Upload inv_reference_mixed_ema_b099

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: allenai/OLMo-2-1124-7B-Instruct
+tags: [tokenization, robustness, safety, adversarial-tokenization]
+---
+
+# inv_reference_mixed_ema_b099
+
+Research checkpoint from a study of **tokenization (reader) invariance** and its
+effect on robustness to adversarial re-tokenization. Fine-tuned from
+`allenai/OLMo-2-1124-7B-Instruct`.
+
+**These are research artifacts, not products.** Numbers below are measured on a
+200-prompt AdvBench holdout that was excluded from training by construction.
+
+## Measured
+
+| metric | value |
+| --- | --- |
+| AdvTok ASR (greedy) | 0.17 |
+| AdvTok canonical ASR (greedy) | 0.065 |
+| XSTest over-refusal (safe) | 0.104 |
+| XSTest refusal (unsafe) | 0.856 |
+| margin_spread | 0.571 |
+| Alpaca token F1 | 0.4 |
+
+`AdvTok ASR` is attack success rate under adversarial tokenization
+(Geh et al., arXiv:2503.02174), Llama-Guard-3-8B judged, greedy decoding.
+`XSTest over-refusal` is the refusal rate on *safe* prompts — the cost side.
+
+## Training configuration
+
+| field | value |
+| --- | --- |
+| `mode` | `reference` | 
+| `objective` | `invariance` | 
+| `ce_weighting` | `uniform` | 
+| `ema_beta` | `0.99` | 
+| `harmful_mix` | `mixed` | 
+| `harmful_fraction` | `0.286` | 
+| `num_encodings` | `8` | 
+| `cvar_quantile` | `0.25` | 
+| `max_steps` | `700` | 
+| `learning_rate` | `1e-05` | 
+| `grad_accum` | `8` | 
+| `seed` | `42` | 
+| `reference_model` | `allenai/OLMo-2-1124-7B-Instruct` | 
+| `max_new_tokens` | `128` | 
+| `prefix_tokens` | `8` | 
+
+## Parameter drift from base (training-happened guard)
+
+| group | relative L2 |
+| --- | --- |
+| attn | 0.01193 |
+| embed_tokens | 0.00096 |
+| lm_head | 0.00674 |
+| mlp | 0.01300 |
+| norm | 0.00099 |
+
+## Caveats
+
+- Single seed. No claim of significance across seeds.
+- Evaluated on English AdvBench/XSTest/Alpaca only.
+- The safety numbers are for the *specific* attack studied; they do not imply
+  robustness to other jailbreaks.

assert_teacher_moved.json

@@ -0,0 +1,34 @@
+{
+  "failed_groups": [],
+  "groups": {
+    "attn": {
+      "bit_identical_tensors": 0,
+      "relative_l2_drift": 0.010697613173222148,
+      "tensors": 192
+    },
+    "embed_tokens": {
+      "bit_identical_tensors": 0,
+      "relative_l2_drift": 0.000821722985817651,
+      "tensors": 1
+    },
+    "lm_head": {
+      "bit_identical_tensors": 0,
+      "relative_l2_drift": 0.006046310942873348,
+      "tensors": 1
+    },
+    "mlp": {
+      "bit_identical_tensors": 0,
+      "relative_l2_drift": 0.011632260148117404,
+      "tensors": 96
+    },
+    "norm": {
+      "bit_identical_tensors": 1,
+      "relative_l2_drift": 0.0008530631866974095,
+      "tensors": 65
+    }
+  },
+  "init": "allenai/OLMo-2-1124-7B-Instruct",
+  "min_drift": 1e-07,
+  "ok": true,
+  "trained": "/home/fs01/smw362/mars/distill/SOLD/outputs/alpaca_smollm_olmo/instruct/inv_reference_mixed_ema_b099/teacher-final"
+}

assert_trained.json

@@ -0,0 +1,34 @@
+{
+  "failed_groups": [],
+  "groups": {
+    "attn": {
+      "bit_identical_tensors": 0,
+      "relative_l2_drift": 0.01193335677050427,
+      "tensors": 192
+    },
+    "embed_tokens": {
+      "bit_identical_tensors": 0,
+      "relative_l2_drift": 0.0009572762731560684,
+      "tensors": 1
+    },
+    "lm_head": {
+      "bit_identical_tensors": 0,
+      "relative_l2_drift": 0.006738371088775685,
+      "tensors": 1
+    },
+    "mlp": {
+      "bit_identical_tensors": 0,
+      "relative_l2_drift": 0.012999441156061864,
+      "tensors": 96
+    },
+    "norm": {
+      "bit_identical_tensors": 1,
+      "relative_l2_drift": 0.000992564048055915,
+      "tensors": 65
+    }
+  },
+  "init": "allenai/OLMo-2-1124-7B-Instruct",
+  "min_drift": 1e-05,
+  "ok": true,
+  "trained": "/home/fs01/smw362/mars/distill/SOLD/outputs/alpaca_smollm_olmo/instruct/inv_reference_mixed_ema_b099"
+}

