LangGraph notebook failing #13
Description
Hi, I'm getting this result when running the notebook:
Iterating dataset: 4% 20/500 [00:08<03:26, 2.32batch/s]Training step 0, epoch 0, epoch step 0
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a540f93a0>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]"./.art/email-search-agent-langgraph/models/email-agent-langgraph-002-nb/history.jsonl" not found
tokenizer_config.json: 7.30k/? [00:00<00:00, 200kB/s]vocab.json: 2.78M/? [00:00<00:00, 27.5MB/s]merges.txt: 1.67M/? [00:00<00:00, 19.0MB/s]tokenizer.json: 7.03M/? [00:00<00:00, 37.7MB/s]Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 0 to 1 (no training occurred)
Completed training step 0
Training step 1, epoch 0, epoch step 1
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a5430ff50>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 1 to 2 (no training occurred)
Completed training step 1
Training step 2, epoch 0, epoch step 2
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a54111f40>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 2 to 3 (no training occurred)
Completed training step 2
Training step 3, epoch 0, epoch step 3
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792b27cfe8d0>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 3 to 4 (no training occurred)
Completed training step 3
Training step 4, epoch 0, epoch step 4
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a4b880290>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 4 to 5 (no training occurred)
Completed training step 4
Training step 5, epoch 0, epoch step 5
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a4b887b90>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 5 to 6 (no training occurred)
Completed training step 5
Training step 6, epoch 0, epoch step 6
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a4b55bc20>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 6 to 7 (no training occurred)
Completed training step 6
Training step 7, epoch 0, epoch step 7
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a3c4cf830>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 7 to 8 (no training occurred)
Completed training step 7
Training step 8, epoch 0, epoch step 8
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a3c57ed20>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 8 to 9 (no training occurred)
Completed training step 8
Training step 9, epoch 0, epoch step 9
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a3c57e3f0>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 9 to 10 (no training occurred)
Completed training step 9
Training step 10, epoch 0, epoch step 10
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a357af230>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 10 to 11 (no training occurred)
Completed training step 10
Training step 11, epoch 0, epoch step 11
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a357ae660>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 11 to 12 (no training occurred)
Completed training step 11
Training step 12, epoch 0, epoch step 12
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a2be41b20>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 12 to 13 (no training occurred)
Completed training step 12
Training step 13, epoch 0, epoch step 13
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a2bdc6ae0>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 13 to 14 (no training occurred)
Completed training step 13
Training step 14, epoch 0, epoch step 14
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a2bca29c0>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 14 to 15 (no training occurred)
Completed training step 14
Training step 15, epoch 0, epoch step 15
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a2bca2420>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 15 to 16 (no training occurred)
Completed training step 15
Training step 16, epoch 0, epoch step 16
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a2bb55670>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 16 to 17 (no training occurred)
Completed training step 16
Training step 17, epoch 0, epoch step 17
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a2bba5970>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 17 to 18 (no training occurred)
Completed training step 17
Training step 18, epoch 0, epoch step 18
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a2ba7be30>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 18 to 19 (no training occurred)
Completed training step 18
Training step 19, epoch 0, epoch step 19
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a2bdc4b00>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 19 to 20 (no training occurred)
Completed training step 19
Training step 20, epoch 0, epoch step 20
Batch contains 2 scenarios
<art.trajectories.TrajectoryGroup.__new__.<locals>.CoroutineWithMetadata object at 0x792a2b96a000>
gather: 0% 0/8 [00:00<?, ?it/s, exceptions=8]No "val/reward" metric found in history
Skipping tuning as there is no suitable data. This can happen when all the trajectories in the same group have the same reward and thus no advantage to train on.
Advanced step from 20 to 21 (no training occurred)
Completed training step 20