timxiaohangt's picture
Training in progress, step 200
0c3b60e
{
"act_dim": 6,
"action_tanh": true,
"activation_function": "relu",
"adv_act_dim": 6,
"architectures": [
"MaxminRobustDT"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"context_size": 20,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"hidden_size": 128,
"initializer_range": 0.02,
"lambda1": 1.0,
"lambda2": 10.0,
"layer_norm_epsilon": 1e-05,
"log_interval_steps": 100,
"max_ep_len": 1000,
"max_ep_return": 12000.0,
"max_obs_len": 1000,
"max_obs_return": 11252.035989716649,
"min_obs_return": -1069.5231598131504,
"model_type": "decision_transformer",
"n_head": 1,
"n_inner": null,
"n_layer": 3,
"n_positions": 1024,
"pr_act_dim": 6,
"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": 17,
"state_mean": [
-0.0956932416496844,
0.17957574200459142,
-0.026755184419532514,
-0.11106382060666384,
-0.0424069304114166,
0.022792510579972024,
-0.053237181058344636,
-0.010153474677794313,
4.5988071058123605,
-0.043043627472847464,
-0.11226828729385846,
0.12210266686783008,
0.09042713419149917,
0.21360644598702644,
0.34716969442339174,
-0.12911719148659412,
0.021956373128626226
],
"state_std": [
0.12497197633480521,
0.6862970710791239,
0.4520271995121863,
0.3665064894694281,
0.34660935995461917,
0.5002668350573675,
0.3997221424686441,
0.3374992214072671,
4.7934872875892625,
0.8653573422987154,
1.6634595801023424,
8.176506856523494,
8.255387333932662,
6.260486262480971,
8.952409227141477,
6.675583604008942,
5.523564743313133
],
"torch_dtype": "float32",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 1,
"warmup_steps": 1000
}