chore: fix mypy violations in post_training modules

Note: this patch touches all files but post_training.py that will be
significantly changed by #1437, hence leaving it out of the picture for
now.

running_loss is now always Tensor (on-device) and doesn't change its
type from int to Tensor (which made mypy unhappy).

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>

docs/_static/llama-stack-spec.html

@@ -9830,23 +9830,6 @@
                 ],
                 "title": "ScoreBatchResponse"
             },
-            "AlgorithmConfig": {
-                "oneOf": [
-                    {
-                        "$ref": "#/components/schemas/LoraFinetuningConfig"
-                    },
-                    {
-                        "$ref": "#/components/schemas/QATFinetuningConfig"
-                    }
-                ],
-                "discriminator": {
-                    "propertyName": "type",
-                    "mapping": {
-                        "LoRA": "#/components/schemas/LoraFinetuningConfig",
-                        "QAT": "#/components/schemas/QATFinetuningConfig"
-                    }
-                }
-            },
             "LoraFinetuningConfig": {
                 "type": "object",
                 "properties": {
@@ -9982,7 +9965,14 @@
                         "type": "string"
                     },
                     "algorithm_config": {
-                        "$ref": "#/components/schemas/AlgorithmConfig"
+                        "oneOf": [
+                            {
+                                "$ref": "#/components/schemas/LoraFinetuningConfig"
+                            },
+                            {
+                                "$ref": "#/components/schemas/QATFinetuningConfig"
+                            }
+                        ]
                     }
                 },
                 "additionalProperties": false,

docs/_static/llama-stack-spec.yaml

@@ -6615,15 +6615,6 @@ components:
       required:
         - results
       title: ScoreBatchResponse
-    AlgorithmConfig:
-      oneOf:
-        - $ref: '#/components/schemas/LoraFinetuningConfig'
-        - $ref: '#/components/schemas/QATFinetuningConfig'
-      discriminator:
-        propertyName: type
-        mapping:
-          LoRA: '#/components/schemas/LoraFinetuningConfig'
-          QAT: '#/components/schemas/QATFinetuningConfig'
     LoraFinetuningConfig:
       type: object
       properties:
@@ -6707,7 +6698,9 @@ components:
         checkpoint_dir:
           type: string
         algorithm_config:
-          $ref: '#/components/schemas/AlgorithmConfig'
+          oneOf:
+            - $ref: '#/components/schemas/LoraFinetuningConfig'
+            - $ref: '#/components/schemas/QATFinetuningConfig'
       additionalProperties: false
       required:
         - job_uuid