FrontD.11m completed session 1

README.md

@@ -0,0 +1,51 @@
+---
+license: mit
+library_name: pytorch
+pipeline_tag: text-generation
+tags:
+- text-generation
+- pretraining
+- decoder-only
+- from-scratch
+- 11m
+- 1096-context
+- rope
+- rmsnorm
+- swiglu
+---
+
+# FrontD.11m
+
+FrontD.11m is an approximately 11-million-parameter
+decoder-only language model trained completely from scratch.
+
+## Architecture
+
+- Parameters: 10,996,608
+- Context: 1096
+- Vocabulary: 16000
+- Hidden size: 256
+- Layers: 6
+- Attention heads: 16
+- FFN size: 1152
+- RoPE
+- RMSNorm
+- SwiGLU
+- Tied input/output embeddings
+
+## Pretraining
+
+Dataset:
+
+`Plans11/Organized_PreTrain_1k_Context`
+
+Training is performed in 20,000-example sessions.
+
+A persistent SHA-256 ledger prevents completed examples
+from being selected again.
+
+Interrupted sessions resume from their latest checkpoint.
+
+## Training from scratch
+
+No pretrained model weights are imported.

config.json

@@ -0,0 +1,31 @@
+{
+  "model_type": "frontd",
+  "architectures": [
+    "FrontD11M"
+  ],
+  "model_name": "FrontD.11m",
+  "vocab_size": 16000,
+  "context_length": 1096,
+  "hidden_size": 256,
+  "num_hidden_layers": 6,
+  "num_attention_heads": 16,
+  "intermediate_size": 1152,
+  "position_embedding_type": "rope",
+  "rope_theta": 10000.0,
+  "normalization": "rmsnorm",
+  "activation_function": "silu",
+  "attention_bias": false,
+  "mlp_bias": false,
+  "tie_word_embeddings": true,
+  "dropout": 0.0,
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>",
+  "parameter_target": "~11M",
+  "parameter_count": 10996608,
+  "dataset": "Plans11/Organized_PreTrain_1k_Context",
+  "session_examples": 20000,
+  "training_from_scratch": true,
+  "license": "mit"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1dbc61d3691a3b5d97446b5f400c0f638c7f36b2089981751c122927a25e32
+size 44000846

session_000001.json

@@ -0,0 +1,9 @@
+{
+  "session": 1,
+  "parameters": 10996608,
+  "context_length": 1096,
+  "vocab_size": 16000,
+  "dataset": "Plans11/Organized_PreTrain_1k_Context",
+  "examples_per_session": 20000,
+  "uploaded_at": "2026-08-19 06:22:30 UTC"
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

training_state/latest.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439f3806541090f30e1ed5b09aed57833bae14132ba9cc1806153f33cc8dd66f
+size 164223243

training_state/run_state.json

@@ -0,0 +1,15 @@
+{
+  "checkpoint_version": 4,
+  "model_repo": "ITLL/FrontD.11m",
+  "dataset_repo": "Plans11/Organized_PreTrain_1k_Context",
+  "session_number": 1,
+  "global_step": 313,
+  "examples_seen_total": 20000,
+  "session_examples_current": 20000,
+  "next_batch_index": 2500,
+  "session_complete": true,
+  "parameter_count": 10996608,
+  "context_length": 1096,
+  "vocab_size": 16000,
+  "updated_at": "2026-08-19 06:22:29 UTC"
+}