Document missing runs in README and add train_missing.yaml
Browse files- README.md +13 -1
- train_missing.yaml +41 -0
README.md
CHANGED
|
@@ -54,13 +54,25 @@ wandb_project=jaxgmg2_3phase_fast_tight
|
|
| 54 |
|
| 55 |
Checkpoints are named `al_{alpha}_g_{discount_rate}_seed_{seed}_pa_1`.
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
## Reproduced with
|
| 58 |
|
| 59 |
-
See `train.yaml` (initial sweep)
|
|
|
|
| 60 |
|
| 61 |
```bash
|
| 62 |
timaeus run train.yaml
|
| 63 |
timaeus run train_extended.yaml
|
|
|
|
| 64 |
```
|
| 65 |
|
| 66 |
from the [timaeus monorepo](https://github.com/timaeus-research/timaeus).
|
|
|
|
| 54 |
|
| 55 |
Checkpoints are named `al_{alpha}_g_{discount_rate}_seed_{seed}_pa_1`.
|
| 56 |
|
| 57 |
+
## Missing runs
|
| 58 |
+
|
| 59 |
+
5 runs from the initial sweep failed and are not present:
|
| 60 |
+
|
| 61 |
+
- `al_0.0_g_0.97_seed_100_pa_1`
|
| 62 |
+
- `al_0.0_g_0.99_seed_100_pa_1`
|
| 63 |
+
- `al_0.45_g_0.97_seed_103_pa_1`
|
| 64 |
+
- `al_0.45_g_0.98_seed_100_pa_1`
|
| 65 |
+
- `al_0.4_g_0.99_seed_104_pa_1`
|
| 66 |
+
|
| 67 |
## Reproduced with
|
| 68 |
|
| 69 |
+
See `train.yaml` (initial sweep), `train_extended.yaml` (extended sweep), and
|
| 70 |
+
`train_missing.yaml` (5 failed runs from initial sweep) in this repository. Run with:
|
| 71 |
|
| 72 |
```bash
|
| 73 |
timaeus run train.yaml
|
| 74 |
timaeus run train_extended.yaml
|
| 75 |
+
timaeus run train_missing.yaml
|
| 76 |
```
|
| 77 |
|
| 78 |
from the [timaeus monorepo](https://github.com/timaeus-research/timaeus).
|
train_missing.yaml
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
parameters:
|
| 2 |
+
project_name: jaxgmg2_3phase_fast_tight
|
| 3 |
+
action: rl
|
| 4 |
+
rl_action: train
|
| 5 |
+
|
| 6 |
+
lr: 5e-5
|
| 7 |
+
cheese_loc: any
|
| 8 |
+
env_layout: open
|
| 9 |
+
mask_type: first_episode
|
| 10 |
+
use_prev_action: false
|
| 11 |
+
|
| 12 |
+
num_total_env_steps: 10_000_000_000
|
| 13 |
+
num_levels: 9600
|
| 14 |
+
grad_acc_per_chunk: 4
|
| 15 |
+
num_rollout_steps: 64
|
| 16 |
+
|
| 17 |
+
ckpt_dir: jaxgmg2_3phase_fast_tight
|
| 18 |
+
eval_schedule: "0:1,250:2,500:5,2000:10"
|
| 19 |
+
f_str_ckpt: "al_{alpha}_g_{discount_rate}_seed_{seed}_pa_1"
|
| 20 |
+
|
| 21 |
+
use_wandb: true
|
| 22 |
+
use_hf: true
|
| 23 |
+
wandb_project: jaxgmg2_3phase_fast_tight
|
| 24 |
+
ntfy: david_jaxgmg
|
| 25 |
+
|
| 26 |
+
sweep:
|
| 27 |
+
- - alpha: 0.0
|
| 28 |
+
discount_rate: 0.97
|
| 29 |
+
seed: 100
|
| 30 |
+
- alpha: 0.0
|
| 31 |
+
discount_rate: 0.99
|
| 32 |
+
seed: 100
|
| 33 |
+
- alpha: 0.45
|
| 34 |
+
discount_rate: 0.97
|
| 35 |
+
seed: 103
|
| 36 |
+
- alpha: 0.45
|
| 37 |
+
discount_rate: 0.98
|
| 38 |
+
seed: 100
|
| 39 |
+
- alpha: 0.4
|
| 40 |
+
discount_rate: 0.99
|
| 41 |
+
seed: 104
|