alefarasin
commited on
Commit
•
ff8a453
1
Parent(s):
ab68ef8
End of training
Browse files- .gitignore +1 -0
- config.json +36 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"act_dim": 6,
|
3 |
+
"action_tanh": true,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"TrainableDT"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 50256,
|
12 |
+
"hidden_size": 128,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"layer_norm_epsilon": 1e-05,
|
15 |
+
"max_ep_len": 4096,
|
16 |
+
"model_type": "decision_transformer",
|
17 |
+
"n_embd": 768,
|
18 |
+
"n_head": 1,
|
19 |
+
"n_inner": null,
|
20 |
+
"n_layer": 3,
|
21 |
+
"n_positions": 1024,
|
22 |
+
"reorder_and_upcast_attn": false,
|
23 |
+
"resid_pdrop": 0.1,
|
24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
25 |
+
"scale_attn_weights": true,
|
26 |
+
"state_dim": 17,
|
27 |
+
"summary_activation": null,
|
28 |
+
"summary_first_dropout": 0.1,
|
29 |
+
"summary_proj_to_labels": true,
|
30 |
+
"summary_type": "cls_index",
|
31 |
+
"summary_use_proj": true,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.23.1",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 1
|
36 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1611376b79fcbfcd1fee02c0d8c238e7bcff6002d7fef8a71a4d594b04a3a8d4
|
3 |
+
size 8192558
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a41c9acc2956d16a556248a2492fbe5ef8d766a3ae9b6b6bc41d3b6860bf84b
|
3 |
+
size 3375
|