Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,36 @@
+{
+  "act_dim": 1,
+  "action_tanh": true,
+  "activation_function": "relu",
+  "architectures": [
+    "TrainableDT"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_ep_len": 4096,
+  "model_type": "decision_transformer",
+  "n_embd": 768,
+  "n_head": 1,
+  "n_inner": null,
+  "n_layer": 3,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "state_dim": 28,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 1
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3183070ecdd2fbf08a26c2a84aec6ebf64205293913f68981b066f799935963
+size 8200360

runs/Mar01_21-02-43_3b98ab78e6d4/1677704569.233675/events.out.tfevents.1677704569.3b98ab78e6d4.177.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ed7780611bae211d0c43c8a7b8e2a2fb8bdf34cefb811960ca1ac03b4fab57
+size 5697

runs/Mar01_21-02-43_3b98ab78e6d4/events.out.tfevents.1677704569.3b98ab78e6d4.177.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cec298df4e0b232f6f8414dbc6ca8966babf695198e19cb48a6c412876374f2
+size 4148

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf0e68e667e1fbffda1d96080a6549beca673392051b3255e1e784a3bb3af0f
+size 3515