| .gitattributes | 2.16 KB | 72830af7ca2e98099043961900863f9990e32e88e2855211290125b65fe169c8 |
| README.md | 1.08 KB | 379a08859e15a808aa65b55ad1baa7aebbb2e97c562f5122d04e64bc85b35f79 |
| 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 | d64c4c111c0e674ca42193f6456087928359120312e518347c272e681f8e4705 |
| model-00002-of-00004.safetensors | 4.92 GB | bfa8edcdfe585b27d4b7b59c38c548043499747d75c0ea2be592a25a7664f14f |
| model-00003-of-00004.safetensors | 4.98 GB | b38c647466a4fa3b2ce97422a578c425dcfecc481ce1644217a6e93ecff30609 |
| model-00004-of-00004.safetensors | 1.58 GB | 072f1769897157c462d2b178442faecbde237a70f9cf0a0e0ada54307656561d |
| model.safetensors.index.json | 32.9 KB | e7e4bdc58d3302c97357f27979b270987dd620cf0cd9b1c130e3a51c9d64df95 |
| rl_config.yaml | 12.9 KB | 2be48e2c00316e279a28d772dd832ad6673a08a459b8f9f067e6033b87b2cb34 |
| special_tokens_map.json | 613 B | 76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd |
| tokenizer.json | 11.4 MB | aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 |
| tokenizer_config.json | 5.43 KB | 3e27b302e9844c5b9648a8dbc1958fbbf3bda640e07302f53c17ac7a3192def5 |
| training_logs/20260609_214045_metrics_job_653585.csv | 10.8 KB | a0b8532e24f7ffb6ddd8e63c194c29fc1da7471d4132c703e4da2c80f22a6b7f |
| training_logs/20260609_214045_metrics_job_653586.csv | 14.2 KB | 2e10ae1836ca48218ed3e84d3e44e2223d0bbe75b90f59aaf86c2aac90a24b94 |
| training_logs/20260609_214045_metrics_job_653587.csv | 17.1 KB | 62a52e952c99ac1ac9a3531c7a9a4ab6dcec3ff6585652096c01a2ace2ee6efb |
| training_logs/20260609_214045_metrics_job_653588.csv | 13.6 KB | 9e6bf3caed959a84994cdf0a462da5a36247ad892e4e78922f3e7fb6a7708548 |
| training_logs/20260609_214045_metrics_job_653589.csv | 2.50 KB | d387f0be691f2f8bf95d6189a41afb4ab8e7704aa6f6da65fc9e9f69b690123a |
| training_logs/20260609_214045_metrics_report.md | 23.7 KB | 37ea9fbdd8fa25cf96bcf921e998074666ac808403ba9d9a3b76cebd10a7e689 |
| training_logs/20260609_214045_metrics_table.csv | 50.2 KB | bdcc9cfb23016b8ba678d95edb1b06dbcca2a5a56c622428ae9dcc3cc192f064 |
| training_logs/20260609_214045_reward_vs_steps.png | 279 KB | 612865ae3e1c26bbb62acd3b75a903c3737903b78337e3f078bfae1aef54a63e |
| training_logs/20260609_214045_trial_results.csv | 3.97 MB | eae34e3245431a070275788b58f690391e3627ed03acc18b52317cb872a774c7 |
| training_logs/20260609_214045_turn_count_distribution.png | 125 KB | 8ecd219d48c7d160a3992c1b141f6ffcf6ad7d6e00a5da914040d313d22249ca |
| training_logs/20260609_214045_vllm_metrics_job_653585.csv | 549 KB | 7b354a689c502a5f9393bfff0b0983426ffcaf1fc46b1c46bb4c738aec0579d4 |
| training_logs/20260609_214045_vllm_metrics_job_653586.csv | 666 KB | e3f8a91bac3f118e82e851e78186716076d41a9bc28c5b0818e9ef96a07df540 |
| training_logs/20260609_214045_vllm_metrics_job_653587.csv | 688 KB | d98f4088234c25be3f3aebfc32a94303a667e2d8d48a6ee6f9dd5f2139cde02f |
| training_logs/20260609_214045_vllm_metrics_job_653588.csv | 572 KB | b7acfca2e5efc086482256cb180ff1b0a295daaa62bb9ad0f5e52f7d012b8572 |
| training_logs/20260609_214045_vllm_metrics_job_653589.csv | 52.9 KB | 30795b9254d78988ae8faf7e0cacdd8138d26a59644ad0beae0d64973a0e0009 |
| training_logs/20260609_214045_vllm_metrics_table.csv | 2.88 MB | 3e8aa5ca765741f6c6a4a770c8736e5d82f8bce28bcd2315a44da1672fc0df67 |
| training_logs/ablation-pymethods2test-seqmean-arm0-tis_653583.out | 53.6 KB | e18233cd6428e8dcaba11f7a539ca3432594adbbbe2dc576e345262dbc20c87e |
| training_logs/ablation-pymethods2test-seqmean-arm0-tis_653584.out | 372 KB | ef7f4845b3b2d8addac5b16adf4ffff7ca0a23de7b7c45999f9c919dfe1ee3a8 |
| training_logs/ablation-pymethods2test-seqmean-arm0-tis_653585.out | 23.2 MB | a383fcb87f44eb8202d493c3a075d21b029c8a48345094d3b87e1b5b26bc7e48 |
| training_logs/ablation-pymethods2test-seqmean-arm0-tis_653586.out | 29.5 MB | 6eb312e5d802af500569a6b68dbce64468e96a285edd5cf1acd375e81b907b99 |
| training_logs/ablation-pymethods2test-seqmean-arm0-tis_653587.out | 39.4 MB | f3b467320252ddc62ad9ee956a782634573d6751244537854604e946364df5b9 |
| training_logs/ablation-pymethods2test-seqmean-arm0-tis_653588.out | 37.8 MB | 6306300b94a9bf493d8856124479d39ace101f1de2d402289704da14505fbdb9 |
| training_logs/ablation-pymethods2test-seqmean-arm0-tis_653589.out | 3.29 MB | 1aa698402f61c8a042a09a4c50fc4f3eed2a522c5dae5a99afa038498050f878 |
| vocab.json | 2.78 MB | ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 |