chat_template.jinja

@@ -0,0 +1,9 @@
+{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>
+' + message['content'] + '
+' }}{% elif message['role'] == 'user' %}{{ '<|user|>
+' + message['content'] + '
+' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>
+'  + message['content'] + eos_token + '
+' }}{% else %}{{ '<|assistant|>
+'  + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>
+' }}{% endif %}{% endfor %}

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "Olmo2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "olmo2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 100352
+}

experiment_config.json

@@ -0,0 +1,33 @@
+{
+  "advbench_path": "/home/fs01/smw362/mars/distill/SOLD/experiments/alpaca_smollm/data_advbench/advbench.jsonl",
+  "ce_weighting": "uniform",
+  "cvar_quantile": 0.25,
+  "dataset_path": "/home/fs01/smw362/mars/distill/SOLD/experiments/alpaca_smollm/data",
+  "ema_beta": 0.99,
+  "ema_target_source": "frozen",
+  "eval_holdout_count": 200,
+  "eval_holdout_seed": 0,
+  "grad_accum": 8,
+  "harmful_fraction": 0.286,
+  "harmful_mix": "mixed",
+  "learning_rate": 1e-05,
+  "log_every": 10,
+  "max_grad_norm": 1.0,
+  "max_new_tokens": 128,
+  "max_prompt_chars": 400,
+  "max_steps": 700,
+  "mode": "reference",
+  "model_kind": "instruct",
+  "model_name": "allenai/OLMo-2-1124-7B-Instruct",
+  "num_encodings": 8,
+  "objective": "invariance",
+  "optim": "paged_adamw_8bit",
+  "output_dir": "/home/fs01/smw362/mars/distill/SOLD/outputs/alpaca_smollm_olmo/instruct/inv_reference_mixed_ema_b099",
+  "prefix_tokens": 8,
+  "reference_device": null,
+  "reference_model": "allenai/OLMo-2-1124-7B-Instruct",
+  "save_steps": 175,
+  "seed": 42,
+  "vocab_cache_file": null,
+  "warmup_steps": 20
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 100257,
+  "pad_token_id": 100277,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cdd91acfcabc43fe0bee4a3aafe2f0a4de9517a8bc4d302f781938dae701fd
+size 4970591184

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da1668ab3da03ba46b1df69d1d59ea26eb2ffd1f5896b548e86e8a0a6632b0f
+size 4981161496

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369b458e68d7c4d705cbb7b07d9a0531184fc95346de515875066a85df525341
+size 4645523448

model.safetensors.index.json

@@ -0,0 +1,363 @@
+{
+  "metadata": {
+    "total_parameters": 7298617344,
+    "total_size": 14597234688
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test_metrics.json

@@ -0,0 +1,18 @@
+{
+  "canonical_answer_nll": 1.2359538929751188,
+  "canonical_answer_perplexity": 3.4416599306299465,
+  "evaluated_prompts": 2477,
+  "generation_rouge_l_f1": 0.2799314612088651,
+  "generation_token_f1": 0.399937108335985,
+  "path_samples_per_prompt": 4,
+  "preparation": {
+    "discarded_prompts": 111,
+    "discarded_responses": 111,
+    "kept_prompts": 2477
+  },
+  "reading_logprob_std": 1.044033064655204,
+  "reading_span_available_prompts": 2477,
+  "reading_span_unavailable_prompts": 0,
+  "tokenization_path_logprob_std": 115.44147033811237,
+  "trajectory_balance_rmse": 3419.86204789599
+}

tokenizer_config.json

@@ -0,0 +1,189 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|extra_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|extra_id_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "<|extra_id_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<|extra_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "<|extra_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<|extra_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "<|extra_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<|extra_id_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "<|extra_id_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<|extra_id_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "<|extra_id_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_metrics.jsonl

