Upload PolyGuard artifact: log command_complete
Browse files
outputs/logs/hf_training.log
CHANGED
|
@@ -20107,3 +20107,5 @@ Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00
|
|
| 20107 |
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.17it/s]
|
| 20108 |
The following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
|
| 20109 |
postsave_inference_ok
|
|
|
|
|
|
|
|
|
| 20107 |
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.17it/s]
|
| 20108 |
The following generation flags are not valid and may be ignored: ['temperature', 'top_p', 'top_k']. Set `TRANSFORMERS_VERBOSITY=info` for more details.
|
| 20109 |
postsave_inference_ok
|
| 20110 |
+
$ python scripts/evaluate_policy_ablations.py --episodes 8 --checkpoint-dir checkpoints/sweeps/qwen-qwen2-5-3b-instruct --output outputs/reports/sweeps/qwen-qwen2-5-3b-instruct/grpo_ablation_report.json
|
| 20111 |
+
policy_ablations_done
|