ncduy0303
commited on
Commit
•
eb272c8
1
Parent(s):
5369d71
add model
Browse files- .gitignore +1 -0
- README.md +62 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- runs/Aug06_13-44-14_67165c4eb041/1628257481.4292328/events.out.tfevents.1628257481.67165c4eb041.61.1 +3 -0
- runs/Aug06_13-44-14_67165c4eb041/events.out.tfevents.1628257481.67165c4eb041.61.0 +3 -0
- runs/Aug06_13-44-14_67165c4eb041/events.out.tfevents.1628260056.67165c4eb041.61.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- null
|
6 |
+
model_index:
|
7 |
+
- name: gpt2-wikitext2
|
8 |
+
results:
|
9 |
+
- task:
|
10 |
+
name: Causal Language Modeling
|
11 |
+
type: text-generation
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# gpt2-wikitext2
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 6.3114
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 3.0
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 6.7439 | 1.0 | 2249 | 6.6501 |
|
53 |
+
| 6.4023 | 2.0 | 4498 | 6.3852 |
|
54 |
+
| 6.2426 | 3.0 | 6747 | 6.3114 |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.9.1
|
60 |
+
- Pytorch 1.9.0+cu102
|
61 |
+
- Datasets 1.11.0
|
62 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"resid_pdrop": 0.1,
|
21 |
+
"scale_attn_weights": true,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"task_specific_params": {
|
28 |
+
"text-generation": {
|
29 |
+
"do_sample": true,
|
30 |
+
"max_length": 50
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.9.1",
|
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 sha256:79494e848e5198c43ae0d9d0bb2b5149d01bb9c6614cee13492e885e2792ea2c
|
3 |
+
size 510403817
|
runs/Aug06_13-44-14_67165c4eb041/1628257481.4292328/events.out.tfevents.1628257481.67165c4eb041.61.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c55d3e47a7206bdf32e4cd6ffd742bbd2a38e724a2f01a4a528f270d4ee2281b
|
3 |
+
size 4175
|
runs/Aug06_13-44-14_67165c4eb041/events.out.tfevents.1628257481.67165c4eb041.61.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c31840cbfa94a85cfea0b995c1076115fbce0e17036957b6087c4261f087ee13
|
3 |
+
size 6314
|
runs/Aug06_13-44-14_67165c4eb041/events.out.tfevents.1628260056.67165c4eb041.61.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a887fc44afed5e2a93863e87759eb23a45c4a08268899f5a09740e6458368841
|
3 |
+
size 311
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbde47ba45baf1ef2c533cf1e714a718b65263da20b8a6c5a86706d62dea52ef
|
3 |
+
size 2671
|