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 sha256:94c414f6e68f6f9e4d8eb497e609d9689c23a02972c25757b9015fad355890cd
+size 8200360

runs/Mar01_20-31-27_3b98ab78e6d4/1677702702.1120687/events.out.tfevents.1677702702.3b98ab78e6d4.177.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a24d92793804124e369f10940aa71793c07da1a54090cce5327e1c0ce4c90ef8
+size 5697

runs/Mar01_20-31-27_3b98ab78e6d4/events.out.tfevents.1677702702.3b98ab78e6d4.177.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bde5f906d534b88fb3e81d22cecd30036c43e2083a6ce50155814cab7ea2e24
+size 4148

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94eebdb98246a0fbba65ce727b5a8e15415e509b588eef7ecab1cff77a55c72
+size 3515