python-124m-muon-5b-20261021-v1: 4500012372 training targets
Browse files- README.md +1 -1
- evaluation.json +0 -0
- evaluations/004500012372-evaluated.json +0 -0
- metrics.jsonl +2 -2
- model.safetensors +1 -1
- provenance.json +11 -11
- runtime-cost-estimate.json +2 -2
- training-curves.png +2 -2
- validation-curves.png +2 -2
- validation.jsonl +22 -0
README.md
CHANGED
|
@@ -11,7 +11,7 @@ tags:
|
|
| 11 |
# Simple LLM Python 124M / 5B
|
| 12 |
|
| 13 |
Run: `python-124m-muon-5b-20261021-v1`. This is an **intermediate** base-model checkpoint, freshly initialized.
|
| 14 |
-
Processed **4,
|
| 15 |
The exact target is 5,000,000,000. This model is not instruction-tuned.
|
| 16 |
|
| 17 |
124,389,632 parameters; 14 layers, width 768, 12 attention heads, RMSNorm,
|
|
|
|
| 11 |
# Simple LLM Python 124M / 5B
|
| 12 |
|
| 13 |
Run: `python-124m-muon-5b-20261021-v1`. This is an **intermediate** base-model checkpoint, freshly initialized.
|
| 14 |
+
Processed **4,500,012,372 nonpadding training targets** in **77,343 optimizer updates**.
|
| 15 |
The exact target is 5,000,000,000. This model is not instruction-tuned.
|
| 16 |
|
| 17 |
124,389,632 parameters; 14 layers, width 768, 12 attention heads, RMSNorm,
|
evaluation.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
evaluations/004500012372-evaluated.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
metrics.jsonl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:229e017128f87668e50edaea485b12413911517552ef41ff3a4d54cd85bf8af3
|
| 3 |
+
size 132011652
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 598238584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a55cd981a99fa31a4440f8f33792bec5db53273d5afb41e309e666cb194a080f
|
| 3 |
size 598238584
|
provenance.json
CHANGED
|
@@ -49,20 +49,20 @@
|
|
| 49 |
"torch_version": "2.6.0+cu124",
|
| 50 |
"gpu": "NVIDIA H100 80GB HBM3",
|
| 51 |
"parameters": 124389632,
|
| 52 |
-
"resume_from": "/runs/python-124m-muon-5b-20261021-v1-
|
| 53 |
-
"step":
|
| 54 |
-
"tokens":
|
| 55 |
"run_id": "python-124m-muon-5b-20261021-v1",
|
| 56 |
-
"checkpoint": "/runs/python-124m-muon-5b-20261021-v1-
|
| 57 |
-
"weights_sha256": "
|
| 58 |
"weight_roundtrip_exact": true,
|
| 59 |
"cpu_logits_roundtrip_exact": true,
|
| 60 |
"loss_token_exposures": {
|
| 61 |
-
"python_implementation":
|
| 62 |
-
"python_tests_examples":
|
| 63 |
-
"python_documentation":
|
| 64 |
-
"cs_math":
|
| 65 |
-
"general_education":
|
| 66 |
-
"books":
|
| 67 |
}
|
| 68 |
}
|
|
|
|
| 49 |
"torch_version": "2.6.0+cu124",
|
| 50 |
"gpu": "NVIDIA H100 80GB HBM3",
|
| 51 |
"parameters": 124389632,
|
| 52 |
+
"resume_from": "/runs/python-124m-muon-5b-20261021-v1-s019/step-000072999.pt",
|
| 53 |
+
"step": 77343,
|
| 54 |
+
"tokens": 4500012372,
|
| 55 |
"run_id": "python-124m-muon-5b-20261021-v1",
|
| 56 |
+
"checkpoint": "/runs/python-124m-muon-5b-20261021-v1-s022/step-000077343.pt",
|
| 57 |
+
"weights_sha256": "a55cd981a99fa31a4440f8f33792bec5db53273d5afb41e309e666cb194a080f",
|
| 58 |
"weight_roundtrip_exact": true,
|
| 59 |
"cpu_logits_roundtrip_exact": true,
|
| 60 |
"loss_token_exposures": {
|
| 61 |
+
"python_implementation": 2925006747,
|
| 62 |
+
"python_tests_examples": 675001115,
|
| 63 |
+
"python_documentation": 450000440,
|
| 64 |
+
"cs_math": 225001202,
|
| 65 |
+
"general_education": 135000835,
|
| 66 |
+
"books": 90002033
|
| 67 |
}
|
| 68 |
}
|
runtime-cost-estimate.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"kind": "GPU compute estimate, not measured invoice",
|
| 3 |
-
"training_worker_reported_seconds":
|
| 4 |
"h100_usd_per_second": 0.001097,
|
| 5 |
"excludes": [
|
| 6 |
"GPU work outside recorded training segments",
|
| 7 |
"CPU preparation and evaluation",
|
| 8 |
"storage and transfer"
|
| 9 |
],
|
| 10 |
-
"training_gpu_usd_estimate":
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"kind": "GPU compute estimate, not measured invoice",
|
| 3 |
+
"training_worker_reported_seconds": 28541.214711139,
|
| 4 |
"h100_usd_per_second": 0.001097,
|
| 5 |
"excludes": [
|
| 6 |
"GPU work outside recorded training segments",
|
| 7 |
"CPU preparation and evaluation",
|
| 8 |
"storage and transfer"
|
| 9 |
],
|
| 10 |
+
"training_gpu_usd_estimate": 250.4777003049559
|
| 11 |
}
|
training-curves.png
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
