Skip to main content
jon-tow
Projects
trlx
Workspace
Log in
Sign up
Overview
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Jon-tow's workspace
Personal workspace
Automated workspace
Changes are only visible to you.
Runs
237
Name
1 visualized
ppo_sentiments/gpt2-imdb/8gpus:reduce-target-kl
ppo_sentiments/gpt2-imdb/8gpus:reduce-target-kl
ppo_sentiments/gpt2-imdb/1gpu:reduce-target-kl
ppo_sentiments/gpt2-imdb/1gpu:reduce-target-kl
ppo_sentiments/gpt2-imdb/1gpu:reduce-target-kl
ppo_sentiments/gpt2-imdb/1gpu:reduce-target-kl
ppo_translation_t5/t5-large/1gpu:translation
ppo_translation_t5/t5-large/1gpu:translation
ppo_hh/gpt-j-6B/7gpus:ppo-hh
ppo_hh/gpt-j-6B/7gpus:ppo-hh
ppo_hh/gpt-j-6B/7gpus:ppo-hh
ppo_hh/gpt-j-6B/7gpus:ppo-hh
ppo_hh/gpt-j-6B/7gpus:ppo-hh
ppo_hh/gpt-j-6B/7gpus:ppo-hh
ppo_hh/gpt-j-6B/7gpus:ppo-hh
ppo_hh/gpt-j-6B/7gpus:ppo-hh
/gpt2/1gpu:update-deprecated-args
/gpt2/1gpu:update-deprecated-args
t5_summarize_daily_cnn/flan-t5-xxl/2gpus:main
t5_summarize_daily_cnn/flan-t5-xxl/2gpus:main
t5_summarize_daily_cnn/flan-t5-xxl/2gpus:main
t5_summarize_daily_cnn/flan-t5-xxl/2gpus:main
ppo_sentiments/t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-base/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-base/2gpus:rewrite-gather-for-metrics
ppo_sentiments/gpt2-imdb/2gpus:rewrite-gather-for-metrics
ppo_sentiments/gpt2-imdb/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/flan-t5-small/2gpus:rewrite-gather-for-metrics
ppo_sentiments/gpt2-imdb/3gpus:rewrite-gather-for-metrics
ppo_sentiments/gpt2-imdb/3gpus:rewrite-gather-for-metrics
ppo_randomwalks/GPT2Config/8gpus:update-save-pretrained
ppo_randomwalks/GPT2Config/8gpus:update-save-pretrained
ilql_randomwalks/GPT2Config/8gpus:main
ilql_randomwalks/GPT2Config/8gpus:main
ilql_randomwalks/GPT2Config/8gpus:update-save-pretrained
ilql_randomwalks/GPT2Config/8gpus:update-save-pretrained
ilql_randomwalks/GPT2Config/8gpus:update-save-pretrained
ilql_randomwalks/GPT2Config/8gpus:update-save-pretrained
ilql_randomwalks/GPT2Config/2gpus:update-save-pretrained
ilql_randomwalks/GPT2Config/2gpus:update-save-pretrained
sft_sentiments/gpt2/2gpus:update-save-pretrained
sft_sentiments/gpt2/2gpus:update-save-pretrained
sft_sentiments/gpt2/3gpus:update-save-pretrained
sft_sentiments/gpt2/3gpus:update-save-pretrained
sft_sentiments/gpt2/1gpu:update-save-pretrained
sft_sentiments/gpt2/1gpu:update-save-pretrained
sft_sentiments/gpt2/2gpus:update-save-pretrained
sft_sentiments/gpt2/2gpus:update-save-pretrained
ppo_sentiments/gpt2-imdb/2gpus:update-save-pretrained
ppo_sentiments/gpt2-imdb/2gpus:update-save-pretrained
ppo_sentiments/gpt2-imdb/2gpus:update-save-pretrained
ppo_sentiments/gpt2-imdb/2gpus:update-save-pretrained
