| .gitattributes | 2.23 KB | 2099d3764929ed8245c14b011233d933781d52609c85aca559cedfe393fc91ae |
| README.md | 1.49 KB | d65fdcfa9eb80d10ae368b12a83fc8e4eec7b194de79ccd1fb842cb5e51baf0b |
| added_tokens.json | 707 B | c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680 |
| chat_template.jinja | 4.17 KB | a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8 |
| config.json | 1.54 KB | ed36641e183b3d95dcefad8906aa22d183c445e4b582c8a0ca7d71a713c85f2d |
| generation_config.json | 188 B | 3b101cd89b140b757d0bca469e75570e75789a2423ada90a33ec17707dfacf08 |
| merges.txt | 1.67 MB | 8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 |
| model-00001-of-00004.safetensors | 4.90 GB | 08dffda571c5f9229fe3ecf8c5340b17d8cfd723313d6b9f661e711914e75b8e |
| model-00002-of-00004.safetensors | 4.92 GB | de0aed7896d7576214ae37b72bff5b47ee8d352c359118ca8551c588703cdebf |
| model-00003-of-00004.safetensors | 4.98 GB | 371b52edd0d450b4477ecc9335baf1fd7663af1e568ba8f901ac98497d77e20c |
| model-00004-of-00004.safetensors | 1.58 GB | 506f23dc01c5a0e19de21f45f1218ff85c5b8d5ecc81f7b18b09d1a5b3688039 |
| model.safetensors.index.json | 32.9 KB | e7e4bdc58d3302c97357f27979b270987dd620cf0cd9b1c130e3a51c9d64df95 |
| rl_config.yaml | 12.0 KB | 5c099dabcd49c1a6aad4fa002b1f5e31f976308bae18e36b2dbb74ce0550e544 |
| special_tokens_map.json | 613 B | 76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd |
| tokenizer.json | 11.4 MB | aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 |
| tokenizer_config.json | 5.43 KB | 3e27b302e9844c5b9648a8dbc1958fbbf3bda640e07302f53c17ac7a3192def5 |
| training_logs/20260528_035228_metrics_job_515478.csv | 26.1 KB | 94445ea7ae3c07df176bd669ed1ae51bc440def225921b693d0e124df974d92d |
| training_logs/20260528_035228_metrics_job_515479.csv | 1.95 KB | 1490ac13a130a4383d3ee474182fed1ef456c3c716fc83dc5adfb3ad109f5bf0 |
| training_logs/20260528_035228_metrics_job_515480.csv | 4.62 KB | d8a4c96bc18ecd553080d82dcd1faefa5a486862930d8fda84ff093b369f228c |
| training_logs/20260528_035228_metrics_job_515482.csv | 1.93 KB | b2720661fbef237cc664591fd613e8a7eb0cae4324c95b7df413f123d8ab580c |
| training_logs/20260528_035228_metrics_job_515483.csv | 2.05 KB | 1da1a4fb9f588ec22c5a983031fd05424199faa70660dddc4ffbc61f780f8761 |
| training_logs/20260528_035228_metrics_job_515484.csv | 2.88 KB | bf100465ff9eb2b03d740ca2bd7524f2200afff7eb93bfaf97b3a87352fa5536 |
| training_logs/20260528_035228_metrics_job_522590.csv | 1.94 KB | 5f66fdf5492c77616291527488c91520fb9dcf591609eded920b80f159da564c |
| training_logs/20260528_035228_metrics_job_523050.csv | 2.49 KB | b9865618f794696545b67999ef2b6daf48fe86e0cf771ccd96bc7e586e5678fd |
| training_logs/20260528_035228_metrics_job_523051.csv | 2.04 KB | f0c6a77fa6dc2431255060031463bbd365e2bc77af847ea492cfe6cddb63e0bc |
| training_logs/20260528_035228_metrics_job_523052.csv | 5.48 KB | 01bd2661279ae215f4d0a5eac5ec708838aeddc327c6dc048455964c26fec1c3 |
| training_logs/20260528_035228_metrics_report.md | 26.1 KB | 2315c77933ba29867b4674d0d1ec495de542f56874af02839815e076297234dd |
| training_logs/20260528_035228_metrics_table.csv | 37.9 KB | 43d6033598b786f0809b24b067fccd6520b599d545a318a92b8f476cd6ea1826 |
| training_logs/20260528_035228_reward_vs_steps.png | 256 KB | 4d46ddb639de7d9e2fa20d9e54d1d3c9ef1ad0a518f7ca3f0b41449063ee5ff9 |