validation-curves.png
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
validation.jsonl
CHANGED
|
@@ -184,3 +184,25 @@
|
|
| 184 |
{"step": 72000, "tokens": 4191378329, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4621123048860443, "python_tests_examples": 1.3141731589968928, "python_documentation": 2.353899680810144, "cs_math": 2.4273978093821316, "general_education": 3.4530181637640363, "books": 3.6280979757917677}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4621123048860443, "python_tests_examples": 1.3141731589968928, "python_documentation": 2.353899680810144, "cs_math": 2.4273978093821316, "general_education": 3.4530181637640363, "books": 3.6280979757917677}, "weighted_loss": 1.6804113350043401}
|
| 185 |
{"step": 72500, "tokens": 4220576095, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4524975155407107, "python_tests_examples": 1.2874576690182498, "python_documentation": 2.375524896441134, "cs_math": 2.409801992323874, "general_education": 3.41783198769218, "books": 3.566619371763918}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4524975155407107, "python_tests_examples": 1.2874576690182498, "python_documentation": 2.375524896441134, "cs_math": 2.409801992323874, "general_education": 3.41783198769218, "books": 3.566619371763918}, "weighted_loss": 1.6691519717805503}
|
| 186 |
{"step": 72999, "tokens": 4250017085, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4449019714130305, "python_tests_examples": 1.302770082559299, "python_documentation": 2.348897355095165, "cs_math": 2.419067476980199, "general_education": 3.4275809564496287, "books": 3.5823515418480465}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4449019714130305, "python_tests_examples": 1.302770082559299, "python_documentation": 2.348897355095165, "cs_math": 2.419067476980199, "general_education": 3.4275809564496287, "books": 3.5823515418480465}, "weighted_loss": 1.664919362691341}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 184 |
{"step": 72000, "tokens": 4191378329, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4621123048860443, "python_tests_examples": 1.3141731589968928, "python_documentation": 2.353899680810144, "cs_math": 2.4273978093821316, "general_education": 3.4530181637640363, "books": 3.6280979757917677}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4621123048860443, "python_tests_examples": 1.3141731589968928, "python_documentation": 2.353899680810144, "cs_math": 2.4273978093821316, "general_education": 3.4530181637640363, "books": 3.6280979757917677}, "weighted_loss": 1.6804113350043401}
|
| 185 |
{"step": 72500, "tokens": 4220576095, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4524975155407107, "python_tests_examples": 1.2874576690182498, "python_documentation": 2.375524896441134, "cs_math": 2.409801992323874, "general_education": 3.41783198769218, "books": 3.566619371763918}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4524975155407107, "python_tests_examples": 1.2874576690182498, "python_documentation": 2.375524896441134, "cs_math": 2.409801992323874, "general_education": 3.41783198769218, "books": 3.566619371763918}, "weighted_loss": 1.6691519717805503}
|
| 186 |
{"step": 72999, "tokens": 4250017085, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4449019714130305, "python_tests_examples": 1.302770082559299, "python_documentation": 2.348897355095165, "cs_math": 2.419067476980199, "general_education": 3.4275809564496287, "books": 3.5823515418480465}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4449019714130305, "python_tests_examples": 1.302770082559299, "python_documentation": 2.348897355095165, "cs_math": 2.419067476980199, "general_education": 3.4275809564496287, "books": 3.5823515418480465}, "weighted_loss": 1.664919362691341}
|
| 187 |
+
{"step": 72999, "tokens": 4250017085, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4450214528863299, "python_tests_examples": 1.3028045984565555, "python_documentation": 2.3491112342734075, "cs_math": 2.419083590522221, "general_education": 3.4276583210053437, "books": 3.5822907777391677}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4450214528863299, "python_tests_examples": 1.3028045984565555, "python_documentation": 2.3491112342734075, "cs_math": 2.419083590522221, "general_education": 3.4276583210053437, "books": 3.5822907777391677}, "weighted_loss": 1.6650255022829932}
