Proteinrequired/enterprise-email-triage
0
1{2 "nbformat": 4,3 "nbformat_minor": 0,4 "metadata": {5 "colab": {6 "provenance": []7 },8 "kernelspec": {9 "name": "python3",10 "display_name": "Python 3"11 },12 "language_info": {13 "name": "python"14 }15 },16 "cells": [17 {18 "cell_type": "code",19 "execution_count": null,20 "metadata": {21 "colab": {22 "base_uri": "https://localhost:8080/",23 "height": 1000,24 "referenced_widgets": [25 "db441240ce3548bfb4ba2f9c149a84f8",26 "992852aedd074b999bb3d9f14f470a35",27 "861dfc8a4c9849a38ac23dffe19e3f13",28 "aba88d7d83964522831187874dbbc27a",29 "0cac4910335848689bdca8154f71ed93",30 "fd81c0390e0c494fbb1150d2b8e5344d",31 "d73f968a5e2f44a28139f8e2be8cd676",32 "a432627561b649f597da827798fa4406",33 "30a8a97f231242898550d40b9dfde958",34 "3f1c8c3d30a943f4a695c4e91c2ad750",35 "36f3ef789e914ca98a1a2ea903f6194c",36 "b6ef5519fca04fc0b485e3e17292d7b8",37 "6353ec74a14a44b1bb9b2289707955ec",38 "18279f32691b46d7aaeaf3ba8d5e6c76",39 "54520b08fa1e40c5ae9abdc726ee9463",40 "00fa39c62c12469ba606e024a5ee0f48",41 "291d635e101f4fd3a497fecbb217598d",42 "02bf580c8c4f48f694992e4a73ec6226",43 "2f955225d1cc471daaf77c5b8913a499",44 "7ffa4300065e4813a4daaafcc19e34d3",45 "027e2b346ddc470da1ec31a6dea54899",46 "f14f3c647a6548cebc1c290867c478d1",47 "12124f93dded468d88c2cada8002549b",48 "c6bb0a4c01e847ecab1583327e24b595",49 "ebe7c61ab91e4952b86d39609d7aa51f",50 "0113ddeabf7f45738cd238e31c72be9f",51 "2bc50b56fdd4400291e7fdf3a2f67559",52 "d5ffd60026384b63a682604c150c9545",53 "d93a882bf6d745a5bf53e2be9c7ae7d1",54 "d4f526dab75b4603a5119484146c74de",55 "19a085dd9ec64b27a0afa96a1cf9c77b",56 "9c3bf725edbf427b98c1d4b78d145eb6",57 "242a9b4c2cf44ef3989e600f99109dbd",58 "8a7601455aba41ba94d99b3995022a4f",59 "1116d04e353145b2bdee2f7c26fcb89a",60 "c905b377085744fdacf0f2378962a7e8",61 "afa9dd62ef78469698b3a262485c33db",62 "0a25f46ee05648f4ba25bfb6acb815b8",63 "438f2815c7c54ccabe57f109137f8cbe",64 "60fca3cfad0d445bb866e9f5f063c600",65 "c95450890a2e4068a991be5e11e7a556",66 "ac68d50c3c6d4bf59f1bd3a1dc828c2c",67 "3f9fc317542449749f74866e810b4fa4",68 "761400ae50244385b7d0327dca7579b4",69 "38145911d9984423a641bdab06c7231c",70 "b65dc7b82f75468a81b47ab8e7893533",71 "b7493c1aff4d43d4a520a65deb750f5a",72 "bf576b18b17845bbac1c69ffd03c24f5",73 "a29e91582b7643c7bd6020d7446c31d7",74 "953b54e107d04fec84dd319b6abcba2e",75 "063ac09bae2a4fc2b3daaf039f321478",76 "d25128bf88ee429db92d6263741086f5",77 "f61ba17d9de94592a6c5bc49fa616d1c",78 "69fe402d16d44c8ea2facc26e386da26",79 "d7fd250697024498802e5d7f3f6d1e76",80 "1f1e1cb6c61d4b97af3eb737b52b1bd7",81 "74035c3be87642b8ba6cb52d3198e911",82 "9b5b0f47fab4471fab26173bdaa23824",83 "e19e4ea11dde4e5fb84e90a872f70b6c",84 "3855b1c8b8a64b1bbcdd92b46dd36700",85 "6db67239856e40cb8d51840c255d5bc1",86 "1fa5ce55c24647b29cfb4ddd46d6dcdb",87 "9a5bff8deaba4b6180eb9f41df22f496",88 "02c4ce7351584a7bbe3cf8d97cf1ea37",89 "56a8f068b9b24407903996d7504e743a",90 "50820d432efa4a2ba0d9682da82c47b9",91 "e0782f135c1b4f8cb7ef46943b98a1c0",92 "bc11d54419954bbdac4fc737ccb44667",93 "601386462eca4ffea1aca99301ac7f64",94 "3b8249ea24514f1bb0b7b384d0303c79",95 "90dfddf605af450dbd4fd84118ce30f6",96 "f88c7ec5136b4ab7aa9cb3c5fa7c59fa",97 "78724f98a0e24165b13ffddc77b0ffb0",98 "ff75cc9e11454d5dbf99c066f320e5a2",99 "04332c8400af4f97ae43732bb33318cb",100 "fde1580f854d494e837ebf61ccb08c12",101 "ab87218e1a0d43d4a6e340fbec7223da",102 "85a90ff7a9d743d089cf1a2df0fee00c",103 "981e7b377ce2429c84d1e1c7711b1d84",104 "45f029954fbc49b59549dcbaf78e6c57",105 "bcde68e0cf7b447c920b0008f2c1d0b3",106 "8fa0da896b1e499c9363bca8f3e77161",107 "e44da1ff410e491bbdd2b9e6944b5dd4",108 "32ed4e3fbccb401b95caa32a8b416a46",109 "700eb3be104145d8856116cf1ec97a91",110 "f05c27c995b24dc591bb3cc2eb88498d",111 "61ec0d4a5aad459fb7e17c7a1f40d8ea",112 "256ba051b8974a22a8c5806c33036302",113 "81e383a7144d40758155b7390f96cd36",114 "81509994ee72468c94c6446e4dce7bc4",115 "aa59aa4191814f5590df7b615cba8662",116 "fb30c48831ff49c0a93afe9f78b3d3ce",117 "100017db2b1643959e5fa9f9a151eca0",118 "d158b2021779494e8f45093dbd19763e",119 "94f2273c0d184bc1b45b8822eac844ae",120 "0e883221fdf44ceb9a3edb8a9d2e0f3e",121 "665a16b9f1c84a37b4e98e3ebb018079",122 "c494fae99a17475a888f2906e6777299",123 "c8e4bfe829f74f488afc145663efad9e",124 "70f74db9f35e49ad9ce25e676163bc27",125 "8a3d7e1753ad43a28764bf320dfb1f27",126 "fe7f9eb43f1546d6b1c2ebe6b667bba9",127 "84ff6cd46c124ae3a81efae655ab19ca",128 "10631bc855c94fd9a709405dbdc3e282",129 "9d857b4eb8964338ad440b0ce0dd04a4",130 "eb3604ac38d54a529309e6c5de500b28",131 "0ea515fd0808401b9fdeef8af42d3a84",132 "52143427e13f4f2f9c5bdba7894f45c4",133 "87021fde2b3447c0b901cf8256f0e48b",134 "167b90e3a1ce4e91bc28f3ab63952a4f",135 "301bb7b48eae4c8dbb8d0d746ceae489",136 "83e048ac798e4fe8af4188bc81c45a1f",137 "93db3f978c784c9285120f19bb9b064b",138 "5985cad0fc474efb89e677e281694696",139 "6efe3801db2346fba192e10136b58b62",140 "e3ccb91b91e54c0e9d41752b2f71e40a",141 "b880c1cf529b4462aa65da4d13a76193",142 "30b9e64f2db14bbaa9e81bc613cdaf2f",143 "a324204e66f44ab9a4653085b9ea7eb6"144 ]145 },146 "id": "72b21d99-0540-4ec4-9e6b-618d41eb6fb4",147 "outputId": "6dfd6ea9-32e0-4c8a-8b92-8f4ec785b6b7"148 },149 "outputs": [150 {151 "output_type": "stream",152 "name": "stdout",153 "text": [154 "🔍 Fetching required dependencies...\n",155 "✅ All files ready!\n",156 "\n",157 "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.12/dist-packages (1.10.1)\n",158 "Requirement already satisfied: filelock>=3.10.0 in /usr/local/lib/python3.12/dist-packages (from huggingface_hub) (3.25.2)\n",159 "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.12/dist-packages (from huggingface_hub) (2025.3.0)\n",160 "Requirement already satisfied: hf-xet<2.0.0,>=1.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface_hub) (1.4.3)\n",161 "Requirement already satisfied: httpx<1,>=0.23.0 in /usr/local/lib/python3.12/dist-packages (from huggingface_hub) (0.28.1)\n",162 "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.12/dist-packages (from huggingface_hub) (26.0)\n",163 "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from huggingface_hub) (6.0.3)\n",164 "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.12/dist-packages (from huggingface_hub) (4.67.3)\n",165 "Requirement already satisfied: typer in /usr/local/lib/python3.12/dist-packages (from huggingface_hub) (0.24.1)\n",166 "Requirement already satisfied: typing-extensions>=4.1.0 in /usr/local/lib/python3.12/dist-packages (from huggingface_hub) (4.15.0)\n",167 "Requirement already satisfied: anyio in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface_hub) (4.13.0)\n",168 "Requirement already satisfied: certifi in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface_hub) (2026.2.25)\n",169 "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface_hub) (1.0.9)\n",170 "Requirement already satisfied: idna in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface_hub) (3.11)\n",171 "Requirement already satisfied: h11>=0.16 in /usr/local/lib/python3.12/dist-packages (from httpcore==1.*->httpx<1,>=0.23.0->huggingface_hub) (0.16.0)\n",172 "Requirement already satisfied: click>=8.2.1 in /usr/local/lib/python3.12/dist-packages (from typer->huggingface_hub) (8.3.2)\n",173 "Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.12/dist-packages (from typer->huggingface_hub) (1.5.4)\n",174 "Requirement already satisfied: rich>=12.3.0 in /usr/local/lib/python3.12/dist-packages (from typer->huggingface_hub) (13.9.4)\n",175 "Requirement already satisfied: annotated-doc>=0.0.2 in /usr/local/lib/python3.12/dist-packages (from typer->huggingface_hub) (0.0.4)\n",176 "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich>=12.3.0->typer->huggingface_hub) (4.0.0)\n",177 "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich>=12.3.0->typer->huggingface_hub) (2.20.0)\n",178 "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich>=12.3.0->typer->huggingface_hub) (0.1.2)\n",179 "☁️ Colab detected! Please log in to Hugging Face to download Llama-3.2:\n"180 ]181 },182 {183 "output_type": "display_data",184 "data": {185 "text/plain": [186 "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"187 ],188 "application/vnd.jupyter.widget-view+json": {189 "version_major": 2,190 "version_minor": 0,191 "model_id": "db441240ce3548bfb4ba2f9c149a84f8"192 }193 },194 "metadata": {}195 },196 {197 "output_type": "stream",198 "name": "stdout",199 "text": [200 "Loading Unsloth 3B Model...\n",201 "==((====))== Unsloth 2026.4.8: Fast Llama patching. Transformers: 5.5.0.\n",202 " \\\\ /| Tesla T4. Num GPUs = 1. Max memory: 14.563 GB. Platform: Linux.\n",203 "O^O/ \\_/ \\ Torch: 2.10.0+cu128. CUDA: 7.5. CUDA Toolkit: 12.8. Triton: 3.6.0\n",204 "\\ / Bfloat16 = FALSE. FA [Xformers = 0.0.35. FA2 = False]\n",205 " \"-____-\" Free license: http://github.com/unslothai/unsloth\n",206 "Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!\n"207 ]208 },209 {210 "output_type": "display_data",211 "data": {212 "text/plain": [213 "model.safetensors: 0%| | 0.00/2.24G [00:00<?, ?B/s]"214 ],215 "application/vnd.jupyter.widget-view+json": {216 "version_major": 2,217 "version_minor": 0,218 "model_id": "02bf580c8c4f48f694992e4a73ec6226"219 }220 },221 "metadata": {}222 },223 {224 "output_type": "display_data",225 "data": {226 "text/plain": [227 "Loading weights: 0%| | 0/254 [00:00<?, ?it/s]"228 ],229 "application/vnd.jupyter.widget-view+json": {230 "version_major": 2,231 "version_minor": 0,232 "model_id": "d93a882bf6d745a5bf53e2be9c7ae7d1"233 }234 },235 "metadata": {}236 },237 {238 "output_type": "display_data",239 "data": {240 "text/plain": [241 "generation_config.json: 0%| | 0.00/234 [00:00<?, ?B/s]"242 ],243 "application/vnd.jupyter.widget-view+json": {244 "version_major": 2,245 "version_minor": 0,246 "model_id": "60fca3cfad0d445bb866e9f5f063c600"247 }248 },249 "metadata": {}250 },251 {252 "output_type": "display_data",253 "data": {254 "text/plain": [255 "config.json: 0.00B [00:00, ?B/s]"256 ],257 "application/vnd.jupyter.widget-view+json": {258 "version_major": 2,259 "version_minor": 0,260 "model_id": "063ac09bae2a4fc2b3daaf039f321478"261 }262 },263 "metadata": {}264 },265 {266 "output_type": "display_data",267 "data": {268 "text/plain": [269 "tokenizer_config.json: 0.00B [00:00, ?B/s]"270 ],271 "application/vnd.jupyter.widget-view+json": {272 "version_major": 2,273 "version_minor": 0,274 "model_id": "1fa5ce55c24647b29cfb4ddd46d6dcdb"275 }276 },277 "metadata": {}278 },279 {280 "output_type": "display_data",281 "data": {282 "text/plain": [283 "tokenizer.json: 0%| | 0.00/17.2M [00:00<?, ?B/s]"284 ],285 "application/vnd.jupyter.widget-view+json": {286 "version_major": 2,287 "version_minor": 0,288 "model_id": "78724f98a0e24165b13ffddc77b0ffb0"289 }290 },291 "metadata": {}292 },293 {294 "output_type": "display_data",295 "data": {296 "text/plain": [297 "special_tokens_map.json: 0%| | 0.00/454 [00:00<?, ?B/s]"298 ],299 "application/vnd.jupyter.widget-view+json": {300 "version_major": 2,301 "version_minor": 0,302 "model_id": "32ed4e3fbccb401b95caa32a8b416a46"303 }304 },305 "metadata": {}306 },307 {308 "output_type": "display_data",309 "data": {310 "text/plain": [311 "chat_template.jinja: 0.00B [00:00, ?B/s]"312 ],313 "application/vnd.jupyter.widget-view+json": {314 "version_major": 2,315 "version_minor": 0,316 "model_id": "94f2273c0d184bc1b45b8822eac844ae"317 }318 },319 "metadata": {}320 },321 {322 "output_type": "stream",323 "name": "stderr",324 "text": [325 "Unsloth: Will load unsloth/Llama-3.2-3B-Instruct-bnb-4bit as a legacy tokenizer.\n",326 "Unsloth 2026.4.8 patched 28 layers with 28 QKV layers, 28 O layers and 28 MLP layers.