Reorganize LastFM PO checkpoints by method family
Browse filesThis view is limited to 50 files because it contains too many changes. Β See raw diff
- .gitattributes +3 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/adapter_config.json +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/adapter_model.safetensors +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/eval.log +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/optimizer.pt +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/rng_state_0.pth +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/rng_state_1.pth +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/rng_state_2.pth +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/rng_state_3.pth +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/scheduler.pt +0 -0
- PO/LastFM/DMPO/{special_tokens_map.json β DynamicPO/special_tokens_map.json} +0 -0
- PO/LastFM/DMPO/{tokenizer.json β DynamicPO/tokenizer.json} +0 -0
- PO/LastFM/DMPO/{tokenizer.model β DynamicPO/tokenizer.model} +0 -0
- PO/LastFM/DMPO/{tokenizer_config.json β DynamicPO/tokenizer_config.json} +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/trainer_state.json +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/training_args.bin +0 -0
- PO/LastFM/DMPO/{adapter_config.json β Vanilla/adapter_config.json} +0 -0
- PO/LastFM/DMPO/{adapter_model.safetensors β Vanilla/adapter_model.safetensors} +0 -0
- PO/LastFM/DMPO/{eval.log β Vanilla/eval.log} +0 -0
- PO/LastFM/DMPO/{optimizer.pt β Vanilla/optimizer.pt} +0 -0
- PO/LastFM/DMPO/{rng_state_0.pth β Vanilla/rng_state_0.pth} +0 -0
- PO/LastFM/DMPO/{rng_state_1.pth β Vanilla/rng_state_1.pth} +0 -0
- PO/LastFM/DMPO/{rng_state_2.pth β Vanilla/rng_state_2.pth} +0 -0
- PO/LastFM/DMPO/{rng_state_3.pth β Vanilla/rng_state_3.pth} +0 -0
- PO/LastFM/DMPO/{scheduler.pt β Vanilla/scheduler.pt} +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/Vanilla}/special_tokens_map.json +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/Vanilla}/tokenizer.json +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/Vanilla}/tokenizer.model +0 -0
- PO/LastFM/{DynamicPO_DMPO β DMPO/Vanilla}/tokenizer_config.json +0 -0
- PO/LastFM/DMPO/{trainer_state.json β Vanilla/trainer_state.json} +0 -0
- PO/LastFM/DMPO/{training_args.bin β Vanilla/training_args.bin} +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/adapter_config.json +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/adapter_model.safetensors +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/eval.log +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/optimizer.pt +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/rng_state_0.pth +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/rng_state_1.pth +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/rng_state_2.pth +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/rng_state_3.pth +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/scheduler.pt +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/special_tokens_map.json +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/tokenizer.json +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/tokenizer.model +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/tokenizer_config.json +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/trainer_state.json +0 -0
- PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/training_args.bin +0 -0
- PO/LastFM/MPPO/{adapter_config.json β Vanilla/adapter_config.json} +0 -0
- PO/LastFM/MPPO/{adapter_model.safetensors β Vanilla/adapter_model.safetensors} +0 -0
- PO/LastFM/MPPO/{eval.log β Vanilla/eval.log} +0 -0
- PO/LastFM/MPPO/{optimizer.pt β Vanilla/optimizer.pt} +0 -0
.gitattributes
CHANGED
|
@@ -36,3 +36,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 36 |
PO/LastFM/DynamicPO_DMPO/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
PO/LastFM/DynamicPO_MPPO/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
PO/LastFM/DynamicPO_SDPO/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
PO/LastFM/DynamicPO_DMPO/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
PO/LastFM/DynamicPO_MPPO/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
PO/LastFM/DynamicPO_SDPO/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
PO/LastFM/DMPO/DynamicPO/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
PO/LastFM/MPPO/DynamicPO/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
PO/LastFM/SDPO/DynamicPO/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/adapter_config.json
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/adapter_model.safetensors
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/eval.log
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/optimizer.pt
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/rng_state_0.pth
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/rng_state_1.pth
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/rng_state_2.pth
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/rng_state_3.pth
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/scheduler.pt
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{special_tokens_map.json β DynamicPO/special_tokens_map.json}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{tokenizer.json β DynamicPO/tokenizer.json}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{tokenizer.model β DynamicPO/tokenizer.model}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{tokenizer_config.json β DynamicPO/tokenizer_config.json}
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/trainer_state.json
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/DynamicPO}/training_args.bin
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{adapter_config.json β Vanilla/adapter_config.json}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{adapter_model.safetensors β Vanilla/adapter_model.safetensors}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{eval.log β Vanilla/eval.log}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{optimizer.pt β Vanilla/optimizer.pt}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{rng_state_0.pth β Vanilla/rng_state_0.pth}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{rng_state_1.pth β Vanilla/rng_state_1.pth}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{rng_state_2.pth β Vanilla/rng_state_2.pth}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{rng_state_3.pth β Vanilla/rng_state_3.pth}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{scheduler.pt β Vanilla/scheduler.pt}
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/Vanilla}/special_tokens_map.json
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/Vanilla}/tokenizer.json
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/Vanilla}/tokenizer.model
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_DMPO β DMPO/Vanilla}/tokenizer_config.json
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{trainer_state.json β Vanilla/trainer_state.json}
RENAMED
|
File without changes
|
PO/LastFM/DMPO/{training_args.bin β Vanilla/training_args.bin}
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/adapter_config.json
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/adapter_model.safetensors
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/eval.log
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/optimizer.pt
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/rng_state_0.pth
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/rng_state_1.pth
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/rng_state_2.pth
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/rng_state_3.pth
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/scheduler.pt
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/special_tokens_map.json
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/tokenizer.json
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/tokenizer.model
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/tokenizer_config.json
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/trainer_state.json
RENAMED
|
File without changes
|
PO/LastFM/{DynamicPO_MPPO β MPPO/DynamicPO}/training_args.bin
RENAMED
|
File without changes
|
PO/LastFM/MPPO/{adapter_config.json β Vanilla/adapter_config.json}
RENAMED
|
File without changes
|
PO/LastFM/MPPO/{adapter_model.safetensors β Vanilla/adapter_model.safetensors}
RENAMED
|
File without changes
|
PO/LastFM/MPPO/{eval.log β Vanilla/eval.log}
RENAMED
|
File without changes
|
PO/LastFM/MPPO/{optimizer.pt β Vanilla/optimizer.pt}
RENAMED
|
File without changes
|