8ball / rl_agent_config.json
VioletCrown's picture
8ball-laya-mtl2: persona fine-tune of laya-typed-decisions (S1MB 26.70 TA)
fc3b0d2 verified
Raw History Blame Contribute Delete
580 Bytes
{
"encoder": "answerdotai/ModernBERT-large",
"head_layers": 2,
"max_len": 2048,
"head_max_len": 256,
"max_prefixes": 6,
"act_costs": {
"escalate": 0.5
},
"cost_wrong_act": 3.0,
"amp_dtype": "bf16",
"model_name": "8ball-laya",
"temperature": [
1.231265902519226,
1.6906861066818237,
2.8751964569091797
],
"training": {
"updates": 7313,
"epochs_completed": 1,
"hours": 1.96,
"world_size": 1,
"fine_tuned_from_checkpoint": true
},
"gradient_checkpointing": true,
"max_tokens_per_batch": 8192,
"fine_tuned": true
}