curl --request POST \
--url 'http://localhost:8000/training' \
--header "Authorization: Bearer $STATESET_AGENTS_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"agent_config": {
"enable_planning": false,
"max_new_tokens": 256,
"model_name": "gpt2",
"temperature": 0.7
},
"environment_scenarios": [
{
"id": "customer_support",
"topic": "support",
"user_responses": [
"I need help",
"Thank you"
]
}
],
"num_episodes": 50,
"profile": "balanced",
"resume_from_checkpoint": "./outputs/checkpoint-100",
"reward_config": {
"helpfulness_weight": 0.7,
"safety_weight": 0.3
},
"training_config_overrides": {
"continual_strategy": "replay_lwf",
"replay_ratio": 0.3
}
}'
{
"training_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"status": "pending",
"estimated_time": 1.5,
"message": "Two-person tent, green — replacement for damaged pole set."
}
Start Training
Start a new training job with the specified configuration.
POST
/
training
curl --request POST \
--url 'http://localhost:8000/training' \
--header "Authorization: Bearer $STATESET_AGENTS_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"agent_config": {
"enable_planning": false,
"max_new_tokens": 256,
"model_name": "gpt2",
"temperature": 0.7
},
"environment_scenarios": [
{
"id": "customer_support",
"topic": "support",
"user_responses": [
"I need help",
"Thank you"
]
}
],
"num_episodes": 50,
"profile": "balanced",
"resume_from_checkpoint": "./outputs/checkpoint-100",
"reward_config": {
"helpfulness_weight": 0.7,
"safety_weight": 0.3
},
"training_config_overrides": {
"continual_strategy": "replay_lwf",
"replay_ratio": 0.3
}
}'
{
"training_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"status": "pending",
"estimated_time": 1.5,
"message": "Two-person tent, green — replacement for damaged pole set."
}
Start a new training job with the specified configuration.
Request body
TrainingRequest
AgentConfigRequest
required
object[]
required
Training scenarios
object
required
Reward function configuration
integer
Number of training episodes
string
Training profile
string,null
Checkpoint path to resume training from
object,null
Optional training configuration overrides
Response
TrainingResponse
string
required
Training job identifier
string
required
Training status
number,null
Estimated completion time
string
required
Status message
Status codes
| Code | Meaning |
|---|---|
200 | Successful response |
202 | Training started successfully |
400 | Invalid configuration |
401 | Authentication required |
403 | Insufficient permissions |
422 | Validation Error |
429 | Rate limit exceeded |
500 | Internal server error |
curl --request POST \
--url 'http://localhost:8000/training' \
--header "Authorization: Bearer $STATESET_AGENTS_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"agent_config": {
"enable_planning": false,
"max_new_tokens": 256,
"model_name": "gpt2",
"temperature": 0.7
},
"environment_scenarios": [
{
"id": "customer_support",
"topic": "support",
"user_responses": [
"I need help",
"Thank you"
]
}
],
"num_episodes": 50,
"profile": "balanced",
"resume_from_checkpoint": "./outputs/checkpoint-100",
"reward_config": {
"helpfulness_weight": 0.7,
"safety_weight": 0.3
},
"training_config_overrides": {
"continual_strategy": "replay_lwf",
"replay_ratio": 0.3
}
}'
{
"training_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"status": "pending",
"estimated_time": 1.5,
"message": "Two-person tent, green — replacement for damaged pole set."
}
Last modified on August 31, 2026