diff --git a/notebooks/en/grpo_vllm_online_training.ipynb b/notebooks/en/grpo_vllm_online_training.ipynb index a60a5822..2dd83ebe 100644 --- a/notebooks/en/grpo_vllm_online_training.ipynb +++ b/notebooks/en/grpo_vllm_online_training.ipynb @@ -52,9 +52,9 @@ }, "outputs": [], "source": [ - "!pip install -U -q trl[vllm] peft math_verify trackio\n", + "!pip install -U -q trl[vllm] peft math_verify trackio transformers\n", "\n", - "# Tested with trl==0.23.0, peft==0.17.1, math_verify==0.8.0, vllm==0.10.2, trackio==0.5.0" + "# Tested with trl==0.23.1, peft==0.17.1, math_verify==0.8.0, vllm==0.11.0, trackio==0.5.2 transformers==4.57.0" ] }, { @@ -96,71 +96,71 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "metadata": { "id": "QFe_A78aIwK8", "colab": { "base_uri": "https://localhost:8080/", "height": 266, "referenced_widgets": [ - "5d91dfed37914f2cb2dcf073ca4e8f67", - "c7da5cf6020a48ecb17b43e7270ced53", - "dbcf83ff32dc4a50870eb24d2460a446", - "23ab7880e51b45e0afe2051949e55f27", - "4fbe0ddf1fe14a5bad5c59a585e4da82", - "261bc4e6de3644be81f23e824009b913", - "51464b07e9264cccb2ac01f93b785f6a", - "e26dd71a4da641c78d3df1f9a975663f", - "d6f6e5ac000a4c2abfcc33e2fedae696", - "46e8a924553c4a4b9dcb55086f74b82e", - "9146eebb3df84976b5e3b58b69b79549", - "6e453c865e5e448b91ceed2f3f07f8d7", - "3831e4fba6b146baa2c06cc48b4ee96b", - "95f49d13fe9b40abbc5889db349711a0", - "b69ec5bc43de4c2d9e5b87fea1f1dda4", - "6e7ca2a24ce6422aa66c55d4e04ef902", - "ddbfad298c35447d83ed1ef023dca1d8", - "82c0108fcebf4eac8c1fddde533baf90", - "4c9796ebeb1b4d1ebfca705c3a5665b3", - "fe10dc9dce584f87b73aa3d5224c6a14", - "a21e9ed6efd24a468da249d1ac0a6db2", - "324790ad29ba475c8e56f6587c7872cd", - "98227a25e0ac4c7595367e46a857a7bd", - "cebdd6e6eaaf4e03a2c949dddc587543", - "2060f989b2b144c6b389d4bf64a2b639", - "7206475129324f29b96e2267f0feb906", - "b6c285a088e5495e8f14bb5bb23cab81", - "5ca762e8499e427c94554977ab0599b7", - "ff6577b9fd024b37bb6e8edd6ff9a3cf", - "68bc43a5757e44dbb8cb5437fd45eecf", - "7181f90983da47cca5669c5ecb136377", - "56b428f1af6049b7971f4ae7b13efee3", - "7ee1b7458a96400190472779f0074a7d", - "5bd4cd3466b94628bfcbbd3f2723b694", - "58174211c1854d4983824de0aea25e6a", - "7101bf7ba3474416b51375adaffbdce3", - "d280a3eb1f01430c82a17dca8034c657", - "7fc98632a7664fae9fc2c2b9ba431903", - "3dbcbb90f68f4436964dfde5fba974dc", - "0a7cc81000a643c8b4842777529be824", - "c5d985cb74b2473193cfc7d7b15d7c2b", - "526219c7bb8540ec9a90d8f3640cf6b0", - "ab6721bacbbe4a398c54e0ed3b3e5b06", - "fdfbd1f1f87443b5b2981d3adaf1ddb7", - "09d4238537aa404899a6d53b2f8ba81a", - "2112c72ad2874f998690d5d8ffb4e26b", - "a50d398e9b9b4f1f96dc76f79833f298", - "d33b608e4ad94887acaf9ceed694f9d3", - "1e49b5b81fdd4f06bd122d5fa26b18d3", - "113ba51bf3ef487bad5e95c3f4b7382c", - "be32345635e440faa08d5ea44c5b4b15", - "1a7247a7746f4421aa3deddad26bb6ed", - "852bb6974d9e42538171a5a4d52838b3", - "2ec5331a7f50461cb328c1bad4deb816", - "043eb371e5394efba9e3c7ad73b3b661" - ] - }, - "outputId": "fa254c2a-ae46-4e6e-c5e9-5beb8ba45041" + "ab38bce8146748048694f93a0fcc6492", + "9263335abec04d3990d54f3606d349f1", + "dfe0e4a6bd4f43a08491a1b2e46a1348", + "431f6cf8a2d346ae9b0fb009dd43671b", + "ade213c324de4e2fbde910d7f1f0e8a9", + "b5787477b99d4c57a1f0adb7a1d44f48", + "95d0992e9de744b18479f85ddbc1ec16", + "fb93edfdd19c4fd4a6b5912cf3100f74", + "e3ea88d6b31c4d0881fd54562f75979b", + "25694b4245b6484689a65f3c20d22747", + "24959d905cac49729436a5666cd62b89", + "8891af773f724a13b198e53f5fb60ca7", + "1090a54b4ba749699b056106c73c9432", + "2f0a42072704451f8f0e09732d3fb62f", + "9c62d75e9f834e80a25302d3a5dfe2fc", + "92514545532d4f1889addd0e9b886bb7", + "d8eae67257c84376b0e1f629a501b85c", + "3758054cbfc2486494da2a4db3a80a5c", + "66872b37633644e8805b1cb6eef7f53f", + "2a8c130105874eff96e34df9d2384579", + "206ef50483b34cfdb0f716dd7765c501", + "fdb9d52fb01b4141a69d5cf77e001246", + "a9866eb4ea4b4823a1b7aa18f411460c", + "8baed42c565641deb7258c0fef01c8bd", + "404a31feeda24d339fe65681ecc3a7cf", + "539747bfa09f48879e17193879ff59ff", + "658c581b2bd247ec82e0a491c3aa3279", + "932fd59c451f491095a66e4b7d3be281", + "4cd0d4478e254d33a1f5e5026c2a735f", + "19d5ce21a1b44e7299f1084fb131b580", + "19d6ddaf30c94ce8bc29fc8e31cb2c15", + "2c9356298e02473d9492218521100733", + "967d1c71c23d4eee947f62513be85db7", + "584b32f0e4d44e1ebb5c94db4969f248", + "b67d84f05fd74f63908d5abff2bf72cd", + "5c510e32d1354c3f94211debcd1d4a52", + "c8399c5f150149a0a3f34905654a4933", + "c39a9e76b561458aac9e420c2d550f06", + "10a7a92cbce24aad8452205421057175", + "b8d9856157f14f16b081e155cb43ef62", + "65afe0a143a04defaa32675f91f8973e", + "2bc3c1014e144abab21a24299ec8c6c9", + "042e27a9ca1d4586bbe999fca9191359", + "81ef353b7e2d488bac4c0a04d2356269", + "c757c5e9181544d6968b45c3b2764ece", + "e8725111b4894ed9af669d4cc4832dd9", + "72e555b84d35422d8e0b182a0a3fa47e", + "35554cfb48b641a1bed1620d2731cf92", + "dc49abcb90e74247942c53da97bcbce8", + "4b11f69470e742af891b2f8be85fa37b", + "6dccaf0a5da140d8bf6ec913699e0777", + "326191eaa6064f73985425b7d5b6f2b7", + "2c457e2fc14e4c47ac29de6862e9483c", + "1e2c626df8c346988a35c92cab80c432", + "59d562ea9e824554b9f302f04e687f70" + ] + }, + "outputId": "847f404c-b5e5-4b3f-b5a1-2680b4930d37" }, "outputs": [ { @@ -183,7 +183,7 @@ "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, - "model_id": "5d91dfed37914f2cb2dcf073ca4e8f67" + "model_id": "ab38bce8146748048694f93a0fcc6492" } }, "metadata": {} @@ -197,7 +197,7 @@ "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, - "model_id": "6e453c865e5e448b91ceed2f3f07f8d7" + "model_id": "8891af773f724a13b198e53f5fb60ca7" } }, "metadata": {} @@ -211,7 +211,7 @@ "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, - "model_id": "98227a25e0ac4c7595367e46a857a7bd" + "model_id": "a9866eb4ea4b4823a1b7aa18f411460c" } }, "metadata": {} @@ -225,7 +225,7 @@ "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, - "model_id": "5bd4cd3466b94628bfcbbd3f2723b694" + "model_id": "584b32f0e4d44e1ebb5c94db4969f248" } }, "metadata": {} @@ -239,7 +239,7 @@ "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, - "model_id": "09d4238537aa404899a6d53b2f8ba81a" + "model_id": "c757c5e9181544d6968b45c3b2764ece" } }, "metadata": {} @@ -263,13 +263,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "o2UKZj15jGwv", - "outputId": "5789f26c-2529-4a15-d299-f96a74956e63" + "outputId": "059002b9-c29e-4f7e-9b31-e2c1923e9898" }, "outputs": [ { @@ -306,9 +306,9 @@ "base_uri": "https://localhost:8080/" }, "id": "5BglCVLLzY0S", - "outputId": "ae136405-ccf9-4199-c0bb-bba9609837b0" + "outputId": "2d0fbaef-fc3c-414f-ae86-7bb1cb6cf49e" }, - "execution_count": null, + "execution_count": 13, "outputs": [ { "output_type": "stream", @@ -369,33 +369,33 @@ "base_uri": "https://localhost:8080/", "height": 81, "referenced_widgets": [ - "214f0c4f680141d7a37f5ca71c2af48f", - "8c58eb689ee34851b5f57117994b39fc", - "45e8592006fe4b6a8deacde57816557a", - "fd063592e19840afa1e40cf8aef9be6d", - "8b210e791c0e480eb3232914b4b21f7d", - "63368a5047da44e6842fcdf63ff34e08", - "c06c51b4ad40406095fcc7bb6fd3b91c", - "2e5e7ca8869541c5a23c3bcce0311b70", - "7d09436859be4542aee51b7948ce772b", - "25b64fb47ee34076816cae2e5c09b509", - "c2f77bb1300147328c325a776d8be38a", - "f257f6609ee5431e91e24e762949bc5b", - "bf664d457c1c45c59514b2b46a5d31b1", - "cca36113523844f19f611063e36df649", - "a63985f3f7224765a8c7f0a5442b6a1a", - "1dca0157fdc54ccda2a2a3d901b779e3", - "6ca597da1d8545108e25cc500f9d95a9", - "57b5c8748c2240dbb362574871799984", - "f1fb075e51914ea39a7ece988f3917a1", - "515d2d5ac9d84df69c165d941ff3fb48", - "1b0b5f3e75f94976b7a89895b4904011", - "d907dd928c2143478e08584359a338bb" - ] - }, - "outputId": "b6edcaa7-21c2-4080-c3c3-f298e29ce5de" + "781196eed312434b9d79a0e0703996d2", + "61de41b10dc14e7fb36db1e79dc056ce", + "76beed2455824399ba0240d02494a068", + "211482f7033549259be43db4a92dd9a4", + "cb2fc63dcb6d4e359bc9622a1a11f56e", + "a9e555ca230346dfb5d5b50e20250726", + "4301589a5694419fa0513ab039744893", + "e04036b0ff65492faf914e1d37cdda53", + "e8003c9bc19a4b88ac1f5037b06a88f3", + "a33a5017ca184293bd0d3c0f244b2fb8", + "28ab3ee8f14c4602bb78eef31c7f039b", + "d2a7a21a5bb1438b8b6539f0803bb7e6", + "54e81fa0de944329aff464f331b00f57", + "22365d5abca149958dd65cb6bbc8ee7f", + "d3f6a26af55047fca2dcd679f4f57553", + "1ede7f514ee84ea398f5d41d49eba214", + "bd795aa08e3b47a1bc2558b0dbe65aa2", + "6ef467e9952841a89c9fb0a8fd5f45c6", + "14fab363ef464f0bb7e8978d473a82bb", + "4d2f9a16c7f54551a1c89b5bb90f8c2e", + "0ad37648e44d49d9b6a009ef34247811", + "9ad48acf088c406cb534d2abdf42ee8e" + ] + }, + "outputId": "7cbc193c-fca6-48b6-d0be-7ab526376ce4" }, - "execution_count": null, + "execution_count": 14, "outputs": [ { "output_type": "display_data", @@ -406,7 +406,7 @@ "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, - "model_id": "214f0c4f680141d7a37f5ca71c2af48f" + "model_id": "781196eed312434b9d79a0e0703996d2" } }, "metadata": {} @@ -420,7 +420,7 @@ "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, - "model_id": "f257f6609ee5431e91e24e762949bc5b" + "model_id": "d2a7a21a5bb1438b8b6539f0803bb7e6" } }, "metadata": {} @@ -446,9 +446,9 @@ "base_uri": "https://localhost:8080/" }, "id": "s48vCAy3e1x0", - "outputId": "6d229399-8bfd-4f4f-c199-a8c5cdc1309e" + "outputId": "d5679ce2-6cd6-4178-89fd-9a9a17da3a72" }, - "execution_count": null, + "execution_count": 15, "outputs": [ { "output_type": "stream", @@ -479,9 +479,9 @@ "base_uri": "https://localhost:8080/" }, "id": "EaY8lUYSHyhA", - "outputId": "c68ccd91-2a7b-4efa-a3f1-b52c3aafa6e8" + "outputId": "fd2b6c99-b629-48ac-a80e-835199eb8e93" }, - "execution_count": null, + "execution_count": 16, "outputs": [ { "output_type": "stream", @@ -543,96 +543,14 @@ " model_id,\n", " dtype=\"auto\",\n", " device_map=\"auto\",\n", - ")" + ")\n", + "tokenizer = AutoTokenizer.from_pretrained(model_id)" ], "metadata": { - "id": "qv02eazzEUeJ", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 113, - "referenced_widgets": [ - "90d7546a359446979dc099eda12e2daf", - "0caf5d4fd2544b9096d103e530b547ea", - "12e4f6d37b8a4bdaa8f57d3dca4f00da", - "9aa07ea1ce764493acf4c89af08857f5", - "a709c8b483b344ffb293dfdd3cf1d314", - "ec5802db1887471c953c0b8f0bce0434", - "6168aae951c445c793f99d5e699ed558", - "452884ff62a54d04ac1cb531471a18fa", - "86be624af61e4ae182ec3272adac0e3a", - "fcb1a787aacc44b28d2c69279b01130a", - "e2015f7b376140e8a9e366710db55df8", - "e791e33969424dafb0b022dce21d2abf", - "b291793a1aa54c0b8837c81df0ac0b8e", - "b73f6bfa74a44e81a28767c70c3f2565", - "50fbecea76244671b33c921d7ba9ee22", - "1429d281bc94424aaa0c95928db9d635", - "41ad9d1595d641b4af06362498bf39a7", - "d3a9c397a4244335ada594ee6c9919c6", - "91b2a4d4fa9743b9baa6c23521f4ed17", - "c98e3f4bbed94beb9cc2befcce9fd15d", - "400f76d7eed747bbaff9ec2c4829da2c", - "eeab31123abe44b1bdab8fd67ada5ae5", - "681626e8db874460a9fe5e6692defa3b", - "c28de1b3f9b64580881500f5cbd1e11b", - "064ef8cd267845958af36f94e157f916", - "233d42eabb704a219195cd50bc88673f", - "76ac51b551234954bdae19a8a02eea42", - "1ec65e0a3ea94ef4bfbd29b1d0c71579", - "76a0b1ef868f458bbb8ae38801abe361", - "20b32d7743584b4b83bb84efda8b4107", - "4517fb94752943659174fea5b41cde88", - "48aa6f9cf71b4274b4be95bb128db23a", - "6cf35cab1e9f438999c71035645c60ee" - ] - }, - "outputId": "fd0b2c98-20b0-4208-d83b-92674ab18a6a" + "id": "qv02eazzEUeJ" }, - "execution_count": null, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "config.json: 0%| | 0.00/659 [00:00" ], "text/html": [ - "
" + "
" ] }, "metadata": {} @@ -1192,16 +1103,7 @@ "output_type": "stream", "name": "stdout", "text": [ - "* Created new run: dainty-sunset-0\n", - "INFO 10-03 11:32:29 [block_pool.py:292] Successfully reset prefix cache\n" - ] - }, - { - "output_type": "stream", - "name": "stderr", - "text": [ - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n" + "* Created new run: sergiopaniego-1759912821\n" ] }, { @@ -1215,7 +1117,7 @@ "
\n", " \n", " \n", - " [452/452 1:00:28, Epoch 1/1]\n", + " [452/452 51:46, Epoch 1/1]\n", "
\n", " \n", " \n", @@ -1227,183 +1129,183 @@ " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", "
100.0809000.090200
200.1285000.124600
300.2098000.168800
400.2815000.292600
500.3952000.307700
600.2975000.339800
700.2942000.439700
800.2468000.183900
900.2058000.147400
1000.1719000.180900
1100.0988000.093800
1200.1116000.029500
1300.0864000.116800
1400.0551000.102200
150-0.0144000.026500
1600.0899000.004000
1700.0512000.071900
1800.0817000.063800
1900.0978000.022200
2000.0392000.038800
2100.0733000.035200
2200.2203000.073000
2300.0407000.004600
2400.1651000.029600
2500.0263000.045500
2600.0962000.029300
2700.0630000.099400
2800.0242000.066400
2900.0541000.022100
3000.0510000.058400
3100.1249000.064300
3200.047900-0.000200
330-0.000400-0.000500
3400.0312000.003100
3500.0066000.034300
3600.0231000.064800
3700.0147000.096900
3800.0070000.058700
3900.0631000.032100
4000.0207000.076200
4100.0981000.038100
4200.0703000.018900
4300.0024000.011800
4400.072800-0.002600
4500.0131000.032800

" @@ -1411,19 +1313,42 @@ }, "metadata": {} }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "INFO 10-03 11:32:44 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:32:58 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:33:12 [block_pool.py:292] Successfully reset prefix cache\n" - ] - }, { "output_type": "stream", "name": "stderr", "text": [ + "/usr/local/lib/python3.12/dist-packages/math_verify/parser.py:450: SymPyDeprecationWarning: \n", + "\n", + "Using non-Expr arguments in Mul is deprecated (in this case, one of\n", + "the arguments has type 'And').\n", + "\n", + "If you really did intend to use a multiplication or addition operation with\n", + "this object, use the * or + operator instead.\n", + "\n", + "See https://docs.sympy.org/latest/explanation/active-deprecations.html#non-expr-args-deprecated\n", + "for details.\n", + "\n", + "This has been deprecated since SymPy version 1.7. It\n", + "will be removed in a future version of SymPy.\n", + "\n", + " return sympy.Mul(number, sympy.Rational(1, 100), evaluate=False)\n", + "/usr/local/lib/python3.12/dist-packages/sympy/simplify/radsimp.py:1131: SymPyDeprecationWarning: \n", + "\n", + "Using non-Expr arguments in Mul is deprecated (in this case, one of\n", + "the arguments has type 'And').\n", + "\n", + "If you really did intend to use a multiplication or addition operation with\n", + "this object, use the * or + operator instead.\n", + "\n", + "See https://docs.sympy.org/latest/explanation/active-deprecations.html#non-expr-args-deprecated\n", + "for details.\n", + "\n", + "This has been deprecated since SymPy version 1.7. It\n", + "will be removed in a future version of SymPy.\n", + "\n", + " return Mul(*numer, evaluate=not exact), Mul(*denom, evaluate=not exact)\n", + "WARNING:math_verify.grader:Timeout during comparison\n", + "WARNING:math_verify.grader:Timeout during comparison\n", "WARNING:math_verify.grader:Timeout during comparison\n" ] }, @@ -1431,4531 +1356,882 @@ "output_type": "stream", "name": "stdout", "text": [ - "INFO 10-03 11:33:33 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:33:47 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:34:00 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:34:13 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:34:41 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:34:54 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:35:08 [block_pool.py:292] Successfully reset prefix cache\n" + "* Run finished. Uploading logs to Trackio (please wait...)\n" ] }, { - "output_type": "stream", - "name": "stderr", - "text": [ - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n" - ] - }, + "output_type": "execute_result", + "data": { + "text/plain": [ + "TrainOutput(global_step=452, training_loss=0.08485318411067458, metrics={'train_runtime': 3130.2902, 'train_samples_per_second': 2.314, 'train_steps_per_second': 0.144, 'total_flos': 0.0, 'train_loss': 0.08485318411067458})" + ] + }, + "metadata": {}, + "execution_count": 25 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "Let's save the results 💾" + ], + "metadata": { + "id": "z7_y1x7E1JY9" + } + }, + { + "cell_type": "code", + "source": [ + "trainer.save_model(training_args.output_dir)\n", + "trainer.push_to_hub(dataset_name=dataset_id)" + ], + "metadata": { + "id": "Cazf4AB2nbRT", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 426, + "referenced_widgets": [ + "4a4905fc39064e74a7dd3c4d88dd0da7", + "9cbd611b7f4a4fdfa19bb9bf93c90257", + "b71780eaac064cf6b69ea2d319229a7b", + "b81291f7ee604cacaa5adcd6203f329c", + "780a254131554e09b9d3a9a96119a63a", + "33b847be661b44db921fff01aadb473f", + "966153912c914a57903387926b983b4d", + "6aed13f0ed3e4ff4a53f8e4795b9d148", + "3293c29f428d4de9867021ab0119c7be", + "b76b566ccd1741a1817db0346c58a6e6", + "89e84faa23ec4b348b52459154672479", + "61280e79049443d2b9b44718c7d3734e", + "63a3a983dc8d49469c748dfc5386462b", + "da558dc6cdcb402bb3a9b3caa8a62e7e", + "f769c624319344ad8550824a54253933", + "815cba23e9c24ab4a9db8105d6c3424d", + "9e713c6fd6dd4465ab351b3421e60c06", + "32d730d1a8ee4ff5ac0783f341134e08", + "fb86e80670d24b4da7927cbc870db739", + "db56169082574594bcfd40adcdfa624b", + "f1794020f4dd49b7969a283746fa18aa", + "d3fec749dbfd477894a01b04a7ee3b11", + "7eb45608f0e14f19bcf77dd7f2671068", + "d575411df04e4f7b8624c8e6f11b6b18", + "40662e0043814cb29e98a50758d631f3", + "82d75aeb4a1c4b3d805a711f4e4af615", + "2724fb37c20a4d3b93bb9f12c63657cc", + "085225f0a24d46a191a3d6f7c01ac5bc", + "464236cc3c5a4428b15df1909b11fc5c", + "08d4c4ce64df46689e88a61c1cf3ec8d", + "4c3a040ad61d4de2843dc203628b9576", + "c3c75015bc854f6f8806f4ce8bc4d2eb", + "dba44ee614e145db925e08351868a058", + "cbf1da1278b4481c9fe7e8bb3e4ae240", + "249c1285734a45c8a107b106add81084", + "e281a02dc250489998385d58632d5b1d", + "9bdd8c3205d2400fb6f4c5e21df4e4d1", + "d008369537f54fa9994a09969bfc7a8e", + "29252b97ac0640308e4210a8d140dc10", + "8f0bcc39527142de94cf2538b1b8484f", + "05767d5e2f4941e8ae0254f173e63bc4", + "67ab35173a674254b5a3af041c3de705", + "261eb91f9a054e7d8743c21bb60d5c83", + "3e911c4bbe61404b96d7e4e839c34afe", + "3b316f8bc0c14eb5b56bdb216ca557af", + "25c81bf175fe4233a9741f112fab5e4e", + "47d2f9e33b9147a6acc218d00141d6a3", + "6ab9dbe545fc4eca98736951bded7ab7", + "174b81a6864c4e5084e3f7c0d4387285", + "78cfb0eed7154ac8b3af8824f42db4c1", + "82ad899a03c8423fb58a4170760585e5", + "e43a50b7db9149ae88e20e7f3d03bd9c", + "fa447aeca8a94f6894fea23a8fb6ff0e", + "5ee1f8c92f324ce9bf92855ba22a9013", + "d23ce2884e484c3b81eedb86527a1006", + "13b47839181a4af18bc633ed343e3f27", + "971e8aa8c1524c7ea802b067fc92baed", + "78ad01990aa046879ab5788a53b0bb98", + "0cab2756be0d4c1babf632b7172f49d8", + "2254389c32714a84a4bdb1ea693c779b", + "a867d54613e6418990ef8218e3f98e52", + "f24d5808d2dd48909ad11226e607df2b", + "0108fc90142143649f204472accc2c1c", + "ef8a8cee818c49de8c4b550a2ced472c", + "27802c3021924a07b23f3f3f4fb80631", + "e9147b82df4c4c9c804609e1093f416a", + "210f1f1b481f4d73aeaeefda52ab2765", + "d3a6cd8cab6a4f62a54fbab6bc2f8fdb", + "035ab76a836b47f3a3b4dd4747b93cd7", + "365064fd3840402eae1d9eae1d0b2675", + "a72c092f943942179bd2fe15d1a5405f", + "95407380ef46471d847214dd9a213b1e", + "243479bef39c44048efdba8e815356d3", + "1979581d0f134a848a83bc63bdd49e8e", + "bc2bdaffe13143ec9a01ef174ae67e46", + "ace8f9ae16f64106a682508d4bfbd5eb", + "bdfe3a68362747058a657611173ca684", + "d1c8bf2bdfa643bcb1da5602ca6e955e", + "3a8416f53f794f699b12ee00d83c90c7", + "becd166518ad4719bb992e96f8d61986", + "54c4feb98af24d6cab772c077417c109", + "8f3db48c42be4d51ab98e9dbd21771d6", + "81fa1c82f7e741abab99fb7d9f977487", + "5a6c3b588111498b8acfae4eb94c7403", + "f6e2c182f2cd4996b855b248fdbeed0a", + "ff70330750ed405eb1100496531c843e", + "d429b5f9a8184dbab68149429fb5b4e1", + "30f6cc4c53a640e3abaeafae1e7af8b9", + "177544738fe54eafab020e721b825d4c", + "13a5d9ffe70f4eaea1d2fcbc233a1e11", + "7606d85131d4485eb80c0f3a59e41043", + "f06878fa8117458c8f66dfc1772dbed0", + "309cd48a0a6c4ad08ae7a02716e4c3bd", + "32c24280dba14f3080b73f7ad437d7af", + "fa73ed0177334daf9eb5efc46125e3d1", + "3ac2168b52544123b6279ae4ec159090", + "a1faaeac2589460f8706f6389721399e", + "679a0d1988ee4a51852542dfc422afc4", + "93609c63d9384091a63bac2d185e4ac7", + "4147642626e344bbafc83fad079e1586", + "344d2c5fec1149c692d04f0a73932da7", + "8cd39f08f5b1400ab0400800b61c58db", + "6da0a2cfdd234d46a52e2a66a3072ef1", + "32316dc9369f4c6a8731efbb40b91387", + "a0e3709c53fe440082c8c035c64d5ab9", + "de804e2e009640cca664410a100eb685", + "025a62229f914f199761bb6ddacf6cce", + "ef2ac10d1dfc47798a32c12790d58476", + "ea2a7baa396947f0a6b267ba02bb4258", + "22c28bbd11e546ac8c802caa8661e6f0" + ] + }, + "outputId": "e5878319-e56a-4aee-9fd7-79881d81f071" + }, + "execution_count": 26, + "outputs": [ { - "output_type": "stream", - "name": "stdout", - "text": [ - "INFO 10-03 11:35:22 [block_pool.py:292] Successfully reset prefix cache\n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + "Processing Files (0 / 0) : | | 0.00B / 0.00B " + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "4a4905fc39064e74a7dd3c4d88dd0da7" + } + }, + "metadata": {} }, { - "output_type": "stream", - "name": "stderr", - "text": [ - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + "New Data Upload : | | 0.00B / 0.00B " + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "61280e79049443d2b9b44718c7d3734e" + } + }, + "metadata": {} }, { - "output_type": "stream", - "name": "stdout", - "text": [ - "INFO 10-03 11:35:38 [block_pool.py:292] Successfully reset prefix cache\n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + " ...llm-trl/training_args.bin: 100%|##########| 7.25kB / 7.25kB " + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "7eb45608f0e14f19bcf77dd7f2671068" + } + }, + "metadata": {} }, { - "output_type": "stream", - "name": "stderr", - "text": [ - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + " ...adapter_model.safetensors: 100%|##########| 2.18MB / 2.18MB " + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "cbf1da1278b4481c9fe7e8bb3e4ae240" + } + }, + "metadata": {} }, { - "output_type": "stream", - "name": "stdout", - "text": [ - "INFO 10-03 11:35:50 [block_pool.py:292] Successfully reset prefix cache\n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + " ...O-vllm-trl/tokenizer.json: 100%|##########| 11.4MB / 11.4MB " + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "3b316f8bc0c14eb5b56bdb216ca557af" + } + }, + "metadata": {} }, { "output_type": "stream", "name": "stderr", "text": [ - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n", - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n" + "No files have been modified since last commit. Skipping to prevent empty commit.