End of training
Browse files- .gitattributes +1 -0
- README.md +54 -0
- config.json +30 -0
- model.safetensors +3 -0
- replay.mp4 +3 -0
- runs/Aug18_05-56-14_92cb352aa3a7/events.out.tfevents.1723960575.92cb352aa3a7.569.0 +3 -0
- runs/Aug18_06-04-21_92cb352aa3a7/events.out.tfevents.1723961062.92cb352aa3a7.569.1 +3 -0
- runs/Aug18_06-25-13_92cb352aa3a7/events.out.tfevents.1723962314.92cb352aa3a7.858.0 +3 -0
- runs/Aug18_06-46-10_92cb352aa3a7/events.out.tfevents.1723963570.92cb352aa3a7.858.1 +3 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
replay.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- edbeeching/decision_transformer_gym_replay
|
7 |
+
model-index:
|
8 |
+
- name: decision-transformer-halfcheetah-v4
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# decision-transformer-halfcheetah-v4
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the halfcheetah-expert-v2 dataset.
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0001
|
37 |
+
- train_batch_size: 64
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- lr_scheduler_warmup_ratio: 0.1
|
43 |
+
- num_epochs: 360
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- Transformers 4.45.0.dev0
|
52 |
+
- Pytorch 2.1.2+cpu
|
53 |
+
- Datasets 2.20.0
|
54 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_head": 1,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 3,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"state_dim": 17,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.45.0.dev0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 1
|
30 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb6469896a7f1e16b3450d369ee6dba82d1539e938b690e27b0cdb49df21b46c
|
3 |
+
size 5034448
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77546e2b119c4ec3bb9122830b656f5c2949142fb0b50213a83953740e603156
|
3 |
+
size 1166038
|
runs/Aug18_05-56-14_92cb352aa3a7/events.out.tfevents.1723960575.92cb352aa3a7.569.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46b37731ecf95164da09252dba7d3652a8204e4de2437f0983911e2990b153e2
|
3 |
+
size 4851
|
runs/Aug18_06-04-21_92cb352aa3a7/events.out.tfevents.1723961062.92cb352aa3a7.569.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c92a2bfa096a66c94937648ef014dbf790b454739add3867d163fbe13651286
|
3 |
+
size 5204
|
runs/Aug18_06-25-13_92cb352aa3a7/events.out.tfevents.1723962314.92cb352aa3a7.858.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:089c854eb4fb24f843c73a2220e3a58161a76419920cc428a0213b2811d2b7f7
|
3 |
+
size 5204
|
runs/Aug18_06-46-10_92cb352aa3a7/events.out.tfevents.1723963570.92cb352aa3a7.858.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8df30084ba6b9b8f670fcbd59ce8a9638b71d1d96ae99b234f6980eef17940ac
|
3 |
+
size 7598
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d4b8a914addf534d505fb1ae4aa5dc5ac6286aca408b52ee6154ba5f4c77582
|
3 |
+
size 5176
|