ppo_sentiments/gpt2-imdb/2gpus:update-save-pretrained
ppo_sentiments/gpt2-imdb/2gpus:update-save-pretrained
sft_sentiments/gpt2/2gpus:update-save-pretrained
sft_sentiments/gpt2/2gpus:update-save-pretrained
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
trlx_gptj_text_summarization/openai_summarize_tldr_sft/2gpus:gather-exp-samples
trlx_gptj_text_summarization/openai_summarize_tldr_sft/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
ppo_sentiments/gpt2-imdb/2gpus:gather-exp-samples
t5_summarize_daily_cnn/flan-t5-large/2gpus:fix-prompt-pipeline-tokens
t5_summarize_daily_cnn/flan-t5-large/2gpus:fix-prompt-pipeline-tokens
t5_summarize_daily_cnn/flan-t5-large/2gpus:fix-prompt-pipeline-tokens
t5_summarize_daily_cnn/flan-t5-large/2gpus:fix-prompt-pipeline-tokens
t5_summarize_daily_cnn/flan-t5-large/2gpus:fix-prompt-pipeline-tokens
t5_summarize_daily_cnn/flan-t5-large/2gpus:fix-prompt-pipeline-tokens
t5_summarize_daily_cnn/flan-t5-large/2gpus:main
t5_summarize_daily_cnn/flan-t5-large/2gpus:main
t5_summarize_daily_cnn/flan-t5-large/2gpus:main
t5_summarize_daily_cnn/flan-t5-large/2gpus:main
t5_summarize_daily_cnn/flan-t5-large/2gpus:main
t5_summarize_daily_cnn/flan-t5-large/2gpus:main
t5_summarize_daily_cnn/flan-t5-large/2gpus:fix-prompt-pipeline-tokens
t5_summarize_daily_cnn/flan-t5-large/2gpus:fix-prompt-pipeline-tokens
t5_summarize_daily_cnn/flan-t5-small/2gpus:main
t5_summarize_daily_cnn/flan-t5-small/2gpus:main
t5_summarize_daily_cnn/flan-t5-small/2gpus:remove-orchs
t5_summarize_daily_cnn/flan-t5-small/2gpus:remove-orchs
ppo_sentiments/flan-t5-small/2gpus:remove-orchs
ppo_sentiments/flan-t5-small/2gpus:remove-orchs
ppo_sentiments/gpt2-imdb/2gpus:remove-orchs
ppo_sentiments/gpt2-imdb/2gpus:remove-orchs
ilql_sentiments/gpt2/2gpus:remove-orchs
ilql_sentiments/gpt2/2gpus:remove-orchs
ilql_sentiments/gpt2/2gpus:main
ilql_sentiments/gpt2/2gpus:main
ppo_sentiments/gpt2-imdb/2gpus:main
ppo_sentiments/gpt2-imdb/2gpus:main
ilql_sentiments/gpt2/2gpus:main
ilql_sentiments/gpt2/2gpus:main
ppo_sentiments/gpt2-imdb/2gpus:remove-orchs
ppo_sentiments/gpt2-imdb/2gpus:remove-orchs
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ppo_sentiments/flan-t5-small/2gpus:patch-ppo-seq2seq
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:log-verbosity
ilql_sentiments/gpt2/8gpus:fix-eval-pbar
ilql_sentiments/gpt2/8gpus:fix-eval-pbar
ilql_sentiments/gpt2/8gpus:fix-eval-pbar
ilql_sentiments/gpt2/8gpus:fix-eval-pbar
ilql_sentiments/gpt2/8gpus:fix-eval-pbar
ilql_sentiments/gpt2/8gpus:fix-eval-pbar
1-100
of 237
old_values/std
old_values/std
500
1k
1.5k
Step
0.5
1
1.5
2
2.5
3
ppo_sentiments/gpt2-imdb/8gpus:reduce-target-kl
Previous
Next