Kastan's group workspace
Group: Jul-27__18:15
Name
32 visualized
Name: gpt2_8b_2p5d_256
Name: gpt2_8b_2p5d_256
32
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
Crashed
-
kastan
2h 30m 55s
-
1280
-
0.00015
-
60
8
-
-
1024
-
2.5d
16
-
1280
50304
21
0.01
-
1
-
-
/u/kastanday/LLM-Distributed-Quantization/datasets/small-gpt-dataset.json
AMP_TYPE.NAIVE
-
titans.model.gpt.gpt.gpt2_8B
-
titans.model.gpt.gpt.gpt2_xl
1
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
torch.float16
true
1024
-
50304
0.00015
-
0.01
2
2.5d
16
-
-
Failed
-
kastan
my_first_tag
31m 32s
-
1280
-
0.00015
-
60
8
-
-
1024
-
2.5d
16
-
1280
50304
21
0.01
-
1
-
-
/u/kastanday/LLM-Distributed-Quantization/datasets/small-gpt-dataset.json
AMP_TYPE.NAIVE
-
titans.model.gpt.gpt.gpt2_8B
-
titans.model.gpt.gpt.gpt2_xl
1
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
torch.float16
true
1024
-
50304
0.00015
-
0.01
2
2.5d
16
-
-
Crashed
-
kastan
my_first_tag
2h 30m 37s
-
1280
-
0.00015
-
60
8
-
-
1024
-
2.5d
16
-
1280
50304
21
0.01
-
1
-
-
/u/kastanday/LLM-Distributed-Quantization/datasets/small-gpt-dataset.json
AMP_TYPE.NAIVE
-
titans.model.gpt.gpt.gpt2_8B
-
titans.model.gpt.gpt.gpt2_xl
1
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
torch.float16
true
1024
-
50304
0.00015
-
0.01
2
2.5d
16
-
-
Crashed
-
kastan
my_first_tag
2h 30m 51s
-
1280
-
0.00015
-
60
8
-
-
1024
-
2.5d
16
-
1280
50304
21
0.01
-
1
-
-
/u/kastanday/LLM-Distributed-Quantization/datasets/small-gpt-dataset.json
AMP_TYPE.NAIVE
-
titans.model.gpt.gpt.gpt2_8B
-
titans.model.gpt.gpt.gpt2_xl
1
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
torch.float16
true
1024
-
50304
0.00015
-
0.01
2
2.5d
16
-
-
Crashed
-
kastan
my_first_tag
2h 30m 24s
-
1280
-
0.00015
-
60
8
-
-
1024
-
2.5d
16
-
1280
50304
21
0.01
-
1
-
-
/u/kastanday/LLM-Distributed-Quantization/datasets/small-gpt-dataset.json
AMP_TYPE.NAIVE
-
titans.model.gpt.gpt.gpt2_8B
-
titans.model.gpt.gpt.gpt2_xl
1
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
torch.float16
true
1024
-
50304
0.00015
-
0.01
2
2.5d
16
-
-
Crashed
-
kastan
my_first_tag
2h 30m 47s
-
1280
-
0.00015
-
60
8
-
-
1024
-
2.5d
16
-
1280
50304
21
0.01
-
1
-
-
/u/kastanday/LLM-Distributed-Quantization/datasets/small-gpt-dataset.json
AMP_TYPE.NAIVE
-
titans.model.gpt.gpt.gpt2_8B
-
titans.model.gpt.gpt.gpt2_xl
1
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
torch.float16
true
1024
-
50304
0.00015
-
0.01
2
2.5d
16
-
-
Crashed
-
kastan
my_first_tag
2h 30m 28s
-
1280
-
0.00015
-
60
8
-
-
1024
-
2.5d
16
-
1280
50304
21
0.01
-
1
-
-
/u/kastanday/LLM-Distributed-Quantization/datasets/small-gpt-dataset.json
AMP_TYPE.NAIVE
-
titans.model.gpt.gpt.gpt2_8B
-
titans.model.gpt.gpt.gpt2_xl
1
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
torch.float16
true
1024
-
50304
0.00015
-
0.01
2
2.5d
16
-
-
Failed
-
kastan
my_first_tag
31m 12s
-
1280
-
0.00015
-
60
8
-
-
1024
-
2.5d
16
-
1280
50304
21
0.01
-
1
-
-
/u/kastanday/LLM-Distributed-Quantization/datasets/small-gpt-dataset.json
AMP_TYPE.NAIVE
-
titans.model.gpt.gpt.gpt2_8B
-
titans.model.gpt.gpt.gpt2_xl
1
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
torch.float16
true
1024
-
50304
0.00015
-
0.01
2
2.5d
16
-
-
Failed
-
kastan
my_first_tag
31m 13s
-
1280
-
0.00015
-
60
8
-
-
1024
-
2.5d
16
-
1280
50304
21
0.01
-
1
-
-
/u/kastanday/LLM-Distributed-Quantization/datasets/small-gpt-dataset.json
AMP_TYPE.NAIVE
-
titans.model.gpt.gpt.gpt2_8B
-
titans.model.gpt.gpt.gpt2_xl
1
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
torch.float16
true
1024
-
50304
0.00015
-
0.01
2
2.5d
16
-
-
Crashed
-
kastan
my_first_tag
2h 30m 37s
-
1280
-
0.00015
-
60
8
-
-
1024
-
2.5d
16
-
1280
50304
21
0.01
-
1
-
-
/u/kastanday/LLM-Distributed-Quantization/datasets/small-gpt-dataset.json
AMP_TYPE.NAIVE
-
titans.model.gpt.gpt.gpt2_8B
-
titans.model.gpt.gpt.gpt2_xl
1
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
torch.float16
true
1024
-
50304
0.00015
-
0.01
2
2.5d
16
-
-
Crashed
-
kastan
my_first_tag
2h 30m 36s
-
1280
-
0.00015
-
60
8
-
-
1024
-
2.5d
16
-
1280
50304
21
0.01
-
1
-
-
/u/kastanday/LLM-Distributed-Quantization/datasets/small-gpt-dataset.json
AMP_TYPE.NAIVE
-
titans.model.gpt.gpt.gpt2_8B
-
titans.model.gpt.gpt.gpt2_xl
1
titans.loss.lm_loss.gpt_lmloss.GPTLMLoss
-
true
torch.float16
true
1024
-
50304
0.00015
-
0.01
2
2.5d
16
-
-
1-1
of 1