| .gitattributes | 1.90 KB | 0910f84d65a00589ece1b7a230c5205da83c390634c603508ac1772a6ba7c8a6 |
| README.md | 1.27 KB | 9a6e8594f0e0f4923d29a15df124dc6aeebee7366680ae50547d6ab973638aa5 |
| 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 | 95e51502a9930ce581a9f463fd9da5dc0e804f80e4b3fccd0755a5a4516ef9ec |
| model-00002-of-00004.safetensors | 4.92 GB | a0270ed4cf1a42a3b75763bd26ed069be06ff30805f33a8b1e5a377ea369eb54 |
| model-00003-of-00004.safetensors | 4.98 GB | d776bfb2e9b61f966130b9efffae2d4c2159a8287e25a626d8fadd8d13b33f2e |
| model-00004-of-00004.safetensors | 1.58 GB | 1e9b30f722d7e8fe7ba35d68e40ec6557a54cecd245d01e265ee0c5a188ca46a |
| model.safetensors.index.json | 32.9 KB | e7e4bdc58d3302c97357f27979b270987dd620cf0cd9b1c130e3a51c9d64df95 |
| rl_config.yaml | 8.34 KB | b0d3449fd9a259dd1b4ebd898a82ae0cef85d69a3f7316cbcae97f2ae1cf8ef2 |
| special_tokens_map.json | 613 B | 76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd |
| tokenizer.json | 11.4 MB | aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 |
| tokenizer_config.json | 5.43 KB | 3e27b302e9844c5b9648a8dbc1958fbbf3bda640e07302f53c17ac7a3192def5 |
| training_logs/20260612_111835_metrics_explore-tis-temp10_736670.csv | 22.8 KB | a010542be352a7031cb05e63c03a62108ade0e69afdf605905409dfe1f0ed9bf |
| training_logs/20260612_111835_metrics_explore-tis-temp10_736671.csv | 21.9 KB | 6e5a0e95a66c04621fc0fee5f09251300f140680dc0cbc30b6f3c9441ded2c94 |
| training_logs/20260612_111835_metrics_explore-tis-temp10_736672.csv | 5.88 KB | 2420f4a19f8ac1042065e8286bc1d39966a125f82d317fa2bfc461eb4dde53ea |
| training_logs/20260612_111835_metrics_explore-tis-temp10_736673.csv | 2.50 KB | a14c2a3265a5da20bade3661a9cc92a794c3c09f1a1aaeb8c1f4a3a679772c4b |
| training_logs/20260612_111835_metrics_explore-tis-temp10_736674.csv | 2.59 KB | c6cf97a2c0006e831ebef331f4f0fb07fabddfc404dc2052dce8cf541679925c |
| training_logs/20260612_111835_metrics_explore-tis-temp10_736675.csv | 2.60 KB | 060bc70c103fddc5def20d6966f17166d8947507fc58d1fc19fd1469c4df309f |
| training_logs/20260612_111835_metrics_report.md | 24.1 KB | 68e15e71a1adac19f791275b783e85697f8d5cba910353d268906ce0b9124bb5 |
| training_logs/20260612_111835_metrics_table.csv | 50.3 KB | d888f04ad95d1bc32c24793d3a73b6c07f15bce8c8e23db387c2dd6c94f1b29c |
| training_logs/20260612_111835_reward_vs_steps.png | 299 KB | ae7d1c68293bcb1b295887242220c3d424b8cfa63b4051d710cdd73976f0cb59 |
| training_logs/20260612_111835_vllm_metrics_explore-tis-temp10_736670.csv | 694 KB | e113d608681d3ae6aa5815268c64f761556d31f15482221912fc35eda8ac528b |
| training_logs/20260612_111835_vllm_metrics_explore-tis-temp10_736671.csv | 691 KB | 9d4d4aa484329262c9780a300d102f9113903953961b833b451cc7db94ac5a4c |
| training_logs/20260612_111835_vllm_metrics_explore-tis-temp10_736672.csv | 213 KB | 415c3bf0ed065b45baeb7566953133b329f55861b6100faabf6b72b1a1c761ff |
| training_logs/20260612_111835_vllm_metrics_explore-tis-temp10_736673.csv | 35.4 KB | bd6febc6dab5ddb4de857ec776c3a0f5376e5f32efaf68038258d894c4f93881 |
| training_logs/20260612_111835_vllm_metrics_explore-tis-temp10_736674.csv | 29.1 KB | 8cc9aea7b108438964d49acd4eeabf2d00cad06161ae0c29ade10968027bfb9c |
| training_logs/20260612_111835_vllm_metrics_explore-tis-temp10_736675.csv | 28.3 KB | bae5d71b6914985da8cd0f2721e1cc2f3d22069dde135abb4b2b3fac9aa76ce7 |
| training_logs/20260612_111835_vllm_metrics_table.csv | 2.24 MB | b8cd174b8eba605c9be703c7e48e1c5886846468f1a6747ebcc18e645d9a9fb9 |
| training_logs/explore-tis-temp10_736670.out | 100 MB | e2fbe1fb878039cd1eaac721b558fb6ba2dd5b341c5d6835a6ab585d5c18c15c |
| training_logs/explore-tis-temp10_736671.out | 94.7 MB | 2ed910a4dae796fb24c9cbc8f84a98f3de882f91f7142a6894417dc38fd016af |
| training_logs/explore-tis-temp10_736672.out | 21.4 MB | 68ac2a81f622f86520928f531ee4afc2f7704f76b27a15f567c335200be8adf6 |
| training_logs/explore-tis-temp10_736673.out | 4.59 MB | af0390f80e551afa72f4e41289bcf44c39ece603bbbe059ed60c38b2266d4398 |
| training_logs/explore-tis-temp10_736674.out | 3.84 MB | efc450dc75074cd33578dfeb96ce7572981129993b46167437970373ede36596 |
| training_logs/explore-tis-temp10_736675.out | 3.76 MB | 48880f44d643aa477e3515af38287782023b1b89ba4b5d95161b34c917048bef |
| vocab.json | 2.78 MB | ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 |