lmc7150
/

rl-nethack-models

Model card Files Files and versions

Metrics Training metrics Community

rl-nethack-models / artifacts /output /qwen14b_long_medium_50step

1.12 GB

Ctrl+K

Ctrl+K

2 contributors

History: 1 commit

Luc

preserve medium adapter, evals, and rl train artifacts

9a8acce 4 months ago

checkpoint-50
preserve medium adapter, evals, and rl train artifacts 4 months ago
README.md

5.21 kB
preserve medium adapter, evals, and rl train artifacts 4 months ago
adapter_config.json

1.11 kB
xet

preserve medium adapter, evals, and rl train artifacts 4 months ago
adapter_model.safetensors

275 MB
xet

preserve medium adapter, evals, and rl train artifacts 4 months ago
chat_template.jinja

2.43 kB
preserve medium adapter, evals, and rl train artifacts 4 months ago
tokenizer.json

11.4 MB
xet

preserve medium adapter, evals, and rl train artifacts 4 months ago
tokenizer_config.json

666 Bytes
xet

preserve medium adapter, evals, and rl train artifacts 4 months ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.OptimizerNames",
- "torch.device",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.TrainingArguments"
How to fix it?
5.2 kB
xet

preserve medium adapter, evals, and rl train artifacts 4 months ago
training_meta.json

1.09 kB
xet

preserve medium adapter, evals, and rl train artifacts 4 months ago