Som's workspace
Runs
19
Name
19 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
batch_size
checkpointer._component_
checkpointer.checkpoint_dir
checkpointer.checkpoint_files
checkpointer.model_type
checkpointer.output_dir
compile
dataset._component_
dataset.max_seq_len
dataset.source
dataset.split
dataset.template
dataset.train_on_input
device
dtype
enable_activation_checkpointing
epochs
gradient_accumulation_steps
loss._component_
lr_scheduler._component_
lr_scheduler.num_warmup_steps
metric_logger._component_
metric_logger.project
model._component_
model.apply_lora_to_mlp
model.apply_lora_to_output
model.lora_alpha
model.lora_attn_modules
model.lora_rank
optimizer._component_
optimizer.lr
optimizer.weight_decay
output_dir
profiler._component_
profiler.enabled
resume_from_checkpoint
shuffle
tokenizer._component_
tokenizer.path
gpu_resources
loss
lr
peak_memory_active
peak_memory_alloc
Failed
-
som
6s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
10s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
6s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
11s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
13s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
8s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
RyanSaleh/fdd
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
9s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
/teamspace/studios/this_studio/1.json
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
30s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
/teamspace/studios/this_studio/1.json
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
7s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3/
false
torchtune.datasets.instruct_dataset
512
/teamspace/studios/this_studio/1.json
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
6s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
/teamspace/studios/this_studio/1.json
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
6s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
/teamspace/studios/this_studio/1.json
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Killed
-
som
31s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
28s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
9s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
30s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
7s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
10s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Failed
-
som
34s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
-
-
-
-
-
Finished
-
som
2h 42m 40s
-
2
torchtune.utils.FullModelMetaCheckpointer
/teamspace/studios/this_studio/llama3-8b-hf/original/
["consolidated.00.pth"]
LLAMA3
/teamspace/studios/this_studio/llama3-8b-hf/
false
torchtune.datasets.instruct_dataset
512
Someshfengde/AIMO_dataset
train
AlpacaInstructTemplate
true
cuda
bf16
true
1
64
torch.nn.CrossEntropyLoss
torchtune.modules.get_cosine_schedule_with_warmup
100
torchtune.utils.metric_logging.WandBLogger
torchtune_llama3
torchtune.models.llama3.lora_llama3_8b
false
false
16
["q_proj","v_proj"]
8
torch.optim.AdamW
0.0003
0.01
lora_finetune_output
torchtune.utils.profiler
false
false
true
torchtune.models.llama3.llama3_tokenizer
/teamspace/studios/this_studio/llama3-8b-hf/original/tokenizer.model
17055448064
0.76291
0
17.3223
17.3223
1-19
of 19