Upload policy weights, train config and readme
Browse files- config.json +3 -0
- model.safetensors +2 -2
- train_config.json +5 -2
config.json
CHANGED
|
@@ -352,5 +352,8 @@
|
|
| 352 |
"action_batch_size": 20,
|
| 353 |
"sampling_strategy": "stochastic",
|
| 354 |
"sampling_temperature": 1.0,
|
|
|
|
|
|
|
|
|
|
| 355 |
"training_stage": "slow_policy"
|
| 356 |
}
|
|
|
|
| 352 |
"action_batch_size": 20,
|
| 353 |
"sampling_strategy": "stochastic",
|
| 354 |
"sampling_temperature": 1.0,
|
| 355 |
+
"smooth_slow_policy_output": false,
|
| 356 |
+
"apply_slow_policy_output": false,
|
| 357 |
+
"use_image_features_for_fast_policy": true,
|
| 358 |
"training_stage": "slow_policy"
|
| 359 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ee812314f3cb558991d938e17f18e9ea40c5ae6303a510511101f0c3cb691ea
|
| 3 |
+
size 384843576
|
train_config.json
CHANGED
|
@@ -419,9 +419,12 @@
|
|
| 419 |
"action_batch_size": 20,
|
| 420 |
"sampling_strategy": "stochastic",
|
| 421 |
"sampling_temperature": 1.0,
|
|
|
|
|
|
|
|
|
|
| 422 |
"training_stage": "slow_policy"
|
| 423 |
},
|
| 424 |
-
"output_dir": "outputs/train/2025-11-
|
| 425 |
"job_name": "cascaded_flow_triage_v2_slow_policy",
|
| 426 |
"resume": false,
|
| 427 |
"seed": 1000,
|
|
@@ -460,7 +463,7 @@
|
|
| 460 |
"project": "policies",
|
| 461 |
"entity": null,
|
| 462 |
"notes": null,
|
| 463 |
-
"run_id": "
|
| 464 |
"mode": null
|
| 465 |
}
|
| 466 |
}
|
|
|
|
| 419 |
"action_batch_size": 20,
|
| 420 |
"sampling_strategy": "stochastic",
|
| 421 |
"sampling_temperature": 1.0,
|
| 422 |
+
"smooth_slow_policy_output": false,
|
| 423 |
+
"apply_slow_policy_output": false,
|
| 424 |
+
"use_image_features_for_fast_policy": true,
|
| 425 |
"training_stage": "slow_policy"
|
| 426 |
},
|
| 427 |
+
"output_dir": "outputs/train/2025-11-19/12-25-17_cascaded_flow_triage_v2_slow_policy",
|
| 428 |
"job_name": "cascaded_flow_triage_v2_slow_policy",
|
| 429 |
"resume": false,
|
| 430 |
"seed": 1000,
|
|
|
|
| 463 |
"project": "policies",
|
| 464 |
"entity": null,
|
| 465 |
"notes": null,
|
| 466 |
+
"run_id": "ct6pce3j",
|
| 467 |
"mode": null
|
| 468 |
}
|
| 469 |
}
|