Skip to content

Updated 1B Configs #866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jul 16, 2025
Merged

Updated 1B Configs #866

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0db5b52
updated 1b config's and readme
aman-17 Jul 16, 2025
09d9a7c
updated the load_paths
aman-17 Jul 16, 2025
600a8d0
updated `save_num_checkpoints_to_keep=0` in all the configs to not sa…
aman-17 Jul 16, 2025
acf344d
updated README
aman-17 Jul 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,7 @@ For the 1B model, we have trained three times with different data order on 50B h

| | Checkpoint | Training config | WandB |
|------------------------|-------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------|-------------|
| random seed 42049 | [stage2-ingredient1-step23852-tokens50B](https://huggingface.co/allenai/OLMo-2-0425-1B/tree/stage2-ingredient1-step23852-tokens51B) | [OLMo2-1B-stage2-seed42069.yaml](configs/official-0425/OLMo2-1B-stage2-seed42069.yaml) | [wandb.ai/OLMo2-1B](https://api.wandb.ai/links/ai2-llm/izdtrtu0) |
| random seed 42069 | [stage2-ingredient1-step23852-tokens50B](https://huggingface.co/allenai/OLMo-2-0425-1B/tree/stage2-ingredient1-step23852-tokens51B) | [OLMo2-1B-stage2-seed42069.yaml](configs/official-0425/OLMo2-1B-stage2-seed42069.yaml) | [wandb.ai/OLMo2-1B](https://api.wandb.ai/links/ai2-llm/izdtrtu0) |
| random seed 666 | [stage2-ingredient2-step23852-tokens50B](https://huggingface.co/allenai/OLMo-2-0425-1B/tree/stage2-ingredient2-step23852-tokens51B) | [OLMo2-1B-stage2-seed666.yaml](configs/official-0425/OLMo2-1B-stage2-seed666.yaml) | [wandb.ai/OLMo2-1B](https://api.wandb.ai/links/ai2-llm/izdtrtu0) |
| random seed 42 (main) | [stage2-ingredient3-step23852-tokens50B](https://huggingface.co/allenai/OLMo-2-0425-1B/tree/stage2-ingredient3-step23852-tokens51B) | [OLMo2-1B-stage2-seed42.yaml](configs/official-0425/OLMo2-1B-stage2-seed42.yaml) | [wandb.ai/OLMo2-1B](https://api.wandb.ai/links/ai2-llm/izdtrtu0) |

Expand Down
4 changes: 2 additions & 2 deletions configs/official-0425/OLMo2-1B-stage1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,10 +75,10 @@ save_overwrite: false

save_interval: 1000
save_interval_ephemeral: 1000
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: null
Expand Down
10 changes: 5 additions & 5 deletions configs/official-0425/OLMo2-1B-stage2-seed42.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ compile: null

optimizer:
name: adamw
learning_rate: 0.00036279
learning_rate: 0.000074487
weight_decay: 0.1
eps: 1e-8
decay_norm_and_bias: true
Expand All @@ -72,13 +72,13 @@ save_overwrite: false

save_interval: 1000
save_interval_ephemeral: 250
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: null
load_path: https://olmo-checkpoints.org/ai2-llm/peteish1/step1907359-unsharded/

restore_dataloader: false
no_pre_train_checkpoint: true
Expand Down Expand Up @@ -107,7 +107,7 @@ gen1_gc_interval: 10

eval_interval: 1000
eval_subset_num_batches: -1
device_eval_batch_size: ${device_train_microbatch_size}
device_eval_batch_size: 8
evaluators:
# - label: all-small-ppl-validation
# data:
Expand Down
10 changes: 5 additions & 5 deletions configs/official-0425/OLMo2-1B-stage2-seed42069.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ compile: null

optimizer:
name: adamw
learning_rate: 0.00036279
learning_rate: 0.000074487
weight_decay: 0.1
eps: 1e-8
decay_norm_and_bias: true
Expand All @@ -72,13 +72,13 @@ save_overwrite: false

save_interval: 1000
save_interval_ephemeral: 250
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: null
load_path: https://olmo-checkpoints.org/ai2-llm/peteish1/step1907359-unsharded/

restore_dataloader: false
no_pre_train_checkpoint: true
Expand Down Expand Up @@ -107,7 +107,7 @@ gen1_gc_interval: 10

