Training in progress, step 2000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,83 @@
+{
+  "act_dim": 6,
+  "action_tanh": true,
+  "activation_function": "relu",
+  "adv_act_dim": 6,
+  "architectures": [
+    "MultipartADT"
+  ],
+  "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": 0.7749999999999693,
+  "lambda2": 250.0,
+  "layer_norm_epsilon": 1e-05,
+  "log_interval_steps": 100,
+  "max_ep_len": 999,
+  "max_ep_return": 3741,
+  "max_obs_len": 999,
+  "max_obs_return": 3741,
+  "min_ep_return": -71.98172901599999,
+  "min_obs_return": -71.98172901599999,
+  "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": [
+    1.1698974923507626,
+    0.223154082356817,
+    -0.14717483827069816,
+    -0.08734744700468072,
+    0.2607501139506204,
+    -0.2384946074777136,
+    -0.04083484368202344,
+    0.2587883759189921,
+    1.5419008871035536,
+    -0.09001055239971398,
+    0.054388104601454115,
+    -0.1577685210129317,
+    -0.10998624278790205,
+    -0.5520018536871275,
+    -0.13226761327391778,
+    -0.19474253062192323,
+    -0.5372108504899912
+  ],
+  "state_std": [
+    0.09078947748328232,
+    0.30587571303184147,
+    0.3076702261569018,
+    0.314313081443578,
+    0.6490516124582122,
+    0.33459145953013525,
+    0.3087582793956342,
+    0.6916715043075827,
+    1.1540282526646086,
+    0.6234008346937597,
+    2.4913034179940303,
+    2.880059719125051,
+    2.7305158024692244,
+    5.467779603577728,
+    2.9765821637971275,
+    2.046332210659901,
+    4.517001439968036
+  ],
+  "torch_dtype": "float32",
+  "total_train_steps": 10000,
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 1,
+  "warmup_steps": 1000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca9043d6f1699fcf80cf133fbb05c8966bc427ca2287f3dd79a33480f9cc337
+size 19857646

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4201db81d5abf697eb922a02fbe467beed10b0b42bd83fa765d2c90adc5073
+size 4664