@@ -0,0 +1,71 @@
+{"step": 1, "loss": 0.0866396956553217, "mean_kl_all_encodings": 9.932099401950836, "max_kl": 12.255531311035156, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 38.2}
+{"step": 10, "loss": 0.1365234165338549, "mean_kl_all_encodings": 16.13855540752411, "max_kl": 20.092830657958984, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 342.1}
+{"step": 20, "loss": 0.1189691794628743, "mean_kl_all_encodings": 6.255168318748474, "max_kl": 6.886162757873535, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 675.2}
+{"step": 30, "loss": 0.11099562134186272, "mean_kl_all_encodings": 21.564103364944458, "max_kl": 23.082454681396484, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 1005.1}
+{"step": 40, "loss": 0.1140018825622974, "mean_kl_all_encodings": 17.584762692451477, "max_kl": 28.804838180541992, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 1346.4}
+{"step": 50, "loss": 0.10816270459763473, "mean_kl_all_encodings": 9.60380607843399, "max_kl": 17.090181350708008, "encodings": 9, "continuation_len": 46, "harmful": false, "skipped": 0, "elapsed_s": 1688.4}
+{"step": 60, "loss": 0.09857497838966083, "mean_kl_all_encodings": 7.645306408405304, "max_kl": 9.891454696655273, "encodings": 9, "continuation_len": 13, "harmful": false, "skipped": 0, "elapsed_s": 2027.5}
+{"step": 70, "loss": 0.1203537780966144, "mean_kl_all_encodings": 4.649314731359482, "max_kl": 5.749394416809082, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 2356.4}
+{"step": 80, "loss": 0.10512727607565467, "mean_kl_all_encodings": 5.289893269538879, "max_kl": 5.908370018005371, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 2677.1}
+{"step": 90, "loss": 0.09597887445124798, "mean_kl_all_encodings": 6.714143514633179, "max_kl": 13.55076789855957, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 3011.9}
+{"step": 100, "loss": 0.10564328102045692, "mean_kl_all_encodings": 9.997235894203186, "max_kl": 12.462834358215332, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 3339.3}
+{"step": 110, "loss": 0.13118936559767463, "mean_kl_all_encodings": 9.606377124786377, "max_kl": 9.997570037841797, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 3665.9}
+{"step": 120, "loss": 0.07823299946612679, "mean_kl_all_encodings": 2.8782172948122025, "max_kl": 5.041347026824951, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 4006.6}
+{"step": 130, "loss": 0.10868425846274476, "mean_kl_all_encodings": 10.380228400230408, "max_kl": 14.30942153930664, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 4327.3}
+{"step": 140, "loss": 0.09226702387386468, "mean_kl_all_encodings": 6.931229948997498, "max_kl": 8.81066608428955, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 4661.2}
+{"step": 150, "loss": 0.09483509657729883, "mean_kl_all_encodings": 13.449027419090271, "max_kl": 15.744531631469727, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 4986.9}
+{"step": 160, "loss": 0.07584121506952216, "mean_kl_all_encodings": 4.485615015029907, "max_kl": 4.83007287979126, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 5313.6}
+{"step": 170, "loss": 0.07976060172077268, "mean_kl_all_encodings": 5.094437122344971, "max_kl": 5.5528459548950195, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 5635.8}
+{"step": 180, "loss": 0.07472177234303672, "mean_kl_all_encodings": 7.897445797920227, "max_kl": 10.553351402282715, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 6008.7}
+{"step": 190, "loss": 0.079243556552683, "mean_kl_all_encodings": 5.09459912776947, "max_kl": 6.567409515380859, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 6341.0}
+{"step": 200, "loss": 0.06848474791186163, "mean_kl_all_encodings": 4.935326099395752, "max_kl": 6.570274353027344, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 6669.9}
+{"step": 210, "loss": 0.06401680548733565, "mean_kl_all_encodings": 3.5473398864269257, "max_kl": 3.8068959712982178, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 7015.0}
+{"step": 220, "loss": 0.07895144915237325, "mean_kl_all_encodings": 7.956559062004089, "max_kl": 8.366889953613281, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 7349.9}
+{"step": 230, "loss": 0.06235686911677476, "mean_kl_all_encodings": 3.5469586551189423, "max_kl": 3.7422657012939453, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 7684.8}
