size 51464851
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe18072d6456fa1fbffc13c802e9175d40001ca2d1523002ce3c8f5ee1223ab
3
  size 51464851
training_metadata.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "checkpoint_id": "ckpt_20260425_020902_17000_22deff1b_9470fbb7",
3
- "created_at": "2026-04-25T02:09:03.008963",
4
- "iteration": 17000,
5
  "epoch": 0,
6
  "train_loss": 0.0,
7
- "val_loss": 0.0004727929548971588,
8
- "learning_rate": 0.00011800063532061465,
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": 0.0004727929548971588,
40
  "connection_ratio": 1.0,
41
- "tokens_processed": 34816000,
42
- "training_speed_iters_per_sec": 0.07718279031666281
43
  },
44
  "tags": [
45
  "phase_adaptive_mastery",
@@ -49,7 +49,7 @@
49
  "introspection"
50
  ],
51
  "parent_checkpoint": null,
52
- "notes": "Training checkpoint at iteration 17000 (resumed from iteration 16500) | Phase: adaptive_mastery",
53
  "file_size_mb": 253.3669786453247,
54
- "quality_score": 2611200.7804933703
55
  }
 
1
  {
2
+ "checkpoint_id": "ckpt_20260425_080703_17500_22deff1b_9470fbb7",
3
+ "created_at": "2026-04-25T08:07:03.306817",
4
+ "iteration": 17500,
5
  "epoch": 0,
6
  "train_loss": 0.0,
7
+ "val_loss": 0.00011886571933246159,
8
+ "learning_rate": 0.00011624893235938535,
9
  "model_config": {
10
  "n_layer": 4,
11
  "n_head": 4,
 
36
  "block_size": 1024
37
  },
38
  "metrics": {
39
+ "val_loss": 0.00011886571933246159,
40
  "connection_ratio": 1.0,
41
+ "tokens_processed": 35840000,
42
+ "training_speed_iters_per_sec": 0.0864942270221606
43
  },
44
  "tags": [
45
  "phase_adaptive_mastery",
 
49
  "introspection"
50
  ],
51
  "parent_checkpoint": null,
52
+ "notes": "Training checkpoint at iteration 17500 (resumed from iteration 17000) | Phase: adaptive_mastery",
53
  "file_size_mb": 253.3669786453247,
54
+ "quality_score": 2688000.781412786
55
  }