Pszemraj's workspace
Runs
5
Name
5 visualized
Tags
loss
step
Notes
learning_rate
batch_size
wizard of wikipedia
1.50245
10454
-
0.0000042428
32
No EOS token
1.40829
2014
no eos token appended at the end
0.000042216
32
Chatbot
ai-msgbot
gpt-peter
1.48527
4139
the first training run of the GPT-peter dataset V5 on GPT-J 8bit
1.2385e-8
32
Chatbot
ai-msgbot
dailydialogue
1.49044
2723
single epoch
1.8825e-8
32
Chatbot
ai-msgbot
wizard of wikipedia
1.52689
1001
1000k steps or 5% of train
0.000049028
32
State
User
Created
Runtime
Sweep
dataset
epochs
gradient_acc_steps
learning_rate
max_grad_norm
max_length
output_file
warmup_ratio
weight_decay
epoch
Crashed
pszemraj
19h 52s
-
KILT-wow-cased
1
2
0.00005
1
512
/content/drive/MyDrive/Projects/chatbots/6b-models/clean-start-tuning/gptj_8bitmodel_Sep-16-2022_t-17.pt
0.025
0.1
0
Finished
pszemraj
4h 1m 55s
-
KILT-wow-cased
1
2
0.00005
1
512
/content/drive/MyDrive/Projects/chatbots/6b-models/clean-start-tuning/gptj_8bitmodel_Sep-16-2022_t-13.pt
0.025
0.1
0
Crashed
pszemraj
7h 40m 25s
-
gpt-peter-v5
1
1
0.00005
1
512
/content/drive/MyDrive/Projects/chatbots/6b-models/clean-start-tuning/gptj_8bitmodel_Sep-06-2022_t-13.pt
0.025
0.1
0
Finished
pszemraj
5h 6m 48s
-
daily-dialogues-cased
1
1
0.00005
1
512
/content/drive/MyDrive/Projects/chatbots/6b-models/clean-start-tuning/gptj_8bitmodel_Sep-06-2022_t-07.pt
0.025
0.1
0
Finished
pszemraj
1h 51m 53s
-
KILT-wow-cased
2
1
0.00005
1
512
/content/drive/MyDrive/Projects/chatbots/6b-models/clean-start-tuning/gptj_8bitmodel_Sep-06-2022_t-05.pt
0.025
0.1
0
1-5
of 5