timxiaohangt commited on
Commit
268dd2e
1 Parent(s): bf837aa

Training in progress, step 2000

Browse files
Files changed (4) hide show
  1. .gitignore +1 -0
  2. config.json +49 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "act_dim": 1,
3
+ "action_tanh": true,
4
+ "activation_function": "relu",
5
+ "adv_act_dim": 1,
6
+ "architectures": [
7
+ "SimpleRobustDT"
8
+ ],
9
+ "attn_pdrop": 0.1,
10
+ "bos_token_id": 50256,
11
+ "context_size": 1,
12
+ "discrete": true,
13
+ "embd_pdrop": 0.1,
14
+ "eos_token_id": 50256,
15
+ "hidden_size": 128,
16
+ "initializer_range": 0.02,
17
+ "lambda1": 1.0,
18
+ "lambda2": 10.0,
19
+ "layer_norm_epsilon": 1e-05,
20
+ "log_interval_steps": 100,
21
+ "max_ep_len": 1,
22
+ "max_ep_return": 1000.0,
23
+ "max_obs_len": 1,
24
+ "max_obs_return": 30.0,
25
+ "min_obs_return": 0.0,
26
+ "model_type": "decision_transformer",
27
+ "n_head": 1,
28
+ "n_inner": null,
29
+ "n_layer": 3,
30
+ "n_positions": 1024,
31
+ "pr_act_dim": 1,
32
+ "reorder_and_upcast_attn": false,
33
+ "resid_pdrop": 0.1,
34
+ "returns_scale": 1000,
35
+ "scale_attn_by_inverse_layer_idx": false,
36
+ "scale_attn_weights": true,
37
+ "state_dim": 1,
38
+ "state_mean": [
39
+ 1.0
40
+ ],
41
+ "state_std": [
42
+ 1e-08
43
+ ],
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.31.0",
46
+ "use_cache": true,
47
+ "vocab_size": 1,
48
+ "warmup_steps": 1000
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c56188791998addf8fff897605cdfdc9c85c060c7555a725884eae08bfa2f9e
3
+ size 2935470
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2b4ccb566ee2f48bd596d3f6410d214f0231ce9223be2bb3e2e7afeba72f8a
3
+ size 4283