Upload best checkpoint for v5 bs6 WSD fast-decay run (step 10000)

README.md

@@ -0,0 +1,74 @@
+---
+language:
+- en
+- it
+license: other
+library_name: custom
+pipeline_tag: text-generation
+tags:
+- nanochat
+- gpt2-small
+- bilingual
+- english
+- italian
+- pretraining
+---
+
+# gpt2small-en-it-nanochat-lr2e4-bs6-wsd-fastdecay-step10000
+
+This repo stages the best saved checkpoint from the local NanoChat EN/IT GPT-2-small-like run `20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay`.
+
+## What this is
+
+- model family: GPT-2-small-like decoder-only LM
+- parameters: ~136M
+- languages: English + Italian
+- context length: 2500
+- selected checkpoint: `step_10000.pt`
+- selection reason: lowest recorded validation loss among saved checkpoints in `best_validation.json`
+
+## Best validation
+
+- step: 10000
+- validation loss: 3.8945770748
+- validation perplexity: 49.1352684243
+- validation batches: 128
+
+## Important caveat
+
+This checkpoint is the best validation checkpoint **within this run family**. It is a useful intermediate bilingual pretraining artifact, not a polished factual assistant model.
+
+## Training/data provenance
+
+- training config: `training_config.yaml`
+- tokenizer: `tokenizer.json` + `tokenizer_meta.json`
+- packed dataset root used by the run: `/mnt/apps/llm-nanochat/datasets/202605011052_fresh_50_50_score100_2500_sourcebalanced`
+- tokenizer root used by the run: `/mnt/apps/llm-nanochat/tokenizers/tok_202605011052_fresh_50_50_score100_32k_fromscratch`
+
+## Included files
+
+- `step_10000.pt`
+- `step_10000.safetensors`
+- `step_10000.safetensors.json`
+- `training_config.yaml`
+- `tokenizer.json`
+- `tokenizer_meta.json`
+- `best_validation.json`
+- `eval_summary.json`
+- `probe_step10000_summary.json`
+- full run telemetry snapshots: `eval_metrics.jsonl`, `metrics.jsonl`, `probe_generations.jsonl`
+
+## Probe reading at step 10000
+
+The run includes probe telemetry, but the stored payload for this experiment is legacy/partial: the `probe_generations.jsonl` entries at step `10000` keep prompts and expected continuations, while generated text / target-rank fields are null. So this release does **not** make strong probe-quality claims from those rows.
+
+## Usage
+
+This project uses a custom NanoChat inference/training stack. The easiest local UI in the source repo is the Chainlit checkpoint tester documented in the repo README.
+
+## Limitations
+
+- factual recall is still limited
+- generations may become repetitive
+- the model was selected by validation loss inside this run family, not by broad downstream benchmark performance
+- dataset redistribution for the full training corpus may have separate licensing constraints; this repo contains model artifacts, not the raw/prepared training corpus

best_validation.json

@@ -0,0 +1,8 @@
+{
+  "step": 10000,
+  "validation_loss": 3.8945770747959614,
+  "validation_perplexity": 49.1352684243327,
+  "validation_num_batches": 128,
+  "elapsed_sec": 82998.0124297142,
+  "checkpoint_path": "/mnt/apps/llm-nanochat/checkpoints/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay/step_10000.pt"
+}