\n", + "WARNING:huggingface_hub.hf_api:No files have been modified since last commit. Skipping to prevent empty commit.\n" ] }, { - "output_type": "stream", - "name": "stdout", - "text": [ - "INFO 10-03 11:36:04 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:36:17 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:36:30 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:36:43 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:36:57 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:37:09 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:37:23 [block_pool.py:292] Successfully reset prefix cache\n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + "Processing Files (0 / 0) : | | 0.00B / 0.00B " + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "13b47839181a4af18bc633ed343e3f27" + } + }, + "metadata": {} }, { - "output_type": "stream", - "name": "stderr", - "text": [ - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n" - ] - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "INFO 10-03 11:37:35 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:37:48 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:38:01 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:38:14 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:38:28 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:38:42 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:38:56 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:39:09 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:39:22 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:39:35 [block_pool.py:292] Successfully reset prefix cache\n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + "New Data Upload : | | 0.00B / 0.00B " + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "210f1f1b481f4d73aeaeefda52ab2765" + } + }, + "metadata": {} }, { - "output_type": "stream", - "name": "stderr", - "text": [ - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + " ...llm-trl/training_args.bin: 100%|##########| 7.25kB / 7.25kB " + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "d1c8bf2bdfa643bcb1da5602ca6e955e" + } + }, + "metadata": {} }, { - "output_type": "stream", - "name": "stdout", - "text": [ - "INFO 10-03 11:39:48 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:40:03 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:40:15 [block_pool.py:292] Successfully reset prefix cache\n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + " ...adapter_model.safetensors: 100%|##########| 2.18MB / 2.18MB " + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "177544738fe54eafab020e721b825d4c" + } + }, + "metadata": {} }, { - "output_type": "stream", - "name": "stderr", - "text": [ - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + " ...O-vllm-trl/tokenizer.json: 100%|##########| 11.4MB / 11.4MB " + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "4147642626e344bbafc83fad079e1586" + } + }, + "metadata": {} }, { - "output_type": "stream", - "name": "stdout", - "text": [ - "INFO 10-03 11:40:28 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:40:40 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:40:53 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:41:06 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:41:19 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:41:31 [block_pool.py:292] Successfully reset prefix cache\n", - "INFO 10-03 11:41:44 [block_pool.py:292] Successfully reset prefix cache\n" + "output_type": "execute_result", + "data": { + "text/plain": [ + "CommitInfo(commit_url='https://huggingface.co/sergiopaniego/Qwen2-0-5B-GRPO-vllm-trl/commit/618d7e892e9c9b082f6d8725da4e046ef6cd99ee', commit_message='End of training', commit_description='', oid='618d7e892e9c9b082f6d8725da4e046ef6cd99ee', pr_url=None, repo_url=RepoUrl('https://huggingface.co/sergiopaniego/Qwen2-0-5B-GRPO-vllm-trl', endpoint='https://huggingface.co', repo_type='model', repo_id='sergiopaniego/Qwen2-0-5B-GRPO-vllm-trl'), pr_revision=None, pr_num=None)" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + } + }, + "metadata": {}, + "execution_count": 26 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "In the HF Space, you can review the training results tracked by `trackio`. The metrics look very promising!\n" + ], + "metadata": { + "id": "CqUFU6t71iNi" + } + }, + { + "cell_type": "markdown", + "source": [ + "The setup shown here runs on a single GPU, yet we can already see how vLLM boosts training efficiency. With vLLM enabled, training reaches **0.07 it/s**, whereas disabling it (`use_vllm=False`) drops performance to **0.04 it/s**—an immediate **~75% speedup** even in this basic configuration. \n", + "\n", + "And this is just the beginning: we haven't yet explored more optimal setups. For further efficiency gains, you can experiment with training parameters like `max_completion_length`, `num_generations`, or `max_prompt_length`, and scale across multiple GPUs to fully leverage vLLM's high-throughput generation." + ], + "metadata": { + "id": "RCuQUEemG3p4" + } + }, + { + "cell_type": "markdown", + "source": [ + "## 4. Evaluating Different Training Configurations\n", + "\n", + "After training a model efficiently with a single configuration, it's insightful to explore other possible configurations to understand how training performance changes when using vLLM versus not using it. The table below shows various configurations along with their corresponding `it/s` (iterations per second), highlighting the performance impact of vLLM. \n", + "\n", + "These results were obtained using a Colab setup, so you can expect significantly higher gains when scaling to more advanced environments with multiple GPUs or distributed nodes.\n" + ], + "metadata": { + "id": "i0PXwdNgjqsj" + } + }, + { + "cell_type": "markdown", + "source": [ + "| `max_completion_length` | `num_generations` | `max_prompt_length` | `vLLM` | `it/s` |\n", + "|----------------------|----------------|-----------------|------|------|\n", + "| 64 | 4 | 128 | ✅ | 0.14 |\n", + "| 64 | 4 | 128 | ❌ | 0.12 |\n", + "| 64 | 8 | 128 | ✅ | 0.14 |\n", + "| 64 | 8 | 128 | ❌ | 0.12 |\n", + "| 128 | 8 | 128 | ✅ | 0.13 |\n", + "| 128 | 8 | 128 | ❌ | 0.09 |\n", + "| 128 | 16 | 128 | ✅ | 0.13 |\n", + "| 128 | 16 | 128 | ❌ | 0.09 |\n", + "| 256 | 8 | 128 | ✅ | 0.10 |\n", + "| 256 | 8 | 128 | ❌ | 0.06 |\n", + "| 256 | 16 | 128 | ✅ | 0.10 |\n", + "| 256 | 16 | 128 | ❌ | 0.06 |\n", + "| 512 | 8 | 128 | ✅ | 0.07 |\n", + "| 512 | 8 | 128 | ❌ | 0.04 |\n", + "| 512 | 16 | 128 | ✅ | 0.07 |\n", + "| 512 | 16 | 128 | ❌ | 0.04 |\n", + "| 1024 | 16 | 128 | ✅ | 0.04 |\n", + "| 1024 | 16 | 128 | ❌ | 0.02 |\n", + "| 1024 | 32 | 128 | ✅ | 0.04 |\n", + "| 1024 | 32 | 128 | ❌ | 0.02 |" + ], + "metadata": { + "id": "9lcApSmukdjn" + } + }, + { + "cell_type": "markdown", + "source": [ + "From the table above, several observations can be made:\n", + "\n", + "- As `max_completion_length` increases, the `it/s` naturally decreases, which is expected due to the larger computation per iteration. \n", + "- vLLM consistently provides faster training, and the performance gain becomes more significant as we scale to larger `max_completion_length` values. \n", + "- The `num_generations` parameter has minimal impact on `it/s`, showing that parallel generation does not significantly affect throughput in this setup. \n", + "- Although `max_prompt_length` was kept constant in these experiments, similar trends would apply if it were increased: higher values would reduce `it/s` depending on the dataset characteristics, just like `max_completion_length`.\n" + ], + "metadata": { + "id": "xOg20gROuk_z" + } + }, + { + "cell_type": "markdown", + "source": [ + "## 5. Check the Model Performance\n", + "\n", + "We've kept things simple so far, but now let's check if the model has already learned to reason. We'll load the saved model and run an evaluation on a test sample." + ], + "metadata": { + "id": "PGPNqMlfurC9" + } + }, + { + "cell_type": "code", + "source": [ + "from transformers import AutoModelForCausalLM, AutoTokenizer\n", + "\n", + "model_id = \"sergiopaniego/Qwen2-0-5B-GRPO-vllm-trl\"\n", + "trained_model = AutoModelForCausalLM.from_pretrained(\n", + " model_id,\n", + " dtype=\"auto\",\n", + " device_map=\"auto\",\n", + ")\n", + "trained_tokenizer = AutoTokenizer.from_pretrained(model_id)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 305, + "referenced_widgets": [ + "72c97ddd0f914f03bbd737cd3684af83", + "3223c35b9d164a66af6e5adf0eda6ecc", + "8d53711ed464459ba3a4a7fc78e75dc1", + "6a5c29a7044747a59de4a0b8ba29a431", + "ba199cb427a24d9aa06d0773e6a4753c", + "9440c1ba99e84a7d8f8669fbf97a04c0", + "5597c5332a25452e86fbede66c3d6903", + "d83b7c1398e04577baee7e17ec35cef6", + "6e6eabc156d440358daf8ceca52493f7", + "5c63b58b89b54dc7b190909629dd3051", + "e865c3619d7a4f0fb07b09bffb6465fa", + "9f3346e32e47498bab1076cfe404b359", + "e408459fd0d34067a7237320dc740b0c", + "06a7b5966cab4eb982ccd501185df725", + "ead55c8fbe134cb5944eb4fdca7caf2f", + "1ce8780db26c49769f463ddbac112e9f", + "71abcdcdb2654d38927221f765758294", + "c86de2dd069a4b018aadd6ae78da146c", + "8ae6eaaf83af46c1b02b7b397a607ce6", + "e110a1dace1f487f98744b645fd1c616", + "4aa6c5e1586f4a8e9071382c91169d5e", + "f1b95dc5c34b4318917b2bdb374f1081", + "2c159e922dde4e108e4c33a0cd52240c", + "eb5a6815d0294aaa830b3818105c7fba", + "15223c3aa0254747b2f6362bdbab253f", + "be6843c8def24105a9319fce252c8deb", + "0a5883fd63024dad997289714dbb9bb2", + "2137c9e1130245229a6f06ae79640812", + "1e5b8134ea704f7ca97f1e4eb8e4b15f", + "059831fa728b4cbe9680f259b42e2324", + "e41308674e4c4d878b99ab33f618a2e3", + "0173e8a7c9e14c06b1d8e9cf4030ae5d", + "070b4ade060f4593994fbab78434bc0f", + "f5cbe29f0f704fb5bf977bf882557548", + "91cf88d605c044c28125a0f47a22dc15", + "0f6e4953353e46d58ca413c896521e75", + "73b839f10d4c47b28703859913f447be", + "98e7098caa774049bd1e35746993f46c", + "582a666ee19b4fce9f66a5780d244f4c", + "86890b32676441a3a2008b95b234a650", + "13d571b60f9d488b897fa159c1242cce", + "2360cdab2b2a4dc19fbe13505dcd4ad1", + "5972f6f336b548f2b1b26303d9b24669", + "c1a19e066cbc4175b7716bdb255acb9e", + "1203ab14808c4652b8c1f974e09c79c7", + "fc7da4497c904de690e83afbdfb50be0", + "545f39a2b0c541c9bc9a3062e00ed088", + "c641b73c9d63465caddb6dc32f11a3a6", + "14950c86260f4fa99f41be6cb0c65b32", + "557a4337be7441fbb43fc753295af804", + "688c2ce6d721433e8685f4248c2e341f", + "81246711b0a24be6ac6c91a68eb74313", + "8f5434c2e2f6433eba78b601f5789ddd", + "8bf8239650844eda82c9b4c40574b496", + "d164a27bbc944bfb92fc620142fc83c1", + "7c2f6691f3f44b62aca4a481cc4ba75d", + "1f8386e4159f4c78854d491aa455920b", + "7a5aa4e7f4014148badd950998a5fe6f", + "9460d198df13442f8d5e2f97de22c70a", + "1c7395b641b44c9780d03a701b8bd542", + "c65f952fcaa2465f9bc7ecc82e11e055", + "e64b1fcd9a244247aacb57580b1dfef6", + "ffad176a7ff84ca3b205a890fcac3584", + "628a9ac305694d6791c63cd8b01bebe2", + "03776b2b33dc4988a7465217b26aad22", + "5bcbccea676f4fbf9fa65b6bdcb6a89d", + "fb0decf6380d4fd38ad19747363cd436", + "8ac581a5ba694f4592a04535e83e853b", + "f92f06d606b94385bd59f8e220480375", + "8f4a73c122ed4c028af018c4281b9f6c", + "c183147474ce48258ada0b6a356692ab", + "72204822c05c491c9f55fa84ed93ce16", + "503a3db6639644588125b9c666f6f726", + "bbf1d801f7d34cc4964cee6965433c4e", + "e218255545cb441cb243601d71b75de4", + "fd9ac1cc42604153a63475de1d3c0633", + "28db4660c52e4954a2dbd14146fbffde", + "24a27c7c58604c5890317c65bb7e4120", + "5f73e5d097f043ad89ec180770e3aea3", + "4f4aba3191e546ce9685d1c1d3ef7921", + "786d6b794ffd4fc195e9ee27c250542b", + "a2049e1174a2400ab4e3195a43df2d09", + "d51d6b7c071f4ec096a0353aa88142d2", + "77fc4a53278c4ad6930875d5af406fe4", + "aa7bd7525dc942f0917f204d5dc4f18e", + "f41e21c3ea2348fb89dd733bb5a8b72a", + "fa3ed6b006b844d2a62faf3378defa48", + "7d36628a40934a43b9aafed04446a748", + "16874265452a43a09bff4b194b18dc75", + "6a8b1c227c674dbfa7a6a6d158f50ff1", + "d922f3e918c3406987d4a7be6025efa9", + "37684561c72a41e18592d441355ec730", + "3a7a7a995bab43b894c027a0c3c9d34f", + "ad2a06d6be1340bfb16b7fc36c2558b1", + "a6308fa1425e4b5591f012b74848b551", + "7aa324d55a7b41e28f048823a24b888c", + "26d478b283834e0eb98e5a29268ee9d8", + "8e9ae466ab79444c8ee4fc38758312d8", + "66eba3ce1b974632a00b59212a131927" ] }, + "id": "4ohoSJYy9AZf", + "outputId": "ebfa2045-cbc5-4406-b069-31754be68930" + }, + "execution_count": 27, + "outputs": [ { - "output_type": "stream", - "name": "stderr", - "text": [ - "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py:85: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n", - " warnings.warn(\n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + "adapter_config.json: 0%| | 0.00/857 [00:00 reasoning process here $a_1=1997^{1996^{1997}} = 7$ reasoning process here $a_2=7+1997^{1996^{1997}}=8$ reasoning process here $a_3=8+1997^{1996^{1997}}=9$ reasoning process here $a_4=9+1997^{1996^{1997}}=10$ reasoning process here $a_5=10+1997^{1996^{1997}}=11$ reasoning process here $a_6=11+1997^{1996^{1997}}=12$ reasoning process here $a_7=12+1997^{1996^{1997}}=13$ reasoning process here $a_8=13+1997^{1996^{1997}}=14$ reasoning process here $a_9=14+1997^{1996^{1997}}=15$ reasoning process here $a_{10}=15+1997^{1996^{1997}}=16$ \n" - ] + "output_type": "display_data", + "data": { + "text/plain": [ + "tokenizer_config.json: 0%| | 0.00/973 [00:00 and tags, respectively, i.e., reasoning process here answer here ', 'role': 'system'}, {'content': \"In 1988, a person's age was equal to the sum of the digits of their birth year. How old was this person?\", 'role': 'user'}]\n" - ] - } - ] - }, - { - "cell_type": "markdown", - "source": [ - "We'll create a function to interact with the model. In addition to generating the answer, we'll measure the inference duration and count the number of generated tokens. This will give us insights into how much the model has reasoned during generation." - ], - "metadata": { - "id": "Y1S11SHZuviW" - } - }, - { - "cell_type": "code", - "source": [ - "import time\n", - "import torch\n", - "\n", - "def generate_with_reasoning(prompt):\n", - " # Build the prompt from the dataset\n", - " prompt = \" \".join(entry['content'] for entry in prompt)\n", - "\n", - " # Tokenize and move to the same device as the model\n", - " inputs = trained_tokenizer(prompt, return_tensors=\"pt\").to(trained_model.device)\n", - "\n", - " # Generate text without gradients\n", - " start_time = time.time()\n", - " with torch.no_grad():\n", - " output_ids = trained_model.generate(**inputs, max_length=500)\n", - " end_time = time.time()\n", - "\n", - " # Decode and extract model response\n", - " generated_text = trained_tokenizer.decode(output_ids[0], skip_special_tokens=True)\n", - "\n", - " # Get inference time\n", - " inference_duration = end_time - start_time\n", - "\n", - " # Get number of generated tokens\n", - " num_input_tokens = inputs['input_ids'].shape[1]\n", - " num_generated_tokens = output_ids.shape[1] - num_input_tokens\n", - "\n", - " return generated_text, inference_duration, num_generated_tokens" - ], - "metadata": { - "id": "X7ujV-wi9IaQ" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "source": [ - "Let's generate the answer for that test sample!" - ], - "metadata": { - "id": "p6Oav0X2uywO" - } - }, - { - "cell_type": "code", - "source": [ - "prompt = test_dataset['prompt'][0]\n", - "generated_text, inference_duration, num_generated_tokens = generate_with_reasoning(prompt)\n", - "print(generated_text)" - ], - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "mP1QgN5o9JmS", - "outputId": "802652f3-fca2-4e4a-8afb-6ca3e0119909" - }, - "execution_count": null, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "A conversation between User and Assistant. The user asks a question, and the Assistant solves it. The assistant first thinks about the reasoning process in the mind and then provides the user with the answer. The reasoning process and answer are enclosed within and tags, respectively, i.e., reasoning process here answer here In 1988, a person's age was equal to the sum of the digits of their birth year. How old was this person?< think > Reasoning process: Let's assume that the person's birth year is x. Then the age would be y = x + (x/10). We know that the age is equal to the sum of the digits of the birth year, so we can write y = 10y. Solving for y, we get y = 10x - 10, or y = x/3. Since the age must be an integer, we need to find the smallest integer value for x such that x/3 is greater than or equal to 1988. So, we have x = 1988 * 3 = 5964. Substituting this into our equation for y, we get y = 5964/3 = 1928. Therefore, this person's age was 1928 years old. < think > answer 1928 \n" - ] - } - ] - }, - { - "cell_type": "markdown", - "source": [ - "The model already demonstrates the ability to generate the correct `` and `` tags, even though the solution itself is incorrect.