| --- |
| library_name: nanochat |
| license: apache-2.0 |
| tags: |
| - nanochat |
| - nanochat_gpt |
| - pt_fineweb-nanochatbpe-20B |
| - ppt_github-code-nanochatbpe-1B |
| - seed_1 |
| - case_b |
| - lr_trapezoid |
| - depth_12 |
| --- |
| |
| # code_5pct_1e18_seed1_2026-07-12_01-12-46_897145-pt |
|
|
| Trained with [nanochat](https://github.com/karpathy/nanochat). Checkpoint at step **3,368**. |
|
|
| **W&B run:** https://wandb.ai/alexksternteam/optimal_seed_replicas_v1/runs/33ea3a6t |
| |
| ## Outcome |
| |
| | metric | value | |
| | --- | --- | |
| | `step` | 3368 | |
| | `smooth_train_loss` | 3.2399237155914307 | |
| | `min_objective` | 0.9851442932664687 | |
| | `flops_used` | 9.498592991426642e+17 | |
| | `flops_per_token` | 1075838976.0 | |
| | `total_training_time` | 422.86022329330444 | |
|
|
| ## Training config |
|
|
| ```json |
| { |
| "model_pt": { |
| "sequence_len": 2048, |
| "vocab_size": 65536, |
| "n_layer": 12, |
| "n_head": 6, |
| "n_kv_head": 6, |
| "n_embd": 768 |
| }, |
| "model_ppt": { |
| "sequence_len": 2048, |
| "vocab_size": 65536, |
| "n_layer": 12, |
| "n_head": 6, |
| "n_kv_head": 6, |
| "n_embd": 768 |
| }, |
| "optim": { |
| "matrix_lr": 0.015, |
| "embedding_lr": 0.3, |
| "unembedding_lr": 0.004, |
| "weight_decay": 0.0 |
| }, |
| "train": { |
| "num_iterations": 1000, |
| "eval_every_n_steps": null, |
| "eval_every_flops_frac": null, |
| "save_every_n_steps": null, |
| "log_every_n_steps": 100, |
| "eval_at_end": true, |
| "save_at_end": true, |
| "grad_clip": 1.0, |
| "ema_beta": 0.0 |
| }, |
| "eval": { |
| "eval_steps": 8, |
| "eval_tokens": 2016000 |
| }, |
| "hardware": { |
| "device_batch_size": 32, |
| "grad_accum_steps": 1, |
| "peak_tflops": 2250.0 |
| }, |
| "wandb": { |
| "enabled": true, |
| "notes": "", |
| "group": "1e18_ppt0.05", |
| "tags": [ |
| "nanochat_gpt", |
| "pt_fineweb-nanochatbpe-20B", |
| "ppt_github-code-nanochatbpe-1B", |
| "seed_1", |
| "case_b", |
| "lr_trapezoid", |
| "depth_12" |
| ], |
| "entity": null |
| }, |
| "data_pt": "fineweb-nanochatbpe-20B", |
| "data_ppt": "github-code-nanochatbpe-1B", |
| "extra_eval": [ |
| "c4-nanochatbpe-10B" |
| ], |
| "train_split": "train", |
| "pad_vocab": 65536, |
| "ppt_vocab_size": null, |
| "ppt_same_vocab_as_pt": true, |
| "ppt_unified_lr": true, |
| "lr_kind": "trapezoid", |
| "lr_warmup_ratio": 0.0, |
| "lr_warmdown_ratio": 0.4, |
| "lr_final_frac": 0.0, |
| "ppt_lr_kind": "trapezoid", |
| "ppt_lr_warmup_ratio": null, |
| "ppt_lr_warmdown_ratio": null, |
| "ppt_lr_final_frac": 0.0, |
| "ppt_lr": null, |
| "ppt_weight_decay": 0.0, |
| "ppt_device_batch_size": null, |
| "ppt_grad_accum_steps": null, |
| "eval_tokens": 2016000, |
| "reinit_embed_at_transition": false, |
| "reset_optimizer_at_transition": false, |
| "depth": 12, |
| "compile_model": true, |
| "model_project": "optimal_seed_replicas_v1", |
| "run_name": "code_5pct_1e18_seed1", |
| "target_flops": 1e+18, |
| "alpha_ppt": 0.05, |
| "use_measured_flops": true, |
| "flops_per_token": null, |
| "ppt_flops_per_token": null, |
| "seed": 1, |
| "metrics_output_file": null, |
| "push_to_hf": true, |
| "hf_repo_org": "alexkstern", |
| "cleanup_checkpoints": true |
| } |
| ``` |
|
|
| ## Files |
|
|
| - `model_003368.pt` — model weights (`state_dict`). |
| - `meta_003368.json` — training metadata. |
| - `config_003368.json` — run config snapshot. |
| - `rng_003368.pt` — RNG state (when present). |
|
|