eval_metrics.jsonl

@@ -0,0 +1,10 @@
+{"step": 1000, "validation_loss": 5.782403785735369, "validation_perplexity": 324.5383742611778, "validation_num_batches": 128, "elapsed_sec": 8294.764070749283}
+{"step": 2000, "validation_loss": 4.983233451843262, "validation_perplexity": 145.94552736410432, "validation_num_batches": 128, "elapsed_sec": 16590.22207093239}
+{"step": 3000, "validation_loss": 4.501660106703639, "validation_perplexity": 90.16669345385398, "validation_num_batches": 128, "elapsed_sec": 24894.24841451645}
+{"step": 4000, "validation_loss": 4.2645480167120695, "validation_perplexity": 71.13276188688639, "validation_num_batches": 128, "elapsed_sec": 33190.52204680443}
+{"step": 5000, "validation_loss": 4.109950916841626, "validation_perplexity": 60.94372618564526, "validation_num_batches": 128, "elapsed_sec": 41488.19192171097}
+{"step": 6000, "validation_loss": 3.989347394555807, "validation_perplexity": 54.01962435656213, "validation_num_batches": 128, "elapsed_sec": 49786.84053468704}
+{"step": 7000, "validation_loss": 4.209565173834562, "validation_perplexity": 67.32725779094922, "validation_num_batches": 128, "elapsed_sec": 58085.096895217896}
+{"step": 8000, "validation_loss": 4.077932074666023, "validation_perplexity": 59.023287809598706, "validation_num_batches": 128, "elapsed_sec": 66384.57489657402}
+{"step": 9000, "validation_loss": 3.966189209371805, "validation_perplexity": 52.78300212187296, "validation_num_batches": 128, "elapsed_sec": 74691.24132275581}
+{"step": 10000, "validation_loss": 3.8945770747959614, "validation_perplexity": 49.1352684243327, "validation_num_batches": 128, "elapsed_sec": 82998.0124297142}

eval_summary.json

@@ -0,0 +1,26 @@
+{
+  "model_name": "gpt2small-en-it-nanochat-lr2e4-bs6-wsd-fastdecay-step10000",
+  "selected_checkpoint": "step_10000.pt",
+  "selection_reason": "best_validation.json minimum validation loss for this run",
+  "best_validation": {
+    "step": 10000,
+    "validation_loss": 3.8945770747959614,
+    "validation_perplexity": 49.1352684243327,
+    "validation_num_batches": 128,
+    "elapsed_sec": 82998.0124297142
+  },
+  "final_validation_step_10000": {
+    "step": 10000,
+    "validation_loss": 3.8945770747959614,
+    "validation_perplexity": 49.1352684243327,
+    "validation_num_batches": 128,
+    "elapsed_sec": 82998.0124297142
+  },
+  "notes": [
+    "This is the best saved checkpoint of the stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay run.",
+    "For this run the final saved checkpoint step_10000.pt is also the best validation checkpoint.",
+    "Probe telemetry exists, but this run wrote legacy/null probe target fields, so probe quality claims are intentionally conservative."
+  ],
+  "tokenizer_dir": "/mnt/apps/llm-nanochat/tokenizers/tok_202605011052_fresh_50_50_score100_32k_fromscratch",
+  "dataset_dir": "/mnt/apps/llm-nanochat/datasets/202605011052_fresh_50_50_score100_2500_sourcebalanced"
+}

probe_step10000_summary.json

@@ -0,0 +1,38 @@
+[
+  {
+    "language": "en",
+    "prompt": "The capital of Italy is",
+    "expected_next_text": " Rome",
+    "completion": null,
+    "correct_token_rank": null,
+    "correct_token_probability": null,
+    "note": "legacy/null probe payload in this run"
+  },
+  {
+    "language": "en",
+    "prompt": "A small language model should",
+    "expected_next_text": " be",
+    "completion": null,
+    "correct_token_rank": null,
+    "correct_token_probability": null,
+    "note": "legacy/null probe payload in this run"
+  },
+  {
+    "language": "it",
+    "prompt": "La capitale d'Italia è",
+    "expected_next_text": " Roma",
+    "completion": null,
+    "correct_token_rank": null,
+    "correct_token_probability": null,
+    "note": "legacy/null probe payload in this run"
+  },
+  {
+    "language": "it",
+    "prompt": "Un piccolo modello linguistico dovrebbe",
+    "expected_next_text": " essere",
+    "completion": null,
+    "correct_token_rank": null,
+    "correct_token_probability": null,
+    "note": "legacy/null probe payload in this run"
+  }
+]

step_10000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff6ac107365b9e3820863926c8990299b4be6e52c9587ce7033fc165ad09e2c
+size 1633717975

step_10000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8b68a5746314c08c2162f1e00bce5c26a70f71a71c4a4eadb1646b68568170f
+size 544531144

