kastan
/

rlhf-qa-ppo

Text Generation

Model card Files Files and versions

rlhf-qa-ppo / pytorch_model

40.6 GB

1 contributor

History: 1 commit

kastan's picture

Step 3 of 3; First attempt at a PPO fine-tuned model.

959dbed almost 3 years ago

mp_rank_00_model_states.pt
Detected Pickle imports (6)
- "torch.HalfStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.Size",
- "torch.ByteStorage",
- "__builtin__.set",
- "collections.OrderedDict"
How to fix it?
16 GB
xet

Step 3 of 3; First attempt at a PPO fine-tuned model. almost 3 years ago
zero_pp_rank_0_mp_rank_00_optim_states.pt
Detected Pickle imports (6)
- "collections.OrderedDict",
- "deepspeed.utils.tensor_fragment.fragment_address",
- "torch.FloatStorage",
- "deepspeed.runtime.zero.config.ZeroStageEnum",
- "deepspeed.runtime.fp16.loss_scaler.DynamicLossScaler",
- "torch._utils._rebuild_tensor_v2"
How to fix it?
24.7 GB
xet

Step 3 of 3; First attempt at a PPO fine-tuned model. almost 3 years ago