Comment
objective/verifiable_correct_rate
objective/verifiable_correct_rate
Run set
2
Name
2 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
actor_num_gpus_per_node
add_bos
add_r1_style_format_reward
apply_arithmetic_reward
apply_r1_style_format_reward
apply_verifiable_reward
arithmetic_reward
async_mode
batched
beaker_dataset_id_urls
beaker_dataset_ids
beaker_experiment_url
beaker_node_hostname
beaker_workload_id
beta
binary_messages_key
bnb_4bit_quant_type
cache_dataset_only
chat_template_name
clip_grad_norm
cliprange
concatenated_forward
convert_preference_to_binary_dataset
dataset_mixer_eval_list
dataset_mixer_eval_list_splits
dataset_mixer_list
dataset_mixer_list_splits
dataset_source_key
deepspeed_stage
dpo_beta
dpo_gamma_beta_ratio
dpo_label_smoothing
dpo_loss_type
dpo_use_paged_optimizer
enable_prefix_caching
eps
eval_freq
eval_priority
exp_name
fused_optimizer
gamma
gather_whole_model
gradient_accumulation_steps
gradient_checkpointing
Failed
-
costah
no-tag-682-g782d335
olmo2_13b_grpo_fast_zero
pr-629
1d 5h 37m 20s
-
-
true
-
false
true
true
10
true
-
["https://beaker.org/ds/01JQEEBCJ0DFS1ND3C7KYYTSBJ","https://beaker.org/ds/01JQEEBCPQQSWC0BQ7RGSWW7EQ"]
["01JQEEBCJ0DFS1ND3C7KYYTSBJ","01JQEEBCPQQSWC0BQ7RGSWW7EQ"]
augusta-gcp-357
01JQEEBCGFVQ9DMEMHKM0V2AZR
0
-
nf4
false
r1_simple_chat_postpend_think
-
0.2
-
-
["ai2-adapt-dev/math_ground_truth_zs","16"]
["train"]
["ai2-adapt-dev/math_ground_truth_zs","1.0"]
["train"]
-
3
-
-
-
-
-
-
-
6
normal
olmo2_13b_grpo_fast_zero
false
-
true
-
true
Finished
-
costah
no-tag-682-g782d335
olmo2_7b_grpo_fast_zero
pr-629
20h 38m 27s
-
-
true
-
false
true
true
10
true
-
["https://beaker.org/ds/01JQD7TJENHSAAK54P5KRNKG45","https://beaker.org/ds/01JQD7TJKW69M2WM55CEJZ2644"]
["01JQD7TJENHSAAK54P5KRNKG45","01JQD7TJKW69M2WM55CEJZ2644"]
augusta-gcp-352
01JQD7TJCZM4MF7QRH8EGXRZZM
0
-
nf4
false
r1_simple_chat_postpend_think
-
0.2
-
-
["ai2-adapt-dev/math_ground_truth_zs","16"]
["train"]
["ai2-adapt-dev/math_ground_truth_zs","1.0"]
["train"]
-
3
-
-
-
-
-
-
-
6
normal
olmo2_7b_grpo_fast_zero
false
-
true
-
true
Finished
-
costah
no-tag-680-gbba6fab8
olmo2_13b_sft
pr-629
14h 28m
-
-
true
-
-
-
-
-
-
-
["https://beaker.org/ds/01JQBVCDA9646J0NFECEBSJ6R9","https://beaker.org/ds/01JQBVCDFEMJ6HN7S50WZGT0KS","https://beaker.org/ds/01JQBVCDMBGSCW33WBJ4ZDPZFK","https://beaker.org/ds/01JQBVCDSCQ1SEBYWCQ902B7P4","https://beaker.org/ds/01JQBVCDY5WQJHPTH5KTR9PF7Z","https://beaker.org/ds/01JQBVCE2ZSVDM2AZNKS55YMXW","https://beaker.org/ds/01JQBVCE7VAPTR1B6E2N8BW9YE","https://beaker.org/ds/01JQBVCECVP29VDZ3DBX7EDCPY"]