step_10000.safetensors.json

@@ -0,0 +1,287 @@
+{
+  "checkpoint_config": {
+    "actual_precision": "bf16",
+    "adamw_betas": [
+      0.9,
+      0.95
+    ],
+    "adamw_eps": 1e-08,
+    "attention_kernel_policy": "auto",
+    "batch_size": 6,
+    "benchmark": {
+      "enable_central_tensorboard": true,
+      "enable_local_tensorboard": true,
+      "enabled": false,
+      "output_path": "/mnt/apps/llm-nanochat/artifacts/runs/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay/throughput_benchmark.json",
+      "warmup_steps": 0
+    },
+    "checkpoint_dir": "/mnt/apps/llm-nanochat/checkpoints/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay",
+    "clip_grad_norm": 1.0,
+    "compile": {
+      "backend": null,
+      "compile_setup_sec": 0.0,
+      "diagnostic": null,
+      "dynamic": false,
+      "enabled": false,
+      "error_policy": "raise",
+      "fullgraph": false,
+      "mode": null,
+      "requested": false,
+      "status": "disabled"
+    },
+    "dataset": {
+      "storage_mode": "indexed_jsonl"
+    },
+    "decay_steps": 2500,
+    "deterministic_algorithms": false,
+    "device": "cuda",
+    "dim": 768,
+    "final_lr": 1e-05,
+    "fp8_backend": null,
+    "grad_accum_steps": 16,
+    "learning_rate": 0.0002,
+    "logging": {
+      "enable_central_tensorboard": true,
+      "enable_local_tensorboard": true,
+      "metrics_flush_every_steps": 1,
+      "metrics_writer": "persistent_jsonl_handle"
+    },
+    "lr": 0.0002,
+    "lr_schedule": "wsd",
+    "max_seq_len": 2500,
+    "max_steps": 10000,
+    "n_heads": 12,
+    "n_layers": 12,
+    "optimizer": {
+      "backend": "torch",
+      "betas": [
+        0.9,
+        0.95
+      ],
+      "eps": 1e-08,
+      "implementation": "torch.optim.AdamW",
+      "learning_rate": 0.0002,
+      "state_precision": "full_precision",
+      "type": "adamw",
+      "weight_decay": 0.1
+    },
+    "optimizer_backend": "torch",
+    "optimizer_implementation": "torch.optim.AdamW",
+    "optimizer_state_precision": "full_precision",
+    "optimizer_type": "adamw",
+    "peak_lr": 0.0002,
+    "repro": {
+      "attention_kernel_policy": "auto",
+      "cublas_workspace_config": null,
+      "cudnn_benchmark": true,
+      "cudnn_deterministic": false,
+      "deterministic_algorithms": false,
+      "flash_sdp_enabled": true,
+      "math_sdp_enabled": true,
+      "mem_efficient_sdp_enabled": true,
+      "pythonhashseed": "1337",
+      "seed": 1337
+    },
+    "requested_precision": "bf16",
+    "save_every_steps": 500,
+    "scheduler": {
+      "decay_steps": 2500,
+      "final_lr": 1e-05,
+      "peak_lr": 0.0002,
+      "schedule_type": "wsd",
+      "stable_steps": 7000,
+      "total_steps": 10000,
+      "warmup_steps": 500
+    },
+    "seed": 1337,
+    "stable_steps": 7000,
+    "train_cache_ram_bytes": 1073741824,
+    "train_cache_ram_mb": 1024,
+    "vocab_size": 32000,
+    "warmup_steps": 500,
+    "weight_decay": 0.1
+  },
+  "checkpoint_path": "/mnt/apps/llm-nanochat/checkpoints/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay/step_10000.pt",
+  "exported_at": "2026-05-19T13:49:55.443068+00:00",
+  "format": "llm-nanochat-safetensors-export",
+  "global_step": 10000,
+  "metadata_path": "/mnt/apps/llm-nanochat/hf_exports/gpt2small-en-it-nanochat-lr2e4-bs6-wsd-fastdecay-step10000/step_10000.safetensors.json",
+  "model_config": {
+    "dim": 768,
+    "max_seq_len": 2500,
+    "n_heads": 12,
+    "n_layers": 12,
+    "vocab_size": 32000
+  },
+  "num_parameters": 136128000,
+  "num_tensors": 149,
+  "provenance": {
+    "checkpoint_dir": "/mnt/apps/llm-nanochat/checkpoints/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay",