|
| 188 |
+
{"step": 73000, "tokens": 4250062319, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4445107584614711, "python_tests_examples": 1.3025777348944054, "python_documentation": 2.348206049155906, "cs_math": 2.419501314812875, "general_education": 3.429193719814367, "books": 3.58331502744273}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4445107584614711, "python_tests_examples": 1.3025777348944054, "python_documentation": 2.348206049155906, "cs_math": 2.419501314812875, "general_education": 3.429193719814367, "books": 3.58331502744273}, "weighted_loss": 1.664656436033637}
|
| 189 |
+
{"step": 73500, "tokens": 4278822271, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4432504098540635, "python_tests_examples": 1.3012707276122606, "python_documentation": 2.342511382435812, "cs_math": 2.4169364655750707, "general_education": 3.433766681879804, "books": 3.5740465532955645}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4432504098540635, "python_tests_examples": 1.3012707276122606, "python_documentation": 2.342511382435812, "cs_math": 2.4169364655750707, "general_education": 3.433766681879804, "books": 3.5740465532955645}, "weighted_loss": 1.6628952685916205}
|
| 190 |
+
{"step": 74000, "tokens": 4307134781, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4421581860546335, "python_tests_examples": 1.280923686396494, "python_documentation": 2.334483118636643, "cs_math": 2.3733285601658385, "general_education": 3.4148360546788266, "books": 3.5860736966637408}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4421581860546335, "python_tests_examples": 1.280923686396494, "python_documentation": 2.334483118636643, "cs_math": 2.3733285601658385, "general_education": 3.4148360546788266, "books": 3.5860736966637408}, "weighted_loss": 1.6558226693405815}
|
| 191 |
+
{"step": 74500, "tokens": 4336347331, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4529924073982645, "python_tests_examples": 1.3014247387290216, "python_documentation": 2.346843622115611, "cs_math": 2.3971338333213184, "general_education": 3.4358715194687, "books": 3.5814746600530056}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4529924073982645, "python_tests_examples": 1.3014247387290216, "python_documentation": 2.346843622115611, "cs_math": 2.3971338333213184, "general_education": 3.4358715194687, "books": 3.5814746600530056}, "weighted_loss": 1.6689054682809734}
|
| 192 |
+
{"step": 75000, "tokens": 4364616790, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4437207306161652, "python_tests_examples": 1.2726201169769302, "python_documentation": 2.333263184959784, "cs_math": 2.3884864708735734, "general_education": 3.4204042842349414, "books": 3.5701753152864906}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4437207306161652, "python_tests_examples": 1.2726201169769302, "python_documentation": 2.333263184959784, "cs_math": 2.3884864708735734, "general_education": 3.4204042842349414, "books": 3.5701753152864906}, "weighted_loss": 1.656077769319482}
|
| 193 |
+
{"step": 75500, "tokens": 4393734922, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.437985471544216, "python_tests_examples": 1.2889781937490294, "python_documentation": 2.3351068016787173, "cs_math": 2.397134814838488, "general_education": 3.4203907019117583, "books": 3.5644635766247177}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.437985471544216, "python_tests_examples": 1.2889781937490294, "python_documentation": 2.3351068016787173, "cs_math": 2.397134814838488, "general_education": 3.4203907019117583, "books": 3.5644635766247177}, "weighted_loss": 1.655305699065738}
|
| 194 |
+
{"step": 76000, "tokens": 4423063432, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4364570914244281, "python_tests_examples": 1.268169115422805, "python_documentation": 2.3275949092568937, "cs_math": 2.416674711968535, "general_education": 3.407860257036291, "books": 3.530221859017581}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4364570914244281, "python_tests_examples": 1.268169115422805, "python_documentation": 2.3275949092568937, "cs_math": 2.416674711968535, "general_education": 3.407860257036291, "books": 3.530221859017581}, "weighted_loss": 1.6503559481548555}
|
| 195 |
+