["01JQBVCDA9646J0NFECEBSJ6R9","01JQBVCDFEMJ6HN7S50WZGT0KS","01JQBVCDMBGSCW33WBJ4ZDPZFK","01JQBVCDSCQ1SEBYWCQ902B7P4","01JQBVCDY5WQJHPTH5KTR9PF7Z","01JQBVCE2ZSVDM2AZNKS55YMXW","01JQBVCE7VAPTR1B6E2N8BW9YE","01JQBVCECVP29VDZ3DBX7EDCPY"]
augusta-gcp-292
01JQBVCD8RWJ3RXREQWFAQGJ88
-
-
-
false
tulu
-1
-
-
-
-
-
["allenai/tulu-3-sft-olmo-2-mixture-0225","1.0"]
["train"]
-
-
-
-
-
-
-
-
-
-
-
olmo2_13b_sft
true
-
-
1
true
Finished
-
costah
no-tag-743-g52acdce
olmo2_32b_sft
pr-616
23h 14m 18s
-
-
true
-
-
-
-
-
-
-
["https://beaker.org/ds/01JPXYETPXXFVBTC5VSSDXCK2F","https://beaker.org/ds/01JPXYETWCW49WTEJKM56DANPS","https://beaker.org/ds/01JPXYEV1FKWPJYHSXM2J5VXQD","https://beaker.org/ds/01JPXYEV6TEBCPFZ1YGGP6CKWB","https://beaker.org/ds/01JPXYEVBXVFBFQ9T0C9P9AVJ4","https://beaker.org/ds/01JPXYEVH2PZHXPD1XZDDDBM0M","https://beaker.org/ds/01JPXYEVNWTHQFSFEDWF3GV7MQ","https://beaker.org/ds/01JPXYEVV9WVVCPC25GTCF6941","https://beaker.org/ds/01JPY98QWDHBGC9K2JE55YY7EB","https://beaker.org/ds/01JPY98R0K3VMNP9D56ED78ZGV","https://beaker.org/ds/01JPY98R5Q8QPY4XFYNW4SQEFM","https://beaker.org/ds/01JPY98RAJ7BSCFSH4H6C7VJR0","https://beaker.org/ds/01JPY98RFEJXZ94RDR20T0PG7P","https://beaker.org/ds/01JPY98RKF10AG1R95SHB9TARP","https://beaker.org/ds/01JPY98RQKVM0JW49MJBN46DRW","https://beaker.org/ds/01JPY98SG0KJW65W3KFDNBZWGE","https://beaker.org/ds/01JQ00TPC8PKMW5QASX5S6FJN2","https://beaker.org/ds/01JQ00TQBGYG3J7PZRKX0E3SPH","https://beaker.org/ds/01JQ00TQG1DJKFNDERTPEYR04H","https://beaker.org/ds/01JQ00TQRN05KM8D5V8NV1SAD7","https://beaker.org/ds/01JQ00TR10GFP0ZJECRR2FJA0Z","https://beaker.org/ds/01JQ00TR52MAQEBZMSS9WNEC10","https://beaker.org/ds/01JQ00TR94JHG7QVQDGBC3YTDS","https://beaker.org/ds/01JQ00TRVR8SPCCH3A4MT31TM3","https://beaker.org/ds/01JQ06XDJV58S7EB89HDH90Y8G","https://beaker.org/ds/01JQ06XDRXQCXR4AZVJD00TVC3","https://beaker.org/ds/01JQ06XDXVTZQYQMSVY55T6VRE","https://beaker.org/ds/01JQ06XE2DRTD6Z4CY7W9AXM6B","https://beaker.org/ds/01JQ06XE6RKA8XND2A0Q4929BE","https://beaker.org/ds/01JQ06XEB33EMX8HK6G9SBXJA4","https://beaker.org/ds/01JQ06XEFC3EKD67CYR9WRW9B1","https://beaker.org/ds/01JQ06XEKPT1PHRNMJG4H30WX3","https://beaker.org/ds/01JQ089BRWPJPB8YV3R3Q10E1Z","https://beaker.org/ds/01JQ089BXPH7SXFKWSQPTSJSA1","https://beaker.org/ds/01JQ089C1XEZABQQ22MVGB2HV2","https://beaker.org/ds/01JQ089C6SGSP1SYNWZP1F3VEB","https://beaker.org/ds/01JQ089CBCYZC5CDVPNFW0V3RN","https://beaker.org/ds/01JQ089CFW5KR7RSQYJ13D7ZA8","https://beaker.org/ds/01JQ089CMBV1MG8G1CZ4C9H69C","https://beaker.org/ds/01JQ089CRG90XKWXKF3R8C17B7"]
