Commit
•
0c3b60e
1
Parent(s):
684a9f7
Training in progress, step 200
Browse files- .gitignore +1 -0
- config.json +80 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"act_dim": 6,
|
| 3 |
+
"action_tanh": true,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"adv_act_dim": 6,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"MaxminRobustDT"
|
| 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 |
+
"hidden_size": 128,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"lambda1": 1.0,
|
| 17 |
+
"lambda2": 10.0,
|
| 18 |
+
"layer_norm_epsilon": 1e-05,
|
| 19 |
+
"log_interval_steps": 100,
|
| 20 |
+
"max_ep_len": 1000,
|
| 21 |
+
"max_ep_return": 12000.0,
|
| 22 |
+
"max_obs_len": 1000,
|
| 23 |
+
"max_obs_return": 11252.035989716649,
|
| 24 |
+
"min_obs_return": -1069.5231598131504,
|
| 25 |
+
"model_type": "decision_transformer",
|
| 26 |
+
"n_head": 1,
|
| 27 |
+
"n_inner": null,
|
| 28 |
+
"n_layer": 3,
|
| 29 |
+
"n_positions": 1024,
|
| 30 |
+
"pr_act_dim": 6,
|
| 31 |
+
"reorder_and_upcast_attn": false,
|
| 32 |
+
"resid_pdrop": 0.1,
|
| 33 |
+
"returns_scale": 1000,
|
| 34 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 35 |
+
"scale_attn_weights": true,
|
| 36 |
+
"state_dim": 17,
|
| 37 |
+
"state_mean": [
|
| 38 |
+
-0.0956932416496844,
|
| 39 |
+
0.17957574200459142,
|
| 40 |
+
-0.026755184419532514,
|
| 41 |
+
-0.11106382060666384,
|
| 42 |
+
-0.0424069304114166,
|
| 43 |
+
0.022792510579972024,
|
| 44 |
+
-0.053237181058344636,
|
| 45 |
+
-0.010153474677794313,
|
| 46 |
+
4.5988071058123605,
|
| 47 |
+
-0.043043627472847464,
|
| 48 |
+
-0.11226828729385846,
|
| 49 |
+
0.12210266686783008,
|
| 50 |
+
0.09042713419149917,
|
| 51 |
+
0.21360644598702644,
|
| 52 |
+
0.34716969442339174,
|
| 53 |
+
-0.12911719148659412,
|
| 54 |
+
0.021956373128626226
|
| 55 |
+
],
|
| 56 |
+
"state_std": [
|
| 57 |
+
0.12497197633480521,
|
| 58 |
+
0.6862970710791239,
|
| 59 |
+
0.4520271995121863,
|
| 60 |
+
0.3665064894694281,
|
| 61 |
+
0.34660935995461917,
|
| 62 |
+
0.5002668350573675,
|
| 63 |
+
0.3997221424686441,
|
| 64 |
+
0.3374992214072671,
|
| 65 |
+
4.7934872875892625,
|
| 66 |
+
0.8653573422987154,
|
| 67 |
+
1.6634595801023424,
|
| 68 |
+
8.176506856523494,
|
| 69 |
+
8.255387333932662,
|
| 70 |
+
6.260486262480971,
|
| 71 |
+
8.952409227141477,
|
| 72 |
+
6.675583604008942,
|
| 73 |
+
5.523564743313133
|
| 74 |
+
],
|
| 75 |
+
"torch_dtype": "float32",
|
| 76 |
+
"transformers_version": "4.31.0",
|
| 77 |
+
"use_cache": true,
|
| 78 |
+
"vocab_size": 1,
|
| 79 |
+
"warmup_steps": 1000
|
| 80 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af0b3364c9242863e03955140f0f59de39adbe1c7acab5ef769e611a3f16b172
|
| 3 |
+
size 3477230
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4e39c9a288299990d51877bb7f6177d4f418c8e52e369190f112d65acd537e1
|
| 3 |
+
size 4347
|