add model
Browse files- .gitignore +1 -0
- README.md +65 -0
- config.json +38 -0
- pytorch_model.bin +3 -0
- runs/Sep08_05-28-07_fbd567ce2372/1631078894.917259/events.out.tfevents.1631078894.fbd567ce2372.77.4 +3 -0
- runs/Sep08_05-28-07_fbd567ce2372/events.out.tfevents.1631078894.fbd567ce2372.77.3 +3 -0
- runs/Sep08_05-28-07_fbd567ce2372/events.out.tfevents.1631082229.fbd567ce2372.77.5 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- null
|
7 |
+
model-index:
|
8 |
+
- name: gpt2-nft-poetry
|
9 |
+
results:
|
10 |
+
- task:
|
11 |
+
name: Causal Language Modeling
|
12 |
+
type: text-generation
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# gpt2-nft-poetry
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 4.0243
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 8
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 5
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| No log | 1.0 | 282 | 4.3092 |
|
54 |
+
| 4.5403 | 2.0 | 564 | 4.1283 |
|
55 |
+
| 4.5403 | 3.0 | 846 | 4.0605 |
|
56 |
+
| 4.039 | 4.0 | 1128 | 4.0321 |
|
57 |
+
| 4.039 | 5.0 | 1410 | 4.0243 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- Transformers 4.10.0
|
63 |
+
- Pytorch 1.9.0+cu102
|
64 |
+
- Datasets 1.11.0
|
65 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.10.0",
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50257
|
38 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1121c85a0a13732b5c4b1c6897af90f2b78763fc4eda4372f26918a96818f5a
|
3 |
+
size 510403817
|
runs/Sep08_05-28-07_fbd567ce2372/1631078894.917259/events.out.tfevents.1631078894.fbd567ce2372.77.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff989ecb0c77d57632e829191e60b1d6e089117921060618964f1eb7ae38225d
|
3 |
+
size 4188
|
runs/Sep08_05-28-07_fbd567ce2372/events.out.tfevents.1631078894.fbd567ce2372.77.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e70577c048ec8aa9aacfeac951930042a7f809b8e6fbf4e0540e2c325b9c32ca
|
3 |
+
size 5168
|
runs/Sep08_05-28-07_fbd567ce2372/events.out.tfevents.1631082229.fbd567ce2372.77.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1899d956234b010e706fa71d71e9355f154768c86a380f1c4d73106a58c2fef1
|
3 |
+
size 311
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9750920060c8be2e8ea4077f3cecb4563674a09e17a56881050cf92ea6ea7a9b
|
3 |
+
size 2671
|