{"step": 76500, "tokens": 4452424643, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.429740053352582, "python_tests_examples": 1.2881456804095337, "python_documentation": 2.329605763948252, "cs_math": 2.397799851273951, "general_education": 3.409607674969531, "books": 3.57028379134777}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.429740053352582, "python_tests_examples": 1.2881456804095337, "python_documentation": 2.329605763948252, "cs_math": 2.397799851273951, "general_education": 3.409607674969531, "books": 3.57028379134777}, "weighted_loss": 1.6490973617751725}
|
| 196 |
+
{"step": 77000, "tokens": 4480870579, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4280693440611754, "python_tests_examples": 1.2829960412103318, "python_documentation": 2.3218908046756273, "cs_math": 2.3667088214407355, "general_education": 3.4152464388580346, "books": 3.5417886644777625}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4280693440611754, "python_tests_examples": 1.2829960412103318, "python_documentation": 2.3218908046756273, "cs_math": 2.3667088214407355, "general_education": 3.4152464388580346, "books": 3.5417886644777625}, "weighted_loss": 1.6445121678162096}
|
| 197 |
+
{"step": 77343, "tokens": 4500012372, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4280485852366456, "python_tests_examples": 1.2579982131499265, "python_documentation": 2.3126501857367705, "cs_math": 2.3745552652743678, "general_education": 3.3886645951681356, "books": 3.5145153839387016}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4280485852366456, "python_tests_examples": 1.2579982131499265, "python_documentation": 2.3126501857367705, "cs_math": 2.3745552652743678, "general_education": 3.3886645951681356, "books": 3.5145153839387016}, "weighted_loss": 1.6388743397475223}
|
| 198 |
+
{"step": 72999, "tokens": 4250017085, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4450214528863299, "python_tests_examples": 1.3028045984565555, "python_documentation": 2.3491112342734075, "cs_math": 2.419083590522221, "general_education": 3.4276583210053437, "books": 3.5822907777391677}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4450214528863299, "python_tests_examples": 1.3028045984565555, "python_documentation": 2.3491112342734075, "cs_math": 2.419083590522221, "general_education": 3.4276583210053437, "books": 3.5822907777391677}, "weighted_loss": 1.6650255022829932}
|
| 199 |
+
{"step": 73000, "tokens": 4250062319, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4446754716918264, "python_tests_examples": 1.302551091236298, "python_documentation": 2.3482267905264838, "cs_math": 2.4195365999325777, "general_education": 3.429355762239148, "books": 3.5833004275319906}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4446754716918264, "python_tests_examples": 1.302551091236298, "python_documentation": 2.3482267905264838, "cs_math": 2.4195365999325777, "general_education": 3.429355762239148, "books": 3.5833004275319906}, "weighted_loss": 1.6647679107522233}
|
| 200 |
+
{"step": 73500, "tokens": 4278822271, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4436008820024306, "python_tests_examples": 1.301352445609624, "python_documentation": 2.3424995877444426, "cs_math": 2.41688959662112, "general_education": 3.433970397595272, "books": 3.5740721512092177}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4436008820024306, "python_tests_examples": 1.301352445609624, "python_documentation": 2.3424995877444426, "cs_math": 2.41688959662112, "general_education": 3.433970397595272, "books": 3.5740721512092177}, "weighted_loss": 1.6631384337005664}
|
| 201 |
+
{"step": 74000, "tokens": 4307134781, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4425219096434159, "python_tests_examples": 1.2816182126038491, "python_documentation": 2.336192495113983, "cs_math": 2.362833806745745, "general_education": 3.413945246238543, "books": 3.5902677509023504}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4425219096434159, "python_tests_examples": 1.2816182126038491, "python_documentation": 2.336192495113983, "cs_math": 2.362833806745745, "general_education": 3.413945246238543, "books": 3.5902677509023504}, "weighted_loss": 1.6558666254126866}
|
| 202 |
+
