Spaces:
Running
Running
r1cksync commited on
Commit Β·
dce8d90
1
Parent(s): 5be0e41
rename hybrid-ollama-bedrock -> ppo-v3-hybrid-ollama-bedrock so it sorts last and becomes dashboard default
Browse files- rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/adversarial_history.jsonl +0 -0
- rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/cluster_snapshot.json +0 -0
- rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/critic_shaping.jsonl +0 -0
- rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/curriculum_snapshot.json +0 -0
- rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/metrics.jsonl +0 -0
- rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/reward_breakdown_history.jsonl +0 -0
- rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/summary.json +2 -2
rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/adversarial_history.jsonl
RENAMED
|
File without changes
|
rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/cluster_snapshot.json
RENAMED
|
File without changes
|
rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/critic_shaping.jsonl
RENAMED
|
File without changes
|
rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/curriculum_snapshot.json
RENAMED
|
File without changes
|
rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/metrics.jsonl
RENAMED
|
File without changes
|
rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/reward_breakdown_history.jsonl
RENAMED
|
File without changes
|
rl-agent/checkpoints/{hybrid-ollama-bedrock β ppo-v3-hybrid-ollama-bedrock}/summary.json
RENAMED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"mode": "hybrid-ollama-bedrock",
|
| 3 |
"actor": "ollama:qwen2.5:0.5b",
|
| 4 |
"critic": "heuristic-fallback",
|
| 5 |
"total_episodes": 36,
|
|
@@ -105,4 +105,4 @@
|
|
| 105 |
"expert"
|
| 106 |
],
|
| 107 |
"timestamp": 1776905949.061191
|
| 108 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"mode": "ppo-v3-hybrid-ollama-bedrock",
|
| 3 |
"actor": "ollama:qwen2.5:0.5b",
|
| 4 |
"critic": "heuristic-fallback",
|
| 5 |
"total_episodes": 36,
|
|
|
|
| 105 |
"expert"
|
| 106 |
],
|
| 107 |
"timestamp": 1776905949.061191
|
| 108 |
+
}
|