upload 8m near-capacity checkpoint

README.md

@@ -0,0 +1,37 @@
+---
+language: en
+library_name: transformers
+tags:
+  - memorization
+  - capacity
+  - gpt2
+  - random-data
+license: mit
+---
+# Tiny GPT memorization checkpoint (8m, near-capacity / saturation boundary)
+
+From an exploratory tiny-scale replication of
+[How much do language models memorize?](https://huggingface.co/papers/2505.24832).
+
+- Architecture: GPT-2 (transformers), trained from scratch.
+- Parameters: 7,916,160 (non-embedding 7,098,624).
+- Vocab: 2048 data tokens (uniform random) + BOS = 2049 model vocab.
+- Sequence length: 64 (paper S=64).
+- Dataset: 44000 sequences, 2,816,000 data tokens,
+  dataset entropy 30,976,000 bits (30.976 Mbits).
+- Trained 15698 steps, AdamW, bfloat16, lr 0.002, batch 512.
+- Result: train loss 5.8075 bits/tok, held loss 16.6023,
+  memorized 14,622,163 bits = **1.847 bits/parameter**.
+
+This is the **near-capacity (saturation-boundary)** run for this model size.
+Below- and above-capacity checkpoints for the same architecture are published as
+`state.pt` files in the results dataset `evalstate/tiny-memorization-results`.
+
+Load with:
+```python
+from transformers import GPT2LMHeadModel
+model = GPT2LMHeadModel.from_pretrained("evalstate/tiny-gpt-memorization-8m")
+```
+
+Findings are scoped as an exploratory tiny-scale check (three architectures),
+NOT a universal scaling law.

config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 2048,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2048,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 80,
+  "n_embd": 384,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 4,
+  "n_positions": 80,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_first_pdrop": 0.0,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 2049
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2048,
+  "eos_token_id": 2048,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300cb2f0b3a6f33d13b66ca438c800a3bb5482e40402b072cf45783dceca265b
+size 15837488