{"step": 74500, "tokens": 4336347331, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4540436404117967, "python_tests_examples": 1.3008506998006044, "python_documentation": 2.345021800805805, "cs_math": 2.394745640272166, "general_education": 3.4322443982475037, "books": 3.5793186402705053}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4540436404117967, "python_tests_examples": 1.3008506998006044, "python_documentation": 2.345021800805805, "cs_math": 2.394745640272166, "general_education": 3.4322443982475037, "books": 3.5793186402705053}, "weighted_loss": 1.6690491380847825}
|
| 203 |
+
{"step": 75000, "tokens": 4364616790, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.443059605666682, "python_tests_examples": 1.2727208119494704, "python_documentation": 2.334100274970831, "cs_math": 2.3833329358973527, "general_education": 3.419340470574454, "books": 3.572053112438251}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.443059605666682, "python_tests_examples": 1.2727208119494704, "python_documentation": 2.334100274970831, "cs_math": 2.3833329358973527, "general_education": 3.419340470574454, "books": 3.572053112438251}, "weighted_loss": 1.6554948161337133}
|
| 204 |
+
{"step": 75500, "tokens": 4393734922, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4413701465631716, "python_tests_examples": 1.2885593861140738, "python_documentation": 2.336339048633912, "cs_math": 2.4054127483487138, "general_education": 3.423165489704181, "books": 3.5659673978910154}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4413701465631716, "python_tests_examples": 1.2885593861140738, "python_documentation": 2.336339048633912, "cs_math": 2.4054127483487138, "general_education": 3.423165489704181, "books": 3.5659673978910154}, "weighted_loss": 1.6580933581129453}
|
| 205 |
+
{"step": 76000, "tokens": 4423063432, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4386894977131521, "python_tests_examples": 1.2689994422206938, "python_documentation": 2.3253944815162453, "cs_math": 2.437377306128314, "general_education": 3.4066313892115585, "books": 3.528999972707743}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4386894977131521, "python_tests_examples": 1.2689994422206938, "python_documentation": 2.3253944815162453, "cs_math": 2.437377306128314, "general_education": 3.4066313892115585, "books": 3.528999972707743}, "weighted_loss": 1.6526853444351948}
|
| 206 |
+
{"step": 76500, "tokens": 4452424643, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4346523147303771, "python_tests_examples": 1.2887002692074538, "python_documentation": 2.331498547349368, "cs_math": 2.3950093333711164, "general_education": 3.406365126889861, "books": 3.5684094837821854}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4346523147303771, "python_tests_examples": 1.2887002692074538, "python_documentation": 2.331498547349368, "cs_math": 2.3950093333711164, "general_education": 3.406365126889861, "books": 3.5684094837821854}, "weighted_loss": 1.6522885098416953}
|
| 207 |
+
{"step": 77000, "tokens": 4480870579, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4310025712497352, "python_tests_examples": 1.2813642657564959, "python_documentation": 2.3158815390696508, "cs_math": 2.3618321455357827, "general_education": 3.4129844742455044, "books": 3.5421648430098194}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4310025712497352, "python_tests_examples": 1.2813642657564959, "python_documentation": 2.3158815390696508, "cs_math": 2.3618321455357827, "general_education": 3.4129844742455044, "books": 3.5421648430098194}, "weighted_loss": 1.645268903447118}
|
| 208 |
+
{"step": 77343, "tokens": 4500012372, "target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "per_stratum": {"python_implementation": 1.4291383842176961, "python_tests_examples": 1.2583781308643684, "python_documentation": 2.3137639397863023, "cs_math": 2.371446938631287, "general_education": 3.3883845464456206, "books": 3.512148372696119}, "stratum_target_counts": {"python_implementation": 55027, "python_tests_examples": 97392, "python_documentation": 28953, "cs_math": 50556, "general_education": 38282, "books": 256483}, "windows": 192, "per_source": {"python_implementation": 1.4291383842176961, "python_tests_examples": 1.2583781308643684, "python_documentation": 2.3137639397863023, "cs_math": 2.371446938631287, "general_education": 3.3883845464456206, "books": 3.512148372696119}, "weighted_loss": 1.6395399141286433}
|