+    "checkpoint_name": "step_10000.pt",
+    "checkpoint_path": "/mnt/apps/llm-nanochat/checkpoints/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay/step_10000.pt",
+    "global_step": 10000,
+    "packed_dataset_config_path": null,
+    "run_dir": "/mnt/apps/llm-nanochat/artifacts/runs/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay",
+    "tokenizer_dir": "/mnt/apps/llm-nanochat/tokenizers/tok_202605011052_fresh_50_50_score100_32k_fromscratch",
+    "training_config_path": "/home/descanso/.openclaw/workspace/python_project/llm-nanochat/configs/testing/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay.yaml"
+  },
+  "safetensors_path": "/mnt/apps/llm-nanochat/hf_exports/gpt2small-en-it-nanochat-lr2e4-bs6-wsd-fastdecay-step10000/step_10000.safetensors",
+  "source_checkpoint_path": "/mnt/apps/llm-nanochat/checkpoints/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay/step_10000.pt",
+  "source_global_step": 10000,
+  "tensor_names": [
+    "token_emb.weight",
+    "pos_emb.weight",
+    "blocks.layers.0.self_attn.in_proj_weight",
+    "blocks.layers.0.self_attn.in_proj_bias",
+    "blocks.layers.0.self_attn.out_proj.weight",
+    "blocks.layers.0.self_attn.out_proj.bias",
+    "blocks.layers.0.linear1.weight",
+    "blocks.layers.0.linear1.bias",
+    "blocks.layers.0.linear2.weight",
+    "blocks.layers.0.linear2.bias",
+    "blocks.layers.0.norm1.weight",
+    "blocks.layers.0.norm1.bias",
+    "blocks.layers.0.norm2.weight",
+    "blocks.layers.0.norm2.bias",
+    "blocks.layers.1.self_attn.in_proj_weight",
+    "blocks.layers.1.self_attn.in_proj_bias",
+    "blocks.layers.1.self_attn.out_proj.weight",
+    "blocks.layers.1.self_attn.out_proj.bias",
+    "blocks.layers.1.linear1.weight",
+    "blocks.layers.1.linear1.bias",
+    "blocks.layers.1.linear2.weight",
+    "blocks.layers.1.linear2.bias",
+    "blocks.layers.1.norm1.weight",
+    "blocks.layers.1.norm1.bias",
+    "blocks.layers.1.norm2.weight",
+    "blocks.layers.1.norm2.bias",
+    "blocks.layers.2.self_attn.in_proj_weight",
+    "blocks.layers.2.self_attn.in_proj_bias",
+    "blocks.layers.2.self_attn.out_proj.weight",
+    "blocks.layers.2.self_attn.out_proj.bias",
+    "blocks.layers.2.linear1.weight",
+    "blocks.layers.2.linear1.bias",
+    "blocks.layers.2.linear2.weight",
+    "blocks.layers.2.linear2.bias",
+    "blocks.layers.2.norm1.weight",
+    "blocks.layers.2.norm1.bias",
+    "blocks.layers.2.norm2.weight",
+    "blocks.layers.2.norm2.bias",
+    "blocks.layers.3.self_attn.in_proj_weight",
+    "blocks.layers.3.self_attn.in_proj_bias",
+    "blocks.layers.3.self_attn.out_proj.weight",
+    "blocks.layers.3.self_attn.out_proj.bias",
+    "blocks.layers.3.linear1.weight",
+    "blocks.layers.3.linear1.bias",
+    "blocks.layers.3.linear2.weight",
+    "blocks.layers.3.linear2.bias",
+    "blocks.layers.3.norm1.weight",
+    "blocks.layers.3.norm1.bias",
+    "blocks.layers.3.norm2.weight",
+    "blocks.layers.3.norm2.bias",
+    "blocks.layers.4.self_attn.in_proj_weight",
+    "blocks.layers.4.self_attn.in_proj_bias",
+    "blocks.layers.4.self_attn.out_proj.weight",
+    "blocks.layers.4.self_attn.out_proj.bias",
+    "blocks.layers.4.linear1.weight",
+    "blocks.layers.4.linear1.bias",
+    "blocks.layers.4.linear2.weight",
+    "blocks.layers.4.linear2.bias",
+    "blocks.layers.4.norm1.weight",
+    "blocks.layers.4.norm1.bias",
+    "blocks.layers.4.norm2.weight",
+    "blocks.layers.4.norm2.bias",
+    "blocks.layers.5.self_attn.in_proj_weight",
+    "blocks.layers.5.self_attn.in_proj_bias",
+    "blocks.layers.5.self_attn.out_proj.weight",
+    "blocks.layers.5.self_attn.out_proj.bias",
