afonsosamarques's picture
Training in progress, step 2000
e226691
raw
history blame
No virus
1.62 kB
{
"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": 0.98062783,
"min_obs_return": 0.98062783,
"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": [
1.209087606182348,
-0.0024433804464966537,
-0.5121224035046005,
-0.1792276788145927,
0.10206460331576518,
1.9267843346155455,
-0.18265996445338303,
0.02094631569481702,
-0.3570970607279206,
-0.25557554713170616,
-0.5014115326841497
],
"state_std": [
0.14455136461248416,
0.08059303935274553,
0.2651650281434884,
0.2943715715574719,
0.6045520274648529,
0.9001491436425907,
1.2017406710493554,
1.029395608366261,
2.059115337608456,
2.898265052736193,
6.197472424851261
],
"torch_dtype": "float32",
"total_train_steps": 10000,
"transformers_version": "4.29.2",
"use_cache": true,
"vocab_size": 1,
"warmup_steps": 1000
}