CriteriaPO
/

llama3.2-3b-orpo-finegrained-2e

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

llama3.2-3b-orpo-finegrained-2e / checkpoint-27706

45 GB

1 contributor

History: 1 commit

obiwit's picture

Training in progress, step 27706, checkpoint

43b031a verified 6 months ago

global_step27706
Training in progress, step 27706, checkpoint 6 months ago
config.json

886 Bytes

Training in progress, step 27706, checkpoint 6 months ago
generation_config.json

180 Bytes

Training in progress, step 27706, checkpoint 6 months ago
latest

16 Bytes

Training in progress, step 27706, checkpoint 6 months ago
model-00001-of-00002.safetensors

4.97 GB
xet

Training in progress, step 27706, checkpoint 6 months ago
model-00002-of-00002.safetensors

1.46 GB
xet

Training in progress, step 27706, checkpoint 6 months ago
model.safetensors.index.json

20.9 kB

Training in progress, step 27706, checkpoint 6 months ago
rng_state_0.pth
Detected Pickle imports (7)
- "torch._utils._rebuild_tensor_v2",
- "_codecs.encode",
- "torch.ByteStorage",
- "numpy.core.multiarray._reconstruct",
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict"
How to fix it?
16 kB
xet

Training in progress, step 27706, checkpoint 6 months ago
rng_state_1.pth
Detected Pickle imports (7)
- "torch._utils._rebuild_tensor_v2",
- "_codecs.encode",
- "torch.ByteStorage",
- "numpy.core.multiarray._reconstruct",
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict"
How to fix it?
16 kB
xet

Training in progress, step 27706, checkpoint 6 months ago
rng_state_2.pth
Detected Pickle imports (7)
- "torch._utils._rebuild_tensor_v2",
- "_codecs.encode",
- "torch.ByteStorage",
- "numpy.core.multiarray._reconstruct",
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict"
How to fix it?
16 kB
xet

Training in progress, step 27706, checkpoint 6 months ago
rng_state_3.pth
Detected Pickle imports (7)
- "torch._utils._rebuild_tensor_v2",
- "_codecs.encode",
- "torch.ByteStorage",
- "numpy.core.multiarray._reconstruct",
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict"
How to fix it?
16 kB
xet

Training in progress, step 27706, checkpoint 6 months ago
rng_state_4.pth
Detected Pickle imports (7)
- "torch._utils._rebuild_tensor_v2",
- "_codecs.encode",
- "torch.ByteStorage",
- "numpy.core.multiarray._reconstruct",
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict"
How to fix it?
16 kB
xet

Training in progress, step 27706, checkpoint 6 months ago
rng_state_5.pth
Detected Pickle imports (7)
- "torch._utils._rebuild_tensor_v2",
- "_codecs.encode",
- "torch.ByteStorage",
- "numpy.core.multiarray._reconstruct",
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict"
How to fix it?
16 kB
xet

Training in progress, step 27706, checkpoint 6 months ago
rng_state_6.pth
Detected Pickle imports (7)
- "torch._utils._rebuild_tensor_v2",
- "_codecs.encode",
- "torch.ByteStorage",
- "numpy.core.multiarray._reconstruct",
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict"
How to fix it?
16 kB
xet

Training in progress, step 27706, checkpoint 6 months ago
rng_state_7.pth
Detected Pickle imports (7)
- "torch._utils._rebuild_tensor_v2",
- "_codecs.encode",
- "torch.ByteStorage",
- "numpy.core.multiarray._reconstruct",
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict"
How to fix it?
16 kB
xet

Training in progress, step 27706, checkpoint 6 months ago
scheduler.pt
Pickle imports
- No problematic imports detected
What is a pickle import?
1.06 kB
xet

Training in progress, step 27706, checkpoint 6 months ago
special_tokens_map.json

335 Bytes

Training in progress, step 27706, checkpoint 6 months ago
tokenizer.json

17.2 MB
xet

Training in progress, step 27706, checkpoint 6 months ago
tokenizer_config.json

51.3 kB

Training in progress, step 27706, checkpoint 6 months ago
trainer_state.json

1.26 MB

Training in progress, step 27706, checkpoint 6 months ago
training_args.bin
Detected Pickle imports (14)
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "torch.device",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.IntervalStrategy",
- "alignment.configs.DPOConfig",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "trl.trainer.dpo_config.FDivergenceType",
- "torch.bfloat16",
- "accelerate.state.PartialState"
How to fix it?
7.86 kB
xet

Training in progress, step 27706, checkpoint 6 months ago
zero_to_fp32.py

29.2 kB

Training in progress, step 27706, checkpoint 6 months ago