+    "blocks.layers.5.linear1.weight",
+    "blocks.layers.5.linear1.bias",
+    "blocks.layers.5.linear2.weight",
+    "blocks.layers.5.linear2.bias",
+    "blocks.layers.5.norm1.weight",
+    "blocks.layers.5.norm1.bias",
+    "blocks.layers.5.norm2.weight",
+    "blocks.layers.5.norm2.bias",
+    "blocks.layers.6.self_attn.in_proj_weight",
+    "blocks.layers.6.self_attn.in_proj_bias",
+    "blocks.layers.6.self_attn.out_proj.weight",
+    "blocks.layers.6.self_attn.out_proj.bias",
+    "blocks.layers.6.linear1.weight",
+    "blocks.layers.6.linear1.bias",
+    "blocks.layers.6.linear2.weight",
+    "blocks.layers.6.linear2.bias",
+    "blocks.layers.6.norm1.weight",
+    "blocks.layers.6.norm1.bias",
+    "blocks.layers.6.norm2.weight",
+    "blocks.layers.6.norm2.bias",
+    "blocks.layers.7.self_attn.in_proj_weight",
+    "blocks.layers.7.self_attn.in_proj_bias",
+    "blocks.layers.7.self_attn.out_proj.weight",
+    "blocks.layers.7.self_attn.out_proj.bias",
+    "blocks.layers.7.linear1.weight",
+    "blocks.layers.7.linear1.bias",
+    "blocks.layers.7.linear2.weight",
+    "blocks.layers.7.linear2.bias",
+    "blocks.layers.7.norm1.weight",
+    "blocks.layers.7.norm1.bias",
+    "blocks.layers.7.norm2.weight",
+    "blocks.layers.7.norm2.bias",
+    "blocks.layers.8.self_attn.in_proj_weight",
+    "blocks.layers.8.self_attn.in_proj_bias",
+    "blocks.layers.8.self_attn.out_proj.weight",
+    "blocks.layers.8.self_attn.out_proj.bias",
+    "blocks.layers.8.linear1.weight",
+    "blocks.layers.8.linear1.bias",
+    "blocks.layers.8.linear2.weight",
+    "blocks.layers.8.linear2.bias",
+    "blocks.layers.8.norm1.weight",
+    "blocks.layers.8.norm1.bias",
+    "blocks.layers.8.norm2.weight",
+    "blocks.layers.8.norm2.bias",
+    "blocks.layers.9.self_attn.in_proj_weight",
+    "blocks.layers.9.self_attn.in_proj_bias",
+    "blocks.layers.9.self_attn.out_proj.weight",
+    "blocks.layers.9.self_attn.out_proj.bias",
+    "blocks.layers.9.linear1.weight",
+    "blocks.layers.9.linear1.bias",
+    "blocks.layers.9.linear2.weight",
+    "blocks.layers.9.linear2.bias",
+    "blocks.layers.9.norm1.weight",
+    "blocks.layers.9.norm1.bias",
+    "blocks.layers.9.norm2.weight",
+    "blocks.layers.9.norm2.bias",
+    "blocks.layers.10.self_attn.in_proj_weight",
+    "blocks.layers.10.self_attn.in_proj_bias",
+    "blocks.layers.10.self_attn.out_proj.weight",
+    "blocks.layers.10.self_attn.out_proj.bias",
+    "blocks.layers.10.linear1.weight",
+    "blocks.layers.10.linear1.bias",
+    "blocks.layers.10.linear2.weight",
+    "blocks.layers.10.linear2.bias",
+    "blocks.layers.10.norm1.weight",
+    "blocks.layers.10.norm1.bias",
+    "blocks.layers.10.norm2.weight",
+    "blocks.layers.10.norm2.bias",
+    "blocks.layers.11.self_attn.in_proj_weight",
+    "blocks.layers.11.self_attn.in_proj_bias",
+    "blocks.layers.11.self_attn.out_proj.weight",
+    "blocks.layers.11.self_attn.out_proj.bias",
+    "blocks.layers.11.linear1.weight",
+    "blocks.layers.11.linear1.bias",
+    "blocks.layers.11.linear2.weight",
+    "blocks.layers.11.linear2.bias",
+    "blocks.layers.11.norm1.weight",
+    "blocks.layers.11.norm1.bias",
+    "blocks.layers.11.norm2.weight",
+    "blocks.layers.11.norm2.bias",
+    "ln_f.weight",
+    "ln_f.bias",
+    "head.weight"
+  ],
+  "tokenizer_reference": {
+    "packed_dataset_config_path": null,
+    "tokenizer_dir": "/mnt/apps/llm-nanochat/tokenizers/tok_202605011052_fresh_50_50_score100_32k_fromscratch",
+    "training_config_path": "/home/descanso/.openclaw/workspace/python_project/llm-nanochat/configs/testing/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay.yaml"
+  }
+}