| training_logs/20260528_035228_trial_results.csv | 3.68 MB | 478199f2b0e066844f49fbedd2f5fd3158f88c7c51c31a533c57e542638f6371 |
| training_logs/20260528_035228_turn_count_distribution.png | 144 KB | 38bc1f1a1405b4f29ef2e029ba91be50b5e2a067de0a108c8b08a26ccae6e7f8 |
| training_logs/20260528_035228_vllm_metrics_job_515478.csv | 515 KB | 48f68c0f0cea628e13266d473adc10068d1db0914c39b43378aabd1a9ee6d4af |
| training_logs/20260528_035228_vllm_metrics_job_515479.csv | 37.6 KB | 3fb902f83ec1911eb6a5a9e545f693131fbc9a475b2bb1f01af140de88ebf28e |
| training_logs/20260528_035228_vllm_metrics_job_515480.csv | 126 KB | 40567679220a381f17519d2be401b3058477dfb8e2e2be1e114f599a869927bf |
| training_logs/20260528_035228_vllm_metrics_job_515482.csv | 43.1 KB | b42471a5127201f65dca1293ca3fea2cbba7009c676f062bfdaceb0112d07545 |
| training_logs/20260528_035228_vllm_metrics_job_515483.csv | 62.0 KB | edf6ee09dd271992e49287fb2e1f9750fcf1777c342194de6e444f42194476ae |
| training_logs/20260528_035228_vllm_metrics_job_515484.csv | 91.3 KB | 2afbcfe45c9b02ba1550915c06a064dcc6052b652326918f48e0ebb0039e4141 |
| training_logs/20260528_035228_vllm_metrics_job_522590.csv | 38.5 KB | 1c1bb50681869af02286b957915f68c579c34adab42bf65cd477b401f12b6264 |
| training_logs/20260528_035228_vllm_metrics_job_523050.csv | 67.3 KB | 23db4daeca6915d03c4972500e0b06909cbd8a21d7449537ee16c648f2b4dc5b |
| training_logs/20260528_035228_vllm_metrics_job_523051.csv | 56.4 KB | ff382660911b93ecbb9bee82aec709b2947489b32832676f45362bb223a10d1c |
| training_logs/20260528_035228_vllm_metrics_job_523052.csv | 212 KB | 21a26c0a23927f2b9efc6b2f8de7e98140bdd14ea9cb2088861456f5c5a3cee3 |
| training_logs/20260528_035228_vllm_metrics_table.csv | 1.43 MB | d7859e9c91c2df35521bdbd7bb4f2f06ddc797ad30a5d38f6ac7fe894bbf4672 |
| training_logs/a3-rl-DCAgent_exp_rpt_e2egit-large_515478.out | 15.4 MB | 0f7df7a6abcbe39970ee5a392ac24aa6ff6d068ec8b77fe63dcc34d156cb8f42 |
| training_logs/a3-rl-DCAgent_exp_rpt_e2egit-large_515479.out | 7.10 MB | 2b003ef1b4fabb6074373543c1606f6db32a37bfb00bce7cb28e21f9498909d0 |
| training_logs/a3-rl-DCAgent_exp_rpt_e2egit-large_515480.out | 18.0 MB | 957dfa5bd98e17fb1787382a5fa688814a4a28fbe819b2ac048990b27fa33917 |
| training_logs/a3-rl-DCAgent_exp_rpt_e2egit-large_515481.out | 313 KB | e9c901731ae7d5ce9dcf5e3130e0d361f5795a2e40648f9d6c5f9482ae6a6b4c |
| training_logs/a3-rl-DCAgent_exp_rpt_e2egit-large_515482.out | 6.24 MB | 361361e4dd5592d4dccca9d39274ed18318440ba8f9564eb5ef3d8be8c39b998 |
| training_logs/a3-rl-DCAgent_exp_rpt_e2egit-large_515483.out | 8.08 MB | 8d9d1c6a3ce3b8bce28f03f67229d182c0c01b2ee69db4ca0dfa3ec94a61870e |
| training_logs/a3-rl-DCAgent_exp_rpt_e2egit-large_515484.out | 12.0 MB | e7f858fd77d3888b4212369d1209cd3990386ecfcd82176d5dc69b536830615d |
| training_logs/a3-rl-DCAgent_exp_rpt_e2egit-large_522590.out | 7.11 MB | e4d84b0e376de1e01ff6722c4a1e988d16748f30be60913174448462daad517f |
| training_logs/a3-rl-DCAgent_exp_rpt_e2egit-large_523050.out | 13.8 MB | 9f46f23c1a17fdf629cd43fde645f1a1749b38a0b5192b3bf14668bf74d6670f |
| training_logs/a3-rl-DCAgent_exp_rpt_e2egit-large_523051.out | 10.4 MB | 81c1239ca7987d82407a3b0e08702cf5fd4c6f50dc126f655d2c82d9604092ff |
| training_logs/a3-rl-DCAgent_exp_rpt_e2egit-large_523052.out | 32.5 MB | 91fd6721608ed83b2d950c5d648315c2976e8d146402722b6931d0ec5a648011 |
| vocab.json | 2.78 MB | ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 |