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:c1bed5fe862d0f9d6de734b3fcfcb7e7f484a39def1108718a82899b9ff9109a
+size 8200360

runs/Feb24_11-25-14_d17363b0088d/1677237922.8810534/events.out.tfevents.1677237922.d17363b0088d.2554.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b70826e9fbc907e1140f548f0f78797ef7f473089483e8685268f89da1e656
+size 5681

runs/Feb24_11-25-14_d17363b0088d/events.out.tfevents.1677237922.d17363b0088d.2554.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c49e398c7103a2231d11de395e9598c44f9064cfa064a95965f5d2afa070b9f9
+size 4133

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48c2d0cdb9db6cd5b7d2599d40ff7ca233b50336b626bdda1c7093edaca2712
+size 3515