\n"327 ]328 },329 {330 "output_type": "stream",331 "name": "stdout",332 "text": [333 "Initializing OpenEnv...\n",334 "✅ Successfully loaded 100 emails from dataset.json\n",335 "Collecting rollouts (playing the game)...\n"336 ]337 },338 {339 "output_type": "stream",340 "name": "stderr",341 "text": [342 "\n",343 "Collecting rollouts: 0%| | 0/30 [00:00<?, ?it/s]\u001b[A"344 ]345 },346 {347 "output_type": "stream",348 "name": "stdout",349 "text": [350 "✅ Successfully loaded 100 emails from dataset.json\n"351 ]352 },353 {354 "output_type": "stream",355 "name": "stderr",356 "text": [357 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n",358 "/usr/local/lib/python3.12/dist-packages/transformers/modeling_attn_mask_utils.py:71: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.\n",359 " warnings.warn(DEPRECATION_MESSAGE, FutureWarning)\n",360 "/usr/local/lib/python3.12/dist-packages/transformers/modeling_attn_mask_utils.py:281: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.\n",361 " warnings.warn(DEPRECATION_MESSAGE, FutureWarning)\n",362 "/usr/local/lib/python3.12/dist-packages/transformers/modeling_attn_mask_utils.py:71: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.\n",363 " warnings.warn(DEPRECATION_MESSAGE, FutureWarning)\n",364 "/usr/local/lib/python3.12/dist-packages/transformers/modeling_attn_mask_utils.py:281: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.\n",365 " warnings.warn(DEPRECATION_MESSAGE, FutureWarning)\n",366 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"367 ]368 },369 {370 "output_type": "stream",371 "name": "stdout",372 "text": [373 "Step 1: route_to_human -> Reward: +0.83 | Total: +0.83\n"374 ]375 },376 {377 "output_type": "stream",378 "name": "stderr",379 "text": [380 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"381 ]382 },383 {384 "output_type": "stream",385 "name": "stdout",386 "text": [387 "Step 2: route_to_human -> Reward: +0.83 | Total: +1.66\n"388 ]389 },390 {391 "output_type": "stream",392 "name": "stderr",393 "text": [394 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"395 ]396 },397 {398 "output_type": "stream",399 "name": "stdout",400 "text": [401 "Step 3: ask_for_clarification -> Reward: -0.37 | Total: +1.29\n"402 ]403 },404 {405 "output_type": "stream",406 "name": "stderr",407 "text": [408 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"409 ]410 },411 {412 "output_type": "stream",413 "name": "stdout",414 "text": [415 "Step 4: route_to_human -> Reward: -0.97 | Total: +0.32\n"416 ]417 },418 {419 "output_type": "stream",420 "name": "stderr",421 "text": [422 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"423 ]424 },425 {426 "output_type": "stream",427 "name": "stdout",428 "text": [429 "Step 5: auto_reply -> Reward: -0.67 | Total: -0.35\n"430 ]431 },432 {433 "output_type": "stream",434 "name": "stderr",435 "text": [436 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"437 ]438 },439 {440 "output_type": "stream",441 "name": "stdout",442 "text": [443 "Step 6: route_to_human -> Reward: -0.97 | Total: -1.32\n"444 ]445 },446 {447 "output_type": "stream",448 "name": "stderr",449 "text": [450 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"451 ]452 },453 {454 "output_type": "stream",455 "name": "stdout",456 "text": [457 "Step 7: route_to_human -> Reward: +0.83 | Total: -0.49\n"458 ]459 },460 {461 "output_type": "stream",462 "name": "stderr",463 "text": [464 "/usr/local/lib/python3.12/dist-packages/transformers/modeling_attn_mask_utils.py:71: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.\n",465 " warnings.warn(DEPRECATION_MESSAGE, FutureWarning)\n",466 "/usr/local/lib/python3.12/dist-packages/transformers/modeling_attn_mask_utils.py:281: FutureWarning: The attention mask API under `transformers.modeling_attn_mask_utils` (`AttentionMaskConverter`) is deprecated and will be removed in Transformers v5.10. Please use the new API in `transformers.masking_utils`.