Pszemraj's workspace
Runs
11
Name
11 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
_name_or_path
_num_labels
_remove_final_layer_norm
activation_dropout
activation_function
adafactor
adam_beta1
adam_beta2
adam_epsilon
add_cross_attention
architectures
attention_dropout
attention_layers
attention_types
attn_pdrop
auto_find_batch_size
bf16
bf16_full_eval
bos_token_id
chunk_size_feed_forward
data_seed
dataloader_drop_last
dataloader_num_workers
dataloader_pin_memory
ddp_bucket_cap_mb
ddp_find_unused_parameters
ddp_timeout
debug
deepspeed
disable_tqdm
diversity_penalty
do_eval
do_layer_norm_before
do_predict
do_sample
do_train
dropout
early_stopping
embd_pdrop
embed_dropout
encoder_no_repeat_ngram_size
eos_token_id
eval_accumulation_steps
eval_batch_size
Finished
-
pszemraj
distilgpt2
multi-prompt
1h 12m 37s
-
pszemraj/distilgpt2-multiprompt-v1
1
-
-
gelu_new
false
0.9
0.999
1.0000e-8
false
["GPT2LMHeadModel"]
-
-
-
0.1
false
false
false
50256
0
69420
false
40
true
None
None
1800
[]
None
false
0
true
-
false
false
true
-
false
0.1
-
0
50256
None
4
Killed
-
pszemraj
distilgpt2
multi-prompt
39s
-
pszemraj/distilgpt2-multiprompt-v1
1
-
-
gelu_new
false
0.9
0.999
1.0000e-8
false
["GPT2LMHeadModel"]
-
-
-
0.1
false
false
false
50256
0
69420
false
40
true
None
None
1800
[]
None
false
0
true
-
false
false
true
-
false
0.1
-
0
50256
None
4
Finished
-
pszemraj
distilgpt2
multi-prompt
1h 6m 12s
-
pszemraj/distilgpt2-multi-prompt-v0.5
1
-
-
gelu_new
false
0.9
0.999
1.0000e-8
false
["GPT2LMHeadModel"]
-
-
-
0.1
false
true
true
50256
0
69
false
40
true
None
None
1800
[]
None
false
0
true
-
false
false
true
-
false
0.1
-
0
50256
None
4
Finished
-
pszemraj
opt
8h 28m 7s
-
facebook/opt-350m
-
false
0
relu
false
0.9
0.999
1.0000e-8
false
["OPTForCausalLM"]
0
-
-
-
false
true
true
2
0
None
true
16
true
None
None
1800
[]
None
false
0
true
false
false
false
true
0.1
false
-
-
0
2
None
4
Killed
this is actually distilgpt2 v1
pszemraj
distilgpt2
multiprompt
1h 13m 23s
-
distilgpt2
1
-
-
gelu_new
false
0.9
0.999
1.0000e-8
false
["GPT2LMHeadModel"]
-
-
-
0.1
false
false
false
50256
0
None
true
16
true
None
None
1800
[]
None
false
0
true
-
false
false
true
-
false
0.1
-
0
50256
None
4
Finished
-
pszemraj
16m 45s
-
distilgpt2
1
-
-
gelu_new
false
0.9
0.999
1.0000e-8
false
["GPT2LMHeadModel"]
-
-
-
0.1
false
true
false
50256
0
None
true
60
true
None
None
1800
[]
None
false
0
true
-
false
false
true
-
false
0.1
-
0
50256
None
2
Finished
-
pszemraj
4m 58s
-
sshleifer/tiny-gpt2
-
-
-
gelu_new
false
0.9
0.999
1.0000e-8
false
["GPT2LMHeadModel"]
-
-
-
0.1
false
true
false
50256
0
None
true
60
true
None
None
1800
[]
None
false
0
true
-
false
false
true
-
false
0.1
-
0
50256
None
2
Finished
-
pszemraj
48m 26s
-
facebook/opt-350m
-
false
0
relu
false
0.9
0.999
1.0000e-8
false
["OPTForCausalLM"]
0
-
-
-
false
true
false
2
0
None
true
60
true
None
None
1800
[]
None
false
0
true
false
false
false
true
0.1
false
-
-
0
2
None
2
Failed
-
pszemraj
23s
-
EleutherAI/gpt-neo-1.3B
-
-
-
gelu_new
false
0.9
0.999
1.0000e-8
false
["GPTNeoForCausalLM"]
0
["global","local","global","local","global","local","global","local","global","local","global","local","global","local","global","local","global","local","global","local","global","local","global","local"]
[[["global","local"],12]]
-
false
true
false
50256
0
None
true
60
true
None
None
1800
[]
None
false
0
true
-
false
false
true
-
false
-
0
0
50256
None
2
Failed
-
pszemraj
33s
-
EleutherAI/gpt-neo-1.3B
-
-
-
gelu_new
false
0.9
0.999
1.0000e-8
false
["GPTNeoForCausalLM"]
0
["global","local","global","local","global","local","global","local","global","local","global","local","global","local","global","local","global","local","global","local","global","local","global","local"]
[[["global","local"],12]]
-
false
true
false
50256
0
None
true
60
true
None
None
1800
[]
None
false
0
true
-
false
false
true
-
false
-
0
0
50256
None
2
Finished
-
pszemraj
gpt-neo
23m 40s
-
EleutherAI/gpt-neo-125M
-
-
-
gelu_new
false
0.9
0.999
1.0000e-8
false
["GPTNeoForCausalLM"]
0
["global","local","global","local","global","local","global","local","global","local","global","local"]
[[["global","local"],6]]
-
false
true
false
50256
0
None
true
60
true
None
None
1800
[]
None
false
0
true
-
false
false
true
-
false
-
0
0
50256
None
2
1-11
of 11