+{"step": 240, "loss": 0.06535793882067083, "mean_kl_all_encodings": 3.9203283488750458, "max_kl": 4.380084991455078, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 8011.4}
+{"step": 250, "loss": 0.07639811952394666, "mean_kl_all_encodings": 7.531286001205444, "max_kl": 8.335347175598145, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 8345.4}
+{"step": 260, "loss": 0.0788579237938393, "mean_kl_all_encodings": 3.3322284817695618, "max_kl": 4.022709369659424, "encodings": 9, "continuation_len": 47, "harmful": false, "skipped": 0, "elapsed_s": 8673.6}
+{"step": 270, "loss": 0.06376199160495162, "mean_kl_all_encodings": 1.1089829355478287, "max_kl": 1.2751238346099854, "encodings": 9, "continuation_len": 15, "harmful": false, "skipped": 0, "elapsed_s": 8994.0}
+{"step": 280, "loss": 0.0648879926520749, "mean_kl_all_encodings": 19.89403998851776, "max_kl": 35.475372314453125, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 9319.8}
+{"step": 290, "loss": 0.08696906969998963, "mean_kl_all_encodings": 3.3748506009578705, "max_kl": 4.037199974060059, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 9639.3}
+{"step": 300, "loss": 0.05168693323066691, "mean_kl_all_encodings": 7.587746322154999, "max_kl": 9.20698070526123, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 9975.6}
+{"step": 310, "loss": 0.0877826779789757, "mean_kl_all_encodings": 3.075302928686142, "max_kl": 3.7557291984558105, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 10300.4}
+{"step": 320, "loss": 0.0581220130683505, "mean_kl_all_encodings": 3.0441426932811737, "max_kl": 4.639533996582031, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 10641.3}
+{"step": 330, "loss": 0.05216971358750015, "mean_kl_all_encodings": 5.0491108894348145, "max_kl": 7.291123390197754, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 10970.9}
+{"step": 340, "loss": 0.07040360858882196, "mean_kl_all_encodings": 5.071933746337891, "max_kl": 5.240671157836914, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 11298.8}
+{"step": 350, "loss": 0.06275964778324124, "mean_kl_all_encodings": 4.332508683204651, "max_kl": 4.584538459777832, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 11669.8}
+{"step": 360, "loss": 0.048186788910243195, "mean_kl_all_encodings": 4.057336390018463, "max_kl": 6.010736465454102, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 11995.0}
+{"step": 370, "loss": 0.07735600316955242, "mean_kl_all_encodings": 4.806900203227997, "max_kl": 5.396955966949463, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 12314.6}
+{"step": 380, "loss": 0.050656288949539885, "mean_kl_all_encodings": 4.991233170032501, "max_kl": 5.897585868835449, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 12635.4}
+{"step": 390, "loss": 0.048766349304787585, "mean_kl_all_encodings": 1.3704578131437302, "max_kl": 1.5649495124816895, "encodings": 9, "continuation_len": 78, "harmful": false, "skipped": 0, "elapsed_s": 12967.0}
+{"step": 400, "loss": 0.047880088264355435, "mean_kl_all_encodings": 3.5799793899059296, "max_kl": 9.531614303588867, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 13300.6}
+{"step": 410, "loss": 0.04322452151609468, "mean_kl_all_encodings": 3.5225652754306793, "max_kl": 4.392678260803223, "encodings": 9, "continuation_len": 86, "harmful": false, "skipped": 0, "elapsed_s": 13624.4}
+{"step": 420, "loss": 0.0535350565231056, "mean_kl_all_encodings": 9.988838791847229, "max_kl": 10.60676097869873, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 13950.8}
+{"step": 430, "loss": 0.04751132878132012, "mean_kl_all_encodings": 2.9248098134994507, "max_kl": 3.2073445320129395, "encodings": 9, "continuation_len": 41, "harmful": false, "skipped": 0, "elapsed_s": 14280.7}
+{"step": 440, "loss": 0.045491223159478976, "mean_kl_all_encodings": 3.1131866574287415, "max_kl": 3.601966619491577, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 14608.7}
+{"step": 450, "loss": 0.08462069802626501, "mean_kl_all_encodings": 4.647557348012924, "max_kl": 6.579817771911621, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 14936.9}
+{"step": 460, "loss": 0.04995433141157264, "mean_kl_all_encodings": 4.45457136631012, "max_kl": 4.906183242797852, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 15266.6}
+{"step": 470, "loss": 0.049528732733460853, "mean_kl_all_encodings": 17.000159978866577, "max_kl": 17.5895938873291, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 15585.6}
