afonsosamarques commited on
Commit
848da35
1 Parent(s): 3d4259b

Training in progress, step 2000

Browse files
Files changed (4) hide show
  1. .gitignore +1 -0
  2. config.json +83 -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 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "act_dim": 6,
3
+ "action_tanh": true,
4
+ "activation_function": "relu",
5
+ "adv_act_dim": 6,
6
+ "architectures": [
7
+ "MultipartADT"
8
+ ],
9
+ "attn_pdrop": 0.1,
10
+ "bos_token_id": 50256,
11
+ "context_size": 20,
12
+ "embd_pdrop": 0.1,
13
+ "eos_token_id": 50256,
14
+ "flag": false,
15
+ "hidden_size": 128,
16
+ "initializer_range": 0.02,
17
+ "lambda1": 0.7749999999999693,
18
+ "lambda2": 250.0,
19
+ "layer_norm_epsilon": 1e-05,
20
+ "log_interval_steps": 100,
21
+ "max_ep_len": 999,
22
+ "max_ep_return": 3741,
23
+ "max_obs_len": 999,
24
+ "max_obs_return": 3741,
25
+ "min_ep_return": -71.98172901599999,
26
+ "min_obs_return": -71.98172901599999,
27
+ "model_type": "decision_transformer",
28
+ "n_head": 1,
29
+ "n_inner": null,
30
+ "n_layer": 3,
31
+ "n_positions": 1024,
32
+ "pr_act_dim": 6,
33
+ "reorder_and_upcast_attn": false,
34
+ "resid_pdrop": 0.1,
35
+ "returns_scale": 1000,
36
+ "scale_attn_by_inverse_layer_idx": false,
37
+ "scale_attn_weights": true,
38
+ "state_dim": 17,
39
+ "state_mean": [
40
+ 1.1698974923507626,
41
+ 0.223154082356817,
42
+ -0.14717483827069816,
43
+ -0.08734744700468072,
44
+ 0.2607501139506204,
45
+ -0.2384946074777136,
46
+ -0.04083484368202344,
47
+ 0.2587883759189921,
48
+ 1.5419008871035536,
49
+ -0.09001055239971398,
50
+ 0.054388104601454115,
51
+ -0.1577685210129317,
52
+ -0.10998624278790205,
53
+ -0.5520018536871275,
54
+ -0.13226761327391778,
55
+ -0.19474253062192323,
56
+ -0.5372108504899912
57
+ ],
58
+ "state_std": [
59
+ 0.09078947748328232,
60
+ 0.30587571303184147,
61
+ 0.3076702261569018,
62
+ 0.314313081443578,
63
+ 0.6490516124582122,
64
+ 0.33459145953013525,
65
+ 0.3087582793956342,
66
+ 0.6916715043075827,
67
+ 1.1540282526646086,
68
+ 0.6234008346937597,
69
+ 2.4913034179940303,
70
+ 2.880059719125051,
71
+ 2.7305158024692244,
72
+ 5.467779603577728,
73
+ 2.9765821637971275,
74
+ 2.046332210659901,
75
+ 4.517001439968036
76
+ ],
77
+ "torch_dtype": "float32",
78
+ "total_train_steps": 10000,
79
+ "transformers_version": "4.29.2",
80
+ "use_cache": true,
81
+ "vocab_size": 1,
82
+ "warmup_steps": 1000
83
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ca9043d6f1699fcf80cf133fbb05c8966bc427ca2287f3dd79a33480f9cc337
3
+ size 19857646
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f4201db81d5abf697eb922a02fbe467beed10b0b42bd83fa765d2c90adc5073
3
+ size 4664