Jrahn's workspace
Runs
30
Name
5 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
_n_gpu
_name_or_path
_num_labels
activation
activation_dropout
activation_function
adafactor
adam_beta1
adam_beta2
adam_epsilon
add_bias_logits
add_cross_attention
add_final_layer_norm
architectures
attention_dropout
attention_layers
attention_probs_dropout_prob
attention_types
attn_pdrop
bos_token_id
chunk_size_feed_forward
classif_dropout
classifier_dropout
d_model
dataloader_drop_last
dataloader_num_workers
dataloader_pin_memory
ddp_find_unused_parameters
debug
decoder_attention_heads
decoder_ffn_dim
decoder_layerdrop
decoder_layers
decoder_start_token_id
deepspeed
dim
directionality
disable_tqdm
diversity_penalty
do_eval
do_predict
do_sample
do_train
dropout
Finished
-
jrahn
14m 58s
-
1
distilbert-base-uncased
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["DistilBertForMaskedLM"]
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
4h 6m 31s
-
1
distilbert-base-uncased
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["DistilBertForMaskedLM"]
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
19m 32s
-
1
results\distilbert-base-uncased-jigsaw2-regr
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["DistilBertForSequenceClassification"]
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
1h 52m 8s
-
2
distilbert-base-uncased
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["DistilBertForMaskedLM"]
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
19m 30s
-
1
distilbert-base-uncased
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["DistilBertForMaskedLM"]
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
24m 40s
-
1
microsoft/xtremedistil-l12-h384-uncased
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["BertModel"]
-
-
0.1
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
16m 3s
-
1
distilbert-base-uncased
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["DistilBertForMaskedLM"]
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
16m 22s
-
1
distilbert-base-uncased
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["DistilBertForMaskedLM"]
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
23m 57s
-
1
microsoft/MiniLM-L12-H384-uncased
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
-
-
-
0.1
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
4h 30m 25s
-
1
microsoft/deberta-v3-small
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
-
-
-
0.1
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
14m 48s
-
1
distilbert-base-uncased
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["DistilBertForMaskedLM"]
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
8m 37s
-
1
distilbert-base-cased
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
-
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
4h 31m 59s
-
1
distilbert-base-uncased
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["DistilBertForMaskedLM"]
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
14s
-
1
cardiffnlp/twitter-roberta-base-hate
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["RobertaForSequenceClassification"]
-
-
0.1
-
-
0
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
14s
-
1
Hate-speech-CNERG/dehatebert-mono-english
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["BertForSequenceClassification"]
-
-
0.1
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
bidi
false
0
true
false
false
false
-
Finished
-
jrahn
14s
-
1
gpt2
-
-
-
gelu_new
false
0.9
0.999
1.0000e-8
-
false
-
["GPT2LMHeadModel"]
-
-
-
-
0.1
50256
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
13s
-
1
distilgpt2
1
-
-
gelu_new
false
0.9
0.999
1.0000e-8
-
false
-
["GPT2LMHeadModel"]
-
-
-
-
0.1
50256
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
13m 32s
-
1
distilbert-base-uncased
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["DistilBertForMaskedLM"]
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
20s
-
1
facebook/bart-base
-
-
0.1
gelu
false
0.9
0.999
1.0000e-8
false
false
false
["BartModel"]
0.1
-
-
-
-
0
0
0.1
0
768
false
0
true
None
[]
12
3072
0
6
2
None
-
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
1m 9s
-
1
distilbert-base-uncased
-
gelu
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["DistilBertForMaskedLM"]
0.1
-
-
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
768
-
false
0
true
false
false
false
0.1
Finished
-
jrahn
14s
-
1
distilroberta-base
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["RobertaForMaskedLM"]
-
-
0.1
-
-
0
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
57s
-
1
microsoft/deberta-v3-small
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
-
-
-
0.1
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
2m 3s
-
1
microsoft/MiniLM-L12-H384-uncased
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
-
-
-
0.1
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
14s
-
1
unitary/toxic-bert
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["BertForSequenceClassification"]
-
-
0.1
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
15h 20m 39s
-
1
cardiffnlp/twitter-roberta-base-offensive
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["RobertaForSequenceClassification"]
-
-
0.1
-
-
0
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
13s
-
1
distilgpt2
1
-
-
gelu_new
false
0.9
0.999
1.0000e-8
-
false
-
["GPT2LMHeadModel"]
-
-
-
-
0.1
50256
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
14s
-
1
microsoft/deberta-base
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
-
-
-
0.1
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
2m 3s
-
1
microsoft/xtremedistil-l12-h384-uncased
-
-
-
-
false
0.9
0.999
1.0000e-8
-
false
-
["BertModel"]
-
-
0.1
-
-
-
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
14s
-
1
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]]
-
50256
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
Finished
-
jrahn
14s
-
1
gpt2-medium
-
-
-
gelu_new
false
0.9
0.999
1.0000e-8
-
false
-
["GPT2LMHeadModel"]
-
-
-
-
0.1
50256
0
-
-
-
false
0
true
None
[]
-
-
-
-
-
None
-
-
false
0
true
false
false
false
-
1-30
of 30