Catalpa's workspace
Runs
1
Name
1 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
batch_size
config
context_size
eos_token
memmap_path
stride
train_val_ratio
Learning Rate
Training Loss (epoch)
Training Loss (step)
Training Perplexity (epoch)
Training Perplexity (step)
Validation Loss (epoch)
Validation Loss (step)
Validation Perplexity (epoch)
Validation Perplexity (step)
epoch
trainer/global_step
Finished
catalpa
13h 16m 28s
-
18
mamba_4chan_130m_config(d_model=768, n_layer=24, vocab_size=50277, ssm_cfg={}, rms_norm=True, residual_in_fp32=True, fused_add_norm=True, pad_vocab_size_multiple=8, tie_embeddings=True)
2048
0
/dev/shm/dataset.dat
2047
0.95
0.0001
2.89623
2.8321
18.23058
16.9829
2.80002
2.81213
16.48051
16.65859
0
1276
1-1
of 1