+{"step": 480, "loss": 0.04137997361976886, "mean_kl_all_encodings": 2.863017290830612, "max_kl": 3.16949725151062, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 15906.3}
+{"step": 490, "loss": 0.05352126037905691, "mean_kl_all_encodings": 3.4883818328380585, "max_kl": 3.7140088081359863, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 16245.9}
+{"step": 500, "loss": 0.05123089054541197, "mean_kl_all_encodings": 4.208146750926971, "max_kl": 4.457545280456543, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 16563.9}
+{"step": 510, "loss": 0.0557029445131775, "mean_kl_all_encodings": 5.52773505449295, "max_kl": 5.683797836303711, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 16891.1}
+{"step": 520, "loss": 0.051891534187598155, "mean_kl_all_encodings": 4.469800233840942, "max_kl": 5.142128944396973, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 17229.1}
+{"step": 530, "loss": 0.055901893829286564, "mean_kl_all_encodings": 4.680526256561279, "max_kl": 5.070734977722168, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 17594.0}
+{"step": 540, "loss": 0.05645743206478073, "mean_kl_all_encodings": 4.172445356845856, "max_kl": 4.351186275482178, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 17923.5}
+{"step": 550, "loss": 0.04430766925797798, "mean_kl_all_encodings": 8.515578925609589, "max_kl": 11.322582244873047, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 18261.1}
+{"step": 560, "loss": 0.05233717069204431, "mean_kl_all_encodings": 5.658154845237732, "max_kl": 7.338665008544922, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 18598.7}
+{"step": 570, "loss": 0.055730560304073154, "mean_kl_all_encodings": 2.3944428265094757, "max_kl": 2.6513826847076416, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 18928.8}
+{"step": 580, "loss": 0.046436937286125614, "mean_kl_all_encodings": 4.874002039432526, "max_kl": 6.569027900695801, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 19258.0}
+{"step": 590, "loss": 0.04434124162944499, "mean_kl_all_encodings": 1.1784628331661224, "max_kl": 1.5949375629425049, "encodings": 9, "continuation_len": 6, "harmful": false, "skipped": 0, "elapsed_s": 19589.7}
+{"step": 600, "loss": 0.049597708239525674, "mean_kl_all_encodings": 3.963528275489807, "max_kl": 4.744928359985352, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 19920.7}
+{"step": 610, "loss": 0.04179482661420479, "mean_kl_all_encodings": 2.557531639933586, "max_kl": 4.443299293518066, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 20244.8}
+{"step": 620, "loss": 0.03742935151385609, "mean_kl_all_encodings": 5.036036282777786, "max_kl": 7.630575180053711, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 20576.4}
+{"step": 630, "loss": 0.06786806801101193, "mean_kl_all_encodings": 3.7319468557834625, "max_kl": 4.049553394317627, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 20880.3}
+{"step": 640, "loss": 0.04891089114607894, "mean_kl_all_encodings": 6.248214900493622, "max_kl": 7.709578514099121, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 21205.7}
+{"step": 650, "loss": 0.05725062307064945, "mean_kl_all_encodings": 1.4647060930728912, "max_kl": 1.6367084980010986, "encodings": 9, "continuation_len": 128, "harmful": true, "skipped": 0, "elapsed_s": 21527.6}
+{"step": 660, "loss": 0.06638485555413354, "mean_kl_all_encodings": 1.9823969453573227, "max_kl": 2.0852832794189453, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 21854.6}
+{"step": 670, "loss": 0.03882510826697398, "mean_kl_all_encodings": 0.06158064492046833, "max_kl": 0.1284240186214447, "encodings": 9, "continuation_len": 13, "harmful": true, "skipped": 0, "elapsed_s": 22170.6}
+{"step": 680, "loss": 0.03739212173386477, "mean_kl_all_encodings": 3.6681768000125885, "max_kl": 4.763440132141113, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 22511.6}
+{"step": 690, "loss": 0.055762927235628014, "mean_kl_all_encodings": 6.906632840633392, "max_kl": 10.97396183013916, "encodings": 9, "continuation_len": 47, "harmful": false, "skipped": 0, "elapsed_s": 22846.7}
+{"step": 700, "loss": 0.03822668208595133, "mean_kl_all_encodings": 3.0706934332847595, "max_kl": 3.7386813163757324, "encodings": 9, "continuation_len": 128, "harmful": false, "skipped": 0, "elapsed_s": 23181.6}