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 sha256:97612ac2e26ed664abeda4c9e497b0c82cca8bad9befbba370d92c24b21923b9
+size 8200360

runs/Feb24_12-10-48_d17363b0088d/1677240655.9591894/events.out.tfevents.1677240655.d17363b0088d.2554.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d9d11a6c35e6b478960b46d2647105c2b9d70058b08171c4c86141e940ca9f
+size 5679

runs/Feb24_12-10-48_d17363b0088d/events.out.tfevents.1677240655.d17363b0088d.2554.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098c2015333fa6dd0c5acf1ad44472ea4e4bd66d5e9266b104030f3b730dc781
+size 4131

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dae224e66dd908bcd94cf555f43cd066de5e0f9c75cd60241ef1b71827f7ceb
+size 3515