D0rj's workspace
Runs
12
Name
12 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
_name_or_path
adafactor
adam_beta1
adam_beta2
adam_epsilon
add_cross_attention
architectures
auto_find_batch_size
bf16
bf16_full_eval
chunk_size_feed_forward
classifier_dropout
d_ff
d_kv
d_model
data_seed
dataloader_drop_last
dataloader_num_workers
dataloader_pin_memory
ddp_backend
ddp_bucket_cap_mb
ddp_find_unused_parameters
ddp_timeout
debug
decoder_start_token_id
deepspeed
dense_act_fn
disable_tqdm
diversity_penalty
do_eval
do_predict
do_sample
do_train
dropout_rate
early_stopping
encoder_no_repeat_ngram_size
eos_token_id
eval_accumulation_steps
eval_batch_size
eval_delay
eval_steps
evaluation_strategy
feed_forward_proj
fp16
Finished
-
d0rj
11h 1m 39s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
0
2816
64
1024
-
false
0
true
-
-
-
1800
[]
0
-
gelu_new
false
0
false
false
false
false
0.1
false
0
2
-
-
0
-
no
gated-gelu
false
Finished
-
d0rj
7h 6m 23s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
-
2816
64
1024
None
false
0
true
None
None
None
1800
[]
0
None
gelu_new
false
0
false
false
false
false
0.1
false
0
2
None
8
0
None
no
gated-gelu
false
Finished
-
d0rj
11h 3m 23s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
-
2816
64
1024
None
false
0
true
None
None
None
1800
[]
0
None
gelu_new
false
0
false
false
false
false
0.1
false
0
2
None
8
0
None
no
gated-gelu
false
Crashed
-
d0rj
22m 3s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
-
2816
64
1024
None
false
0
true
None
None
None
1800
[]
0
None
gelu_new
false
0
false
false
false
false
0.1
false
0
2
None
8
0
None
no
gated-gelu
false
Finished
-
d0rj
11h 5m 33s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
-
2816
64
1024
None
false
0
true
None
None
None
1800
[]
0
None
gelu_new
false
0
false
false
false
false
0.1
false
0
2
None
8
0
None
no
gated-gelu
false
Finished
-
d0rj
7h 2m 20s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
-
2816
64
1024
None
false
0
true
None
None
None
1800
[]
0
None
gelu_new
false
0
false
false
false
false
0.1
false
0
2
None
8
0
None
no
gated-gelu
false
Finished
-
d0rj
11h 3m 19s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
-
2816
64
1024
None
false
0
true
None
None
None
1800
[]
0
None
gelu_new
false
0
false
false
false
false
0.1
false
0
2
None
8
0
None
no
gated-gelu
false
Finished
-
d0rj
11h 4m 23s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
-
2816
64
1024
None
false
0
true
None
None
None
1800
[]
0
None
gelu_new
false
0
false
false
false
false
0.1
false
0
2
None
8
0
None
no
gated-gelu
false
Finished
-
d0rj
7h 5m 26s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
-
2816
64
1024
None
false
0
true
None
None
None
1800
[]
0
None
gelu_new
false
0
false
false
false
false
0.1
false
0
2
None
8
0
None
no
gated-gelu
false
Finished
-
d0rj
11h 2m 41s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
-
2816
64
1024
None
false
0
true
None
None
None
1800
[]
0
None
gelu_new
false
0
false
false
false
false
0.1
false
0
2
None
8
0
None
no
gated-gelu
false
Finished
-
d0rj
11h 3m 11s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
-
2816
64
1024
None
false
0
true
None
None
None
1800
[]
0
None
gelu_new
false
0
false
false
false
false
0.1
false
0
2
None
8
0
None
no
gated-gelu
false
Crashed
-
d0rj
30m 1s
-
/kaggle/input/fred-t5-large-instruct
false
0.9
0.999
1.0000e-8
false
["T5ForConditionalGeneration"]
false
false
false
0
-
2816
64
1024
None
false
0
true
None
None
None
1800
[]
0
None
gelu_new
false
0
false
false
false
false
0.1
false
0
2
None
8
0
None
no
gated-gelu
false
1-12
of 12