itzPotato's picture
arithmetic relu-2layer-seed2: checkpoint, config, training history
095edfb verified
Raw History Blame Contribute Delete
831 Bytes
{
"d_model": 32,
"d_mlp": 64,
"n_heads": 4,
"d_head": 8,
"n_layers": 2,
"mlp_type": "relu",
"d_vocab": 13,
"n_ctx": 16,
"bias": false,
"norm": false,
"tie_unembed": false,
"model_seed": 2,
"data_config": {
"n_train": 5000000,
"n_val": 10000,
"n_test": 10000,
"seed": 1234,
"balanced_ops": true
},
"vocab": {
"plus": 10,
"minus": 11,
"equals": 12,
"n_operand_digits": 4,
"n_answer_digits": 5
},
"train_config": {
"lr": 0.02,
"betas": [
0.9,
0.98
],
"weight_decay": 0.01,
"batch_size": 1024,
"warmup_steps": 200,
"lr_schedule": "cosine",
"lr_min_frac": 0.1,
"eval_every_steps": 200,
"seed": 2,
"max_steps": null,
"grad_clip": 1.0
},
"planned_repo_id": "itzPotato/arithmetic-relu-2layer-seed2"
}