Kastan's group workspace
Group: <null>
Name
50 visualized
Name: still-resonance-56
Name: still-resonance-56
1
Name: feasible-salad-56
Name: feasible-salad-56
1
Name: robust-terrain-58
Name: robust-terrain-58
1
Name: ethereal-sun-58
Name: ethereal-sun-58
1
Name: divine-smoke-52
Name: divine-smoke-52
1
Name: scarlet-armadillo-55
Name: scarlet-armadillo-55
1
Name: wild-fire-54
Name: wild-fire-54
1
Name: cerulean-durian-52
Name: cerulean-durian-52
1
Name: quiet-river-49
Name: quiet-river-49
1
Name: peach-meadow-51
Name: peach-meadow-51
1
Name: hopeful-bee-48
Name: hopeful-bee-48
1
Name: peach-puddle-49
Name: peach-puddle-49
1
Name: fresh-waterfall-45
Name: fresh-waterfall-45
1
Name: eternal-paper-44
Name: eternal-paper-44
1
Name: ethereal-brook-47
Name: ethereal-brook-47
1
Name: stilted-paper-46
Name: stilted-paper-46
1
Name: golden-valley-40
Name: golden-valley-40
1
Name: wise-sound-43
Name: wise-sound-43
1
Name: peachy-elevator-41
Name: peachy-elevator-41
1
Name: rich-grass-42
Name: rich-grass-42
1
State
Notes
User
Tags
Created
Runtime
Sweep
BATCH_SIZE
HIDDEN_SIZE
LEARNING_RATE
MODE
NUM_EPOCHS
NUM_MICRO_BATCHES
PIPELINE
SEQ_LEN
SEQ_LENGTH
TENSOR_PARALLEL
TENSOR_PARALLEL_MODE
TENSOR_PARALLEL_SIZE
TENSOR_SHAPE
TOTAL_BATCH_SIZE
VOCAB_SIZE
WARMUP_EPOCHS
WEIGHT_DECAY
backend
clip_grad_norm
colossal_config_file
config
data_dir
fp16.mode
from_torch
gpt2_8B
gpt2_small
gpt2_xl
gradient_accumulation
loss.type
loss_fn.type
model.checkpoint
model.dtype
model.fuse_scale_mask_softmax
model.max_position_embeddings
model.type
model.vocab_size
optimizer.lr
optimizer.type
optimizer.weight_decay
parallel.pipeline
parallel.tensor.mode
parallel.tensor.size
zero.model_config.reuse_fp16_shard
zero.model_config.shard_strategy
Finished
kastan
4m 46s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Finished
kastan
4m 47s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Finished
kastan
4m 46s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Finished
kastan
4m 46s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Finished
kastan
44s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
30s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
30s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Finished
kastan
44s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
15s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
15s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
15s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
15s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
18s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
18s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
18s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
18s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
22s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Finished
kastan
35s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Finished
kastan
36s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
Failed
kastan
22s
-
1
-
-
-
60
-
-
1024
-
2
-
-
-
-
-
-
-
nccl
-
gpt2_configs/gpt2_1d.py
gpt2_configs/gpt2_1d.py
/u/kastan/colossal/data/train_data_FINAL.json
AMP_TYPE.NAIVE
true
-
titans.model.gpt.gpt.gpt2_small
-
-
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
-
-
-
titans.model.gpt.gpt.gpt2_small
-
0.00015
torch.optim.adam.Adam
0.01
1
1d
2
-
-
1-20
of 50