Training in progress, step 3334

.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": [
+    "VanillaDT"
+  ],
+  "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": 1000,
+  "max_ep_return": 2055,
+  "max_obs_len": 1000,
+  "max_obs_return": 2055,
+  "min_ep_return": -47.50516876099998,
+  "min_obs_return": -47.50516876099998,
+  "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": [
+    -0.10747138440491079,
+    0.03995273485032268,
+    0.09185042351596463,
+    -0.002178418045573572,
+    -0.050427490730974515,
+    -0.02756966695474998,
+    -0.12579165213917906,
+    -0.29750804079410337,
+    1.7826680548740703,
+    -0.023495016629815995,
+    -0.0013145775596042546,
+    0.027529705594498494,
+    -0.04967560067468856,
+    0.0547487717179461,
+    -0.0642228431410299,
+    0.03850233653563301,
+    0.0018134987559798078
+  ],
+  "state_std": [
+    0.09616721279876324,
+    0.20867135703485673,
+    0.3603536989509704,
+    0.31588992924910747,
+    0.38647119453163514,
+    0.459903069807366,
+    0.36818501521703256,
+    0.2639298709951634,
+    0.753007175738254,
+    0.9662202448438054,
+    1.416250294680542,
+    5.25818001497618,
+    5.043390251956892,
+    5.864381026361581,
+    5.9662069070381785,
+    6.629961878945906,
+    4.991221131905117
+  ],
+  "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 sha256:229406b9ecf795e9822843da1f59b55e1ee6a4ce4d79af2b5b8e70302b38b7c0
+size 6609509

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecdefacbb95ff4f99a60c7087e0064104fdd49b2c7d4bc7fc729d417580e9eca
+size 4664