tokenizer_meta.json

@@ -0,0 +1,10 @@
+{
+  "vocab_size_requested": 32000,
+  "vocab_size_actual": 32000,
+  "special_tokens": [
+    "<pad>",
+    "<bos>",
+    "<eos>",
+    "<unk>"
+  ]
+}

training_config.yaml

@@ -0,0 +1,58 @@
+# Experimental WSD variant: longer stable phase, shorter decay.
+# Goal: reduce time spent in the suspected unstable LR band ~6e-5 -> 1e-4.
+# Keep experiment-only variants under configs/testing/.
+
+dataset_dir: /mnt/apps/llm-nanochat/datasets/202605011052_fresh_50_50_score100_2500_sourcebalanced
+output_dir: /mnt/apps/llm-nanochat/artifacts/runs/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay
+tokenizer_dir: /mnt/apps/llm-nanochat/tokenizers/tok_202605011052_fresh_50_50_score100_32k_fromscratch
+seed: 1337
+
+model:
+  vocab_size: 32000
+  dim: 768
+  n_layers: 12
+  n_heads: 12
+
+training:
+  sequence_length: 2500
+  max_steps: 10000
+  batch_size: 6
+  grad_accum_steps: 16
+
+  learning_rate: 0.0002
+  peak_lr: 0.0002
+  lr_schedule: wsd
+
+  warmup_steps: 500
+  stable_steps: 7000
+  decay_steps: 2500
+  final_lr: 1.0e-05
+
+  adamw_betas:
+    - 0.9
+    - 0.95
+  adamw_eps: 1.0e-08
+  weight_decay: 0.1
+  clip_grad_norm: 1.0
+
+  save_every_steps: 500
+  checkpoint_dir: /mnt/apps/llm-nanochat/checkpoints/20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay
+  precision: bf16
+
+evaluation:
+  validation_every_steps: 1000
+  validation_max_batches: 128
+  probe_every_steps: 1000
+  probe_tokenizer_dir: /mnt/apps/llm-nanochat/tokenizers/tok_202605011052_fresh_50_50_score100_32k_fromscratch
+  probe_max_new_tokens: 32
+  probe_prompts:
+    en:
+      - prompt: "The capital of Italy is"
+        expected_next_text: " Rome"
+      - prompt: "A small language model should"
+        expected_next_text: " be"
+    it:
+      - prompt: "La capitale d'Italia è"
+        expected_next_text: " Roma"
+      - prompt: "Un piccolo modello linguistico dovrebbe"
+        expected_next_text: " essere"