\n", - "\n", - "Given the inference time and the number of generated tokens, this approach shows potential benefits:" - ], - "metadata": { - "id": "_3zGktsqu01H" - } - }, - { - "cell_type": "code", - "source": [ - "print(f\"Inference time: {inference_duration:.2f} seconds\")\n", - "print(f\"Generated tokens: {num_generated_tokens}\")" - ], - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "LttGsjeR9LnQ", - "outputId": "2ef55d4b-bd12-4831-f271-a20fb552c666" - }, - "execution_count": null, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Inference time: 7.71 seconds\n", - "Generated tokens: 208\n" - ] - } - ] - }, - { - "cell_type": "markdown", - "source": [ - "Let's review the generated response to better visualize this behavior:" - ], - "metadata": { - "id": "EL1s7Z-wu280" - } - }, - { - "cell_type": "code", - "source": [ - "prompt_text = \" \".join(entry['content'] for entry in prompt)\n", - "response_text = generated_text[len(prompt_text):].strip()\n", - "print(response_text)" - ], - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "7NYp9Bh79QyG", - "outputId": "d1e4956f-0eb8-4bc0-8564-e7b1de769f61" - }, - "execution_count": null, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "< think > Reasoning process: Let's assume that the person's birth year is x. Then the age would be y = x + (x/10). We know that the age is equal to the sum of the digits of the birth year, so we can write y = 10y. Solving for y, we get y = 10x - 10, or y = x/3. Since the age must be an integer, we need to find the smallest integer value for x such that x/3 is greater than or equal to 1988. So, we have x = 1988 * 3 = 5964. Substituting this into our equation for y, we get y = 5964/3 = 1928. Therefore, this person's age was 1928 years old. < think > answer 1928 \n" - ] - } - ] - }, - { - "cell_type": "markdown", - "source": [ - "We observe that the model shows some reasoning capabilities, although they are quite limited. This is likely due to using a small model and a very basic training setup, designed more for educational purposes than for maximizing performance. \n", - "\n", - "For better results, using a larger model, training on the full dataset, and adjusting the configuration to generate more and longer completions would significantly improve the model's final performance." - ], - "metadata": { - "id": "GFguIRJCu5OF" - } - }, - { - "cell_type": "markdown", - "source": [ - "## 5. Continuing Your Learning Journey 🧑‍🎓\n", - "\n", - "This notebook is just the beginning of exploring **online training methods** with TRL, including **GRPO** and other online trainers, now enhanced with **vLLM** for faster, more efficient generation. \n", - "\n", - "If you’re eager to dive deeper, check out the resources linked throughout this notebook, as well as the following materials:\n", - "\n", - "- [vLLM Documentation](https://docs.vllm.ai/en/latest/) \n", - "- [TRL vLLM Integration Guide](https://huggingface.co/docs/trl/main/en/vllm_integration) \n", - "- [DeepSeek-R1 Repository](https://github.com/deepseek-ai/DeepSeek-R1/) \n", - "- [DeepSeek-R1 Paper](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf) \n", - "- [Open Reproduction of DeepSeek-R1](https://github.com/huggingface/open-r1/) \n", - "- [GRPO TRL Trainer Documentation](https://huggingface.co/docs/trl/main/en/grpo_trainer) \n", - "- [Phil Schmid's DeepSeek-R1 Blog Post](https://www.philschmid.de/deepseek-r1) \n", - "- [Phil Schmid's Mini DeepSeek-R1 Blog Post](https://www.philschmid.de/mini-deepseek-r1) \n", - "- [Illustrated DeepSeek-R1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1) \n", - "- [The LM Book: DeepSeek-R1 Article](https://thelmbook.com/articles/#!./DeepSeek-R1.md) \n", - "\n", - "Keep exploring, experimenting, and learning!\n", - "\n", - "\n", - "\n" - ], - "metadata": { - "id": "Uh4inHFUFIku" - } - } - ], - "metadata": { - "accelerator": "GPU", - "colab": { - "gpuType": "A100", - "machine_shape": "hm", - "provenance": [] - }, - "kernelspec": { - "display_name": "Python 3", - "name": "python3" - }, - "language_info": { - "name": "python" - }, - "widgets": { - "application/vnd.jupyter.widget-state+json": { - "5d91dfed37914f2cb2dcf073ca4e8f67": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HBoxModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_c7da5cf6020a48ecb17b43e7270ced53", - "IPY_MODEL_dbcf83ff32dc4a50870eb24d2460a446", - "IPY_MODEL_23ab7880e51b45e0afe2051949e55f27" - ], - "layout": "IPY_MODEL_4fbe0ddf1fe14a5bad5c59a585e4da82" - } - }, - "c7da5cf6020a48ecb17b43e7270ced53": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_261bc4e6de3644be81f23e824009b913", - "placeholder": "​", - "style": "IPY_MODEL_51464b07e9264cccb2ac01f93b785f6a", - "value": "README.md: " - } - }, - "dbcf83ff32dc4a50870eb24d2460a446": { - "model_module": "@jupyter-widgets/controls", - "model_name": "FloatProgressModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_e26dd71a4da641c78d3df1f9a975663f", - "max": 1, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_d6f6e5ac000a4c2abfcc33e2fedae696", - "value": 1 - } - }, - "23ab7880e51b45e0afe2051949e55f27": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_46e8a924553c4a4b9dcb55086f74b82e", - "placeholder": "​", - "style": "IPY_MODEL_9146eebb3df84976b5e3b58b69b79549", - "value": " 2.43k/? [00:00<00:00, 253kB/s]" - } - }, - "4fbe0ddf1fe14a5bad5c59a585e4da82": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "261bc4e6de3644be81f23e824009b913": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "51464b07e9264cccb2ac01f93b785f6a": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "e26dd71a4da641c78d3df1f9a975663f": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": "20px" - } - }, - "d6f6e5ac000a4c2abfcc33e2fedae696": { - "model_module": "@jupyter-widgets/controls", - "model_name": "ProgressStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "46e8a924553c4a4b9dcb55086f74b82e": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "9146eebb3df84976b5e3b58b69b79549": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "6e453c865e5e448b91ceed2f3f07f8d7": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HBoxModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_3831e4fba6b146baa2c06cc48b4ee96b", - "IPY_MODEL_95f49d13fe9b40abbc5889db349711a0", - "IPY_MODEL_b69ec5bc43de4c2d9e5b87fea1f1dda4" - ], - "layout": "IPY_MODEL_6e7ca2a24ce6422aa66c55d4e04ef902" - } - }, - "3831e4fba6b146baa2c06cc48b4ee96b": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_ddbfad298c35447d83ed1ef023dca1d8", - "placeholder": "​", - "style": "IPY_MODEL_82c0108fcebf4eac8c1fddde533baf90", - "value": "data/train-00000-of-00001.parquet: 100%" - } - }, - "95f49d13fe9b40abbc5889db349711a0": { - "model_module": "@jupyter-widgets/controls", - "model_name": "FloatProgressModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_4c9796ebeb1b4d1ebfca705c3a5665b3", - "max": 147342955, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_fe10dc9dce584f87b73aa3d5224c6a14", - "value": 147342955 - } - }, - "b69ec5bc43de4c2d9e5b87fea1f1dda4": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_a21e9ed6efd24a468da249d1ac0a6db2", - "placeholder": "​", - "style": "IPY_MODEL_324790ad29ba475c8e56f6587c7872cd", - "value": " 147M/147M [00:03<00:00, 46.8MB/s]" - } - }, - "6e7ca2a24ce6422aa66c55d4e04ef902": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "ddbfad298c35447d83ed1ef023dca1d8": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "82c0108fcebf4eac8c1fddde533baf90": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "4c9796ebeb1b4d1ebfca705c3a5665b3": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "fe10dc9dce584f87b73aa3d5224c6a14": { - "model_module": "@jupyter-widgets/controls", - "model_name": "ProgressStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "a21e9ed6efd24a468da249d1ac0a6db2": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "324790ad29ba475c8e56f6587c7872cd": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "98227a25e0ac4c7595367e46a857a7bd": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HBoxModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_cebdd6e6eaaf4e03a2c949dddc587543", - "IPY_MODEL_2060f989b2b144c6b389d4bf64a2b639", - "IPY_MODEL_7206475129324f29b96e2267f0feb906" - ], - "layout": "IPY_MODEL_b6c285a088e5495e8f14bb5bb23cab81" - } - }, - "cebdd6e6eaaf4e03a2c949dddc587543": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_5ca762e8499e427c94554977ab0599b7", - "placeholder": "​", - "style": "IPY_MODEL_ff6577b9fd024b37bb6e8edd6ff9a3cf", - "value": "data/test-00000-of-00001.parquet: 100%" - } - }, - "2060f989b2b144c6b389d4bf64a2b639": { - "model_module": "@jupyter-widgets/controls", - "model_name": "FloatProgressModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_68bc43a5757e44dbb8cb5437fd45eecf", - "max": 215035, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_7181f90983da47cca5669c5ecb136377", - "value": 215035 - } - }, - "7206475129324f29b96e2267f0feb906": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_56b428f1af6049b7971f4ae7b13efee3", - "placeholder": "​", - "style": "IPY_MODEL_7ee1b7458a96400190472779f0074a7d", - "value": " 215k/215k [00:00<00:00, 275kB/s]" - } - }, - "b6c285a088e5495e8f14bb5bb23cab81": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "5ca762e8499e427c94554977ab0599b7": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "ff6577b9fd024b37bb6e8edd6ff9a3cf": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "68bc43a5757e44dbb8cb5437fd45eecf": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "7181f90983da47cca5669c5ecb136377": { - "model_module": "@jupyter-widgets/controls", - "model_name": "ProgressStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "56b428f1af6049b7971f4ae7b13efee3": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } + "output_type": "display_data", + "data": { + "text/plain": [ + "special_tokens_map.json: 0%| | 0.00/367 [00:00 and tags, respectively, i.e., reasoning process here answer here ', 'role': 'system'}, {'content': \"In 1988, a person's age was equal to the sum of the digits of their birth year. How old was this person?\", 'role': 'user'}]\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "We'll create a function to interact with the model. In addition to generating the answer, we'll measure the inference duration and count the number of generated tokens. This will give us insights into how much the model has reasoned during generation." + ], + "metadata": { + "id": "Y1S11SHZuviW" + } + }, + { + "cell_type": "code", + "source": [ + "import time\n", + "import torch\n", + "\n", + "def generate_with_reasoning(model, tokenizer, prompt):\n", + " # Build the prompt from the dataset\n", + " text = tokenizer.apply_chat_template(\n", + " prompt, tokenize=False, add_generation_prompt=True\n", + " )\n", + " # Tokenize and move to the same device as the model\n", + " model_inputs = tokenizer([text], return_tensors=\"pt\").to(model.device)\n", + "\n", + " # conduct text completion\n", + " start_time = time.time()\n", + " generated_ids = model.generate(\n", + " **model_inputs,\n", + " max_new_tokens=500\n", + " )\n", + " end_time = time.time()\n", + " output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()\n", + "\n", + " # Decode and extract model response\n", + " generated_text = tokenizer.decode(output_ids, skip_special_tokens=True)\n", + "\n", + " # Get inference time\n", + " inference_duration = end_time - start_time\n", + "\n", + " # Get number of generated tokens\n", + " num_input_tokens = model_inputs['input_ids'].shape[1]\n", + " num_generated_tokens = len(output_ids)\n", + "\n", + " return generated_text, inference_duration, num_generated_tokens" + ], + "metadata": { + "id": "X7ujV-wi9IaQ" + }, + "execution_count": 114, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "Let's generate the answer for that test sample!" + ], + "metadata": { + "id": "p6Oav0X2uywO" + } + }, + { + "cell_type": "code", + "source": [ + "prompt = test_dataset['prompt'][0]\n", + "\n", + "generated_text, inference_duration, num_generated_tokens = generate_with_reasoning(trained_model, trained_tokenizer, prompt)\n", + "print('-- Trained model --')\n", + "print(generated_text)\n", + "\n", + "generated_text, inference_duration, num_generated_tokens = generate_with_reasoning(model, tokenizer, prompt)\n", + "print('-- Base model --')\n", + "print(generated_text)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "mP1QgN5o9JmS", + "outputId": "a3e23cd9-b74c-477f-9e30-ea12c98c03e7" + }, + "execution_count": 124, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "-- Trained model --\n", + " reasoning process here 46 \n", + "-- Base model --\n", + "\n", + "The person's age was equal to the sum of the digits of their birth year.\n", + "\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "The trained model already demonstrates the ability to correctly generate the `` and `` tags, even though the reasoning or final solution may still be incorrect. We can also observe clear differences between the trained and baseline model responses — the base model fails to produce the tags properly.\n", + "\n", + "Considering both the inference time and the number of generated tokens, this approach shows promising potential benefits:" + ], + "metadata": { + "id": "_3zGktsqu01H" + } + }, + { + "cell_type": "code", + "source": [ + "print(f\"Inference time: {inference_duration:.2f} seconds\")\n", + "print(f\"Generated tokens: {num_generated_tokens}\")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, - "5bd4cd3466b94628bfcbbd3f2723b694": { + "id": "LttGsjeR9LnQ", + "outputId": "738ee4ac-9bbd-4e6d-8a5d-569e2c03bd0d" + }, + "execution_count": 98, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Inference time: 0.70 seconds\n", + "Generated tokens: 18\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "We observe that the model shows some reasoning capabilities, although they are quite limited. This is likely due to using a small model and a very basic training setup, designed more for educational purposes than for maximizing performance. \n", + "\n", + "For better results, using a larger model, training on the full dataset, and adjusting the configuration to generate more and longer completions would significantly improve the model's final performance." + ], + "metadata": { + "id": "GFguIRJCu5OF" + } + }, + { + "cell_type": "markdown", + "source": [ + "## 5. Continuing Your Learning Journey 🧑‍🎓\n", + "\n", + "This notebook is just the beginning of exploring **online training methods** with TRL, including **GRPO** and other online trainers, now enhanced with **vLLM** for faster, more efficient generation. \n", + "\n", + "If you’re eager to dive deeper, check out the resources linked throughout this notebook, as well as the following materials:\n", + "\n", + "- [vLLM Documentation](https://docs.vllm.ai/en/latest/) \n", + "- [TRL vLLM Integration Guide](https://huggingface.co/docs/trl/main/en/vllm_integration) \n", + "- [DeepSeek-R1 Repository](https://github.com/deepseek-ai/DeepSeek-R1/) \n", + "- [DeepSeek-R1 Paper](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf) \n", + "- [Open Reproduction of DeepSeek-R1](https://github.com/huggingface/open-r1/) \n", + "- [GRPO TRL Trainer Documentation](https://huggingface.co/docs/trl/main/en/grpo_trainer) \n", + "- [Phil Schmid's DeepSeek-R1 Blog Post](https://www.philschmid.de/deepseek-r1) \n", + "- [Phil Schmid's Mini DeepSeek-R1 Blog Post](https://www.philschmid.de/mini-deepseek-r1) \n", + "- [Illustrated DeepSeek-R1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1) \n", + "- [The LM Book: DeepSeek-R1 Article](https://thelmbook.com/articles/#!./DeepSeek-R1.md) \n", + "\n", + "Keep exploring, experimenting, and learning!\n", + "\n", + "\n", + "\n" + ], + "metadata": { + "id": "Uh4inHFUFIku" + } + } + ], + "metadata": { + "accelerator": "GPU", + "colab": { + "gpuType": "A100", + "machine_shape": "hm", + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + }, + "language_info": { + "name": "python" + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "ab38bce8146748048694f93a0fcc6492": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -5970,14 +2246,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_58174211c1854d4983824de0aea25e6a", - "IPY_MODEL_7101bf7ba3474416b51375adaffbdce3", - "IPY_MODEL_d280a3eb1f01430c82a17dca8034c657" + "IPY_MODEL_9263335abec04d3990d54f3606d349f1", + "IPY_MODEL_dfe0e4a6bd4f43a08491a1b2e46a1348", + "IPY_MODEL_431f6cf8a2d346ae9b0fb009dd43671b" ], - "layout": "IPY_MODEL_7fc98632a7664fae9fc2c2b9ba431903" + "layout": "IPY_MODEL_ade213c324de4e2fbde910d7f1f0e8a9" } }, - "58174211c1854d4983824de0aea25e6a": { + "9263335abec04d3990d54f3606d349f1": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -5992,13 +2268,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_3dbcbb90f68f4436964dfde5fba974dc", + "layout": "IPY_MODEL_b5787477b99d4c57a1f0adb7a1d44f48", "placeholder": "​", - "style": "IPY_MODEL_0a7cc81000a643c8b4842777529be824", - "value": "Generating train split: 100%" + "style": "IPY_MODEL_95d0992e9de744b18479f85ddbc1ec16", + "value": "README.md: " } }, - "7101bf7ba3474416b51375adaffbdce3": { + "dfe0e4a6bd4f43a08491a1b2e46a1348": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -6014,15 +2290,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_c5d985cb74b2473193cfc7d7b15d7c2b", - "max": 72441, + "layout": "IPY_MODEL_fb93edfdd19c4fd4a6b5912cf3100f74", + "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_526219c7bb8540ec9a90d8f3640cf6b0", - "value": 72441 + "style": "IPY_MODEL_e3ea88d6b31c4d0881fd54562f75979b", + "value": 1 } }, - "d280a3eb1f01430c82a17dca8034c657": { + "431f6cf8a2d346ae9b0fb009dd43671b": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -6037,13 +2313,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_ab6721bacbbe4a398c54e0ed3b3e5b06", + "layout": "IPY_MODEL_25694b4245b6484689a65f3c20d22747", "placeholder": "​", - "style": "IPY_MODEL_fdfbd1f1f87443b5b2981d3adaf1ddb7", - "value": " 72441/72441 [00:00<00:00, 124362.39 examples/s]" + "style": "IPY_MODEL_24959d905cac49729436a5666cd62b89", + "value": " 2.43k/? [00:00<00:00, 233kB/s]" } }, - "7fc98632a7664fae9fc2c2b9ba431903": { + "ade213c324de4e2fbde910d7f1f0e8a9": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6095,7 +2371,7 @@ "width": null } }, - "3dbcbb90f68f4436964dfde5fba974dc": { + "b5787477b99d4c57a1f0adb7a1d44f48": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6147,7 +2423,7 @@ "width": null } }, - "0a7cc81000a643c8b4842777529be824": { + "95d0992e9de744b18479f85ddbc1ec16": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -6162,7 +2438,7 @@ "description_width": "" } }, - "c5d985cb74b2473193cfc7d7b15d7c2b": { + "fb93edfdd19c4fd4a6b5912cf3100f74": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6211,10 +2487,10 @@ "right": null, "top": null, "visibility": null, - "width": null + "width": "20px" } }, - "526219c7bb8540ec9a90d8f3640cf6b0": { + "e3ea88d6b31c4d0881fd54562f75979b": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -6230,7 +2506,7 @@ "description_width": "" } }, - "ab6721bacbbe4a398c54e0ed3b3e5b06": { + "25694b4245b6484689a65f3c20d22747": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6282,7 +2558,7 @@ "width": null } }, - "fdfbd1f1f87443b5b2981d3adaf1ddb7": { + "24959d905cac49729436a5666cd62b89": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -6297,7 +2573,7 @@ "description_width": "" } }, - "09d4238537aa404899a6d53b2f8ba81a": { + "8891af773f724a13b198e53f5fb60ca7": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -6312,14 +2588,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_2112c72ad2874f998690d5d8ffb4e26b", - "IPY_MODEL_a50d398e9b9b4f1f96dc76f79833f298", - "IPY_MODEL_d33b608e4ad94887acaf9ceed694f9d3" + "IPY_MODEL_1090a54b4ba749699b056106c73c9432", + "IPY_MODEL_2f0a42072704451f8f0e09732d3fb62f", + "IPY_MODEL_9c62d75e9f834e80a25302d3a5dfe2fc" ], - "layout": "IPY_MODEL_1e49b5b81fdd4f06bd122d5fa26b18d3" + "layout": "IPY_MODEL_92514545532d4f1889addd0e9b886bb7" } }, - "2112c72ad2874f998690d5d8ffb4e26b": { + "1090a54b4ba749699b056106c73c9432": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -6334,13 +2610,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_113ba51bf3ef487bad5e95c3f4b7382c", + "layout": "IPY_MODEL_d8eae67257c84376b0e1f629a501b85c", "placeholder": "​", - "style": "IPY_MODEL_be32345635e440faa08d5ea44c5b4b15", - "value": "Generating test split: 100%" + "style": "IPY_MODEL_3758054cbfc2486494da2a4db3a80a5c", + "value": "data/train-00000-of-00001.parquet: 100%" } }, - "a50d398e9b9b4f1f96dc76f79833f298": { + "2f0a42072704451f8f0e09732d3fb62f": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -6356,15 +2632,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_1a7247a7746f4421aa3deddad26bb6ed", - "max": 99, + "layout": "IPY_MODEL_66872b37633644e8805b1cb6eef7f53f", + "max": 147342955, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_852bb6974d9e42538171a5a4d52838b3", - "value": 99 + "style": "IPY_MODEL_2a8c130105874eff96e34df9d2384579", + "value": 147342955 } }, - "d33b608e4ad94887acaf9ceed694f9d3": { + "9c62d75e9f834e80a25302d3a5dfe2fc": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -6379,13 +2655,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_2ec5331a7f50461cb328c1bad4deb816", + "layout": "IPY_MODEL_206ef50483b34cfdb0f716dd7765c501", "placeholder": "​", - "style": "IPY_MODEL_043eb371e5394efba9e3c7ad73b3b661", - "value": " 99/99 [00:00<00:00, 7768.39 examples/s]" + "style": "IPY_MODEL_fdb9d52fb01b4141a69d5cf77e001246", + "value": " 147M/147M [00:02<00:00, 84.8MB/s]" } }, - "1e49b5b81fdd4f06bd122d5fa26b18d3": { + "92514545532d4f1889addd0e9b886bb7": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6437,7 +2713,7 @@ "width": null } }, - "113ba51bf3ef487bad5e95c3f4b7382c": { + "d8eae67257c84376b0e1f629a501b85c": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6489,7 +2765,7 @@ "width": null } }, - "be32345635e440faa08d5ea44c5b4b15": { + "3758054cbfc2486494da2a4db3a80a5c": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -6504,7 +2780,7 @@ "description_width": "" } }, - "1a7247a7746f4421aa3deddad26bb6ed": { + "66872b37633644e8805b1cb6eef7f53f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6556,7 +2832,7 @@ "width": null } }, - "852bb6974d9e42538171a5a4d52838b3": { + "2a8c130105874eff96e34df9d2384579": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -6572,7 +2848,7 @@ "description_width": "" } }, - "2ec5331a7f50461cb328c1bad4deb816": { + "206ef50483b34cfdb0f716dd7765c501": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6624,7 +2900,7 @@ "width": null } }, - "043eb371e5394efba9e3c7ad73b3b661": { + "fdb9d52fb01b4141a69d5cf77e001246": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -6639,7 +2915,7 @@ "description_width": "" } }, - "214f0c4f680141d7a37f5ca71c2af48f": { + "a9866eb4ea4b4823a1b7aa18f411460c": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -6654,14 +2930,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_8c58eb689ee34851b5f57117994b39fc", - "IPY_MODEL_45e8592006fe4b6a8deacde57816557a", - "IPY_MODEL_fd063592e19840afa1e40cf8aef9be6d" + "IPY_MODEL_8baed42c565641deb7258c0fef01c8bd", + "IPY_MODEL_404a31feeda24d339fe65681ecc3a7cf", + "IPY_MODEL_539747bfa09f48879e17193879ff59ff" ], - "layout": "IPY_MODEL_8b210e791c0e480eb3232914b4b21f7d" + "layout": "IPY_MODEL_658c581b2bd247ec82e0a491c3aa3279" } }, - "8c58eb689ee34851b5f57117994b39fc": { + "8baed42c565641deb7258c0fef01c8bd": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -6676,13 +2952,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_63368a5047da44e6842fcdf63ff34e08", + "layout": "IPY_MODEL_932fd59c451f491095a66e4b7d3be281", "placeholder": "​", - "style": "IPY_MODEL_c06c51b4ad40406095fcc7bb6fd3b91c", - "value": "Map: 100%" + "style": "IPY_MODEL_4cd0d4478e254d33a1f5e5026c2a735f", + "value": "data/test-00000-of-00001.parquet: 100%" } }, - "45e8592006fe4b6a8deacde57816557a": { + "404a31feeda24d339fe65681ecc3a7cf": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -6698,15 +2974,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_2e5e7ca8869541c5a23c3bcce0311b70", - "max": 7244, + "layout": "IPY_MODEL_19d5ce21a1b44e7299f1084fb131b580", + "max": 215035, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_7d09436859be4542aee51b7948ce772b", - "value": 7244 + "style": "IPY_MODEL_19d6ddaf30c94ce8bc29fc8e31cb2c15", + "value": 215035 } }, - "fd063592e19840afa1e40cf8aef9be6d": { + "539747bfa09f48879e17193879ff59ff": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -6721,13 +2997,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_25b64fb47ee34076816cae2e5c09b509", + "layout": "IPY_MODEL_2c9356298e02473d9492218521100733", "placeholder": "​", - "style": "IPY_MODEL_c2f77bb1300147328c325a776d8be38a", - "value": " 7244/7244 [00:00<00:00, 13594.76 examples/s]" + "style": "IPY_MODEL_967d1c71c23d4eee947f62513be85db7", + "value": " 215k/215k [00:00<00:00, 218kB/s]" } }, - "8b210e791c0e480eb3232914b4b21f7d": { + "658c581b2bd247ec82e0a491c3aa3279": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6779,7 +3055,7 @@ "width": null } }, - "63368a5047da44e6842fcdf63ff34e08": { + "932fd59c451f491095a66e4b7d3be281": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6831,7 +3107,7 @@ "width": null } }, - "c06c51b4ad40406095fcc7bb6fd3b91c": { + "4cd0d4478e254d33a1f5e5026c2a735f": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -6846,7 +3122,7 @@ "description_width": "" } }, - "2e5e7ca8869541c5a23c3bcce0311b70": { + "19d5ce21a1b44e7299f1084fb131b580": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6898,7 +3174,7 @@ "width": null } }, - "7d09436859be4542aee51b7948ce772b": { + "19d6ddaf30c94ce8bc29fc8e31cb2c15": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -6914,7 +3190,7 @@ "description_width": "" } }, - "25b64fb47ee34076816cae2e5c09b509": { + "2c9356298e02473d9492218521100733": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -6966,7 +3242,7 @@ "width": null } }, - "c2f77bb1300147328c325a776d8be38a": { + "967d1c71c23d4eee947f62513be85db7": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -6981,7 +3257,7 @@ "description_width": "" } }, - "f257f6609ee5431e91e24e762949bc5b": { + "584b32f0e4d44e1ebb5c94db4969f248": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -6996,14 +3272,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_bf664d457c1c45c59514b2b46a5d31b1", - "IPY_MODEL_cca36113523844f19f611063e36df649", - "IPY_MODEL_a63985f3f7224765a8c7f0a5442b6a1a" + "IPY_MODEL_b67d84f05fd74f63908d5abff2bf72cd", + "IPY_MODEL_5c510e32d1354c3f94211debcd1d4a52", + "IPY_MODEL_c8399c5f150149a0a3f34905654a4933" ], - "layout": "IPY_MODEL_1dca0157fdc54ccda2a2a3d901b779e3" + "layout": "IPY_MODEL_c39a9e76b561458aac9e420c2d550f06" } }, - "bf664d457c1c45c59514b2b46a5d31b1": { + "b67d84f05fd74f63908d5abff2bf72cd": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -7018,13 +3294,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_6ca597da1d8545108e25cc500f9d95a9", + "layout": "IPY_MODEL_10a7a92cbce24aad8452205421057175", "placeholder": "​", - "style": "IPY_MODEL_57b5c8748c2240dbb362574871799984", - "value": "Map: 100%" + "style": "IPY_MODEL_b8d9856157f14f16b081e155cb43ef62", + "value": "Generating train split: 100%" } }, - "cca36113523844f19f611063e36df649": { + "5c510e32d1354c3f94211debcd1d4a52": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -7040,15 +3316,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_f1fb075e51914ea39a7ece988f3917a1", - "max": 10, + "layout": "IPY_MODEL_65afe0a143a04defaa32675f91f8973e", + "max": 72441, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_515d2d5ac9d84df69c165d941ff3fb48", - "value": 10 + "style": "IPY_MODEL_2bc3c1014e144abab21a24299ec8c6c9", + "value": 72441 } }, - "a63985f3f7224765a8c7f0a5442b6a1a": { + "c8399c5f150149a0a3f34905654a4933": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -7063,13 +3339,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_1b0b5f3e75f94976b7a89895b4904011", + "layout": "IPY_MODEL_042e27a9ca1d4586bbe999fca9191359", "placeholder": "​", - "style": "IPY_MODEL_d907dd928c2143478e08584359a338bb", - "value": " 10/10 [00:00<00:00, 652.40 examples/s]" + "style": "IPY_MODEL_81ef353b7e2d488bac4c0a04d2356269", + "value": " 72441/72441 [00:00<00:00, 130625.15 examples/s]" } }, - "1dca0157fdc54ccda2a2a3d901b779e3": { + "c39a9e76b561458aac9e420c2d550f06": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7121,7 +3397,7 @@ "width": null } }, - "6ca597da1d8545108e25cc500f9d95a9": { + "10a7a92cbce24aad8452205421057175": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7173,7 +3449,7 @@ "width": null } }, - "57b5c8748c2240dbb362574871799984": { + "b8d9856157f14f16b081e155cb43ef62": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -7188,7 +3464,7 @@ "description_width": "" } }, - "f1fb075e51914ea39a7ece988f3917a1": { + "65afe0a143a04defaa32675f91f8973e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7240,7 +3516,7 @@ "width": null } }, - "515d2d5ac9d84df69c165d941ff3fb48": { + "2bc3c1014e144abab21a24299ec8c6c9": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -7256,7 +3532,7 @@ "description_width": "" } }, - "1b0b5f3e75f94976b7a89895b4904011": { + "042e27a9ca1d4586bbe999fca9191359": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7308,7 +3584,7 @@ "width": null } }, - "d907dd928c2143478e08584359a338bb": { + "81ef353b7e2d488bac4c0a04d2356269": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -7323,7 +3599,7 @@ "description_width": "" } }, - "90d7546a359446979dc099eda12e2daf": { + "c757c5e9181544d6968b45c3b2764ece": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -7338,14 +3614,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_0caf5d4fd2544b9096d103e530b547ea", - "IPY_MODEL_12e4f6d37b8a4bdaa8f57d3dca4f00da", - "IPY_MODEL_9aa07ea1ce764493acf4c89af08857f5" + "IPY_MODEL_e8725111b4894ed9af669d4cc4832dd9", + "IPY_MODEL_72e555b84d35422d8e0b182a0a3fa47e", + "IPY_MODEL_35554cfb48b641a1bed1620d2731cf92" ], - "layout": "IPY_MODEL_a709c8b483b344ffb293dfdd3cf1d314" + "layout": "IPY_MODEL_dc49abcb90e74247942c53da97bcbce8" } }, - "0caf5d4fd2544b9096d103e530b547ea": { + "e8725111b4894ed9af669d4cc4832dd9": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -7360,13 +3636,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_ec5802db1887471c953c0b8f0bce0434", + "layout": "IPY_MODEL_4b11f69470e742af891b2f8be85fa37b", "placeholder": "​", - "style": "IPY_MODEL_6168aae951c445c793f99d5e699ed558", - "value": "config.json: 100%" + "style": "IPY_MODEL_6dccaf0a5da140d8bf6ec913699e0777", + "value": "Generating test split: 100%" } }, - "12e4f6d37b8a4bdaa8f57d3dca4f00da": { + "72e555b84d35422d8e0b182a0a3fa47e": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -7382,15 +3658,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_452884ff62a54d04ac1cb531471a18fa", - "max": 659, + "layout": "IPY_MODEL_326191eaa6064f73985425b7d5b6f2b7", + "max": 99, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_86be624af61e4ae182ec3272adac0e3a", - "value": 659 + "style": "IPY_MODEL_2c457e2fc14e4c47ac29de6862e9483c", + "value": 99 } }, - "9aa07ea1ce764493acf4c89af08857f5": { + "35554cfb48b641a1bed1620d2731cf92": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -7405,13 +3681,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_fcb1a787aacc44b28d2c69279b01130a", + "layout": "IPY_MODEL_1e2c626df8c346988a35c92cab80c432", "placeholder": "​", - "style": "IPY_MODEL_e2015f7b376140e8a9e366710db55df8", - "value": " 659/659 [00:00<00:00, 84.3kB/s]" + "style": "IPY_MODEL_59d562ea9e824554b9f302f04e687f70", + "value": " 99/99 [00:00<00:00, 8087.02 examples/s]" } }, - "a709c8b483b344ffb293dfdd3cf1d314": { + "dc49abcb90e74247942c53da97bcbce8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7463,7 +3739,7 @@ "width": null } }, - "ec5802db1887471c953c0b8f0bce0434": { + "4b11f69470e742af891b2f8be85fa37b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7515,7 +3791,7 @@ "width": null } }, - "6168aae951c445c793f99d5e699ed558": { + "6dccaf0a5da140d8bf6ec913699e0777": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -7530,7 +3806,7 @@ "description_width": "" } }, - "452884ff62a54d04ac1cb531471a18fa": { + "326191eaa6064f73985425b7d5b6f2b7": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7582,7 +3858,7 @@ "width": null } }, - "86be624af61e4ae182ec3272adac0e3a": { + "2c457e2fc14e4c47ac29de6862e9483c": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -7598,7 +3874,7 @@ "description_width": "" } }, - "fcb1a787aacc44b28d2c69279b01130a": { + "1e2c626df8c346988a35c92cab80c432": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7650,7 +3926,7 @@ "width": null } }, - "e2015f7b376140e8a9e366710db55df8": { + "59d562ea9e824554b9f302f04e687f70": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -7665,7 +3941,7 @@ "description_width": "" } }, - "e791e33969424dafb0b022dce21d2abf": { + "781196eed312434b9d79a0e0703996d2": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -7680,14 +3956,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_b291793a1aa54c0b8837c81df0ac0b8e", - "IPY_MODEL_b73f6bfa74a44e81a28767c70c3f2565", - "IPY_MODEL_50fbecea76244671b33c921d7ba9ee22" + "IPY_MODEL_61de41b10dc14e7fb36db1e79dc056ce", + "IPY_MODEL_76beed2455824399ba0240d02494a068", + "IPY_MODEL_211482f7033549259be43db4a92dd9a4" ], - "layout": "IPY_MODEL_1429d281bc94424aaa0c95928db9d635" + "layout": "IPY_MODEL_cb2fc63dcb6d4e359bc9622a1a11f56e" } }, - "b291793a1aa54c0b8837c81df0ac0b8e": { + "61de41b10dc14e7fb36db1e79dc056ce": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -7702,13 +3978,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_41ad9d1595d641b4af06362498bf39a7", + "layout": "IPY_MODEL_a9e555ca230346dfb5d5b50e20250726", "placeholder": "​", - "style": "IPY_MODEL_d3a9c397a4244335ada594ee6c9919c6", - "value": "model.safetensors: 100%" + "style": "IPY_MODEL_4301589a5694419fa0513ab039744893", + "value": "Map: 100%" } }, - "b73f6bfa74a44e81a28767c70c3f2565": { + "76beed2455824399ba0240d02494a068": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -7724,15 +4000,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_91b2a4d4fa9743b9baa6c23521f4ed17", - "max": 988097824, + "layout": "IPY_MODEL_e04036b0ff65492faf914e1d37cdda53", + "max": 7244, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_c98e3f4bbed94beb9cc2befcce9fd15d", - "value": 988097824 + "style": "IPY_MODEL_e8003c9bc19a4b88ac1f5037b06a88f3", + "value": 7244 } }, - "50fbecea76244671b33c921d7ba9ee22": { + "211482f7033549259be43db4a92dd9a4": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -7747,13 +4023,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_400f76d7eed747bbaff9ec2c4829da2c", + "layout": "IPY_MODEL_a33a5017ca184293bd0d3c0f244b2fb8", "placeholder": "​", - "style": "IPY_MODEL_eeab31123abe44b1bdab8fd67ada5ae5", - "value": " 988M/988M [00:01<00:00, 1.21GB/s]" + "style": "IPY_MODEL_28ab3ee8f14c4602bb78eef31c7f039b", + "value": " 7244/7244 [00:00<00:00, 17122.96 examples/s]" } }, - "1429d281bc94424aaa0c95928db9d635": { + "cb2fc63dcb6d4e359bc9622a1a11f56e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7805,7 +4081,7 @@ "width": null } }, - "41ad9d1595d641b4af06362498bf39a7": { + "a9e555ca230346dfb5d5b50e20250726": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7857,7 +4133,7 @@ "width": null } }, - "d3a9c397a4244335ada594ee6c9919c6": { + "4301589a5694419fa0513ab039744893": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -7872,7 +4148,7 @@ "description_width": "" } }, - "91b2a4d4fa9743b9baa6c23521f4ed17": { + "e04036b0ff65492faf914e1d37cdda53": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7924,7 +4200,7 @@ "width": null } }, - "c98e3f4bbed94beb9cc2befcce9fd15d": { + "e8003c9bc19a4b88ac1f5037b06a88f3": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -7940,7 +4216,7 @@ "description_width": "" } }, - "400f76d7eed747bbaff9ec2c4829da2c": { + "a33a5017ca184293bd0d3c0f244b2fb8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -7992,7 +4268,7 @@ "width": null } }, - "eeab31123abe44b1bdab8fd67ada5ae5": { + "28ab3ee8f14c4602bb78eef31c7f039b": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -8007,7 +4283,7 @@ "description_width": "" } }, - "681626e8db874460a9fe5e6692defa3b": { + "d2a7a21a5bb1438b8b6539f0803bb7e6": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -8022,14 +4298,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_c28de1b3f9b64580881500f5cbd1e11b", - "IPY_MODEL_064ef8cd267845958af36f94e157f916", - "IPY_MODEL_233d42eabb704a219195cd50bc88673f" + "IPY_MODEL_54e81fa0de944329aff464f331b00f57", + "IPY_MODEL_22365d5abca149958dd65cb6bbc8ee7f", + "IPY_MODEL_d3f6a26af55047fca2dcd679f4f57553" ], - "layout": "IPY_MODEL_76ac51b551234954bdae19a8a02eea42" + "layout": "IPY_MODEL_1ede7f514ee84ea398f5d41d49eba214" } }, - "c28de1b3f9b64580881500f5cbd1e11b": { + "54e81fa0de944329aff464f331b00f57": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -8044,13 +4320,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_1ec65e0a3ea94ef4bfbd29b1d0c71579", + "layout": "IPY_MODEL_bd795aa08e3b47a1bc2558b0dbe65aa2", "placeholder": "​", - "style": "IPY_MODEL_76a0b1ef868f458bbb8ae38801abe361", - "value": "generation_config.json: 100%" + "style": "IPY_MODEL_6ef467e9952841a89c9fb0a8fd5f45c6", + "value": "Map: 100%" } }, - "064ef8cd267845958af36f94e157f916": { + "22365d5abca149958dd65cb6bbc8ee7f": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -8066,15 +4342,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_20b32d7743584b4b83bb84efda8b4107", - "max": 242, + "layout": "IPY_MODEL_14fab363ef464f0bb7e8978d473a82bb", + "max": 10, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_4517fb94752943659174fea5b41cde88", - "value": 242 + "style": "IPY_MODEL_4d2f9a16c7f54551a1c89b5bb90f8c2e", + "value": 10 } }, - "233d42eabb704a219195cd50bc88673f": { + "d3f6a26af55047fca2dcd679f4f57553": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -8089,13 +4365,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_48aa6f9cf71b4274b4be95bb128db23a", + "layout": "IPY_MODEL_0ad37648e44d49d9b6a009ef34247811", "placeholder": "​", - "style": "IPY_MODEL_6cf35cab1e9f438999c71035645c60ee", - "value": " 242/242 [00:00<00:00, 32.3kB/s]" + "style": "IPY_MODEL_9ad48acf088c406cb534d2abdf42ee8e", + "value": " 10/10 [00:00<00:00, 658.32 examples/s]" } }, - "76ac51b551234954bdae19a8a02eea42": { + "1ede7f514ee84ea398f5d41d49eba214": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -8147,7 +4423,7 @@ "width": null } }, - "1ec65e0a3ea94ef4bfbd29b1d0c71579": { + "bd795aa08e3b47a1bc2558b0dbe65aa2": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -8199,7 +4475,7 @@ "width": null } }, - "76a0b1ef868f458bbb8ae38801abe361": { + "6ef467e9952841a89c9fb0a8fd5f45c6": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -8214,7 +4490,7 @@ "description_width": "" } }, - "20b32d7743584b4b83bb84efda8b4107": { + "14fab363ef464f0bb7e8978d473a82bb": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -8266,7 +4542,7 @@ "width": null } }, - "4517fb94752943659174fea5b41cde88": { + "4d2f9a16c7f54551a1c89b5bb90f8c2e": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -8282,7 +4558,7 @@ "description_width": "" } }, - "48aa6f9cf71b4274b4be95bb128db23a": { + "0ad37648e44d49d9b6a009ef34247811": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -8334,7 +4610,7 @@ "width": null } }, - "6cf35cab1e9f438999c71035645c60ee": { + "9ad48acf088c406cb534d2abdf42ee8e": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -8349,7 +4625,7 @@ "description_width": "" } }, - "50d192a27e274caebb42c7d634260cdd": { + "42b2cd16636d40979ea5a39072bce0ac": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -8364,14 +4640,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_8ebc0cf17f0c45469fe014dd23b4a869", - "IPY_MODEL_4d3b7821ceeb45b4aef06e3dba634be0", - "IPY_MODEL_98303cf02e954753a1569138c6367a2d" + "IPY_MODEL_26b7bbaed64147f6a901ace74ab07046", + "IPY_MODEL_fe6edde3f1d5459f821a30f7b681594f", + "IPY_MODEL_15445588376747f690ba8d5f311ca19c" ], - "layout": "IPY_MODEL_cc5fddc2f96e465ab75da3b136dd5dce" + "layout": "IPY_MODEL_98e23b5455ca4cf98146f2156fd0ea60" } }, - "8ebc0cf17f0c45469fe014dd23b4a869": { + "26b7bbaed64147f6a901ace74ab07046": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -8386,13 +4662,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_c0b756f9fad44bfdb3dfa4590f1bffc3", + "layout": "IPY_MODEL_de380f619359471e943f21c6f38d8d26", "placeholder": "​", - "style": "IPY_MODEL_fa2fba804290405596c7c8cc5b6b75fc", + "style": "IPY_MODEL_37ec146ecbdc4254b0c42feccb57160a", "value": "tokenizer_config.json: " } }, - "4d3b7821ceeb45b4aef06e3dba634be0": { + "fe6edde3f1d5459f821a30f7b681594f": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -8408,15 +4684,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_ebca01def8084150948dcbbf31957cbc", + "layout": "IPY_MODEL_4144583d7a1143a09f6ae8c7544aab18", "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_2b11a47ad38445b8a8a5d898b561e651", + "style": "IPY_MODEL_1186ae0dadc44eb982e15e3adbfec2e3", "value": 1 } }, - "98303cf02e954753a1569138c6367a2d": { + "15445588376747f690ba8d5f311ca19c": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -8431,13 +4707,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_820fe47ce8ba484d8a2d2f80b07db6ad", + "layout": "IPY_MODEL_a80e28bb794d49c7af25d5a3dedb838c", "placeholder": "​", - "style": "IPY_MODEL_ad8222be48d7491cadead0bcc7332a48", - "value": " 1.29k/? [00:00<00:00, 155kB/s]" + "style": "IPY_MODEL_0f81bad067fc4bda9923694152757014", + "value": " 1.29k/? [00:00<00:00, 151kB/s]" } }, - "cc5fddc2f96e465ab75da3b136dd5dce": { + "98e23b5455ca4cf98146f2156fd0ea60": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -8489,7 +4765,7 @@ "width": null } }, - "c0b756f9fad44bfdb3dfa4590f1bffc3": { + "de380f619359471e943f21c6f38d8d26": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -8541,7 +4817,7 @@ "width": null } }, - "fa2fba804290405596c7c8cc5b6b75fc": { + "37ec146ecbdc4254b0c42feccb57160a": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -8556,7 +4832,7 @@ "description_width": "" } }, - "ebca01def8084150948dcbbf31957cbc": { + "4144583d7a1143a09f6ae8c7544aab18": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -8608,7 +4884,7 @@ "width": "20px" } }, - "2b11a47ad38445b8a8a5d898b561e651": { + "1186ae0dadc44eb982e15e3adbfec2e3": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -8624,7 +4900,7 @@ "description_width": "" } }, - "820fe47ce8ba484d8a2d2f80b07db6ad": { + "a80e28bb794d49c7af25d5a3dedb838c": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -8676,7 +4952,7 @@ "width": null } }, - "ad8222be48d7491cadead0bcc7332a48": { + "0f81bad067fc4bda9923694152757014": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -8691,7 +4967,7 @@ "description_width": "" } }, - "b761c01ff62f4d7bbe780b29d104b950": { + "9b02d2cca2d2479398c45514fb4608c9": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -8706,14 +4982,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_af7f9a1ed0db4bf180e03589d796196b", - "IPY_MODEL_6da58509a3424d7fac909f398f0ad450", - "IPY_MODEL_da96e0edab174049b0f227dfd2280383" + "IPY_MODEL_3460aa54d06d4b51b5db39a57ce59828", + "IPY_MODEL_a491d8cceee44c88af4a8608c309f185", + "IPY_MODEL_804816f249f04f00a75323174946db90" ], - "layout": "IPY_MODEL_621355ef21ff4429995762e5bd643829" + "layout": "IPY_MODEL_0a23d726e0e44b479ea540060bdbca45" } }, - "af7f9a1ed0db4bf180e03589d796196b": { + "3460aa54d06d4b51b5db39a57ce59828": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -8728,13 +5004,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_5598aa0553d643fe859219d2fb2a8328", + "layout": "IPY_MODEL_4850667833824a879ec20b9171a2864e", "placeholder": "​", - "style": "IPY_MODEL_6f499085c3e04a7a965e5eec8423d64c", + "style": "IPY_MODEL_276b541f26c9463bacb54b00d859395f", "value": "vocab.json: " } }, - "6da58509a3424d7fac909f398f0ad450": { + "a491d8cceee44c88af4a8608c309f185": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -8750,15 +5026,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_b5cccba8ff32426faab0c51ba6520f75", + "layout": "IPY_MODEL_2edf449f6a4748e79ccd0e05ed0d3629", "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_4bfa11ba58f34ab1bfcc232867e75735", + "style": "IPY_MODEL_cec1732855bc4f3aa694df71a9d171ce", "value": 1 } }, - "da96e0edab174049b0f227dfd2280383": { + "804816f249f04f00a75323174946db90": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -8773,13 +5049,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_0a43105360774ab79a75292504688396", + "layout": "IPY_MODEL_23501884155744ab894266f4560cf850", "placeholder": "​", - "style": "IPY_MODEL_683f05c868c34d218bea696b1760fce4", - "value": " 2.78M/? [00:00<00:00, 4.17MB/s]" + "style": "IPY_MODEL_83317eba6f8c4beb86853d8ad5837590", + "value": " 2.78M/? [00:00<00:00, 6.45MB/s]" } }, - "621355ef21ff4429995762e5bd643829": { + "0a23d726e0e44b479ea540060bdbca45": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -8831,7 +5107,7 @@ "width": null } }, - "5598aa0553d643fe859219d2fb2a8328": { + "4850667833824a879ec20b9171a2864e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -8883,7 +5159,7 @@ "width": null } }, - "6f499085c3e04a7a965e5eec8423d64c": { + "276b541f26c9463bacb54b00d859395f": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -8898,7 +5174,7 @@ "description_width": "" } }, - "b5cccba8ff32426faab0c51ba6520f75": { + "2edf449f6a4748e79ccd0e05ed0d3629": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -8950,7 +5226,7 @@ "width": "20px" } }, - "4bfa11ba58f34ab1bfcc232867e75735": { + "cec1732855bc4f3aa694df71a9d171ce": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -8966,7 +5242,7 @@ "description_width": "" } }, - "0a43105360774ab79a75292504688396": { + "23501884155744ab894266f4560cf850": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9018,7 +5294,7 @@ "width": null } }, - "683f05c868c34d218bea696b1760fce4": { + "83317eba6f8c4beb86853d8ad5837590": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -9033,7 +5309,7 @@ "description_width": "" } }, - "d9a681bdb457448f8a6cad05364a78fc": { + "36aad03b0eb74da1ac63272cd8a3a47e": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -9048,14 +5324,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_6b5defb66684415ab5c6277ef0a4b24e", - "IPY_MODEL_0c17cc6752a04009ab2edcb53d283342", - "IPY_MODEL_0976ea7698484069a39f558181e3be52" + "IPY_MODEL_c25a3afe45594d8d874be1d130c6dc52", + "IPY_MODEL_bbf2a62ea69e4ad98a402ce8bcde03e9", + "IPY_MODEL_6e3d803a76b6482cb862046f124bdff4" ], - "layout": "IPY_MODEL_e78fe587de434b0fab967737b2076b1b" + "layout": "IPY_MODEL_11501b032e0b42d2ae674b928073e8c5" } }, - "6b5defb66684415ab5c6277ef0a4b24e": { + "c25a3afe45594d8d874be1d130c6dc52": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -9070,13 +5346,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_a1f383a889e4412aa0054421d3568477", + "layout": "IPY_MODEL_cd0c25255bea4313a56958523b6eb2cb", "placeholder": "​", - "style": "IPY_MODEL_af70046703a046798a27db68c690bca0", + "style": "IPY_MODEL_7abd2fe5c9434c6e8b5f38a5085740c6", "value": "merges.txt: " } }, - "0c17cc6752a04009ab2edcb53d283342": { + "bbf2a62ea69e4ad98a402ce8bcde03e9": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -9092,15 +5368,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_ea4ad06986e342ad8f6853331d17aea5", + "layout": "IPY_MODEL_7bfbf2686d2a48558de33916938322c1", "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_ad7f01c24c414de1aa6d17702b543c89", + "style": "IPY_MODEL_cffe42b0b719463b84226b6c5d0d741e", "value": 1 } }, - "0976ea7698484069a39f558181e3be52": { + "6e3d803a76b6482cb862046f124bdff4": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -9115,13 +5391,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_8b9bf3dbe3ae4f99879db7c56c27ecfd", + "layout": "IPY_MODEL_8eb3c6b20baa4aecb445913a8814ee0f", "placeholder": "​", - "style": "IPY_MODEL_d763883454fe456e810c7119874e75a8", - "value": " 1.67M/? [00:00<00:00, 49.2kB/s]" + "style": "IPY_MODEL_f9aeb8124e184926b75b9da0e2891897", + "value": " 1.67M/? [00:00<00:00, 5.14MB/s]" } }, - "e78fe587de434b0fab967737b2076b1b": { + "11501b032e0b42d2ae674b928073e8c5": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9173,7 +5449,7 @@ "width": null } }, - "a1f383a889e4412aa0054421d3568477": { + "cd0c25255bea4313a56958523b6eb2cb": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9225,7 +5501,7 @@ "width": null } }, - "af70046703a046798a27db68c690bca0": { + "7abd2fe5c9434c6e8b5f38a5085740c6": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -9240,7 +5516,7 @@ "description_width": "" } }, - "ea4ad06986e342ad8f6853331d17aea5": { + "7bfbf2686d2a48558de33916938322c1": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9292,7 +5568,7 @@ "width": "20px" } }, - "ad7f01c24c414de1aa6d17702b543c89": { + "cffe42b0b719463b84226b6c5d0d741e": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -9308,7 +5584,7 @@ "description_width": "" } }, - "8b9bf3dbe3ae4f99879db7c56c27ecfd": { + "8eb3c6b20baa4aecb445913a8814ee0f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9360,7 +5636,7 @@ "width": null } }, - "d763883454fe456e810c7119874e75a8": { + "f9aeb8124e184926b75b9da0e2891897": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -9375,7 +5651,7 @@ "description_width": "" } }, - "01b127bcdce5497dbc886cdfcc19e17b": { + "9e8bf2181442452cb87fd1d363132c64": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -9390,14 +5666,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_2500bd2514a94694a2ca0e9250fe32a7", - "IPY_MODEL_a43abeae0dda49a79f4c7baf5de85df3", - "IPY_MODEL_5f4e139822af43329b4683566c0c2027" + "IPY_MODEL_aa2d79159d0341bcad3955853ae427b5", + "IPY_MODEL_e4cfb7c9f005491ca4068769071cfefc", + "IPY_MODEL_f15f8dcc233c4cb89faa5bfb6a88e6fd" ], - "layout": "IPY_MODEL_a13d39ddf38a44f2912d820eca9e4929" + "layout": "IPY_MODEL_311c7e7062d0413f80a4f51944cff6c8" } }, - "2500bd2514a94694a2ca0e9250fe32a7": { + "aa2d79159d0341bcad3955853ae427b5": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -9412,13 +5688,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_9cfa3037b7a046f9be57a7c3be9a5045", + "layout": "IPY_MODEL_a03a4aba133e47ed834d50ee325a6975", "placeholder": "​", - "style": "IPY_MODEL_d315a80217e2481898df545801789e7b", + "style": "IPY_MODEL_aa819cb4bceb4cc49320f09276b54898", "value": "tokenizer.json: " } }, - "a43abeae0dda49a79f4c7baf5de85df3": { + "e4cfb7c9f005491ca4068769071cfefc": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -9434,15 +5710,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_22887719dd08461993ec5afcd3f1827c", + "layout": "IPY_MODEL_5724fc8f9c894548877e5114e0aec685", "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_5eb7e3e5b75e46adb7a3ee089e3b6053", + "style": "IPY_MODEL_08453b8d94d440ad8e97b1a96c05ad6c", "value": 1 } }, - "5f4e139822af43329b4683566c0c2027": { + "f15f8dcc233c4cb89faa5bfb6a88e6fd": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -9457,13 +5733,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_04af830916fa4a26b14696b4efcf3c2f", + "layout": "IPY_MODEL_0ed6e9510ad04e089ba184613e49a2e2", "placeholder": "​", - "style": "IPY_MODEL_69c778d5ea334ae18eda9701f3875ab7", - "value": " 7.03M/? [00:00<00:00, 19.7MB/s]" + "style": "IPY_MODEL_6a13bc44ec254429a05df65523fa1ca1", + "value": " 7.03M/? [00:00<00:00, 19.6MB/s]" } }, - "a13d39ddf38a44f2912d820eca9e4929": { + "311c7e7062d0413f80a4f51944cff6c8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9515,7 +5791,7 @@ "width": null } }, - "9cfa3037b7a046f9be57a7c3be9a5045": { + "a03a4aba133e47ed834d50ee325a6975": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9567,7 +5843,7 @@ "width": null } }, - "d315a80217e2481898df545801789e7b": { + "aa819cb4bceb4cc49320f09276b54898": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -9582,7 +5858,7 @@ "description_width": "" } }, - "22887719dd08461993ec5afcd3f1827c": { + "5724fc8f9c894548877e5114e0aec685": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9634,7 +5910,7 @@ "width": "20px" } }, - "5eb7e3e5b75e46adb7a3ee089e3b6053": { + "08453b8d94d440ad8e97b1a96c05ad6c": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -9650,7 +5926,7 @@ "description_width": "" } }, - "04af830916fa4a26b14696b4efcf3c2f": { + "0ed6e9510ad04e089ba184613e49a2e2": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9702,7 +5978,7 @@ "width": null } }, - "69c778d5ea334ae18eda9701f3875ab7": { + "6a13bc44ec254429a05df65523fa1ca1": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -9717,7 +5993,7 @@ "description_width": "" } }, - "e58eefaeac2a42db9a0bfb2f6f471c23": { + "6a618dbd32ef4118bc9e413169d287ac": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -9732,14 +6008,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_fe48a86f65d246eea2839d5ee4d445c6", - "IPY_MODEL_49013862fd79419ca64308e4e2131311", - "IPY_MODEL_20fdcdb5429949eba8e975c4a22d28e2" + "IPY_MODEL_ad0d6f8cde0f4a2ca32a6e54cef19309", + "IPY_MODEL_f4d8583a5a8d4dc4b8c8e079c0168038", + "IPY_MODEL_ed26d1c02a0d4477bf5b04304b7b832c" ], - "layout": "IPY_MODEL_3f1a48beef7b412e81c84ea3b2a4378d" + "layout": "IPY_MODEL_a346351fcb78424396d2a30e927e856c" } }, - "fe48a86f65d246eea2839d5ee4d445c6": { + "ad0d6f8cde0f4a2ca32a6e54cef19309": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -9754,13 +6030,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_ce1cfdd89b1d478786a7a7bc3770ba2b", + "layout": "IPY_MODEL_b28785efc88b4ccb832216e67d9fee3d", "placeholder": "​", - "style": "IPY_MODEL_439cf012b34649e9b052a14782a9651f", + "style": "IPY_MODEL_9b143140be6b4102bf417131f85e4019", "value": "" } }, - "49013862fd79419ca64308e4e2131311": { + "f4d8583a5a8d4dc4b8c8e079c0168038": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -9776,15 +6052,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_63c1921a52424f25bd55be6da53c6ad3", + "layout": "IPY_MODEL_f6c41337dc864c4d804bf36da613ab3b", "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_d5be6908b5734fb784968a7b02c52db9", + "style": "IPY_MODEL_f81f41bfb70448299c825ca09477b24d", "value": 1 } }, - "20fdcdb5429949eba8e975c4a22d28e2": { + "ed26d1c02a0d4477bf5b04304b7b832c": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -9799,13 +6075,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_0cc3c8bfba744d368cb0beabf9ea3760", + "layout": "IPY_MODEL_696fd526951b446f877ec243683e3884", "placeholder": "​", - "style": "IPY_MODEL_fc965664a2c84c2d8dced4fe473c3f63", - "value": "Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:00<00:00,  3.16it/s]\n" + "style": "IPY_MODEL_ddc500e885b843c4a007917a0f7c58a5", + "value": "Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:00<00:00,  3.07it/s]\n" } }, - "3f1a48beef7b412e81c84ea3b2a4378d": { + "a346351fcb78424396d2a30e927e856c": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9857,7 +6133,7 @@ "width": null } }, - "ce1cfdd89b1d478786a7a7bc3770ba2b": { + "b28785efc88b4ccb832216e67d9fee3d": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9909,7 +6185,7 @@ "width": null } }, - "439cf012b34649e9b052a14782a9651f": { + "9b143140be6b4102bf417131f85e4019": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -9924,7 +6200,7 @@ "description_width": "" } }, - "63c1921a52424f25bd55be6da53c6ad3": { + "f6c41337dc864c4d804bf36da613ab3b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -9976,7 +6252,7 @@ "width": null } }, - "d5be6908b5734fb784968a7b02c52db9": { + "f81f41bfb70448299c825ca09477b24d": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -9992,7 +6268,7 @@ "description_width": "" } }, - "0cc3c8bfba744d368cb0beabf9ea3760": { + "696fd526951b446f877ec243683e3884": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -10044,7 +6320,7 @@ "width": null } }, - "fc965664a2c84c2d8dced4fe473c3f63": { + "ddc500e885b843c4a007917a0f7c58a5": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -10059,7 +6335,7 @@ "description_width": "" } }, - "24449228956d4761a952e94da93d24ef": { + "4a4905fc39064e74a7dd3c4d88dd0da7": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -10074,14 +6350,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_048a1d87757a41ee95300339b8a6a644", - "IPY_MODEL_38fe395a55264a37ad5db1e4f8833948", - "IPY_MODEL_4cb093284a514340b3500b6384540254" + "IPY_MODEL_9cbd611b7f4a4fdfa19bb9bf93c90257", + "IPY_MODEL_b71780eaac064cf6b69ea2d319229a7b", + "IPY_MODEL_b81291f7ee604cacaa5adcd6203f329c" ], - "layout": "IPY_MODEL_1454c5b00864424fac462e494af1feb4" + "layout": "IPY_MODEL_780a254131554e09b9d3a9a96119a63a" } }, - "048a1d87757a41ee95300339b8a6a644": { + "9cbd611b7f4a4fdfa19bb9bf93c90257": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -10096,13 +6372,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_795444fc6d8b45c788cba7a26e14c704", + "layout": "IPY_MODEL_33b847be661b44db921fff01aadb473f", "placeholder": "​", - "style": "IPY_MODEL_24063846766d4f46bc1745aa72267e99", + "style": "IPY_MODEL_966153912c914a57903387926b983b4d", "value": "Processing Files (3 / 3)      : 100%" } }, - "38fe395a55264a37ad5db1e4f8833948": { + "b71780eaac064cf6b69ea2d319229a7b": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -10118,15 +6394,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_33397a51d88c42fd9e56d44d96063fb3", + "layout": "IPY_MODEL_6aed13f0ed3e4ff4a53f8e4795b9d148", "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_f80c6ba4d3804855bff3c68e4f8bb2ce", + "style": "IPY_MODEL_3293c29f428d4de9867021ab0119c7be", "value": 1 } }, - "4cb093284a514340b3500b6384540254": { + "b81291f7ee604cacaa5adcd6203f329c": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -10141,13 +6417,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_39e32c8487d248689d9f23ce4711a225", + "layout": "IPY_MODEL_b76b566ccd1741a1817db0346c58a6e6", "placeholder": "​", - "style": "IPY_MODEL_8c5811d1ada7419fbe0911a19a55b482", + "style": "IPY_MODEL_89e84faa23ec4b348b52459154672479", "value": " 13.6MB / 13.6MB,  0.00B/s  " } }, - "1454c5b00864424fac462e494af1feb4": { + "780a254131554e09b9d3a9a96119a63a": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -10199,7 +6475,7 @@ "width": null } }, - "795444fc6d8b45c788cba7a26e14c704": { + "33b847be661b44db921fff01aadb473f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -10251,7 +6527,7 @@ "width": null } }, - "24063846766d4f46bc1745aa72267e99": { + "966153912c914a57903387926b983b4d": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -10266,7 +6542,7 @@ "description_width": "" } }, - "33397a51d88c42fd9e56d44d96063fb3": { + "6aed13f0ed3e4ff4a53f8e4795b9d148": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -10318,7 +6594,7 @@ "width": "20px" } }, - "f80c6ba4d3804855bff3c68e4f8bb2ce": { + "3293c29f428d4de9867021ab0119c7be": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -10334,7 +6610,7 @@ "description_width": "" } }, - "39e32c8487d248689d9f23ce4711a225": { + "b76b566ccd1741a1817db0346c58a6e6": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -10386,7 +6662,7 @@ "width": null } }, - "8c5811d1ada7419fbe0911a19a55b482": { + "89e84faa23ec4b348b52459154672479": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -10401,7 +6677,7 @@ "description_width": "" } }, - "c2372bfb130d45d88233800e6a95af01": { + "61280e79049443d2b9b44718c7d3734e": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -10416,14 +6692,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_8722be7f942340eaa77bf1492ff3aa7e", - "IPY_MODEL_f31491b2308f4195b2d61e807f4749c1", - "IPY_MODEL_f27313d601f14c73815c14a9996c2cdf" + "IPY_MODEL_63a3a983dc8d49469c748dfc5386462b", + "IPY_MODEL_da558dc6cdcb402bb3a9b3caa8a62e7e", + "IPY_MODEL_f769c624319344ad8550824a54253933" ], - "layout": "IPY_MODEL_8e1bb97bb9d9497891ea1ee1483cf350" + "layout": "IPY_MODEL_815cba23e9c24ab4a9db8105d6c3424d" } }, - "8722be7f942340eaa77bf1492ff3aa7e": { + "63a3a983dc8d49469c748dfc5386462b": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -10438,13 +6714,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_cbf604590e7d4aea9e8423448a30ce2d", + "layout": "IPY_MODEL_9e713c6fd6dd4465ab351b3421e60c06", "placeholder": "​", - "style": "IPY_MODEL_e0a312eab6ba4c0f935aeb2b74517565", + "style": "IPY_MODEL_32d730d1a8ee4ff5ac0783f341134e08", "value": "New Data Upload               : " } }, - "f31491b2308f4195b2d61e807f4749c1": { + "da558dc6cdcb402bb3a9b3caa8a62e7e": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -10460,15 +6736,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_87020498ca03494e975e9b1d9e17dd8a", + "layout": "IPY_MODEL_fb86e80670d24b4da7927cbc870db739", "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_3ab6858797c34fd4abd5c2cb843488cf", + "style": "IPY_MODEL_db56169082574594bcfd40adcdfa624b", "value": 0 } }, - "f27313d601f14c73815c14a9996c2cdf": { + "f769c624319344ad8550824a54253933": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -10483,13 +6759,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_d28c16e27fd343a28f5a0f785840a83d", + "layout": "IPY_MODEL_f1794020f4dd49b7969a283746fa18aa", "placeholder": "​", - "style": "IPY_MODEL_49dde296c20841cc8743434084c457b2", + "style": "IPY_MODEL_d3fec749dbfd477894a01b04a7ee3b11", "value": "  0.00B /  0.00B,  0.00B/s  " } }, - "8e1bb97bb9d9497891ea1ee1483cf350": { + "815cba23e9c24ab4a9db8105d6c3424d": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -10541,7 +6817,7 @@ "width": null } }, - "cbf604590e7d4aea9e8423448a30ce2d": { + "9e713c6fd6dd4465ab351b3421e60c06": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -10593,7 +6869,7 @@ "width": null } }, - "e0a312eab6ba4c0f935aeb2b74517565": { + "32d730d1a8ee4ff5ac0783f341134e08": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -10608,7 +6884,7 @@ "description_width": "" } }, - "87020498ca03494e975e9b1d9e17dd8a": { + "fb86e80670d24b4da7927cbc870db739": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -10660,7 +6936,7 @@ "width": "20px" } }, - "3ab6858797c34fd4abd5c2cb843488cf": { + "db56169082574594bcfd40adcdfa624b": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -10676,7 +6952,7 @@ "description_width": "" } }, - "d28c16e27fd343a28f5a0f785840a83d": { + "f1794020f4dd49b7969a283746fa18aa": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -10728,7 +7004,7 @@ "width": null } }, - "49dde296c20841cc8743434084c457b2": { + "d3fec749dbfd477894a01b04a7ee3b11": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -10743,7 +7019,7 @@ "description_width": "" } }, - "d8d1d1e2cd0d4fd3948a8dc0ac3b72b1": { + "7eb45608f0e14f19bcf77dd7f2671068": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -10758,14 +7034,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_a230d525e65e430fb082bbd871f7efc1", - "IPY_MODEL_11ac0f8c06804471bd799766ca39a9ef", - "IPY_MODEL_0b7cb3fad35d47ab963e3065d5edbb66" + "IPY_MODEL_d575411df04e4f7b8624c8e6f11b6b18", + "IPY_MODEL_40662e0043814cb29e98a50758d631f3", + "IPY_MODEL_82d75aeb4a1c4b3d805a711f4e4af615" ], - "layout": "IPY_MODEL_e9697ae9d4b5456eaeb9d61a618ca464" + "layout": "IPY_MODEL_2724fb37c20a4d3b93bb9f12c63657cc" } }, - "a230d525e65e430fb082bbd871f7efc1": { + "d575411df04e4f7b8624c8e6f11b6b18": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -10780,13 +7056,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_f73b93eed0a844e0afa66c8ff3ea6e2b", + "layout": "IPY_MODEL_085225f0a24d46a191a3d6f7c01ac5bc", "placeholder": "​", - "style": "IPY_MODEL_30b84b30e0024cc884d5124a4a9561ce", + "style": "IPY_MODEL_464236cc3c5a4428b15df1909b11fc5c", "value": "  ...llm-trl/training_args.bin: 100%" } }, - "11ac0f8c06804471bd799766ca39a9ef": { + "40662e0043814cb29e98a50758d631f3": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -10802,15 +7078,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_763cadd87299481ebe1d7fdaa04718f0", - "max": 7185, + "layout": "IPY_MODEL_08d4c4ce64df46689e88a61c1cf3ec8d", + "max": 7249, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_2d1d125afd42468db94012578ba6a9b0", - "value": 7185 + "style": "IPY_MODEL_4c3a040ad61d4de2843dc203628b9576", + "value": 7249 } }, - "0b7cb3fad35d47ab963e3065d5edbb66": { + "82d75aeb4a1c4b3d805a711f4e4af615": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -10825,13 +7101,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_8cd68cb0e7fb4d4cb4a34c3f36942abc", + "layout": "IPY_MODEL_c3c75015bc854f6f8806f4ce8bc4d2eb", "placeholder": "​", - "style": "IPY_MODEL_469f0b30119b4c5aaf9bfa17e5cb73e9", - "value": " 7.18kB / 7.18kB            " + "style": "IPY_MODEL_dba44ee614e145db925e08351868a058", + "value": " 7.25kB / 7.25kB            " } }, - "e9697ae9d4b5456eaeb9d61a618ca464": { + "2724fb37c20a4d3b93bb9f12c63657cc": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -10883,7 +7159,7 @@ "width": null } }, - "f73b93eed0a844e0afa66c8ff3ea6e2b": { + "085225f0a24d46a191a3d6f7c01ac5bc": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -10935,7 +7211,7 @@ "width": null } }, - "30b84b30e0024cc884d5124a4a9561ce": { + "464236cc3c5a4428b15df1909b11fc5c": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -10950,7 +7226,7 @@ "description_width": "" } }, - "763cadd87299481ebe1d7fdaa04718f0": { + "08d4c4ce64df46689e88a61c1cf3ec8d": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11002,7 +7278,7 @@ "width": null } }, - "2d1d125afd42468db94012578ba6a9b0": { + "4c3a040ad61d4de2843dc203628b9576": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -11018,7 +7294,7 @@ "description_width": "" } }, - "8cd68cb0e7fb4d4cb4a34c3f36942abc": { + "c3c75015bc854f6f8806f4ce8bc4d2eb": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11070,7 +7346,7 @@ "width": null } }, - "469f0b30119b4c5aaf9bfa17e5cb73e9": { + "dba44ee614e145db925e08351868a058": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -11085,7 +7361,7 @@ "description_width": "" } }, - "5ed233a955b14342955f111576a395d9": { + "cbf1da1278b4481c9fe7e8bb3e4ae240": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -11100,14 +7376,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_f522922ce1fd46998a429ea0776e3b59", - "IPY_MODEL_800d09a2000c4d6987fc22b8f27b9f99", - "IPY_MODEL_d7ca74a02a4941e5b8aa2391d0d9e295" + "IPY_MODEL_249c1285734a45c8a107b106add81084", + "IPY_MODEL_e281a02dc250489998385d58632d5b1d", + "IPY_MODEL_9bdd8c3205d2400fb6f4c5e21df4e4d1" ], - "layout": "IPY_MODEL_b68d1f1de1bc400e8603e0060dcf7b97" + "layout": "IPY_MODEL_d008369537f54fa9994a09969bfc7a8e" } }, - "f522922ce1fd46998a429ea0776e3b59": { + "249c1285734a45c8a107b106add81084": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -11122,13 +7398,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_4c4c1787146242e483c4e600a06a7f59", + "layout": "IPY_MODEL_29252b97ac0640308e4210a8d140dc10", "placeholder": "​", - "style": "IPY_MODEL_06cad97cc9d8490ab39b4ae96d524a96", + "style": "IPY_MODEL_8f0bcc39527142de94cf2538b1b8484f", "value": "  ...adapter_model.safetensors: 100%" } }, - "800d09a2000c4d6987fc22b8f27b9f99": { + "e281a02dc250489998385d58632d5b1d": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -11144,15 +7420,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_571227481e684c088b614161965cd29e", + "layout": "IPY_MODEL_05767d5e2f4941e8ae0254f173e63bc4", "max": 2175168, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_5442061b98704a4989f6a765634d0e96", + "style": "IPY_MODEL_67ab35173a674254b5a3af041c3de705", "value": 2175168 } }, - "d7ca74a02a4941e5b8aa2391d0d9e295": { + "9bdd8c3205d2400fb6f4c5e21df4e4d1": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -11167,13 +7443,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_0336d0845ba14dc19179b3a4f6581c55", + "layout": "IPY_MODEL_261eb91f9a054e7d8743c21bb60d5c83", "placeholder": "​", - "style": "IPY_MODEL_2c71dc6b8d4443c7aeda53a49829216f", + "style": "IPY_MODEL_3e911c4bbe61404b96d7e4e839c34afe", "value": " 2.18MB / 2.18MB            " } }, - "b68d1f1de1bc400e8603e0060dcf7b97": { + "d008369537f54fa9994a09969bfc7a8e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11225,7 +7501,7 @@ "width": null } }, - "4c4c1787146242e483c4e600a06a7f59": { + "29252b97ac0640308e4210a8d140dc10": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11277,7 +7553,7 @@ "width": null } }, - "06cad97cc9d8490ab39b4ae96d524a96": { + "8f0bcc39527142de94cf2538b1b8484f": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -11292,7 +7568,7 @@ "description_width": "" } }, - "571227481e684c088b614161965cd29e": { + "05767d5e2f4941e8ae0254f173e63bc4": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11344,7 +7620,7 @@ "width": null } }, - "5442061b98704a4989f6a765634d0e96": { + "67ab35173a674254b5a3af041c3de705": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -11360,7 +7636,7 @@ "description_width": "" } }, - "0336d0845ba14dc19179b3a4f6581c55": { + "261eb91f9a054e7d8743c21bb60d5c83": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11412,7 +7688,7 @@ "width": null } }, - "2c71dc6b8d4443c7aeda53a49829216f": { + "3e911c4bbe61404b96d7e4e839c34afe": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -11427,7 +7703,7 @@ "description_width": "" } }, - "e71e5e084c22439d9cd3ef007beac264": { + "3b316f8bc0c14eb5b56bdb216ca557af": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -11442,14 +7718,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_4b3320e6d1bc404a9401db13702bed43", - "IPY_MODEL_4ac8498aa540457c93d21d428e7b0846", - "IPY_MODEL_77f033d7354d4b53b6dc7e2acd57e3fe" + "IPY_MODEL_25c81bf175fe4233a9741f112fab5e4e", + "IPY_MODEL_47d2f9e33b9147a6acc218d00141d6a3", + "IPY_MODEL_6ab9dbe545fc4eca98736951bded7ab7" ], - "layout": "IPY_MODEL_c98671ae1bc2427a89a8920e71dd9224" + "layout": "IPY_MODEL_174b81a6864c4e5084e3f7c0d4387285" } }, - "4b3320e6d1bc404a9401db13702bed43": { + "25c81bf175fe4233a9741f112fab5e4e": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -11464,13 +7740,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_4dcd6d0e0ade4ec6aa2ac334185f54e2", + "layout": "IPY_MODEL_78cfb0eed7154ac8b3af8824f42db4c1", "placeholder": "​", - "style": "IPY_MODEL_dbda791e57b241eab6e434e500b71555", + "style": "IPY_MODEL_82ad899a03c8423fb58a4170760585e5", "value": "  ...O-vllm-trl/tokenizer.json: 100%" } }, - "4ac8498aa540457c93d21d428e7b0846": { + "47d2f9e33b9147a6acc218d00141d6a3": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -11486,15 +7762,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_59483bad9aad4a8c95bc63042747666f", + "layout": "IPY_MODEL_e43a50b7db9149ae88e20e7f3d03bd9c", "max": 11418433, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_4c8532981d3d49bdbb40c732c642d897", + "style": "IPY_MODEL_fa447aeca8a94f6894fea23a8fb6ff0e", "value": 11418433 } }, - "77f033d7354d4b53b6dc7e2acd57e3fe": { + "6ab9dbe545fc4eca98736951bded7ab7": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -11509,13 +7785,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_3b5c0b62c75a4663b9cd5fe11c05f2d1", + "layout": "IPY_MODEL_5ee1f8c92f324ce9bf92855ba22a9013", "placeholder": "​", - "style": "IPY_MODEL_2a15e209d88744bc867918b0ab5d0cdc", + "style": "IPY_MODEL_d23ce2884e484c3b81eedb86527a1006", "value": " 11.4MB / 11.4MB            " } }, - "c98671ae1bc2427a89a8920e71dd9224": { + "174b81a6864c4e5084e3f7c0d4387285": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11567,7 +7843,7 @@ "width": null } }, - "4dcd6d0e0ade4ec6aa2ac334185f54e2": { + "78cfb0eed7154ac8b3af8824f42db4c1": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11619,7 +7895,7 @@ "width": null } }, - "dbda791e57b241eab6e434e500b71555": { + "82ad899a03c8423fb58a4170760585e5": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -11634,7 +7910,7 @@ "description_width": "" } }, - "59483bad9aad4a8c95bc63042747666f": { + "e43a50b7db9149ae88e20e7f3d03bd9c": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11686,7 +7962,7 @@ "width": null } }, - "4c8532981d3d49bdbb40c732c642d897": { + "fa447aeca8a94f6894fea23a8fb6ff0e": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -11702,7 +7978,7 @@ "description_width": "" } }, - "3b5c0b62c75a4663b9cd5fe11c05f2d1": { + "5ee1f8c92f324ce9bf92855ba22a9013": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11754,7 +8030,7 @@ "width": null } }, - "2a15e209d88744bc867918b0ab5d0cdc": { + "d23ce2884e484c3b81eedb86527a1006": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -11769,7 +8045,7 @@ "description_width": "" } }, - "94b79a811305416b9a442f5bbc5e5636": { + "13b47839181a4af18bc633ed343e3f27": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -11784,14 +8060,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_da01ee1365ea478084d323e046a90f60", - "IPY_MODEL_d47c69a3a2434f3da81cd86780ec4df7", - "IPY_MODEL_6d38d7a5f173427d9970b2f8a6cee941" + "IPY_MODEL_971e8aa8c1524c7ea802b067fc92baed", + "IPY_MODEL_78ad01990aa046879ab5788a53b0bb98", + "IPY_MODEL_0cab2756be0d4c1babf632b7172f49d8" ], - "layout": "IPY_MODEL_96fcc4033bee4b09856e3c1c76064192" + "layout": "IPY_MODEL_2254389c32714a84a4bdb1ea693c779b" } }, - "da01ee1365ea478084d323e046a90f60": { + "971e8aa8c1524c7ea802b067fc92baed": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -11806,13 +8082,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_ff1d855281c644839b0a79be58f7d51b", + "layout": "IPY_MODEL_a867d54613e6418990ef8218e3f98e52", "placeholder": "​", - "style": "IPY_MODEL_856064ebeee7430e9cbe9b3b406ab597", + "style": "IPY_MODEL_f24d5808d2dd48909ad11226e607df2b", "value": "Processing Files (3 / 3)      : 100%" } }, - "d47c69a3a2434f3da81cd86780ec4df7": { + "78ad01990aa046879ab5788a53b0bb98": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -11828,15 +8104,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_4e691f29e56f4b459859f897954b98dc", + "layout": "IPY_MODEL_0108fc90142143649f204472accc2c1c", "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_d49e8a29926a44f782e73a660d64ed97", + "style": "IPY_MODEL_ef8a8cee818c49de8c4b550a2ced472c", "value": 1 } }, - "6d38d7a5f173427d9970b2f8a6cee941": { + "0cab2756be0d4c1babf632b7172f49d8": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -11851,13 +8127,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_e854754fedae47428564740e30ae8ee4", + "layout": "IPY_MODEL_27802c3021924a07b23f3f3f4fb80631", "placeholder": "​", - "style": "IPY_MODEL_4a0e48223abb4253b118dd7e21a9ac2f", + "style": "IPY_MODEL_e9147b82df4c4c9c804609e1093f416a", "value": " 13.6MB / 13.6MB,  0.00B/s  " } }, - "96fcc4033bee4b09856e3c1c76064192": { + "2254389c32714a84a4bdb1ea693c779b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11909,7 +8185,7 @@ "width": null } }, - "ff1d855281c644839b0a79be58f7d51b": { + "a867d54613e6418990ef8218e3f98e52": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -11961,7 +8237,7 @@ "width": null } }, - "856064ebeee7430e9cbe9b3b406ab597": { + "f24d5808d2dd48909ad11226e607df2b": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -11976,7 +8252,7 @@ "description_width": "" } }, - "4e691f29e56f4b459859f897954b98dc": { + "0108fc90142143649f204472accc2c1c": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12028,7 +8304,7 @@ "width": "20px" } }, - "d49e8a29926a44f782e73a660d64ed97": { + "ef8a8cee818c49de8c4b550a2ced472c": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -12044,7 +8320,7 @@ "description_width": "" } }, - "e854754fedae47428564740e30ae8ee4": { + "27802c3021924a07b23f3f3f4fb80631": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12096,7 +8372,7 @@ "width": null } }, - "4a0e48223abb4253b118dd7e21a9ac2f": { + "e9147b82df4c4c9c804609e1093f416a": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -12111,7 +8387,7 @@ "description_width": "" } }, - "7353cb8a39f44e3793a9d14974c8eefa": { + "210f1f1b481f4d73aeaeefda52ab2765": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -12126,14 +8402,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_977a61c8d5ff43168b018d41c163fba4", - "IPY_MODEL_6177906927984900842e9b25f8f19bbb", - "IPY_MODEL_b6e939cfbb0947cdb1c1bdc3ebed9a82" + "IPY_MODEL_d3a6cd8cab6a4f62a54fbab6bc2f8fdb", + "IPY_MODEL_035ab76a836b47f3a3b4dd4747b93cd7", + "IPY_MODEL_365064fd3840402eae1d9eae1d0b2675" ], - "layout": "IPY_MODEL_ff501fc0e8574cf38884e0eec9b6d4c4" + "layout": "IPY_MODEL_a72c092f943942179bd2fe15d1a5405f" } }, - "977a61c8d5ff43168b018d41c163fba4": { + "d3a6cd8cab6a4f62a54fbab6bc2f8fdb": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -12148,13 +8424,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_93c7b1f6a5724b93bc349c36893e28f5", + "layout": "IPY_MODEL_95407380ef46471d847214dd9a213b1e", "placeholder": "​", - "style": "IPY_MODEL_8ec1195d53c44ac7abb7b2d1031b4ee0", + "style": "IPY_MODEL_243479bef39c44048efdba8e815356d3", "value": "New Data Upload               : " } }, - "6177906927984900842e9b25f8f19bbb": { + "035ab76a836b47f3a3b4dd4747b93cd7": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -12170,15 +8446,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_e0694321451a4bec85c2665fe3d1f058", + "layout": "IPY_MODEL_1979581d0f134a848a83bc63bdd49e8e", "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_852adecfa8834dc399772f7510cf37f9", + "style": "IPY_MODEL_bc2bdaffe13143ec9a01ef174ae67e46", "value": 0 } }, - "b6e939cfbb0947cdb1c1bdc3ebed9a82": { + "365064fd3840402eae1d9eae1d0b2675": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -12193,13 +8469,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_dad3d92ad15d4974b16cc3136d8eed90", + "layout": "IPY_MODEL_ace8f9ae16f64106a682508d4bfbd5eb", "placeholder": "​", - "style": "IPY_MODEL_be15a009b42f4f0bbd3123a6c0ca7b5c", + "style": "IPY_MODEL_bdfe3a68362747058a657611173ca684", "value": "  0.00B /  0.00B,  0.00B/s  " } }, - "ff501fc0e8574cf38884e0eec9b6d4c4": { + "a72c092f943942179bd2fe15d1a5405f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12251,7 +8527,7 @@ "width": null } }, - "93c7b1f6a5724b93bc349c36893e28f5": { + "95407380ef46471d847214dd9a213b1e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12303,7 +8579,7 @@ "width": null } }, - "8ec1195d53c44ac7abb7b2d1031b4ee0": { + "243479bef39c44048efdba8e815356d3": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -12318,7 +8594,7 @@ "description_width": "" } }, - "e0694321451a4bec85c2665fe3d1f058": { + "1979581d0f134a848a83bc63bdd49e8e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12370,7 +8646,7 @@ "width": "20px" } }, - "852adecfa8834dc399772f7510cf37f9": { + "bc2bdaffe13143ec9a01ef174ae67e46": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -12386,7 +8662,7 @@ "description_width": "" } }, - "dad3d92ad15d4974b16cc3136d8eed90": { + "ace8f9ae16f64106a682508d4bfbd5eb": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12438,7 +8714,7 @@ "width": null } }, - "be15a009b42f4f0bbd3123a6c0ca7b5c": { + "bdfe3a68362747058a657611173ca684": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -12453,7 +8729,7 @@ "description_width": "" } }, - "d627bf1f35f640339395770218dd4efe": { + "d1c8bf2bdfa643bcb1da5602ca6e955e": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -12468,14 +8744,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_d3b0e9769ac44c89b744b0e72d776298", - "IPY_MODEL_e9fc916db6ba40c886658b0d6193997a", - "IPY_MODEL_5408aecda830430b8ae0178bb8c2c176" + "IPY_MODEL_3a8416f53f794f699b12ee00d83c90c7", + "IPY_MODEL_becd166518ad4719bb992e96f8d61986", + "IPY_MODEL_54c4feb98af24d6cab772c077417c109" ], - "layout": "IPY_MODEL_402171d79af94c71b414f0c81db44b93" + "layout": "IPY_MODEL_8f3db48c42be4d51ab98e9dbd21771d6" } }, - "d3b0e9769ac44c89b744b0e72d776298": { + "3a8416f53f794f699b12ee00d83c90c7": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -12490,13 +8766,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_b374913bd4044a3ea47599db2a064f35", + "layout": "IPY_MODEL_81fa1c82f7e741abab99fb7d9f977487", "placeholder": "​", - "style": "IPY_MODEL_3dff7dab14b04a788b541e4d0fe3a245", + "style": "IPY_MODEL_5a6c3b588111498b8acfae4eb94c7403", "value": "  ...llm-trl/training_args.bin: 100%" } }, - "e9fc916db6ba40c886658b0d6193997a": { + "becd166518ad4719bb992e96f8d61986": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -12512,15 +8788,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_e3210fea513e45d1b7aed645b4e9f0d9", - "max": 7185, + "layout": "IPY_MODEL_f6e2c182f2cd4996b855b248fdbeed0a", + "max": 7249, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_517db374d571445fa78c1eb700d40379", - "value": 7185 + "style": "IPY_MODEL_ff70330750ed405eb1100496531c843e", + "value": 7249 } }, - "5408aecda830430b8ae0178bb8c2c176": { + "54c4feb98af24d6cab772c077417c109": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -12535,13 +8811,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_34b0de046ec2406f9ba59e7dfd159ddc", + "layout": "IPY_MODEL_d429b5f9a8184dbab68149429fb5b4e1", "placeholder": "​", - "style": "IPY_MODEL_426792df69ce454cbbc1cbb89be08802", - "value": " 7.18kB / 7.18kB            " + "style": "IPY_MODEL_30f6cc4c53a640e3abaeafae1e7af8b9", + "value": " 7.25kB / 7.25kB            " } }, - "402171d79af94c71b414f0c81db44b93": { + "8f3db48c42be4d51ab98e9dbd21771d6": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12593,7 +8869,7 @@ "width": null } }, - "b374913bd4044a3ea47599db2a064f35": { + "81fa1c82f7e741abab99fb7d9f977487": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12645,7 +8921,7 @@ "width": null } }, - "3dff7dab14b04a788b541e4d0fe3a245": { + "5a6c3b588111498b8acfae4eb94c7403": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -12660,7 +8936,7 @@ "description_width": "" } }, - "e3210fea513e45d1b7aed645b4e9f0d9": { + "f6e2c182f2cd4996b855b248fdbeed0a": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12712,7 +8988,7 @@ "width": null } }, - "517db374d571445fa78c1eb700d40379": { + "ff70330750ed405eb1100496531c843e": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -12728,7 +9004,7 @@ "description_width": "" } }, - "34b0de046ec2406f9ba59e7dfd159ddc": { + "d429b5f9a8184dbab68149429fb5b4e1": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12780,7 +9056,7 @@ "width": null } }, - "426792df69ce454cbbc1cbb89be08802": { + "30f6cc4c53a640e3abaeafae1e7af8b9": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -12795,7 +9071,7 @@ "description_width": "" } }, - "8162159b397145a9a53d2328f10875fa": { + "177544738fe54eafab020e721b825d4c": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -12810,14 +9086,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_80c822dbe1d8488581f303ff9199ac4b", - "IPY_MODEL_691e6bbeca8b4930a6b4b7ee675f2d5c", - "IPY_MODEL_9aa3b89510094a94b01c69cffeb42ceb" + "IPY_MODEL_13a5d9ffe70f4eaea1d2fcbc233a1e11", + "IPY_MODEL_7606d85131d4485eb80c0f3a59e41043", + "IPY_MODEL_f06878fa8117458c8f66dfc1772dbed0" ], - "layout": "IPY_MODEL_df86ed135ad948b2aa90d0717975944d" + "layout": "IPY_MODEL_309cd48a0a6c4ad08ae7a02716e4c3bd" } }, - "80c822dbe1d8488581f303ff9199ac4b": { + "13a5d9ffe70f4eaea1d2fcbc233a1e11": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -12832,13 +9108,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_be67d7274f0d4db38a02d790a34bb266", + "layout": "IPY_MODEL_32c24280dba14f3080b73f7ad437d7af", "placeholder": "​", - "style": "IPY_MODEL_05fa1783785a42ada12319d1625ac5b0", + "style": "IPY_MODEL_fa73ed0177334daf9eb5efc46125e3d1", "value": "  ...adapter_model.safetensors: 100%" } }, - "691e6bbeca8b4930a6b4b7ee675f2d5c": { + "7606d85131d4485eb80c0f3a59e41043": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -12854,15 +9130,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_b9705036732a43a3ac62c0119f504809", + "layout": "IPY_MODEL_3ac2168b52544123b6279ae4ec159090", "max": 2175168, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_f63f8445964646f8a278c076d9a55248", + "style": "IPY_MODEL_a1faaeac2589460f8706f6389721399e", "value": 2175168 } }, - "9aa3b89510094a94b01c69cffeb42ceb": { + "f06878fa8117458c8f66dfc1772dbed0": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -12877,13 +9153,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_0202ba576bd743fa9adbac32334d220f", + "layout": "IPY_MODEL_679a0d1988ee4a51852542dfc422afc4", "placeholder": "​", - "style": "IPY_MODEL_f2aaef56ac234cb5a3da275e99290200", + "style": "IPY_MODEL_93609c63d9384091a63bac2d185e4ac7", "value": " 2.18MB / 2.18MB            " } }, - "df86ed135ad948b2aa90d0717975944d": { + "309cd48a0a6c4ad08ae7a02716e4c3bd": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12935,7 +9211,7 @@ "width": null } }, - "be67d7274f0d4db38a02d790a34bb266": { + "32c24280dba14f3080b73f7ad437d7af": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -12987,7 +9263,7 @@ "width": null } }, - "05fa1783785a42ada12319d1625ac5b0": { + "fa73ed0177334daf9eb5efc46125e3d1": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -13002,7 +9278,7 @@ "description_width": "" } }, - "b9705036732a43a3ac62c0119f504809": { + "3ac2168b52544123b6279ae4ec159090": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -13054,7 +9330,7 @@ "width": null } }, - "f63f8445964646f8a278c076d9a55248": { + "a1faaeac2589460f8706f6389721399e": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -13070,7 +9346,7 @@ "description_width": "" } }, - "0202ba576bd743fa9adbac32334d220f": { + "679a0d1988ee4a51852542dfc422afc4": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -13122,7 +9398,7 @@ "width": null } }, - "f2aaef56ac234cb5a3da275e99290200": { + "93609c63d9384091a63bac2d185e4ac7": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -13137,7 +9413,7 @@ "description_width": "" } }, - "87adeb2b42734c3895d3c150838b0fef": { + "4147642626e344bbafc83fad079e1586": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -13152,14 +9428,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_24b1e1231df1485480cc9396769ee5f4", - "IPY_MODEL_d375824c68e04ac5861503b776d937ad", - "IPY_MODEL_05696af5f2fd46c8be1f808d2d83b7f4" + "IPY_MODEL_344d2c5fec1149c692d04f0a73932da7", + "IPY_MODEL_8cd39f08f5b1400ab0400800b61c58db", + "IPY_MODEL_6da0a2cfdd234d46a52e2a66a3072ef1" ], - "layout": "IPY_MODEL_d5f6137d88a94cc6b5eeba88b5fa250c" + "layout": "IPY_MODEL_32316dc9369f4c6a8731efbb40b91387" } }, - "24b1e1231df1485480cc9396769ee5f4": { + "344d2c5fec1149c692d04f0a73932da7": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -13174,13 +9450,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_6ed41772918f44ce9a17de77359c0e49", + "layout": "IPY_MODEL_a0e3709c53fe440082c8c035c64d5ab9", "placeholder": "​", - "style": "IPY_MODEL_c6a2e2e8ff9f4a319ace0ec9a0eb5b4b", + "style": "IPY_MODEL_de804e2e009640cca664410a100eb685", "value": "  ...O-vllm-trl/tokenizer.json: 100%" } }, - "d375824c68e04ac5861503b776d937ad": { + "8cd39f08f5b1400ab0400800b61c58db": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -13196,15 +9472,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_5de7bcb9d2d743e6be739a727fb0196c", + "layout": "IPY_MODEL_025a62229f914f199761bb6ddacf6cce", "max": 11418433, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_d395da4881ed4e80afe16ae3b7957754", + "style": "IPY_MODEL_ef2ac10d1dfc47798a32c12790d58476", "value": 11418433 } }, - "05696af5f2fd46c8be1f808d2d83b7f4": { + "6da0a2cfdd234d46a52e2a66a3072ef1": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -13219,13 +9495,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_52c9252b951f4a448c5fc37e98674ec9", + "layout": "IPY_MODEL_ea2a7baa396947f0a6b267ba02bb4258", "placeholder": "​", - "style": "IPY_MODEL_a13a7e158c53426a88895cb1b27d8620", + "style": "IPY_MODEL_22c28bbd11e546ac8c802caa8661e6f0", "value": " 11.4MB / 11.4MB            " } }, - "d5f6137d88a94cc6b5eeba88b5fa250c": { + "32316dc9369f4c6a8731efbb40b91387": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -13277,7 +9553,7 @@ "width": null } }, - "6ed41772918f44ce9a17de77359c0e49": { + "a0e3709c53fe440082c8c035c64d5ab9": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -13329,7 +9605,7 @@ "width": null } }, - "c6a2e2e8ff9f4a319ace0ec9a0eb5b4b": { + "de804e2e009640cca664410a100eb685": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -13344,7 +9620,7 @@ "description_width": "" } }, - "5de7bcb9d2d743e6be739a727fb0196c": { + "025a62229f914f199761bb6ddacf6cce": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -13396,7 +9672,7 @@ "width": null } }, - "d395da4881ed4e80afe16ae3b7957754": { + "ef2ac10d1dfc47798a32c12790d58476": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -13412,7 +9688,7 @@ "description_width": "" } }, - "52c9252b951f4a448c5fc37e98674ec9": { + "ea2a7baa396947f0a6b267ba02bb4258": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -13464,7 +9740,7 @@ "width": null } }, - "a13a7e158c53426a88895cb1b27d8620": { + "22c28bbd11e546ac8c802caa8661e6f0": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -13479,7 +9755,7 @@ "description_width": "" } }, - "29f01bbb3f4641fb8dd48f75c13fe73f": { + "72c97ddd0f914f03bbd737cd3684af83": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -13494,14 +9770,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_b4e71f7a844542d4931a471127711eb8", - "IPY_MODEL_ed07d63bcc684c9ea68e0e344ce10e1f", - "IPY_MODEL_074bfc147c2147e9aef6a2c0886fabb3" + "IPY_MODEL_3223c35b9d164a66af6e5adf0eda6ecc", + "IPY_MODEL_8d53711ed464459ba3a4a7fc78e75dc1", + "IPY_MODEL_6a5c29a7044747a59de4a0b8ba29a431" ], - "layout": "IPY_MODEL_acefc53329024ff6b81b3468103c270a" + "layout": "IPY_MODEL_ba199cb427a24d9aa06d0773e6a4753c" } }, - "b4e71f7a844542d4931a471127711eb8": { + "3223c35b9d164a66af6e5adf0eda6ecc": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -13516,13 +9792,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_75e2391ee60b490083d6f1297da57c22", + "layout": "IPY_MODEL_9440c1ba99e84a7d8f8669fbf97a04c0", "placeholder": "​", - "style": "IPY_MODEL_affadddec7724fbe82d28f71b426180c", + "style": "IPY_MODEL_5597c5332a25452e86fbede66c3d6903", "value": "adapter_config.json: 100%" } }, - "ed07d63bcc684c9ea68e0e344ce10e1f": { + "8d53711ed464459ba3a4a7fc78e75dc1": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -13538,15 +9814,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_e7cdf617673241b09dd63136ab405d79", + "layout": "IPY_MODEL_d83b7c1398e04577baee7e17ec35cef6", "max": 857, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_41ae2beb33b84f778e6a317eab20ec69", + "style": "IPY_MODEL_6e6eabc156d440358daf8ceca52493f7", "value": 857 } }, - "074bfc147c2147e9aef6a2c0886fabb3": { + "6a5c29a7044747a59de4a0b8ba29a431": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -13561,13 +9837,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_b03682c5901949adaf93e8bdbf480e92", + "layout": "IPY_MODEL_5c63b58b89b54dc7b190909629dd3051", "placeholder": "​", - "style": "IPY_MODEL_d2de608d3f2f4f61baae4694a5a8de0a", - "value": " 857/857 [00:00<00:00, 108kB/s]" + "style": "IPY_MODEL_e865c3619d7a4f0fb07b09bffb6465fa", + "value": " 857/857 [00:00<00:00, 106kB/s]" } }, - "acefc53329024ff6b81b3468103c270a": { + "ba199cb427a24d9aa06d0773e6a4753c": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -13619,7 +9895,7 @@ "width": null } }, - "75e2391ee60b490083d6f1297da57c22": { + "9440c1ba99e84a7d8f8669fbf97a04c0": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -13671,7 +9947,7 @@ "width": null } }, - "affadddec7724fbe82d28f71b426180c": { + "5597c5332a25452e86fbede66c3d6903": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -13686,7 +9962,7 @@ "description_width": "" } }, - "e7cdf617673241b09dd63136ab405d79": { + "d83b7c1398e04577baee7e17ec35cef6": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -13738,7 +10014,7 @@ "width": null } }, - "41ae2beb33b84f778e6a317eab20ec69": { + "6e6eabc156d440358daf8ceca52493f7": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -13754,7 +10030,7 @@ "description_width": "" } }, - "b03682c5901949adaf93e8bdbf480e92": { + "5c63b58b89b54dc7b190909629dd3051": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -13806,7 +10082,7 @@ "width": null } }, - "d2de608d3f2f4f61baae4694a5a8de0a": { + "e865c3619d7a4f0fb07b09bffb6465fa": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -13821,7 +10097,7 @@ "description_width": "" } }, - "62bef399c49c4e9b8ffb183c39887495": { + "9f3346e32e47498bab1076cfe404b359": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -13836,14 +10112,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_60bfea04814142dfaacda9aa258de9f8", - "IPY_MODEL_3758f4296d624bdbab1fe007f6991098", - "IPY_MODEL_648e0a34592643a4a492e5e174ee90d4" + "IPY_MODEL_e408459fd0d34067a7237320dc740b0c", + "IPY_MODEL_06a7b5966cab4eb982ccd501185df725", + "IPY_MODEL_ead55c8fbe134cb5944eb4fdca7caf2f" ], - "layout": "IPY_MODEL_3a40365eb00646d293b75d75bb468548" + "layout": "IPY_MODEL_1ce8780db26c49769f463ddbac112e9f" } }, - "60bfea04814142dfaacda9aa258de9f8": { + "e408459fd0d34067a7237320dc740b0c": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -13858,13 +10134,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_8cd4dce996cf45e8a6283a80b63355b4", + "layout": "IPY_MODEL_71abcdcdb2654d38927221f765758294", "placeholder": "​", - "style": "IPY_MODEL_d97d9ea9cf5c4f1fafac1ee469f6a31f", + "style": "IPY_MODEL_c86de2dd069a4b018aadd6ae78da146c", "value": "adapter_model.safetensors: 100%" } }, - "3758f4296d624bdbab1fe007f6991098": { + "06a7b5966cab4eb982ccd501185df725": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -13880,15 +10156,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_6710a9e1ef9a4394922077b99401e87a", + "layout": "IPY_MODEL_8ae6eaaf83af46c1b02b7b397a607ce6", "max": 2175168, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_1f3e9545915841e887390530cfe475d9", + "style": "IPY_MODEL_e110a1dace1f487f98744b645fd1c616", "value": 2175168 } }, - "648e0a34592643a4a492e5e174ee90d4": { + "ead55c8fbe134cb5944eb4fdca7caf2f": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -13903,13 +10179,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_6db82e165cb146a8b1690340986bfc6a", + "layout": "IPY_MODEL_4aa6c5e1586f4a8e9071382c91169d5e", "placeholder": "​", - "style": "IPY_MODEL_862df92699c64c7b8a9ef3c6f969e004", - "value": " 2.18M/2.18M [00:01<00:00, 2.12MB/s]" + "style": "IPY_MODEL_f1b95dc5c34b4318917b2bdb374f1081", + "value": " 2.18M/2.18M [00:02<00:00, 963kB/s]" } }, - "3a40365eb00646d293b75d75bb468548": { + "1ce8780db26c49769f463ddbac112e9f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -13961,7 +10237,7 @@ "width": null } }, - "8cd4dce996cf45e8a6283a80b63355b4": { + "71abcdcdb2654d38927221f765758294": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14013,7 +10289,7 @@ "width": null } }, - "d97d9ea9cf5c4f1fafac1ee469f6a31f": { + "c86de2dd069a4b018aadd6ae78da146c": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -14028,7 +10304,7 @@ "description_width": "" } }, - "6710a9e1ef9a4394922077b99401e87a": { + "8ae6eaaf83af46c1b02b7b397a607ce6": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14080,7 +10356,7 @@ "width": null } }, - "1f3e9545915841e887390530cfe475d9": { + "e110a1dace1f487f98744b645fd1c616": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -14096,7 +10372,7 @@ "description_width": "" } }, - "6db82e165cb146a8b1690340986bfc6a": { + "4aa6c5e1586f4a8e9071382c91169d5e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14148,7 +10424,7 @@ "width": null } }, - "862df92699c64c7b8a9ef3c6f969e004": { + "f1b95dc5c34b4318917b2bdb374f1081": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -14163,7 +10439,7 @@ "description_width": "" } }, - "623fc8677a0241eca1c88146e2daebf0": { + "2c159e922dde4e108e4c33a0cd52240c": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -14178,14 +10454,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_2c1e69d50a7f4673973d06e4f461e63b", - "IPY_MODEL_8021f19a762549cf8571283f43db8d3c", - "IPY_MODEL_d0b91f3a78804a4d9a7961f700070127" + "IPY_MODEL_eb5a6815d0294aaa830b3818105c7fba", + "IPY_MODEL_15223c3aa0254747b2f6362bdbab253f", + "IPY_MODEL_be6843c8def24105a9319fce252c8deb" ], - "layout": "IPY_MODEL_28cd8a0567fa47ffbef58304327990ff" + "layout": "IPY_MODEL_0a5883fd63024dad997289714dbb9bb2" } }, - "2c1e69d50a7f4673973d06e4f461e63b": { + "eb5a6815d0294aaa830b3818105c7fba": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -14200,13 +10476,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_1268a1ecf3204642b0640148a2f01467", + "layout": "IPY_MODEL_2137c9e1130245229a6f06ae79640812", "placeholder": "​", - "style": "IPY_MODEL_3664dd742b134c97a20b8b835b8bb820", + "style": "IPY_MODEL_1e5b8134ea704f7ca97f1e4eb8e4b15f", "value": "tokenizer_config.json: 100%" } }, - "8021f19a762549cf8571283f43db8d3c": { + "15223c3aa0254747b2f6362bdbab253f": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -14222,15 +10498,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_e3dda5cc573e4d998185f4da2a3a2269", + "layout": "IPY_MODEL_059831fa728b4cbe9680f259b42e2324", "max": 973, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_03a82ca0774c4c03854346b385f3dc62", + "style": "IPY_MODEL_e41308674e4c4d878b99ab33f618a2e3", "value": 973 } }, - "d0b91f3a78804a4d9a7961f700070127": { + "be6843c8def24105a9319fce252c8deb": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -14245,13 +10521,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_ba60965841044f7fa93694761f5d3c8b", + "layout": "IPY_MODEL_0173e8a7c9e14c06b1d8e9cf4030ae5d", "placeholder": "​", - "style": "IPY_MODEL_781ec2710ffc45cea6d44ff6be4a3898", + "style": "IPY_MODEL_070b4ade060f4593994fbab78434bc0f", "value": " 973/973 [00:00<00:00, 131kB/s]" } }, - "28cd8a0567fa47ffbef58304327990ff": { + "0a5883fd63024dad997289714dbb9bb2": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14303,7 +10579,7 @@ "width": null } }, - "1268a1ecf3204642b0640148a2f01467": { + "2137c9e1130245229a6f06ae79640812": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14355,7 +10631,7 @@ "width": null } }, - "3664dd742b134c97a20b8b835b8bb820": { + "1e5b8134ea704f7ca97f1e4eb8e4b15f": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -14370,7 +10646,7 @@ "description_width": "" } }, - "e3dda5cc573e4d998185f4da2a3a2269": { + "059831fa728b4cbe9680f259b42e2324": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14422,7 +10698,7 @@ "width": null } }, - "03a82ca0774c4c03854346b385f3dc62": { + "e41308674e4c4d878b99ab33f618a2e3": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -14438,7 +10714,7 @@ "description_width": "" } }, - "ba60965841044f7fa93694761f5d3c8b": { + "0173e8a7c9e14c06b1d8e9cf4030ae5d": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14490,7 +10766,7 @@ "width": null } }, - "781ec2710ffc45cea6d44ff6be4a3898": { + "070b4ade060f4593994fbab78434bc0f": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -14505,7 +10781,7 @@ "description_width": "" } }, - "3f588c0b040242ba90adb291aa080fd1": { + "f5cbe29f0f704fb5bf977bf882557548": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -14520,14 +10796,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_3853ad4388634a769ef8afe7de8af137", - "IPY_MODEL_b1179cf26c554694aa50b9df90f605e9", - "IPY_MODEL_a73ef52b69bc4a3f9902e9c5bdca80e7" + "IPY_MODEL_91cf88d605c044c28125a0f47a22dc15", + "IPY_MODEL_0f6e4953353e46d58ca413c896521e75", + "IPY_MODEL_73b839f10d4c47b28703859913f447be" ], - "layout": "IPY_MODEL_3caf93da780b4fbb9e11302ad9f6f2f8" + "layout": "IPY_MODEL_98e7098caa774049bd1e35746993f46c" } }, - "3853ad4388634a769ef8afe7de8af137": { + "91cf88d605c044c28125a0f47a22dc15": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -14542,13 +10818,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_f8c77e5ba54946eda20ba93a01631686", + "layout": "IPY_MODEL_582a666ee19b4fce9f66a5780d244f4c", "placeholder": "​", - "style": "IPY_MODEL_a2fc5f0a428f4ec49fd4c5c31ce1c281", + "style": "IPY_MODEL_86890b32676441a3a2008b95b234a650", "value": "vocab.json: " } }, - "b1179cf26c554694aa50b9df90f605e9": { + "0f6e4953353e46d58ca413c896521e75": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -14564,15 +10840,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_03f752912fbf48088cb4ac0d37aef7af", + "layout": "IPY_MODEL_13d571b60f9d488b897fa159c1242cce", "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_eca94be852914086b399eda6a37ac5dc", + "style": "IPY_MODEL_2360cdab2b2a4dc19fbe13505dcd4ad1", "value": 1 } }, - "a73ef52b69bc4a3f9902e9c5bdca80e7": { + "73b839f10d4c47b28703859913f447be": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -14587,13 +10863,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_312067e15bf648a79ed9e5c1e1530b72", + "layout": "IPY_MODEL_5972f6f336b548f2b1b26303d9b24669", "placeholder": "​", - "style": "IPY_MODEL_1632afd2894e4f4fbc1935774183bf6c", - "value": " 2.78M/? [00:00<00:00, 4.34MB/s]" + "style": "IPY_MODEL_c1a19e066cbc4175b7716bdb255acb9e", + "value": " 2.78M/? [00:00<00:00, 7.72MB/s]" } }, - "3caf93da780b4fbb9e11302ad9f6f2f8": { + "98e7098caa774049bd1e35746993f46c": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14645,7 +10921,7 @@ "width": null } }, - "f8c77e5ba54946eda20ba93a01631686": { + "582a666ee19b4fce9f66a5780d244f4c": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14697,7 +10973,7 @@ "width": null } }, - "a2fc5f0a428f4ec49fd4c5c31ce1c281": { + "86890b32676441a3a2008b95b234a650": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -14712,7 +10988,7 @@ "description_width": "" } }, - "03f752912fbf48088cb4ac0d37aef7af": { + "13d571b60f9d488b897fa159c1242cce": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14764,7 +11040,7 @@ "width": "20px" } }, - "eca94be852914086b399eda6a37ac5dc": { + "2360cdab2b2a4dc19fbe13505dcd4ad1": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -14780,7 +11056,7 @@ "description_width": "" } }, - "312067e15bf648a79ed9e5c1e1530b72": { + "5972f6f336b548f2b1b26303d9b24669": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14832,7 +11108,7 @@ "width": null } }, - "1632afd2894e4f4fbc1935774183bf6c": { + "c1a19e066cbc4175b7716bdb255acb9e": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -14847,7 +11123,7 @@ "description_width": "" } }, - "82fe3baa961b4d54bc7a8936bbdbd444": { + "1203ab14808c4652b8c1f974e09c79c7": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -14862,14 +11138,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_9459c94019c344f6a32f73f0ee79bd05", - "IPY_MODEL_658f62d6c77d48f0ba9633ce3cfb3d67", - "IPY_MODEL_385c999a90884f669541de594024d915" + "IPY_MODEL_fc7da4497c904de690e83afbdfb50be0", + "IPY_MODEL_545f39a2b0c541c9bc9a3062e00ed088", + "IPY_MODEL_c641b73c9d63465caddb6dc32f11a3a6" ], - "layout": "IPY_MODEL_0190a84980fb4b99a47a8f3742497248" + "layout": "IPY_MODEL_14950c86260f4fa99f41be6cb0c65b32" } }, - "9459c94019c344f6a32f73f0ee79bd05": { + "fc7da4497c904de690e83afbdfb50be0": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -14884,13 +11160,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_f65bba45dae9468d84137bab8570f7e8", + "layout": "IPY_MODEL_557a4337be7441fbb43fc753295af804", "placeholder": "​", - "style": "IPY_MODEL_1debfa4067864d0cad5580f44d6b6b83", + "style": "IPY_MODEL_688c2ce6d721433e8685f4248c2e341f", "value": "merges.txt: " } }, - "658f62d6c77d48f0ba9633ce3cfb3d67": { + "545f39a2b0c541c9bc9a3062e00ed088": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -14906,15 +11182,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_fcd303c072eb499e9940e5e6dbf7b98d", + "layout": "IPY_MODEL_81246711b0a24be6ac6c91a68eb74313", "max": 1, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_d26dff2638e447f9a048a88d1994a174", + "style": "IPY_MODEL_8f5434c2e2f6433eba78b601f5789ddd", "value": 1 } }, - "385c999a90884f669541de594024d915": { + "c641b73c9d63465caddb6dc32f11a3a6": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -14929,13 +11205,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_c417174c8af44956891c6760e6d83838", + "layout": "IPY_MODEL_8bf8239650844eda82c9b4c40574b496", "placeholder": "​", - "style": "IPY_MODEL_a66ff5199c36419daf3cd61dcd664594", - "value": " 1.67M/? [00:00<00:00, 2.33MB/s]" + "style": "IPY_MODEL_d164a27bbc944bfb92fc620142fc83c1", + "value": " 1.67M/? [00:00<00:00, 125kB/s]" } }, - "0190a84980fb4b99a47a8f3742497248": { + "14950c86260f4fa99f41be6cb0c65b32": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -14987,7 +11263,7 @@ "width": null } }, - "f65bba45dae9468d84137bab8570f7e8": { + "557a4337be7441fbb43fc753295af804": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -15039,7 +11315,7 @@ "width": null } }, - "1debfa4067864d0cad5580f44d6b6b83": { + "688c2ce6d721433e8685f4248c2e341f": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -15054,7 +11330,7 @@ "description_width": "" } }, - "fcd303c072eb499e9940e5e6dbf7b98d": { + "81246711b0a24be6ac6c91a68eb74313": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -15106,7 +11382,7 @@ "width": "20px" } }, - "d26dff2638e447f9a048a88d1994a174": { + "8f5434c2e2f6433eba78b601f5789ddd": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -15122,7 +11398,7 @@ "description_width": "" } }, - "c417174c8af44956891c6760e6d83838": { + "8bf8239650844eda82c9b4c40574b496": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -15174,7 +11450,7 @@ "width": null } }, - "a66ff5199c36419daf3cd61dcd664594": { + "d164a27bbc944bfb92fc620142fc83c1": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -15189,7 +11465,7 @@ "description_width": "" } }, - "f763f84995b8409fbd37d88ff1213497": { + "7c2f6691f3f44b62aca4a481cc4ba75d": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -15204,14 +11480,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_a11a91d5b61046da82c23c2a4ef9ef01", - "IPY_MODEL_7a6d9dc8dcc34082b349f9db23c86164", - "IPY_MODEL_ae469db875d84a78ba955eaa622ff578" + "IPY_MODEL_1f8386e4159f4c78854d491aa455920b", + "IPY_MODEL_7a5aa4e7f4014148badd950998a5fe6f", + "IPY_MODEL_9460d198df13442f8d5e2f97de22c70a" ], - "layout": "IPY_MODEL_72d0ea3eb9bb48709dc083d0675a7269" + "layout": "IPY_MODEL_1c7395b641b44c9780d03a701b8bd542" } }, - "a11a91d5b61046da82c23c2a4ef9ef01": { + "1f8386e4159f4c78854d491aa455920b": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -15226,13 +11502,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_a0f0b115e1424c1a8a3ebc8c06d9377c", + "layout": "IPY_MODEL_c65f952fcaa2465f9bc7ecc82e11e055", "placeholder": "​", - "style": "IPY_MODEL_688e24459d0d4ed39adcdad693d3ff92", + "style": "IPY_MODEL_e64b1fcd9a244247aacb57580b1dfef6", "value": "tokenizer.json: 100%" } }, - "7a6d9dc8dcc34082b349f9db23c86164": { + "7a5aa4e7f4014148badd950998a5fe6f": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -15248,15 +11524,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_4341668602b747eba25f1d8fa67c11da", + "layout": "IPY_MODEL_ffad176a7ff84ca3b205a890fcac3584", "max": 11418433, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_d9ced26aa4fe4748b52873f2f409e635", + "style": "IPY_MODEL_628a9ac305694d6791c63cd8b01bebe2", "value": 11418433 } }, - "ae469db875d84a78ba955eaa622ff578": { + "9460d198df13442f8d5e2f97de22c70a": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -15271,13 +11547,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_ed0a734b4e8e4e489531d9f5459d4106", + "layout": "IPY_MODEL_03776b2b33dc4988a7465217b26aad22", "placeholder": "​", - "style": "IPY_MODEL_e2bf90424775413d936c86cd421e1122", - "value": " 11.4M/11.4M [00:01<00:00, 3.52MB/s]" + "style": "IPY_MODEL_5bcbccea676f4fbf9fa65b6bdcb6a89d", + "value": " 11.4M/11.4M [00:02<00:00, 6.23MB/s]" } }, - "72d0ea3eb9bb48709dc083d0675a7269": { + "1c7395b641b44c9780d03a701b8bd542": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -15329,7 +11605,7 @@ "width": null } }, - "a0f0b115e1424c1a8a3ebc8c06d9377c": { + "c65f952fcaa2465f9bc7ecc82e11e055": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -15381,7 +11657,7 @@ "width": null } }, - "688e24459d0d4ed39adcdad693d3ff92": { + "e64b1fcd9a244247aacb57580b1dfef6": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -15396,7 +11672,7 @@ "description_width": "" } }, - "4341668602b747eba25f1d8fa67c11da": { + "ffad176a7ff84ca3b205a890fcac3584": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -15448,7 +11724,7 @@ "width": null } }, - "d9ced26aa4fe4748b52873f2f409e635": { + "628a9ac305694d6791c63cd8b01bebe2": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -15464,7 +11740,7 @@ "description_width": "" } }, - "ed0a734b4e8e4e489531d9f5459d4106": { + "03776b2b33dc4988a7465217b26aad22": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -15516,7 +11792,7 @@ "width": null } }, - "e2bf90424775413d936c86cd421e1122": { + "5bcbccea676f4fbf9fa65b6bdcb6a89d": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -15531,7 +11807,7 @@ "description_width": "" } }, - "10ba9f61c3824dc79f31db0b334f58b8": { + "fb0decf6380d4fd38ad19747363cd436": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -15546,14 +11822,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_c240ed63de3b4f6db02a527e9764bc38", - "IPY_MODEL_5deb7cbe9dc84bca9e64b124c374e142", - "IPY_MODEL_449a66d1e33c416694be64897927d887" + "IPY_MODEL_8ac581a5ba694f4592a04535e83e853b", + "IPY_MODEL_f92f06d606b94385bd59f8e220480375", + "IPY_MODEL_8f4a73c122ed4c028af018c4281b9f6c" ], - "layout": "IPY_MODEL_69e8f81fec2343e2aebfd27d0bc18ceb" + "layout": "IPY_MODEL_c183147474ce48258ada0b6a356692ab" } }, - "c240ed63de3b4f6db02a527e9764bc38": { + "8ac581a5ba694f4592a04535e83e853b": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -15568,13 +11844,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_d23ce595b17342698032c9997e665f4a", + "layout": "IPY_MODEL_72204822c05c491c9f55fa84ed93ce16", "placeholder": "​", - "style": "IPY_MODEL_68d40ba38208430b861e1e7313f97281", + "style": "IPY_MODEL_503a3db6639644588125b9c666f6f726", "value": "added_tokens.json: 100%" } }, - "5deb7cbe9dc84bca9e64b124c374e142": { + "f92f06d606b94385bd59f8e220480375": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -15590,15 +11866,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_ea1a58ccc99740b599d9f51d6d061ed0", + "layout": "IPY_MODEL_bbf1d801f7d34cc4964cee6965433c4e", "max": 80, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_e2d0f7a7d42641909c40212fe7357e85", + "style": "IPY_MODEL_e218255545cb441cb243601d71b75de4", "value": 80 } }, - "449a66d1e33c416694be64897927d887": { + "8f4a73c122ed4c028af018c4281b9f6c": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -15613,13 +11889,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_099f620226c5403e8b484aab8f6e355f", + "layout": "IPY_MODEL_fd9ac1cc42604153a63475de1d3c0633", "placeholder": "​", - "style": "IPY_MODEL_85d5475924c144aca453fc6f5dad30c8", + "style": "IPY_MODEL_28db4660c52e4954a2dbd14146fbffde", "value": " 80.0/80.0 [00:00<00:00, 10.5kB/s]" } }, - "69e8f81fec2343e2aebfd27d0bc18ceb": { + "c183147474ce48258ada0b6a356692ab": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -15671,7 +11947,7 @@ "width": null } }, - "d23ce595b17342698032c9997e665f4a": { + "72204822c05c491c9f55fa84ed93ce16": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -15723,7 +11999,7 @@ "width": null } }, - "68d40ba38208430b861e1e7313f97281": { + "503a3db6639644588125b9c666f6f726": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -15738,7 +12014,7 @@ "description_width": "" } }, - "ea1a58ccc99740b599d9f51d6d061ed0": { + "bbf1d801f7d34cc4964cee6965433c4e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -15790,7 +12066,7 @@ "width": null } }, - "e2d0f7a7d42641909c40212fe7357e85": { + "e218255545cb441cb243601d71b75de4": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -15806,7 +12082,7 @@ "description_width": "" } }, - "099f620226c5403e8b484aab8f6e355f": { + "fd9ac1cc42604153a63475de1d3c0633": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -15858,7 +12134,7 @@ "width": null } }, - "85d5475924c144aca453fc6f5dad30c8": { + "28db4660c52e4954a2dbd14146fbffde": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -15873,7 +12149,7 @@ "description_width": "" } }, - "3fe3512463234826b74f7185d00e887d": { + "24a27c7c58604c5890317c65bb7e4120": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -15888,14 +12164,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_5b2a28e155cd450ab7b1eed3fc670e07", - "IPY_MODEL_3d9f675483a44236a7c73d64cd6b90a1", - "IPY_MODEL_cbc8cc2fae234a9fb7d19c71f16ef843" + "IPY_MODEL_5f73e5d097f043ad89ec180770e3aea3", + "IPY_MODEL_4f4aba3191e546ce9685d1c1d3ef7921", + "IPY_MODEL_786d6b794ffd4fc195e9ee27c250542b" ], - "layout": "IPY_MODEL_be433c4112a3473aa3990cdad0b8671f" + "layout": "IPY_MODEL_a2049e1174a2400ab4e3195a43df2d09" } }, - "5b2a28e155cd450ab7b1eed3fc670e07": { + "5f73e5d097f043ad89ec180770e3aea3": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -15910,13 +12186,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_b039d6aa93c94ffd9ab80de5436f4a74", + "layout": "IPY_MODEL_d51d6b7c071f4ec096a0353aa88142d2", "placeholder": "​", - "style": "IPY_MODEL_7c4b47094c6a46cbbfbc564523a57f50", + "style": "IPY_MODEL_77fc4a53278c4ad6930875d5af406fe4", "value": "special_tokens_map.json: 100%" } }, - "3d9f675483a44236a7c73d64cd6b90a1": { + "4f4aba3191e546ce9685d1c1d3ef7921": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -15932,15 +12208,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_5d8c588bac624efc85fbd6bd2a68cfa8", + "layout": "IPY_MODEL_aa7bd7525dc942f0917f204d5dc4f18e", "max": 367, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_3d16361a71d846019be9bfa1acf90c3f", + "style": "IPY_MODEL_f41e21c3ea2348fb89dd733bb5a8b72a", "value": 367 } }, - "cbc8cc2fae234a9fb7d19c71f16ef843": { + "786d6b794ffd4fc195e9ee27c250542b": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -15955,13 +12231,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_79fe6e3d24234007a49b918be4a64f3f", + "layout": "IPY_MODEL_fa3ed6b006b844d2a62faf3378defa48", "placeholder": "​", - "style": "IPY_MODEL_91eb300d2a694f858aec854f00c0ec05", - "value": " 367/367 [00:00<00:00, 52.3kB/s]" + "style": "IPY_MODEL_7d36628a40934a43b9aafed04446a748", + "value": " 367/367 [00:00<00:00, 50.6kB/s]" } }, - "be433c4112a3473aa3990cdad0b8671f": { + "a2049e1174a2400ab4e3195a43df2d09": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -16013,7 +12289,7 @@ "width": null } }, - "b039d6aa93c94ffd9ab80de5436f4a74": { + "d51d6b7c071f4ec096a0353aa88142d2": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -16065,7 +12341,7 @@ "width": null } }, - "7c4b47094c6a46cbbfbc564523a57f50": { + "77fc4a53278c4ad6930875d5af406fe4": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -16080,7 +12356,7 @@ "description_width": "" } }, - "5d8c588bac624efc85fbd6bd2a68cfa8": { + "aa7bd7525dc942f0917f204d5dc4f18e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -16132,7 +12408,7 @@ "width": null } }, - "3d16361a71d846019be9bfa1acf90c3f": { + "f41e21c3ea2348fb89dd733bb5a8b72a": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -16148,7 +12424,7 @@ "description_width": "" } }, - "79fe6e3d24234007a49b918be4a64f3f": { + "fa3ed6b006b844d2a62faf3378defa48": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -16200,7 +12476,7 @@ "width": null } }, - "91eb300d2a694f858aec854f00c0ec05": { + "7d36628a40934a43b9aafed04446a748": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -16215,7 +12491,7 @@ "description_width": "" } }, - "067de797dc2f440a9312d98da7825510": { + "16874265452a43a09bff4b194b18dc75": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", @@ -16230,14 +12506,14 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_cb847a29bd6846b98b91f739f32cff82", - "IPY_MODEL_72de174496b74ad78c73bc1da8528ad9", - "IPY_MODEL_0b3a7f9f95d542d599bf4f1ff23d5531" + "IPY_MODEL_6a8b1c227c674dbfa7a6a6d158f50ff1", + "IPY_MODEL_d922f3e918c3406987d4a7be6025efa9", + "IPY_MODEL_37684561c72a41e18592d441355ec730" ], - "layout": "IPY_MODEL_05d96c9494e44bbc82a85c4c75663be7" + "layout": "IPY_MODEL_3a7a7a995bab43b894c027a0c3c9d34f" } }, - "cb847a29bd6846b98b91f739f32cff82": { + "6a8b1c227c674dbfa7a6a6d158f50ff1": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -16252,13 +12528,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_07f58707185d443bbfd9a688dadc9769", + "layout": "IPY_MODEL_ad2a06d6be1340bfb16b7fc36c2558b1", "placeholder": "​", - "style": "IPY_MODEL_b084e6e3346a43c488970017dc7eead8", + "style": "IPY_MODEL_a6308fa1425e4b5591f012b74848b551", "value": "chat_template.jinja: 100%" } }, - "72de174496b74ad78c73bc1da8528ad9": { + "d922f3e918c3406987d4a7be6025efa9": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", @@ -16274,15 +12550,15 @@ "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_d0615f5d04434936a6f6780584c71908", + "layout": "IPY_MODEL_7aa324d55a7b41e28f048823a24b888c", "max": 328, "min": 0, "orientation": "horizontal", - "style": "IPY_MODEL_2d19638dd0f146e38178177678fa088f", + "style": "IPY_MODEL_26d478b283834e0eb98e5a29268ee9d8", "value": 328 } }, - "0b3a7f9f95d542d599bf4f1ff23d5531": { + "37684561c72a41e18592d441355ec730": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", @@ -16297,13 +12573,13 @@ "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_3e16885ed06e4c0c9b24c8770ae97fda", + "layout": "IPY_MODEL_8e9ae466ab79444c8ee4fc38758312d8", "placeholder": "​", - "style": "IPY_MODEL_ad14b8a55f7f49b882e81be9e08faa0e", - "value": " 328/328 [00:00<00:00, 42.9kB/s]" + "style": "IPY_MODEL_66eba3ce1b974632a00b59212a131927", + "value": " 328/328 [00:00<00:00, 44.5kB/s]" } }, - "05d96c9494e44bbc82a85c4c75663be7": { + "3a7a7a995bab43b894c027a0c3c9d34f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -16355,7 +12631,7 @@ "width": null } }, - "07f58707185d443bbfd9a688dadc9769": { + "ad2a06d6be1340bfb16b7fc36c2558b1": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -16407,7 +12683,7 @@ "width": null } }, - "b084e6e3346a43c488970017dc7eead8": { + "a6308fa1425e4b5591f012b74848b551": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", @@ -16422,7 +12698,7 @@ "description_width": "" } }, - "d0615f5d04434936a6f6780584c71908": { + "7aa324d55a7b41e28f048823a24b888c": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -16474,7 +12750,7 @@ "width": null } }, - "2d19638dd0f146e38178177678fa088f": { + "26d478b283834e0eb98e5a29268ee9d8": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", @@ -16490,7 +12766,7 @@ "description_width": "" } }, - "3e16885ed06e4c0c9b24c8770ae97fda": { + "8e9ae466ab79444c8ee4fc38758312d8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", @@ -16542,7 +12818,7 @@ "width": null } }, - "ad14b8a55f7f49b882e81be9e08faa0e": { + "66eba3ce1b974632a00b59212a131927": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0",