BRlkl
/

test_multiturn_simple_transcript1024_6_response_loss_only-checkpoints

Model card Files Files and versions

test_multiturn_simple_transcript1024_6_response_loss_only-checkpoints

7.54 GB

Ctrl+K

Ctrl+K

1 contributor

History: 10 commits

BRlkl's picture

Update workspace checkpoint for t5gemma2-thoughtloop-pre-sft-simple-transcript (step-900)

e311227 verified 25 days ago

.gitattributes

1.57 kB
Update workspace checkpoint for t5gemma2-thoughtloop-pre-sft-simple-transcript (step-100) 25 days ago
chat_template.jinja

577 Bytes
Update workspace checkpoint for t5gemma2-thoughtloop-pre-sft-simple-transcript (step-100) 25 days ago
initial_latent_z.safetensors

4.19 MB
xet

Update workspace checkpoint for t5gemma2-thoughtloop-pre-sft-simple-transcript (step-900) 25 days ago
metrics.json

84 Bytes
Update workspace checkpoint for t5gemma2-thoughtloop-pre-sft-simple-transcript (step-900) 25 days ago
model.safetensors

2.52 GB
xet

Update workspace checkpoint for t5gemma2-thoughtloop-pre-sft-simple-transcript (step-900) 25 days ago
sft_b200.yaml

4.46 kB
Update workspace checkpoint for t5gemma2-thoughtloop-pre-sft-simple-transcript (step-100) 25 days ago
sft_config.json

5.32 kB
Update workspace checkpoint for t5gemma2-thoughtloop-pre-sft-simple-transcript (step-100) 25 days ago
tokenizer.json

34.4 MB
xet

Update workspace checkpoint for t5gemma2-thoughtloop-pre-sft-simple-transcript (step-100) 25 days ago
tokenizer_config.json

469 Bytes
Update workspace checkpoint for t5gemma2-thoughtloop-pre-sft-simple-transcript (step-100) 25 days ago
training_state.pt
Detected Pickle imports (4)
- "torch.FloatStorage",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
4.98 GB
xet

Update workspace checkpoint for t5gemma2-thoughtloop-pre-sft-simple-transcript (step-900) 25 days ago