eval_interval: 1000
eval_subset_num_batches: -1
device_eval_batch_size: ${device_train_microbatch_size}
device_eval_batch_size: 8
evaluators:
# - label: all-small-ppl-validation
# data:
Expand Down
10 changes: 5 additions & 5 deletions configs/official-0425/OLMo2-1B-stage2-seed666.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ compile: null

optimizer:
name: adamw
learning_rate: 0.00036279
learning_rate: 0.000074487
weight_decay: 0.1
eps: 1e-8
decay_norm_and_bias: true
Expand All @@ -72,13 +72,13 @@ save_overwrite: false

save_interval: 1000
save_interval_ephemeral: 250
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: null
load_path: https://olmo-checkpoints.org/ai2-llm/peteish1/step1907359-unsharded/

restore_dataloader: false
no_pre_train_checkpoint: true
Expand Down Expand Up @@ -107,7 +107,7 @@ gen1_gc_interval: 10

eval_interval: 1000
eval_subset_num_batches: -1
device_eval_batch_size: ${device_train_microbatch_size}
device_eval_batch_size: 8
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why is this needed?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just matching all the overwritten comments from this bash script.

evaluators:
# - label: all-small-ppl-validation
# data:
Expand Down
4 changes: 2 additions & 2 deletions configs/official-1124/OLMo2-13B-stage1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,10 +69,10 @@ save_overwrite: false

save_interval: 1000
save_interval_ephemeral: 250
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: null
Expand Down
4 changes: 2 additions & 2 deletions configs/official-1124/OLMo2-13B-stage2-seed1110-100B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,10 +62,10 @@ tokenizer:
truncate_direction: right

save_interval: 1000
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: https://olmo-checkpoints.org/ai2-llm/peteish13/step596057-unsharded
Expand Down
4 changes: 2 additions & 2 deletions configs/official-1124/OLMo2-13B-stage2-seed2662-100B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,10 +62,10 @@ tokenizer:
truncate_direction: right

save_interval: 1000
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: https://olmo-checkpoints.org/ai2-llm/peteish13/step596057-unsharded
Expand Down
4 changes: 2 additions & 2 deletions configs/official-1124/OLMo2-13B-stage2-seed2662-300B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,10 +62,10 @@ tokenizer:
truncate_direction: right

save_interval: 1000
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: https://olmo-checkpoints.org/ai2-llm/peteish13/step596057-unsharded
Expand Down
4 changes: 2 additions & 2 deletions configs/official-1124/OLMo2-13B-stage2-seed6209-100B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,10 +62,10 @@ tokenizer:
truncate_direction: right

save_interval: 1000
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: https://olmo-checkpoints.org/ai2-llm/peteish13/step596057-unsharded
Expand Down
4 changes: 2 additions & 2 deletions configs/official-1124/OLMo2-7B-stage1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,10 +69,10 @@ save_overwrite: false

save_interval: 1000
save_interval_ephemeral: 250
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: null
Expand Down
4 changes: 2 additions & 2 deletions configs/official-1124/OLMo2-7B-stage2-seed42.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,10 +66,10 @@ save_overwrite: false

save_interval: 1000
save_interval_ephemeral: 250
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: https://olmo-checkpoints.org/ai2-llm/peteish7/step928646-unsharded
Expand Down
4 changes: 2 additions & 2 deletions configs/official-1124/OLMo2-7B-stage2-seed42069.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,10 +66,10 @@ save_overwrite: false

save_interval: 1000
save_interval_ephemeral: 250
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: https://olmo-checkpoints.org/ai2-llm/peteish7/step928646-unsharded
Expand Down
4 changes: 2 additions & 2 deletions configs/official-1124/OLMo2-7B-stage2-seed666.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,10 +66,10 @@ save_overwrite: false

save_interval: 1000
save_interval_ephemeral: 250
save_num_checkpoints_to_keep: -1
save_num_checkpoints_to_keep: 0
sharded_checkpointer: olmo_core

save_interval_unsharded: null
save_interval_unsharded: 1000
save_num_unsharded_checkpoints_to_keep: -1

load_path: https://olmo-checkpoints.org/ai2-llm/peteish7/step928646-unsharded
Expand Down
Loading