["01JPXYETPXXFVBTC5VSSDXCK2F","01JPXYETWCW49WTEJKM56DANPS","01JPXYEV1FKWPJYHSXM2J5VXQD","01JPXYEV6TEBCPFZ1YGGP6CKWB","01JPXYEVBXVFBFQ9T0C9P9AVJ4","01JPXYEVH2PZHXPD1XZDDDBM0M","01JPXYEVNWTHQFSFEDWF3GV7MQ","01JPXYEVV9WVVCPC25GTCF6941","01JPY98QWDHBGC9K2JE55YY7EB","01JPY98R0K3VMNP9D56ED78ZGV","01JPY98R5Q8QPY4XFYNW4SQEFM","01JPY98RAJ7BSCFSH4H6C7VJR0","01JPY98RFEJXZ94RDR20T0PG7P","01JPY98RKF10AG1R95SHB9TARP","01JPY98RQKVM0JW49MJBN46DRW","01JPY98SG0KJW65W3KFDNBZWGE","01JQ00TPC8PKMW5QASX5S6FJN2","01JQ00TQBGYG3J7PZRKX0E3SPH","01JQ00TQG1DJKFNDERTPEYR04H","01JQ00TQRN05KM8D5V8NV1SAD7","01JQ00TR10GFP0ZJECRR2FJA0Z","01JQ00TR52MAQEBZMSS9WNEC10","01JQ00TR94JHG7QVQDGBC3YTDS","01JQ00TRVR8SPCCH3A4MT31TM3","01JQ06XDJV58S7EB89HDH90Y8G","01JQ06XDRXQCXR4AZVJD00TVC3","01JQ06XDXVTZQYQMSVY55T6VRE","01JQ06XE2DRTD6Z4CY7W9AXM6B","01JQ06XE6RKA8XND2A0Q4929BE","01JQ06XEB33EMX8HK6G9SBXJA4","01JQ06XEFC3EKD67CYR9WRW9B1","01JQ06XEKPT1PHRNMJG4H30WX3","01JQ089BRWPJPB8YV3R3Q10E1Z","01JQ089BXPH7SXFKWSQPTSJSA1","01JQ089C1XEZABQQ22MVGB2HV2","01JQ089C6SGSP1SYNWZP1F3VEB","01JQ089CBCYZC5CDVPNFW0V3RN","01JQ089CFW5KR7RSQYJ13D7ZA8","01JQ089CMBV1MG8G1CZ4C9H69C","01JQ089CRG90XKWXKF3R8C17B7"]
augusta-gcp-277
01JPXYETNCF5AKTQNBEM4FDDJM
-
-
-
false
tulu
-1
-
-
-
-
-
["allenai/tulu-3-sft-olmo-2-mixture-0225","1.0"]
["train"]
-
-
-
-
-
-
-
-
-
-
-
olmo2_32b_sft
true
-
-
4
true
Failed
-
costah
no-tag-699-g2f63029
olmo2_13b_grpo
pr-616
3d 15h 40m 54s
-
[4,8]
true
false
-
-
true
-
true
false
["https://beaker.org/ds/01JPQ8XDX7KKBGRV5VGTBS1REV","https://beaker.org/ds/01JPQ8XE2RGVP9QPWEMR56QH1J"]
["01JPQ8XDX7KKBGRV5VGTBS1REV","01JPQ8XE2RGVP9QPWEMR56QH1J"]
augusta-gcp-420
01JPQ8XDVJBE93TZ42DQ9R2A9P
0.01
messages
nf4
false
tulu
-
0.2
-
false
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","16"]
["train"]
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","1.0"]
["train"]
dataset
2
-
-
-
-
-
false
0.00001
26
normal
olmo2_13b_grpo
-
1
false
32
true
Finished
-
costah
no-tag-699-g2f63029
olmo2_13b_grpo
pr-616
3d 20h 35m 12s
-
[4,8]
true
false
-
-
true
-
true
false
["https://beaker.org/ds/01JPQ8X189ZS8DDQGY2FDRKJCR","https://beaker.org/ds/01JPQ8X1DGK1BYYX1X5QN6DVTQ"]
["01JPQ8X189ZS8DDQGY2FDRKJCR","01JPQ8X1DGK1BYYX1X5QN6DVTQ"]
augusta-gcp-434
01JPQ8X16R92XP6TBYP57GTDTE
0.01
messages
nf4
false
tulu
-
0.2
-
false
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","16"]
["train"]
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","1.0"]
["train"]
dataset
2
-
-
-
-
-
false
0.00001
26
normal
olmo2_13b_grpo
-
1
false
32
true
Finished
-
costah
no-tag-699-g2f63029
olmo2_13b_grpo
