Training update: run 449, 500 iters, cache_key=ci
Browse files- README.md +4 -4
- pytorch_model.bin +1 -1
- training_metadata.json +13 -13
README.md
CHANGED
|
@@ -25,10 +25,10 @@ capabilities inspired by cognitive science and AGI research.
|
|
| 25 |
|
| 26 |
## Training Details
|
| 27 |
|
| 28 |
-
- **Checkpoint ID**:
|
| 29 |
-
- **Training Iteration**:
|
| 30 |
-
- **Validation Loss**:
|
| 31 |
-
- **Quality Score**:
|
| 32 |
|
| 33 |
## Echo Self Features
|
| 34 |
|
|
|
|
| 25 |
|
| 26 |
## Training Details
|
| 27 |
|
| 28 |
+
- **Checkpoint ID**: ckpt_20260517_035406_1000_22deff1b_9470fbb7
|
| 29 |
+
- **Training Iteration**: 1000
|
| 30 |
+
- **Validation Loss**: 3.147248959541321
|
| 31 |
+
- **Quality Score**: 153600.45190942395
|
| 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:
|
| 3 |
size 51464851
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c0568ad25c664990a84c6a7ec3d3871779036549aac8165932fcbd1036a4afa
|
| 3 |
size 51464851
|
training_metadata.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"checkpoint_id": "
|
| 3 |
-
"created_at": "2026-05-
|
| 4 |
-
"iteration":
|
| 5 |
"epoch": 0,
|
| 6 |
"train_loss": 0.0,
|
| 7 |
-
"val_loss":
|
| 8 |
-
"learning_rate":
|
| 9 |
"model_config": {
|
| 10 |
"n_layer": 4,
|
| 11 |
"n_head": 4,
|
|
@@ -36,20 +36,20 @@
|
|
| 36 |
"block_size": 1024
|
| 37 |
},
|
| 38 |
"metrics": {
|
| 39 |
-
"val_loss":
|
| 40 |
-
"connection_ratio": 0.
|
| 41 |
-
"tokens_processed":
|
| 42 |
-
"training_speed_iters_per_sec": 0.
|
| 43 |
},
|
| 44 |
"tags": [
|
| 45 |
"phase_adaptive_mastery",
|
| 46 |
-
"
|
| 47 |
"nanecho",
|
| 48 |
"curriculum",
|
| 49 |
"introspection"
|
| 50 |
],
|
| 51 |
"parent_checkpoint": null,
|
| 52 |
-
"notes": "Training checkpoint at iteration 500 | Phase: adaptive_mastery",
|
| 53 |
-
"file_size_mb": 249.
|
| 54 |
-
"quality_score":
|
| 55 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"checkpoint_id": "ckpt_20260517_035406_1000_22deff1b_9470fbb7",
|
| 3 |
+
"created_at": "2026-05-17T03:54:07.020534",
|
| 4 |
+
"iteration": 1000,
|
| 5 |
"epoch": 0,
|
| 6 |
"train_loss": 0.0,
|
| 7 |
+
"val_loss": 3.147248959541321,
|
| 8 |
+
"learning_rate": 2.7972e-05,
|
| 9 |
"model_config": {
|
| 10 |
"n_layer": 4,
|
| 11 |
"n_head": 4,
|
|
|
|
| 36 |
"block_size": 1024
|
| 37 |
},
|
| 38 |
"metrics": {
|
| 39 |
+
"val_loss": 3.147248959541321,
|
| 40 |
+
"connection_ratio": 0.5499999999999999,
|
| 41 |
+
"tokens_processed": 2048000,
|
| 42 |
+
"training_speed_iters_per_sec": 0.07772219109033594
|
| 43 |
},
|
| 44 |
"tags": [
|
| 45 |
"phase_adaptive_mastery",
|
| 46 |
+
"medium_quality",
|
| 47 |
"nanecho",
|
| 48 |
"curriculum",
|
| 49 |
"introspection"
|
| 50 |
],
|
| 51 |
"parent_checkpoint": null,
|
| 52 |
+
"notes": "Training checkpoint at iteration 1000 (resumed from iteration 500) | Phase: adaptive_mastery",
|
| 53 |
+
"file_size_mb": 249.29106044769287,
|
| 54 |
+
"quality_score": 153600.45190942395
|
| 55 |
}
|