Commit
•
f42afde
1
Parent(s):
8fba479
add model
Browse files- .gitignore +1 -0
- README.md +54 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- runs/Jul16_17-07-38_b5043029bd2f/1626455272.445084/events.out.tfevents.1626455272.b5043029bd2f.66.1 +3 -0
- runs/Jul16_17-07-38_b5043029bd2f/events.out.tfevents.1626455272.b5043029bd2f.66.0 +3 -0
- runs/Jul16_17-09-41_b5043029bd2f/1626455383.0266037/events.out.tfevents.1626455383.b5043029bd2f.66.3 +3 -0
- runs/Jul16_17-09-41_b5043029bd2f/events.out.tfevents.1626455383.b5043029bd2f.66.2 +3 -0
- runs/Jul16_17-11-14_b5043029bd2f/1626455475.1321268/events.out.tfevents.1626455475.b5043029bd2f.66.5 +3 -0
- runs/Jul16_17-11-14_b5043029bd2f/events.out.tfevents.1626455475.b5043029bd2f.66.4 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model_index:
|
6 |
+
- name: ZORK-AI-TEST
|
7 |
+
results:
|
8 |
+
- task:
|
9 |
+
name: Causal Language Modeling
|
10 |
+
type: text-generation
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# ZORK-AI-TEST
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unkown dataset.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
+
- train_batch_size: 1
|
39 |
+
- eval_batch_size: 2
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- lr_scheduler_warmup_steps: 200
|
44 |
+
- num_epochs: 3
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.8.2
|
53 |
+
- Pytorch 1.9.0+cu102
|
54 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"task_specific_params": {
|
29 |
+
"text-generation": {
|
30 |
+
"do_sample": true,
|
31 |
+
"max_length": 50
|
32 |
+
}
|
33 |
+
},
|
34 |
+
"transformers_version": "4.8.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 50257
|
37 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df8d813c3beca7e470c02619dbca94b3f51e5d714db828142178784de53ddeaf
|
3 |
+
size 510403817
|
runs/Jul16_17-07-38_b5043029bd2f/1626455272.445084/events.out.tfevents.1626455272.b5043029bd2f.66.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:186de7640ffccb47d1f1e46356d855477d29e6cb66f6e7d619dc3d98d0055bed
|
3 |
+
size 4182
|
runs/Jul16_17-07-38_b5043029bd2f/events.out.tfevents.1626455272.b5043029bd2f.66.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1f65b652bd9ed776d36aa022a5a5173653f113db80b6da828beac599ce99d6e
|
3 |
+
size 3488
|
runs/Jul16_17-09-41_b5043029bd2f/1626455383.0266037/events.out.tfevents.1626455383.b5043029bd2f.66.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1fadb8540cd2c50bf6991af3ebeaf501f2f11aa9bc346be0a96feef4cccb29e
|
3 |
+
size 4182
|
runs/Jul16_17-09-41_b5043029bd2f/events.out.tfevents.1626455383.b5043029bd2f.66.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac82a046da3cca774758dee57ab0fc7d1dff9015c8c867040c0ebb974bb92d7b
|
3 |
+
size 3488
|
runs/Jul16_17-11-14_b5043029bd2f/1626455475.1321268/events.out.tfevents.1626455475.b5043029bd2f.66.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e95afc6f864c58c6f4ec7d9a5eb2c7a1d7c5c5a0cb66826ae32eb9dacb0aa5fd
|
3 |
+
size 4182
|
runs/Jul16_17-11-14_b5043029bd2f/events.out.tfevents.1626455475.b5043029bd2f.66.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abbeb8e0bc9c6e81389d99b365f19c4e4bbea365b0fece2a6c66a9214b347299
|
3 |
+
size 3488
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e529847181eae6481f2814f4c77f4452bddad0e8a1c157ad67cf91c03201e52a
|
3 |
+
size 2607
|