pr-616
3d 23h 2m 56s
-
[4,8]
true
false
-
-
true
-
true
false
["https://beaker.org/ds/01JPQ8WMSAM1Z32QQA4J6XW0AV","https://beaker.org/ds/01JPQ8WMY2HAFTZT8SXE4Z4CSW"]
["01JPQ8WMSAM1Z32QQA4J6XW0AV","01JPQ8WMY2HAFTZT8SXE4Z4CSW"]
augusta-gcp-391
01JPQ8WMQSSA244TR9S9TNMY7G
0.01
messages
nf4
false
tulu
-
0.2
-
false
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","16"]
["train"]
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","1.0"]
["train"]
dataset
2
-
-
-
-
-
false
0.00001
26
normal
olmo2_13b_grpo
-
1
false
32
true
Failed
-
costah
no-tag-699-g2f63029
olmo2_7b_grpo
pr-616
2d 10h 21m 53s
-
[4,8]
true
false
-
-
true
-
true
false
["https://beaker.org/ds/01JPP8PKBYCC96G3SEZFHT2BMW","https://beaker.org/ds/01JPP8PKH1TNZ2MAJD8K3FTM6K","https://beaker.org/ds/01JPQ4WSA9V7GY4BXEBWEZZBT6","https://beaker.org/ds/01JPQ4WSEAJTRWV3EDNMGGGEZ0"]
["01JPP8PKBYCC96G3SEZFHT2BMW","01JPP8PKH1TNZ2MAJD8K3FTM6K","01JPQ4WSA9V7GY4BXEBWEZZBT6","01JPQ4WSEAJTRWV3EDNMGGGEZ0"]
augusta-gcp-377
01JPP8PKAEFE310C7ATY9AAJDK
0.01
messages
nf4
false
tulu
-
0.2
-
false
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","16"]
["train"]
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","1.0"]
["train"]
dataset
2
-
-
-
-
-
false
0.00001
26
normal
olmo2_7b_grpo
-
1
true
16
true
Finished
-
costah
no-tag-699-g2f63029
olmo2_7b_grpo
pr-616
2d 21h 31m 48s
-
[4,8]
true
false
-
-
true
-
true
false
["https://beaker.org/ds/01JPP8P70DNVWJFH09WY4K9C5D","https://beaker.org/ds/01JPP8P75DNXGX07YQJ01NKP5X"]
["01JPP8P70DNVWJFH09WY4K9C5D","01JPP8P75DNXGX07YQJ01NKP5X"]
augusta-gcp-426
01JPP8P6YR3P5FPBXQRK7GSN4P
0.01
messages
nf4
false
tulu
-
0.2
-
false
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","16"]
["train"]
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","1.0"]
["train"]
dataset
2
-
-
-
-
-
false
0.00001
26
normal
olmo2_7b_grpo
-
1
true
16
true
Failed
-
costah
no-tag-699-g2f63029
olmo2_7b_grpo
pr-616
2d 13h 18m 27s
-
[4,8]
true
false
-
-
true
-
true
false
["https://beaker.org/ds/01JPP8PZHEEQMAHPHKYGJAPV9Q","https://beaker.org/ds/01JPP8PZP7WACN68ZXBWGAXXQA"]
["01JPP8PZHEEQMAHPHKYGJAPV9Q","01JPP8PZP7WACN68ZXBWGAXXQA"]
augusta-gcp-400
01JPP8PZFX9BKK80RBZ78PBY4F
0.01
messages
nf4
false
tulu
-
0.2
-
false
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","16"]
["train"]
["allenai/RLVR-GSM-MATH-IF-Mixed-Constraints","1.0"]
["train"]
dataset
2
-
-
-
-
-
false
0.00001
26
normal
olmo2_7b_grpo
-
1
true
16
true
1-10
of 13
Add a comment
Created with ❤️ on Weights & Biases.
https://wandb.ai/ai2-llm/open_instruct_public/reports/olmo2--VmlldzoxMTg3MjM1NA