Skip to main content
pvduy
Projects
trlx
Workspace
Log in
Sign up
Overview
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Pvduy's workspace
Personal workspace
Automated workspace
Changes are only visible to you.
Runs
1,135
Name
2 visualized
dpo_ultrafeedback/mistral-7b-sft-beta/8gpus:dpo_ultrafeedback
dpo_ultrafeedback/mistral-7b-sft-beta/8gpus:dpo_ultrafeedback
dpo_ultrafeedback/mistral-7b-sft-beta/8gpus:dpo_ultrafeedback
dpo_ultrafeedback/mistral-7b-sft-beta/8gpus:dpo_ultrafeedback
dpo_ultrafeedback/mistral-7b-sft-beta/8gpus:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/8gpus:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/1gpu:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/1gpu:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/8gpus:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/8gpus:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/1gpu:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/1gpu:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/1gpu:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/1gpu:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/1gpu:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/1gpu:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/8gpus:504-dpo-trainer
dpo_ultrafeedback/mistral-7b-sft-beta/8gpus:504-dpo-trainer
rest_code/CodeLlama-7b-Instruct-hf/31gpus:main
rest_code/CodeLlama-7b-Instruct-hf/31gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-7b-Instruct-hf/7gpus:main
rest_code/CodeLlama-13b-Instruct-hf/7gpus:main
rest_code/CodeLlama-13b-Instruct-hf/7gpus:main
rest_code/CodeLlama-13b-Instruct-hf/7gpus:main
rest_code/CodeLlama-13b-Instruct-hf/7gpus:main
rest_code/CodeLlama-13b-Instruct-hf/7gpus:main
rest_code/CodeLlama-13b-Instruct-hf/7gpus:main
1-20
of 1,135
Settings
Add panels
rollout_scores
4
1-4 of 4
reward
1
reward/mean
reward/mean
0
200
400
600
800
1k
1.2k
Step
0.2
0.4
0.6
0.8
without_8bit_sentiment
load_with_8bit_sentiment
old_values
4
1-4 of 4
time
6
1-6 of 6
time/rollout_generate
time/rollout_generate
0
200
400
600
800
1k
1.2k
Step
2
4
6
8
10
without_8bit_sentiment
load_with_8bit_sentiment
time/rollout_time
time/rollout_time
0
200
400
600
800
1k
1.2k
Step
4
6
8
10
12
without_8bit_sentiment
load_with_8bit_sentiment
time/rollout_score
time/rollout_score
0
200
400
600
800
1k
1.2k
Step
0.1
0.2
0.3
0.4
0.5
without_8bit_sentiment
load_with_8bit_sentiment
Tables
1
Add section