\n",467 " warnings.warn(DEPRECATION_MESSAGE, FutureWarning)\n",468 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"469 ]470 },471 {472 "output_type": "stream",473 "name": "stdout",474 "text": [475 "Step 8: route_to_human -> Reward: +0.83 | Total: +0.34\n"476 ]477 },478 {479 "output_type": "stream",480 "name": "stderr",481 "text": [482 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"483 ]484 },485 {486 "output_type": "stream",487 "name": "stdout",488 "text": [489 "Step 9: ask_for_clarification -> Reward: -0.37 | Total: -0.03\n"490 ]491 },492 {493 "output_type": "stream",494 "name": "stderr",495 "text": [496 "\n",497 "Collecting rollouts: 3%|▎ | 1/30 [00:27<13:18, 27.53s/it]\u001b[ABoth `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"498 ]499 },500 {501 "output_type": "stream",502 "name": "stdout",503 "text": [504 "Step 10: route_to_human -> Reward: -0.97 | Total: -1.00\n",505 "✅ Successfully loaded 100 emails from dataset.json\n"506 ]507 },508 {509 "output_type": "stream",510 "name": "stderr",511 "text": [512 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"513 ]514 },515 {516 "output_type": "stream",517 "name": "stdout",518 "text": [519 "Step 1: auto_reply -> Reward: -0.67 | Total: -0.67\n"520 ]521 },522 {523 "output_type": "stream",524 "name": "stderr",525 "text": [526 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"527 ]528 },529 {530 "output_type": "stream",531 "name": "stdout",532 "text": [533 "Step 2: auto_reply -> Reward: +1.14 | Total: +0.47\n"534 ]535 },536 {537 "output_type": "stream",538 "name": "stderr",539 "text": [540 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"541 ]542 },543 {544 "output_type": "stream",545 "name": "stdout",546 "text": [547 "Step 3: route_to_human -> Reward: +0.83 | Total: +1.30\n"548 ]549 },550 {551 "output_type": "stream",552 "name": "stderr",553 "text": [554 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"555 ]556 },557 {558 "output_type": "stream",559 "name": "stdout",560 "text": [561 "Step 4: ask_for_clarification -> Reward: -0.37 | Total: +0.93\n"562 ]563 },564 {565 "output_type": "stream",566 "name": "stderr",567 "text": [568 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"569 ]570 },571 {572 "output_type": "stream",573 "name": "stdout",574 "text": [575 "Step 5: auto_reply -> Reward: +0.93 | Total: +1.86\n"576 ]577 },578 {579 "output_type": "stream",580 "name": "stderr",581 "text": [582 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"583 ]584 },585 {586 "output_type": "stream",587 "name": "stdout",588 "text": [589 "Step 6: auto_reply -> Reward: -0.67 | Total: +1.19\n"590 ]591 },592 {593 "output_type": "stream",594 "name": "stderr",595 "text": [596 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"597 ]598 },599 {600 "output_type": "stream",601 "name": "stdout",602 "text": [603 "Step 7: auto_reply -> Reward: +0.94 | Total: +2.13\n"604 ]605 },606 {607 "output_type": "stream",608 "name": "stderr",609 "text": [610 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"611 ]612 },613 {614 "output_type": "stream",615 "name": "stdout",616 "text": [617 "Step 8: route_to_human -> Reward: -0.98 | Total: +1.15\n"618 ]619 },620 {621 "output_type": "stream",622 "name": "stderr",623 "text": [624 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"625 ]626 },627 {628 "output_type": "stream",629 "name": "stdout",630 "text": [631 "Step 9: auto_reply -> Reward: +0.93 | Total: +2.08\n"632 ]633 },634 {635 "output_type": "stream",636 "name": "stderr",637 "text": [638 "\n",639 "Collecting rollouts: 7%|▋ | 2/30 [01:00<14:24, 30.87s/it]\u001b[ABoth `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"640 ]641 },642 {643 "output_type": "stream",644 "name": "stdout",645 "text": [646 "Step 10: route_to_human -> Reward: +0.83 | Total: +2.91\n",647 "✅ Successfully loaded 100 emails from dataset.json\n"648 ]649 },650 {651 "output_type": "stream",652 "name": "stderr",653 "text": [654 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"655 ]656 },657 {658 "output_type": "stream",659 "name": "stdout",660 "text": [661 "Step 1: auto_reply -> Reward: +0.93 | Total: +0.93\n"662 ]663 },664 {665 "output_type": "stream",666 "name": "stderr",667 "text": [668 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"669 ]670 },671 {672 "output_type": "stream",673 "name": "stdout",674 "text": [675 "Step 2: ask_for_clarification -> Reward: -0.37 | Total: +0.56\n"676 ]677 },678 {679 "output_type": "stream",680 "name": "stderr",681 "text": [682 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"683 ]684 },685 {686 "output_type": "stream",687 "name": "stdout",688 "text": [689 "Step 3: route_to_human -> Reward: +0.83 | Total: +1.39\n"690 ]691 },692 {693 "output_type": "stream",694 "name": "stderr",695 "text": [696 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"697 ]698 },699 {700 "output_type": "stream",701 "name": "stdout",702 "text": [703 "Step 4: route_to_human -> Reward: +0.63 | Total: +2.02\n"704 ]705 },706 {707 "output_type": "stream",708 "name": "stderr",709 "text": [710 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"711 ]712 },713 {714 "output_type": "stream",715 "name": "stdout",716 "text": [717 "Step 5: auto_reply -> Reward: -0.67 | Total: +1.35\n"718 ]719 },720 {721 "output_type": "stream",722 "name": "stderr",723 "text": [724 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"725 ]726 },727 {728 "output_type": "stream",729 "name": "stdout",730 "text": [731 "Step 6: route_to_human -> Reward: +0.83 | Total: +2.18\n"732 ]733 },734 {735 "output_type": "stream",736 "name": "stderr",737 "text": [738 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"739 ]740 },741 {742 "output_type": "stream",743 "name": "stdout",744 "text": [745 "Step 7: route_to_human -> Reward: -0.97 | Total: +1.21\n"746 ]747 },748 {749 "output_type": "stream",750 "name": "stderr",751 "text": [752 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"753 ]754 },755 {756 "output_type": "stream",757 "name": "stdout",758 "text": [759 "Step 8: route_to_human -> Reward: +0.83 | Total: +2.04\n"760 ]761 },762 {763 "output_type": "stream",764 "name": "stderr",765 "text": [766 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"767 ]768 },769 {770 "output_type": "stream",771 "name": "stdout",772 "text": [773 "Step 9: auto_reply -> Reward: -0.67 | Total: +1.37\n"774 ]775 },776 {777 "output_type": "stream",778 "name": "stderr",779 "text": [780 "\n",781 "Collecting rollouts: 10%|█ | 3/30 [01:27<13:04, 29.07s/it]\u001b[ABoth `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"782 ]783 },784 {785 "output_type": "stream",786 "name": "stdout",787 "text": [788 "Step 10: route_to_human -> Reward: +0.83 | Total: +2.20\n",789 "✅ Successfully loaded 100 emails from dataset.json\n"790 ]791 },792 {793 "output_type": "stream",794 "name": "stderr",795 "text": [796 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"797 ]798 },799 {800 "output_type": "stream",801 "name": "stdout",802 "text": [803 "Step 1: route_to_human -> Reward: +0.83 | Total: +0.83\n"804 ]805 },806 {807 "output_type": "stream",808 "name": "stderr",809 "text": [810 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"811 ]812 },813 {814 "output_type": "stream",815 "name": "stdout",816 "text": [817 "Step 2: ask_for_clarification -> Reward: -0.37 | Total: +0.46\n"818 ]819 },820 {821 "output_type": "stream",822 "name": "stderr",823 "text": [824 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"825 ]826 },827 {828 "output_type": "stream",829 "name": "stdout",830 "text": [831 "Step 3: auto_reply -> Reward: +0.94 | Total: +1.40\n"832 ]833 },834 {835 "output_type": "stream",836 "name": "stderr",837 "text": [838 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"839 ]840 },841 {842 "output_type": "stream",843 "name": "stdout",844 "text": [845 "Step 4: route_to_human -> Reward: +0.83 | Total: +2.23\n"846 ]847 },848 {849 "output_type": "stream",850 "name": "stderr",851 "text": [852 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"853 ]854 },855 {856 "output_type": "stream",857 "name": "stdout",858 "text": [859 "Step 5: ask_for_clarification -> Reward: -0.37 | Total: +1.86\n"860 ]861 },862 {863 "output_type": "stream",864 "name": "stderr",865 "text": [866 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"867 ]868 },869 {870 "output_type": "stream",871 "name": "stdout",872 "text": [873 "Step 6: route_to_human -> Reward: +0.83 | Total: +2.69\n"874 ]875 },876 {877 "output_type": "stream",878 "name": "stderr",879 "text": [880 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"881 ]882 },883 {884 "output_type": "stream",885 "name": "stdout",886 "text": [887 "Step 7: route_to_human -> Reward: -0.97 | Total: +1.72\n"888 ]889 },890 {891 "output_type": "stream",892 "name": "stderr",893 "text": [894 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"895 ]896 },897 {898 "output_type": "stream",899 "name": "stdout",900 "text": [901 "Step 8: ask_for_clarification -> Reward: -0.37 | Total: +1.35\n"902 ]903 },904 {905 "output_type": "stream",906 "name": "stderr",907 "text": [908 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"909 ]910 },911 {912 "output_type": "stream",913 "name": "stdout",914 "text": [915 "Step 9: ask_for_clarification -> Reward: -0.37 | Total: +0.98\n"916 ]917 },918 {919 "output_type": "stream",920 "name": "stderr",921 "text": [922 "\n",923 "Collecting rollouts: 13%|█▎ | 4/30 [01:47<10:57, 25.27s/it]\u001b[ABoth `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"924 ]925 },926 {927 "output_type": "stream",928 "name": "stdout",929 "text": [930 "Step 10: route_to_human -> Reward: -0.98 | Total: +0.00\n",931 "✅ Successfully loaded 100 emails from dataset.json\n"932 ]933 },934 {935 "output_type": "stream",936 "name": "stderr",937 "text": [938 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"939 ]940 },941 {942 "output_type": "stream",943 "name": "stdout",944 "text": [945 "Step 1: route_to_human -> Reward: +0.83 | Total: +0.83\n"946 ]947 },948 {949 "output_type": "stream",950 "name": "stderr",951 "text": [952 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"953 ]954 },955 {956 "output_type": "stream",957 "name": "stdout",958 "text": [959 "Step 2: ask_for_clarification -> Reward: -0.37 | Total: +0.46\n"960 ]961 },962 {963 "output_type": "stream",964 "name": "stderr",965 "text": [966 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"967 ]968 },969 {970 "output_type": "stream",971 "name": "stdout",972 "text": [973 "Step 3: route_to_human -> Reward: +0.83 | Total: +1.29\n"974 ]975 },976 {977 "output_type": "stream",978 "name": "stderr",979 "text": [980 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"981 ]982 },983 {984 "output_type": "stream",985 "name": "stdout",986 "text": [987 "Step 4: route_to_human -> Reward: +0.83 | Total: +2.12\n"988 ]989 },990 {991 "output_type": "stream",992 "name": "stderr",993 "text": [994 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"995 ]996 },997 {998 "output_type": "stream",999 "name": "stdout",1000 "text": [1001 "Step 5: ask_for_clarification -> Reward: -0.37 | Total: +1.75\n"1002 ]1003 },1004 {1005 "output_type": "stream",1006 "name": "stderr",1007 "text": [1008 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1009 ]1010 },1011 {1012 "output_type": "stream",1013 "name": "stdout",1014 "text": [1015 "Step 6: auto_reply -> Reward: +0.93 | Total: +2.68\n"1016 ]1017 },1018 {1019 "output_type": "stream",1020 "name": "stderr",1021 "text": [1022 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1023 ]1024 },1025 {1026 "output_type": "stream",1027 "name": "stdout",1028 "text": [1029 "Step 7: route_to_human -> Reward: +0.83 | Total: +3.51\n"1030 ]1031 },1032 {1033 "output_type": "stream",1034 "name": "stderr",1035 "text": [1036 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1037 ]1038 },1039 {1040 "output_type": "stream",1041 "name": "stdout",1042 "text": [1043 "Step 8: route_to_human -> Reward: +0.83 | Total: +4.34\n"1044 ]1045 },1046 {1047 "output_type": "stream",1048 "name": "stderr",1049 "text": [1050 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1051 ]1052 },1053 {1054 "output_type": "stream",1055 "name": "stdout",1056 "text": [1057 "Step 9: route_to_human -> Reward: +0.83 | Total: +5.17\n"1058 ]1059 },1060 {1061 "output_type": "stream",1062 "name": "stderr",1063 "text": [1064 "\n",1065 "Collecting rollouts: 17%|█▋ | 5/30 [02:10<10:12, 24.49s/it]\u001b[ABoth `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1066 ]1067 },1068 {1069 "output_type": "stream",1070 "name": "stdout",1071 "text": [1072 "Step 10: auto_reply -> Reward: -0.67 | Total: +4.50\n",1073 "✅ Successfully loaded 100 emails from dataset.json\n"1074 ]1075 },1076 {1077 "output_type": "stream",1078 "name": "stderr",1079 "text": [1080 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1081 ]1082 },1083 {1084 "output_type": "stream",1085 "name": "stdout",1086 "text": [1087 "Step 1: route_to_human -> Reward: +0.83 | Total: +0.83\n"1088 ]1089 },1090 {1091 "output_type": "stream",1092 "name": "stderr",1093 "text": [1094 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1095 ]1096 },1097 {1098 "output_type": "stream",1099 "name": "stdout",1100 "text": [1101 "Step 2: route_to_human -> Reward: +0.63 | Total: +1.46\n"1102 ]1103 },1104 {1105 "output_type": "stream",1106 "name": "stderr",1107 "text": [1108 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1109 ]1110 },1111 {1112 "output_type": "stream",1113 "name": "stdout",1114 "text": [1115 "Step 3: ask_for_clarification -> Reward: -0.37 | Total: +1.09\n"1116 ]1117 },1118 {1119 "output_type": "stream",1120 "name": "stderr",1121 "text": [1122 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1123 ]1124 },1125 {1126 "output_type": "stream",1127 "name": "stdout",1128 "text": [1129 "Step 4: ask_for_clarification -> Reward: -0.37 | Total: +0.72\n"1130 ]1131 },1132 {1133 "output_type": "stream",1134 "name": "stderr",1135 "text": [1136 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1137 ]1138 },1139 {1140 "output_type": "stream",1141 "name": "stdout",1142 "text": [1143 "Step 5: ask_for_clarification -> Reward: -0.37 | Total: +0.35\n"1144 ]1145 },1146 {1147 "output_type": "stream",1148 "name": "stderr",1149 "text": [1150 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1151 ]1152 },1153 {1154 "output_type": "stream",1155 "name": "stdout",1156 "text": [1157 "Step 6: auto_reply -> Reward: +0.94 | Total: +1.29\n"1158 ]1159 },1160 {1161 "output_type": "stream",1162 "name": "stderr",1163 "text": [1164 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1165 ]1166 },1167 {1168 "output_type": "stream",1169 "name": "stdout",1170 "text": [1171 "Step 7: auto_reply -> Reward: -0.67 | Total: +0.62\n"1172 ]1173 },1174 {1175 "output_type": "stream",1176 "name": "stderr",1177 "text": [1178 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1179 ]1180 },1181 {1182 "output_type": "stream",1183 "name": "stdout",1184 "text": [1185 "Step 8: route_to_human -> Reward: -0.98 | Total: -0.36\n"1186 ]1187 },1188 {1189 "output_type": "stream",1190 "name": "stderr",1191 "text": [1192 "Both `max_new_tokens` (=300) and `max_length`(=131072) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"1193 ]1194 },1195 {1196 "output_type": "stream",1197 "name": "stdout",1198 "text": [1199 "Step 9: route_to_human -> Reward: -0.97 | Total: -1.33\n"1200 ]