afonsosamarques's picture
Training in progress, step 2000
2286b95
{
"act_dim": 3,
"action_tanh": true,
"activation_function": "relu",
"adv_act_dim": 3,
"architectures": [
"AdversarialDT"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"context_size": 20,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"flag": false,
"hidden_size": 128,
"initializer_range": 0.02,
"lambda1": 1.0,
"lambda2": 1.0,
"layer_norm_epsilon": 1e-05,
"log_interval_steps": 100,
"max_ep_len": 999,
"max_ep_return": 3073,
"max_obs_len": 999,
"max_obs_return": 3073,
"min_ep_return": 0.59533596,
"min_obs_return": 0.59533596,
"model_type": "decision_transformer",
"n_head": 1,
"n_inner": null,
"n_layer": 3,
"n_positions": 1024,
"pr_act_dim": 3,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"returns_scale": 1000,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"state_dim": 11,
"state_mean": [
1.2484109448283487,
0.02541937343443989,
-0.417574769829802,
-0.1535401766461714,
0.12844594577746832,
1.7648832092997122,
-0.14629294202424897,
0.005822005615959526,
-0.3319174318352961,
-0.14299996508458745,
-0.5025578820838597
],
"state_std": [
0.14913521175340505,
0.08197128929621504,
0.2847277032366293,
0.2506871380229607,
0.5970928975497837,
0.903718761191001,
1.2132053487487453,
0.9225378063227366,
1.897097236674443,
2.661700770003696,
6.165093175492324
],
"torch_dtype": "float32",
"total_train_steps": 10000,
"transformers_version": "4.29.2",
"use_cache": true,
"vocab_size": 1,
"warmup_steps": 1000
}