End of training
Browse files- README.md +0 -53
- config.json +0 -30
- pytorch_model.bin +0 -3
- training_args.bin +0 -3
README.md
DELETED
|
@@ -1,53 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
tags:
|
| 3 |
-
- generated_from_trainer
|
| 4 |
-
datasets:
|
| 5 |
-
- decision_transformer_gym_replay
|
| 6 |
-
model-index:
|
| 7 |
-
- name: output
|
| 8 |
-
results: []
|
| 9 |
-
---
|
| 10 |
-
|
| 11 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
-
|
| 14 |
-
# output
|
| 15 |
-
|
| 16 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on the decision_transformer_gym_replay dataset.
|
| 17 |
-
|
| 18 |
-
## Model description
|
| 19 |
-
|
| 20 |
-
More information needed
|
| 21 |
-
|
| 22 |
-
## Intended uses & limitations
|
| 23 |
-
|
| 24 |
-
More information needed
|
| 25 |
-
|
| 26 |
-
## Training and evaluation data
|
| 27 |
-
|
| 28 |
-
More information needed
|
| 29 |
-
|
| 30 |
-
## Training procedure
|
| 31 |
-
|
| 32 |
-
### Training hyperparameters
|
| 33 |
-
|
| 34 |
-
The following hyperparameters were used during training:
|
| 35 |
-
- learning_rate: 0.0001
|
| 36 |
-
- train_batch_size: 64
|
| 37 |
-
- eval_batch_size: 8
|
| 38 |
-
- seed: 42
|
| 39 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
-
- lr_scheduler_type: linear
|
| 41 |
-
- lr_scheduler_warmup_ratio: 0.1
|
| 42 |
-
- num_epochs: 120
|
| 43 |
-
|
| 44 |
-
### Training results
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
### Framework versions
|
| 49 |
-
|
| 50 |
-
- Transformers 4.27.2
|
| 51 |
-
- Pytorch 1.13.1+cu116
|
| 52 |
-
- Datasets 2.10.1
|
| 53 |
-
- Tokenizers 0.13.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
DELETED
|
@@ -1,30 +0,0 @@
|
|
| 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": "4.27.2",
|
| 28 |
-
"use_cache": true,
|
| 29 |
-
"vocab_size": 1
|
| 30 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bdfd2e0d3ec5bc2d021b600b8be8732085d2cf857219b02f2aa0ced7b35adffb
|
| 3 |
-
size 8193384
|
|
|
|
|
|
|
|
|
|
|
|
training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:aff55820e48540971df66d88040f6ad21823883b8d27bd04ce0b83e0c8239182
|
| 3 |
-
size 3515
|
|
|
|
|
|
|
|
|
|
|
|